From DLR German Aerospace Center: Terra_Byte – Top computing power for researching global change

From DLR German Aerospace Center

Contacts

Falk Dambowsky
German Aerospace Center (DLR)
Media Relations
Tel.: +49 2203 601-3959

Prof. Dr Stefan Dech
German Aerospace Center (DLR)
Earth Observation Center (EOC) – German Remote Sensing Data Center
Tel.: +49 8153 28-2885
Fax: +49 8153 28-3444

Dr. rer. nat. Vanessa Keuck
German Aerospace Center (DLR)
Programme Strategy Space Research and Technology
Tel.: +49 228 601-5555

Dr Ludger Palm
Leibniz Computer Centre (LRZ)
Tel.: +49 89 35831-8792

Germany’s SuperMUC-NG supercomputer goes live. DatacenterDynamics

One of Europe’s largest supercomputing centres – the Leibniz Computer Centre (LRZ) of the Bavarian Academy of Sciences – and Europe’s largest space research institution – the German Aerospace Center (Deutsches Zentrum für Luft- und Raumfahrt; DLR) – will work together to evaluate the vast quantities of data acquired by Earth observation satellites alongside other global data sources, such as social networks, on the state of our planet on a daily basis.

“The collaboration between DLR and the LRZ marks a milestone in the development of future-oriented research within Bavaria, a hub for science! This project illustrates the wealth of resources that the Munich research landscape has to offer in this area,” said Bavaria’s Minister of Science and Arts/Culture, Bernd Sibler, at the signing of the cooperation agreement between the partner institutions on 27 May 2019 in Garching. “The collaboration between DLR and the LRZ marks a milestone in the development of future studies within Bavaria, an established hub for science research. This project illustrates the wealth of resources that the Munich research landscape has to offer in this area.” With this cooperation, DLR and the LRZ are pooling their vast expertise in the fields of satellite-based Earth observation and supercomputing.

“To understand the processes of global change and their development we must be able to evaluate the data from our satellites as effectively as possible,” stressed Hansjörg Dittus, DLR Executive Board Member for Space Research and Technology. “In future, the cooperation between DLR and the LRZ will make it possible to analyse vast quantities of data using the latest methods independently and highly efficiently, to aid in our understanding of global change and its consequences. Examples of this are increasing urbanisation, the expansion of agricultural land use across the globe at the expense of natural ecosystems and the rapid changes occurring in the Earth’s polar regions and in the atmosphere, which will have an undisputed impact on humankind. We will contribute our innovations and technology from space research, as well as our own sensor data to the analysis.”

Dieter Kranzlmüller, Director of the LRZ, says, “The collaboration between these two leading research institutions brings together two partners that complement each other perfectly and contribute their relevant expertise, resources and research topics. The Leibniz Computing Centre has proven experience as an innovative provider of IT services and a high-performance computing centre. It is also a reliable and capable partner for Bavarian universities and will, in future, cooperate with DLR and its institutes in Oberpfaffenhofen.”

Huge volumes of Earth observation data

Every day, Earth observation satellites generate vast quantities of data at such high resolution that conventional evaluation methods have long been pushed to their limits. “Only the combination of the online availability of a wide range of historical and current data stocks with cutting-edge supercomputing systems will make it possible for our researchers to derive high-resolution global information that will enable us to make statements about the development and evolution of Earth. Artificial intelligence methods are playing an increasingly important role in fully automated analysis. This enables us to identify phenomena and developments in ways that would be difficult to detect using conventional methods,” says Stefan Dech, Director of the DLR German Remote Sensing Data Center. This cooperation is key for the DLR institutes in Oberpfaffenhofen involved in research into satellite-based Earth observation. We can now carry out a range of global methodological and geoscientific analyses, which have been the sole preserve of example cases up until now, due to the sheer quantity of data and limited computing power. The technological data concept jointly developed by DLR and the LRZ is particularly important, as it will link the LRZ up with DLR’s German Satellite Data Archive in Oberpfaffenhofen, and, in addition to making global data stocks available online, will link historical data from our archive and DLR’s own data,” continues Dech.

A challenge for data analysis

To cite one example, the volume of data from the European Earth observation programme Copernicus has already exceeded 10 petabytes.

ESA Sentinels (Copernicus)

One petabtye is equivalent to the content of around 223,000 DVDs – which would weigh approximately 3.5 tonnes. By 2024, the Sentinel satellites of the Copernicus programme will have produced over 40 petabytes of data. These will be supplemented by even more petabytes worth of data from national Earth observation missions, such as DLR’s TerraSAR-X and TanDEM-X radar satellites and US Landsat data.

DLR TerraSAR-X Satellite

DLR TanDEM-X satellite

NASA LandSat 8

However, it is not only the large amounts of data from the satellite missions that are currently presenting scientists with challenges, but also data on global change that are published on social networks. While these are valuable sources, challenges arise because these data are extremely disparate, their accuracy is uncertain and they are only available for a limited period of time.

DLR researchers are thus increasingly using artificial intelligence (AI) and machine learning methods to identify trends in global change and analyses of natural disasters and environmental contexts in global and regional time series spanning several decades. But these methods require that the necessary data be available online, on high-performance data analytics platforms (HPDAs). The technical objective of this collaboration is to set up such a platform, providing researchers with access to all of the necessary Earth observation data via DLR’s German Satellite Data Archive (D-SDA) in Oberpfaffenhofen and data distribution points of various providers of freely available satellite data.

DLR’s German Remote Sensing Data Center (DFD) will coordinate the activities of the participating DLR institutes. In addition to the DFD, the Remote Sensing Technology Institute, the Institute for Atmospheric Physics and the Microwaves and Radar Institute in Oberpfaffenhofen are involved in the project. The Institute of Data Science in Jena and the Simulation and Software Technology Facility in Cologne are also involved in the implementation of the technology.

Cooperation on global change

As part of the collaboration, DLR will address issues relating to environmental development and global change, methodological and algorithmic process development in physical modelling and artificial intelligence, the management of long-term archives and the processing of large data volumes.

The LRZ focuses on the research and implementation of operational, scalable, secure and reliable IT services and technologies, the optimisation of processes and procedures, supercomputing and cloud computing, as well as the use of artificial intelligence and Big Data methods. The LRZ’s existing IT systems (including the MUC-NG supercomputer) and its experience with energy-efficient supercomputing will also prove useful.

The plan is to make around 40 petabytes available online for thousands of computing cores. DLR and the LRZ are arranging joint investment in the project, with the first stage of expansion planned for late 2020. The new HPDA platform will be integrated into the LRZ’s existing infrastructure in Garching, near Munich. Most of the data on the platform will also be freely and openly available to scientists from Bavarian universities and higher education institutions.

See the full article here .

five-ways-keep-your-child-safe-school-shootings

Please help promote STEM in your local schools.

Stem Education Coalition

DLR is the national aeronautics and space research centre of the Federal Republic of Germany. Its extensive research and development work in aeronautics, space, energy, transport and security is integrated into national and international cooperative ventures. In addition to its own research, as Germany’s space agency, DLR has been given responsibility by the federal government for the planning and implementation of the German space programme. DLR is also the umbrella organisation for the nation’s largest project management agency.

DLR has approximately 8000 employees at 16 locations in Germany: Cologne (headquarters), Augsburg, Berlin, Bonn, Braunschweig, Bremen, Goettingen, Hamburg, Juelich, Lampoldshausen, Neustrelitz, Oberpfaffenhofen, Stade, Stuttgart, Trauen, and Weilheim. DLR also has offices in Brussels, Paris, Tokyo and Washington D.C.

From ASCR Discovery: “Lessons machine-learned”

From ASCR Discovery
ASCR – Advancing Science Through Computing

From ASCR Discovery

May 2019

The University of Arizona’s Joshua Levine is using his Department of Energy Early Career Research Program award to combine machine learning and topology data-analysis tools to better understand trends within climate simulations. These map pairs represent data from January 1950 (top) and January 2010. The left panels depict near-surface air temperatures from hot (red) to cool (blue). In the multicolored images, Levine has used topological, or shape-based, data analysis to organize and color-code the temperature data into a tree-like hierarchy. As the time passes, the data behavior around the North Pole (right panels) breaks into smaller chunks. These changes highlight the need for machine-learning tools to understand how these structures evolve over time. Images courtesy of Joshua Levine, University of Arizona, with data from CMIP6/ESGF.

Quantifying the risks buried nuclear waste pose to soil and water near the Department of Energy’s (DOE’s) Hanford site in Washington state is not easy. Researchers can’t measure the earth’s permeability, a key factor in how far chemicals might travel, and mathematical models of how substances move underground are incomplete, says Paris Perdikaris of the University of Pennsylvania.

But where traditional experimental and computational tools fall short, artificial intelligence algorithms can help, building their own inferences based on patterns in the data. “We can’t directly measure the quantities we’re interested in,” he says. “But using this underlying mathematical structure, we can construct machine-learning algorithms that can predict what we care about.”

Perdikaris’ project is one of several sponsored by the DOE Early Career Research Program that apply machine-learning methods. One piece of his challenge is combining disparate data types such as images, simulations and time-resolved sensor information to find patterns. He will also constrain these models using physics and math, so the resulting predictions respect the underlying science and don’t make spurious connections based on data artifacts. “The byproduct of this is that you can significantly reduce the amount of data you need to make robust predictions. So you can save a lot in data efficiency terms.”

Another key obstacle is quantifying the uncertainty within these calculations. Missing aspects of the physical model or physical data can affect the prediction’s quality. Besides studying subsurface transport, such algorithms could also be useful for designing new materials.

Machine learning belongs to a branch of artificial intelligence algorithms that already support our smartphone assistants, manage our home devices and curate our movie and music playlists. Many machine-learning algorithms depend on tools known as neural networks, which mimic the human brain’s ability to filter, classify and draw insights from the patterns within data. Machine-learning methods could help scientists interpret a range of information. In some disciplines, experiments generate more data than researchers can hope to analyze on their own. In others, scientists might be looking for insights about their data and observations.

But industry’s tools alone won’t solve science’s problems. Today’s machine-learning algorithms, though powerful, make inferences researchers can’t verify against established theory. And such algorithms might flag experimental noise as meaningful. But with algorithms designed to handle science’s tenets, machine learning could boost computational efficiency, allow researchers to compare, integrate and improve physical models, and shift the ways that scientists work.

Much of industrial artificial intelligence work started with distinguishing, say, cats from Corvettes – analyzing millions of digital images in which data are abundant and have regular, pixelated structures. But with science, researchers don’t have the same luxury. Unlike the ubiquitous digital photos and language snippets that have powered image and voice recognition, scientific data can be expensive to generate, such as in molecular research experiments or large-scale simulations, says Argonne National Laboratory’s Prasanna Balaprakash.

With his early-career award, he’s designing machine-learning methods that incorporate scientific knowledge. “How do we leverage that? How do we bring in the physics, the domain knowledge, so that an algorithm doesn’t need a lot of data to learn?” He’s also focused on adapting machine-learning algorithms to accept a wider range of data types, including graph-like structures used for encoding molecules or large-scale traffic network scenarios.

Balaprakash also is exploring ways to automate the development of new machine-learning algorithms on supercomputers – a neural network for designing new neural networks. Writing these algorithms requires a lot of trial-and-error work, and a neural network built with one data type often can’t be used on a new data type.

Although some fields have data bottlenecks, in other situations scientific instruments generate gobs of data – gigabytes, even petabytes, of results that are beyond human capability to review and analyze. Machine learning could help researchers sift this information and glean important insights. For example, experiments on Sandia National Laboratories’ Z machine, which compresses energy to produce X-rays and to study nuclear fusion, spew out data about material properties under these extreme conditions.

Sandia Z machine

When superheated, samples studied in the Z machine mix in a complex process that researchers don’t fully understand yet, says Sandia’s Eric Cyr. He’s exploring data-driven algorithms that can divine an initial model of this mixing, giving theoretical physicists a starting point to work from. In addition, combining machine-learning tools with simulation data could help researchers streamline their use of the Z machine, reducing the number of experiments needed to achieve accurate results and minimizing costs.

To reach that goal, Cyr focuses on scalable machine algorithms, a technology known as layer-parallel methods. Today’s machine-learning algorithms have expanded from a handful of processing layers to hundreds. As researchers spread these layers over multiple graphics processing units (GPUs), the computational efficiency eventually breaks down. Cyr’s algorithms would split the neural-network layers across processors as the algorithm trains on the problem of interest, he says. “That way if you want to double the number of layers, basically make your neural network twice as deep, you can use twice as many processors and do it in the same amount of time.”

With problems such as climate and weather modeling, researchers struggle to incorporate the vast range of scales, from globe-circling currents to local eddies. To tackle this problem, Oklahoma State University’s Omer San will apply machine learning to study turbulence in these types of geophysical flows. Researchers must construct a computational grid to run these simulations, but they have to define the scale of the mesh, perhaps 100 kilometers across, to encompass the globe and produce a calculation of manageable size. At that scale, it’s impossible to simulate a range of smaller factors, such as vortices just a few meters wide that can produce important, outsized effects across the whole system because of nonlinear interactions. Machine learning could provide a way to add back in some of these fine details, San says, like software that sharpens a blurry photo.

Machine learning also could help guide researchers as they choose from the available closure models, or ways to model smaller-scale features, as they examine various flow types. It could be a decision-support system, San says, using local data to determine whether Model A or Model B is a better choice. His group also is examining ways to connect existing numerical methods within neural networks, to allow those techniques to partially inform the systems during the learning process, rather than doing blind analysis. San wants “to connect all of these dots: physics, numerics and the learning framework.”

Machine learning also promises to help researchers extend the use of mathematical strategies that already support data analysis. At the University of Arizona, Joshua Levine is combining machine learning with topological data-analysis tools.

These strategies capture data’s shape, which can be useful for visualizing and understanding climate patterns, such as surface temperatures over time. Levine wants to extend topology, which helps researchers analyze a single simulation, to multiple climate simulations with different parameters to understand them as a whole.

As climate scientists use different models, they often struggle to figure out which ones are correct. “More importantly, we don’t always know where they agree and disagree,” Levine says. “It turns out agreement is a little bit more tractable as a problem.” Researchers can do coarse comparisons – calculating the average temperature across the Earth and checking the models to see if those simple numbers agree. But that basic comparison says little about what happened within a simulation.

Topology can help match those average values with their locations, Levine says. “So it’s not just that it was hotter over the last 50 years, but maybe it was much hotter in Africa over the last 50 years than it was in South America.”

All of these projects involve blending machine learning with other disciplines to capitalize on each area’s relative strengths. Computational physics, for example, is built on well-defined principles and mathematical models. Such models provide a good baseline for study, Penn’s Perdikaris says. “But they’re a little bit sterilized and they don’t directly reflect the complexity of the real world.” By contrast, up to now machine learning has only relied on data and observations, he says, throwing away a scientist’s physical knowledge of the world. “Bridging the two approaches will be key in advancing our understanding and enhancing our ability to analyze and predict complex phenomena in the future.”

Although Argonne’s Balaprakash notes that machine learning has been oversold in some cases, he also believes it will be a transformative research tool, much like the Hubble telescope was for astronomy. “It’s a really promising research area.”

See the full article here.

five-ways-keep-your-child-safe-school-shootings

Please help promote STEM in your local schools.

Stem Education Coalition

ASCRDiscovery is a publication of The U.S. Department of Energy

From MIT News: “Painting a fuller picture of how antibiotics act”

From MIT News

May 9, 2019
Anne Trafton

MIT biological engineers used a novel machine-learning approach to discover a mechanism that helps certain antibiotics kill bacteria. Image: Chelsea Turner, MIT

Most antibiotics work by interfering with critical functions such as DNA replication or construction of the bacterial cell wall. However, these mechanisms represent only part of the full picture of how antibiotics act.

In a new study of antibiotic action, MIT researchers developed a new machine-learning approach to discover an additional mechanism that helps some antibiotics kill bacteria. This secondary mechanism involves activating the bacterial metabolism of nucleotides that the cells need to replicate their DNA.

“There are dramatic energy demands placed on the cell as a result of the drug stress. These energy demands require a metabolic response, and some of the metabolic byproducts are toxic and help contribute to killing the cells,” says James Collins, the Termeer Professor of Medical Engineering and Science in MIT’s Institute for Medical Engineering and Science (IMES) and Department of Biological Engineering, and the senior author of the study. Collins is also the faculty co-lead of the Abdul Latif Jameel Clinic for Machine Learning in Health.

Exploiting this mechanism could help researchers to discover new drugs that could be used along with antibiotics to enhance their killing ability, the researchers say.

Jason Yang, an IMES research scientist, is the lead author of the paper, which appears in the May 9 issue of Cell. Other authors include Sarah Wright, a recent MIT MEng recipient; Meagan Hamblin, a former Broad Institute research technician; Miguel Alcantar, an MIT graduate student; Allison Lopatkin, an IMES postdoc; Douglas McCloskey and Lars Schrubbers of the Novo Nordisk Foundation Center for Biosustainability; Sangeeta Satish and Amir Nili, both recent graduates of Boston University; Bernhard Palsson, a professor of bioengineering at the University of California at San Diego; and Graham Walker, an MIT professor of biology.

“White-box” machine-learning

Collins and Walker have studied the mechanisms of antibiotic action for many years, and their work has shown that antibiotic treatment tends to create a great deal of cellular stress that makes huge energy demands on bacterial cells. In the new study, Collins and Yang decided to take a machine-learning approach to investigate how this happens and what the consequences are.

Before they began their computer modeling, the researchers performed hundreds of experiments in E. coli. They treated the bacteria with one of three antibiotics — ampicillin, ciprofloxacin, or gentamicin, and in each experiment, they also added one of about 200 different metabolites, including an array of amino acids, carbohydrates, and nucleotides (the building blocks of DNA). For each combination of antibiotics and metabolites, they measured the effects on cell survival.

“We used a diverse set of metabolic perturbations so that we could see the effects of perturbing nucleotide metabolism, amino acid metabolism, and other kinds of metabolic subnetworks,” Yang says. “We wanted to fundamentally understand which previously undescribed metabolic pathways might be important for us to understand how antibiotics kill.”

Many other researchers have used machine-learning models to analyze data from biological experiments, by training an algorithm to generate predictions based on experimental data. However, these models are typically “black-box,” meaning that they don’t reveal the mechanisms that underlie their predictions.

To get around that problem, the MIT team took a novel approach that they call “white-box” machine-learning. Instead of feeding their data directly into a machine-learning algorithm, they first ran it through a genome-scale computer model of E. coli metabolism that had been characterized by Palsson’s lab. This allowed them to generate an array of “metabolic states” described by the data. Then, they fed these states into a machine-learning algorithm, which was able to identify links between the different states and the outcomes of antibiotic treatment.

Because the researchers already knew the experimental conditions that produced each state, they were able to determine which metabolic pathways were responsible for higher levels of cell death.

“What we demonstrate here is that by having the network simulations first interpret the data and then having the machine-learning algorithm build a predictive model for our antibiotic lethality phenotypes, the items that get selected by that predictive model themselves directly map onto pathways that we’ve been able to experimentally validate, which is very exciting,” Yang says.

Markus Covert, an associate professor of bioengineering at Stanford University, says the study is an important step toward showing that machine learning can be used to uncover the biological mechanisms that link inputs and outputs.

“Biology, especially for medical applications, is all about mechanism,” says Covert, who was not involved in the research. “You want to find something that is druggable. For the typical biologist, it hasn’t been meaningful to find these kinds of links without knowing why the inputs and outputs are linked.”

Metabolic stress

This model yielded the novel discovery that nucleotide metabolism, especially metabolism of purines such as adenine, plays a key role in antibiotics’ ability to kill bacterial cells. Antibiotic treatment leads to cellular stress, which causes cells to run low on purine nucleotides. The cells’ efforts to ramp up production of these nucleotides, which are necessary for copying DNA, boost the cells’ overall metabolism and leads to a buildup of harmful metabolic byproducts that can kill the cells.

“We now believe what’s going on is that in response to this very severe purine depletion, cells turn on purine metabolism to try to deal with that, but purine metabolism itself is very energetically expensive and so this amplifies the energic imbalance that the cells are already facing,” Yang says.

The findings suggest that it may be possible to enhance the effects of some antibiotics by delivering them along with other drugs that stimulate metabolic activity. “If we can move the cells to a more energetically stressful state, and induce the cell to turn on more metabolic activity, this might be a way to potentiate antibiotics,” Yang says.

The “white-box” modeling approach used in this study could also be useful for studying how different types of drugs affect diseases such as cancer, diabetes, or neurodegenerative diseases, the researchers say. They are now using a similar approach to study how tuberculosis survives antibiotic treatment and becomes drug-resistant.

The research was funded by the Defense Threat Reduction Agency, the National Institutes of Health, the Novo Nordisk Foundation, the Paul G. Allen Frontiers Group, the Broad Institute of MIT and Harvard, and the Wyss Institute for Biologically Inspired Engineering.

See the full article here .

five-ways-keep-your-child-safe-school-shootings
Please help promote STEM in your local schools.

Stem Education Coalition

The mission of MIT is to advance knowledge and educate students in science, technology, and other areas of scholarship that will best serve the nation and the world in the twenty-first century. We seek to develop in each member of the MIT community the ability and passion to work wisely, creatively, and effectively for the betterment of humankind.

From University of Maryland CMNS: “University of Maryland Launches Center for Machine Learning”

From University of Maryland

CMNS

April 16, 2019

Abby Robinson
301-405-5845
abbyr@umd.edu

The University of Maryland recently launched a multidisciplinary center that uses powerful computing tools to address challenges in big data, computer vision, health care, financial transactions and more.

The University of Maryland Center for Machine Learning will unify and enhance numerous activities in machine learning already underway on the Maryland campus.

University of Maryland computer science faculty member Thomas Goldstein (on left, with visiting graduate student) is a member of the new Center for Machine Learning. Goldstein’s research focuses on large-scale optimization and distributed algorithms for big data. Photo: John T. Consoli.

Machine learning uses algorithms and statistical models so that computer systems can effectively perform a task without explicit instructions, relying instead on patterns and inference. At UMD, for example, computer vision experts are “training” computers to identify and match key facial characteristics by having machines analyze millions of images publicly available on social media.

Researchers at UMD are exploring other applications such as groundbreaking work in cancer genomics; powerful algorithms to improve the selection process for organ transplants; and an innovative system that can quickly find, translate and summarize information from almost any language in the world.

“We wanted to capitalize on the significant strengths we already have in machine learning, provide additional support, and embrace fresh opportunities arising from new facilities and partnerships,” said Mihai Pop, professor of computer science and director of the University of Maryland Institute for Advanced Computer Studies (UMIACS).

The center officially launched with a workshop last month featuring talks and panel discussions from machine learning experts in auditory systems, biology and medicine, business, chemistry, natural language processing, and security.

Initial funding for the center comes from the College of Computer, Mathematical, and Natural Sciences (CMNS) and UMIACS, which will provide technical and administrative support.

An inaugural partner of the center, financial and technology leader Capital One, provided additional support, including endowing three faculty positions in machine learning and computer science. Those positions received matching funding from the state’s Maryland E-Nnovation Initiative.

Capital One has also provided funding for research projects that align with the organization’s need to stay on the cutting edge in areas like fraud detection and enhancing the customer experience with more personalized, real-time features.

“We are proud to be a part of the launch of the University of Maryland Center for Machine Learning, and are thrilled to extend our partnership with the university in this field,” said Dave Castillo, the company’s managing vice president at the Center for Machine Learning and Emerging Technology. “At Capital One, we believe forward-leaning technologies like machine learning can provide our customers greater protection, security, confidence and control of their finances. We look forward to advancing breakthrough work with the University of Maryland in years to come.”

University of Maryland computer science faculty members David Jacobs (left) and Furong Huang (right) are part of the new Center for Machine Learning. Jacobs is an expert in computer vision and is the center’s interim director; Huang is conducting research in neural networks. Photo: John T. Consoli.

David Jacobs, a professor of computer science with an appointment in UMIACS, will serve as interim director of the new center.

To jumpstart the center’s activities, Jacobs has recruited a core group of faculty members in computer science and UMIACS: John Dickerson, Soheil Feizi, Thomas Goldstein, Furong Huang and Aravind Srinivasan.

Faculty members from mathematics, chemistry, biology, physics, linguistics, and data science are also heavily involved in machine learning applications, and Jacobs said he expects many of them to be active in the center through direct or affiliate appointments.

“We want the center to be a focal point across the campus where faculty, students, and visiting scholars can come to learn about the latest technologies and theoretical applications based in machine learning,” he said.

Key to the center’s success will be a robust computational infrastructure that is needed to perform complex computations involving massive amounts of data.

This is where UMIACS plays an important role, Jacobs said, with the institute’s technical staff already supporting multiple machine learning activities in computer vision and computational linguistics.

Plans call for CMNS, UMIACS and other organizations to invest substantially in new computing resources for the machine learning center, Jacobs added.

The Brendan Iribe Center for Computer Science and Engineering. Photo: John T. Consoli.

The center will be located in the Brendan Iribe Center for Computer Science and Engineering, a new state-of-the-art facility at the entrance to campus that will be officially dedicated later this month. In addition to the very latest in computing resources, the Brendan Iribe Center promotes collaboration and connectivity through its open design and multiple meeting areas.

The Brendan Iribe Center is directly adjacent to the university’s Discovery District, where researchers working in Capital One’s Tech Incubator and other tech startups can interact with UMD faculty members and students on topics related to machine learning.

Amitabh Varshney, professor of computer science and dean of CMNS, said the center will be a valuable resource for the state of Maryland and the region—both for students seeking the latest knowledge and skills and for companies wanting professional development training for their employees.

“We have new educational activities planned by the college that include professional master’s programs in machine learning and data science and analytics,” Varshney said. “We want to leverage our location near numerous federal agencies and private corporations that are interested in expanding their workforce capabilities in these areas.”

See the full article here .

five-ways-keep-your-child-safe-school-shootings

Please help promote STEM in your local schools.

Stem Education Coalition

About CMNS

The thirst for new knowledge is a fundamental and defining characteristic of humankind. It is also at the heart of scientific endeavor and discovery. As we seek to understand our world, across a host of complexly interconnected phenomena and over scales of time and distance that were virtually inaccessible to us a generation ago, our discoveries shape that world. At the forefront of many of these discoveries is the College of Computer, Mathematical, and Natural Sciences (CMNS).

CMNS is home to 12 major research institutes and centers and to 10 academic departments: astronomy, atmospheric and oceanic science, biology, cell biology and molecular genetics, chemistry and biochemistry, computer science, entomology, geology, mathematics, and physics.

Our Faculty

Our faculty are at the cutting edge over the full range of these disciplines. Our physicists fill in major gaps in our fundamental understanding of matter, participating in the recent Higgs boson discovery, and demonstrating the first-ever teleportation of information between atoms. Our astronomers probe the origin of the universe with one of the world’s premier radio observatories, and have just discovered water on the moon. Our computer scientists are developing the principles for guaranteed security and privacy in information systems.

Our Research

Driven by the pursuit of excellence, the University of Maryland has enjoyed a remarkable rise in accomplishment and reputation over the past two decades. By any measure, Maryland is now one of the nation’s preeminent public research universities and on a path to become one of the world’s best. To fulfill this promise, we must capitalize on our momentum, fully exploit our competitive advantages, and pursue ambitious goals with great discipline and entrepreneurial spirit. This promise is within reach. This strategic plan is our working agenda.

The plan is comprehensive, bold, and action oriented. It sets forth a vision of the University as an institution unmatched in its capacity to attract talent, address the most important issues of our time, and produce the leaders of tomorrow. The plan will guide the investment of our human and material resources as we strengthen our undergraduate and graduate programs and expand research, outreach and partnerships, become a truly international center, and enhance our surrounding community.

Our success will benefit Maryland in the near and long term, strengthen the State’s competitive capacity in a challenging and changing environment and enrich the economic, social and cultural life of the region. We will be a catalyst for progress, the State’s most valuable asset, and an indispensable contributor to the nation’s well-being. Achieving the goals of Transforming Maryland requires broad-based and sustained support from our extended community. We ask our stakeholders to join with us to make the University an institution of world-class quality with world-wide reach and unparalleled impact as it serves the people and the state of Maryland.

Our researchers are also at the cusp of the new biology for the 21st century, with bioscience emerging as a key area in almost all CMNS disciplines. Entomologists are learning how climate change affects the behavior of insects, and earth science faculty are coupling physical and biosphere data to predict that change. Geochemists are discovering how our planet evolved to support life, and biologists and entomologists are discovering how evolutionary processes have operated in living organisms. Our biologists have learned how human generated sound affects aquatic organisms, and cell biologists and computer scientists use advanced genomics to study disease and host-pathogen interactions. Our mathematicians are modeling the spread of AIDS, while our astronomers are searching for habitable exoplanets.

Our Education

CMNS is also a national resource for educating and training the next generation of leaders. Many of our major programs are ranked among the top 10 of public research universities in the nation. CMNS offers every student a high-quality, innovative and cross-disciplinary educational experience that is also affordable. Strongly committed to making science and mathematics studies available to all, CMNS actively encourages and supports the recruitment and retention of women and minorities.

Our Students

Our students have the unique opportunity to work closely with first-class faculty in state-of-the-art labs both on and off campus, conducting real-world, high-impact research on some of the most exciting problems of modern science. 87% of our undergraduates conduct research and/or hold internships while earning their bachelor’s degree. CMNS degrees command respect around the world, and open doors to a wide variety of rewarding career options. Many students continue on to graduate school; others find challenging positions in high-tech industry or federal laboratories, and some join professions such as medicine, teaching, and law.

From Geospatial World: “Google and DeepMind predict wind energy output using AI”

From Geospatial World

03/04/2019
Aditya Chaturvedi

Image Courtesy: Unsplash

Google has announced in its official blog post that it has enhanced the feasibility of wind energy by using AI software created by its UK subsidiary DeepMind.

Renewable energy is the way towards lowering carbon emissions and sustainability, so it is imperative that we focus on yielding optimum energy outputs from renewable energy.

Renewable technologies will be at the forefront of climate change mitigation and addressing global warming, however, the complete potential is yet to be harnessed owing to a slew of obstructions. Wind energy has emerged as a crucial source of renewable energy in the past decade due to a decline in the cost of turbines that has led to the gradual mainstreaming of wind power. Though, unpredictability in delivering power at set time frame continues to remain a daunting challenge before the sector.

Google and DeepMind project will change this forever by overcoming this limitation that has hobbled wind energy adoption.

With the help of DeepMind’s Machine Learning algorithms, Google has been able to predict the wind energy output of the farms that it uses for its Green Energy initiatives.

“DeepMind and Google started applying machine learning algorithms to 700 megawatts of wind power capacity in the central United States. These wind farms—part of Google’s global fleet of renewable energy projects—collectively generate as much electricity as is needed by a medium-sized city”, the blog says.

Google is optimistic that it can accurately predict and schedule energy output, which certainly would have an upper hand over non-time based deliveries.

Image Courtesy: Google/ DeepMind

Taking a neural network that makes uses of weather forecasts and turbine data history, DeepMind system has been configured to predict wind power output 36 hours in advance.

Taking a cue from these predictions, the advanced model recommends the best possible method to fulfill, and even exceed, delivery commitments 24 hrs in advance. Its importance can be estimated from the fact that energy sources that deliver a particular amount of power over a defined period of time are usually more vulnerable to the grid.

Google is working to make the algorithm more refined so that any discrepancy that might occur could be nullified. Till date, Google claims that Machine Learning algorithms have boosted wind energy generated by 20%, ‘compared to the to the baseline scenario of no time-based commitments to the grid’, the blog says.

Image Courtesy: Google

Completely doing away with wind variability is next to impossible, but Google claims that Machine Learning and AI would indeed make wind power more predictable and hence more useful.

This unique approach would surely open up new avenues and make wind farm data more reliable and precise. When the productivity of wind power farms in greatly increased and their output can be predicted as well as calculated, wind will have the capability to match conventional electricity sources.

Google is hopeful that the power of Machine Learning and AI would boost the mass adoption of wind power and turn it into a popular alternative to traditional sources of electricity over the years.

See the full article here .

five-ways-keep-your-child-safe-school-shootings

Please help promote STEM in your local schools.

Stem Education Coalition

http://www.geospatialworld.net

With an average of 55,000+ unique visitors per month, http://www.geospatialworld.net is easily the number one media portal in geospatial domain; and is a reliable source of information for professionals in 150+ countries. The website, which integrates text, graphics and video elements, is an interactive medium for geospatial industry stakeholders to connect through several innovative features, including news, videos, guest blogs, case studies, articles, interviews, business listings and events.

600,000+ annual unique visitors

From Symmetry: “Studying the stars with machine learning”

From Symmetry

10/16/18
Evelyn Lamb

Illustration by Sandbox Studio, Chicago with Corinne Mucha

To keep up with an impending astronomical increase in data about our universe, astrophysicists turn to machine learning.

Kevin Schawinski had a problem.

In 2007 he was an astrophysicist at Oxford University and hard at work reviewing seven years’ worth of photographs from the Sloan Digital Sky Survey—images of more than 900,000 galaxies. He spent his days looking at image after image, noting whether a galaxy looked spiral or elliptical, or logging which way it seemed to be spinning.

Technological advancements had sped up scientists’ ability to collect information, but scientists were still processing information at the same rate. After working on the task full time and barely making a dent, Schawinski and colleague Chris Lintott decided there had to be a better way to do this.

There was: a citizen science project called Galaxy Zoo. Schawinski and Lintott recruited volunteers from the public to help out by classifying images online. Showing the same images to multiple volunteers allowed them to check one another’s work. More than 100,000 people chipped in and condensed a task that would have taken years into just under six months.

Citizen scientists continue to contribute to image-classification tasks. But technology also continues to advance.

The Dark Energy Spectroscopic Instrument, scheduled to begin in 2019, will measure the velocities of about 30 million galaxies and quasars over five years.

LBNL/DESI Dark Energy Spectroscopic Instrument for the Nicholas U. Mayall 4-meter telescope at Kitt Peak National Observatory near Tucson, Ariz, USA

The Large Synoptic Survey Telescope, scheduled to begin in the early 2020s, will collect more than 30 terabytes of data each night—for a decade.

LSST

LSST Camera, built at SLAC

LSST telescope, currently under construction on the El Peñón peak at Cerro Pachón Chile, a 2,682-meter-high mountain in Coquimbo Region, in northern Chile, alongside the existing Gemini South and Southern Astrophysical Research Telescopes.

“The volume of datasets [from those surveys] will be at least an order of magnitude larger,” says Camille Avestruz, a postdoctoral researcher at the University of Chicago.

To keep up, astrophysicists like Schawinski and Avestruz have recruited a new class of non-scientist scientists: machines.

Researchers are using artificial intelligence to help with a variety of tasks in astronomy and cosmology, from image analysis to telescope scheduling.

Superhuman scheduling, computerized calibration

Artificial intelligence is an umbrella term for ways in which computers can seem to reason, make decisions, learn, and perform other tasks that we associate with human intelligence. Machine learning is a subfield of artificial intelligence that uses statistical techniques and pattern recognition to train computers to make decisions, rather than programming more direct algorithms.

In 2017, a research group from Stanford University used machine learning to study images of strong gravitational lensing, a phenomenon in which an accumulation of matter in space is dense enough that it bends light waves as they travel around it.

Gravitational Lensing NASA/ESA

Because many gravitational lenses can’t be accounted for by luminous matter alone, a better understanding of gravitational lenses can help astronomers gain insight into dark matter.

In the past, scientists have conducted this research by comparing actual images of gravitational lenses with large numbers of computer simulations of mathematical lensing models, a process that can take weeks or even months for a single image. The Stanford team showed that machine learning algorithms can speed up this process by a factor of millions.

Greg Stewart, SLAC National Accelerator Laboratory

Schawinski, who is now an astrophysicist at ETH Zürich, uses machine learning in his current work. His group has used tools called generative adversarial networks, or GAN, to recover clean versions of images that have been degraded by random noise. They recently published a paper [Astronomy and Astrophysics]about using AI to generate and test new hypotheses in astrophysics and other areas of research.

Another application of machine learning in astrophysics involves solving logistical challenges such as scheduling. There are only so many hours in a night that a given high-powered telescope can be used, and it can only point in one direction at a time. “It costs millions of dollars to use a telescope for on the order of weeks,” says Brian Nord, a physicist at the University of Chicago and part of Fermilab’s Machine Intelligence Group, which is tasked with helping researchers in all areas of high-energy physics deploy AI in their work.

Machine learning can help observatories schedule telescopes so they can collect data as efficiently as possible. Both Schawinski’s lab and Fermilab are using a technique called reinforcement learning to train algorithms to solve problems like this one. In reinforcement learning, an algorithm isn’t trained on “right” and “wrong” answers but through differing rewards that depend on its outputs. The algorithms must strike a balance between the safe, predictable payoffs of understood options and the potential for a big win with an unexpected solution.

Illustration by Sandbox Studio, Chicago with Corinne Mucha

A growing field

When computer science graduate student Shubhendu Trivedi of the Toyota Technological Institute at University of Chicago started teaching a graduate course on deep learning with one of his mentors, Risi Kondor, he was pleased with how many researchers from the physical sciences signed up for it. They didn’t know much about how to use AI in their research, and Trivedi realized there was an unmet need for machine learning experts to help scientists in different fields find ways of exploiting these new techniques.

The conversations he had with researchers in his class evolved into collaborations, including participation in the Deep Skies Lab, an astronomy and artificial intelligence research group co-founded by Avestruz, Nord and astronomer Joshua Peek of the Space Telescope Science Institute. Earlier this month, they submitted their first peer-reviewed paper demonstrating the efficiency of an AI-based method to measure gravitational lensing in the Cosmic Microwave Background [CMB].

Similar groups are popping up across the world, from Schawinski’s group in Switzerland to the Centre for Astrophysics and Supercomputing in Australia. And adoption of machine learning techniques in astronomy is increasing rapidly. In an arXiv search of astronomy papers, the terms “deep learning” and “machine learning” appear more in the titles of papers from the first seven months of 2018 than from all of 2017, which in turn had more than 2016.

“Five years ago, [machine learning algorithms in astronomy] were esoteric tools that performed worse than humans in most circumstances,” Nord says. Today, more and more algorithms are consistently outperforming humans. “You’d be surprised at how much low-hanging fruit there is.”

But there are obstacles to introducing machine learning into astrophysics research. One of the biggest is the fact that machine learning is a black box. “We don’t have a fundamental theory of how neural networks work and make sense of things,” Schawinski says. Scientists are understandably nervous about using tools without fully understanding how they work.

Another related stumbling block is uncertainty. Machine learning often depends on inputs that all have some amount of noise or error, and the models themselves make assumptions that introduce uncertainty. Researchers using machine learning techniques in their work need to understand these uncertainties and communicate those accurately to each other and the broader public.

The state of the art in machine learning is changing so rapidly that researchers are reluctant to make predictions about what will be coming even in the next five years. “I would be really excited if as soon as data comes off the telescopes, a machine could look at it and find unexpected patterns,” Nord says.

No matter exactly the form future advances take, the data keeps coming faster and faster, and researchers are increasingly convinced that artificial intelligence is going to be necessary to help them keep up.

See the full article here .

five-ways-keep-your-child-safe-school-shootings

Please help promote STEM in your local schools.

Stem Education Coalition

Symmetry is a joint Fermilab/SLAC publication.

From Brown University: “Brown awarded $3.5M to speed up atomic-scale computer simulations”

From Brown University

September 20, 2018
Kevin Stacey
kevin_stacey@brown.edu
401-863-3766

Andrew Peterson. No photo credit.

With a new grant from the U.S. Department of Energy, a Brown University-led research team will use machine learning to speed up atom-level simulations of chemical reactions and the properties of materials.

“Simulations provide insights into materials and chemical processes that we can’t readily get from experiments,” said Andrew Peterson, an associate professor in Brown’s School of Engineering who will lead the work.

“Computational power is growing rapidly, which lets us perform larger and more realistic simulations. But as the size of the simulations grows, the time involved in running them can grow exponentially. This paradox means that even with the growth in computational power, our field still cannot perform truly large-scale simulations. Our goal is to speed those simulations up dramatically — ideally by orders of magnitude — using machine learning.”

The grant provides $3.5 million dollars for the work over four years. Peterson will work with two Brown colleagues — Franklin Goldsmith, assistant professor of engineering, and Brenda Rubenstein, assistant professor of chemistry — as well as researchers from Carnegie Mellon, Georgia Tech and MIT.

The idea behind the work is that different simulations often have the same sets of calculations underlying them. Peterson and his colleagues aim to use machine learning to find those underlying similarities and fast-forward through them.

“What we’re doing is taking the results of calculations from prior simulations and using them to predict the outcome of calculations that haven’t been done yet,” Peterson said. “If we can eliminate the need to do similar calculations over and over again, we can speed things up dramatically, potentially by orders of magnitude.”

The team will focus their work initially on simulations of electrocatalysis — the kinds of chemical reactions that are important in devices like fuel cells and batteries. These are complex, often multi-step reactions that are fertile ground for simulation-driven research, Peterson says.

Atomic-scale simulations have demonstrated usefulness in Peterson’s own work in the design of new catalysts. In a recent example, Peterson worked with Brown chemist Shouheng Sun on a gold nanoparticle catalyst that can perform a reaction necessary for converting carbon dioxide into useful forms of carbon. Peterson’s simulations showed it was the sharp edges of the oddly shaped catalyst that were particularly active for the desired reaction.

“That led us to change the geometry of the catalyst to a nanowire — something that’s basically all edges — to maximize its reactivity,” Peterson said. “We might have eventually tried a nanowire by trial and error, but because of the computational insights we were able to get there much more quickly.”

The researchers will use a software package that Peterson’s research group developed previously as a starting point. The software, called AMP (Atomistic Machine-learning Package) is open-source and already widely used in the simulation community, Peterson says.

The Department of Energy grant will bring atomic-scale simulations — and the insights they produce — to bear on ever larger and more complex simulations. And while the work under the grant will focus on electrocatalysis, the tools the team develops should be widely applicable to other types of material and chemical simulations.

Peterson is hopeful that the investment that the federal government is making in machine learning will be repaid by making better use of valuable computing resources.

“Modern supercomputers cost millions of dollars to build, and simulation time on them is precious,” Peterson said. “If we’re able to free up time on those machines for additional simulations to be run, that translates into vastly increased return-on-investment for those machines. It’s real money.”

See the full article here .

five-ways-keep-your-child-safe-school-shootings

Please help promote STEM in your local schools.

Stem Education Coalition

Welcome to Brown

Located in historic Providence, Rhode Island and founded in 1764, Brown University is the seventh-oldest college in the United States. Brown is an independent, coeducational Ivy League institution comprising undergraduate and graduate programs, plus the Alpert Medical School, School of Public Health, School of Engineering, and the School of Professional Studies.

With its talented and motivated student body and accomplished faculty, Brown is a leading research university that maintains a particular commitment to exceptional undergraduate instruction.

Brown’s vibrant, diverse community consists of 6,000 undergraduates, 2,000 graduate students, 400 medical school students, more than 5,000 summer, visiting and online students, and nearly 700 faculty members. Brown students come from all 50 states and more than 100 countries.

Undergraduates pursue bachelor’s degrees in more than 70 concentrations, ranging from Egyptology to cognitive neuroscience. Anything’s possible at Brown—the university’s commitment to undergraduate freedom means students must take responsibility as architects of their courses of study.

From Fermi National Accelerator Lab: “MicroBooNE demonstrates use of convolutional neural networks on liquid-argon TPC data for first time”

FNAL Art Image by Angela Gonzales

Fermi National Accelerator Lab is an enduring source of strength for the US contribution to scientific research world wide.

September 12, 2018
Victor Genty, Kazuhiro Terao and Taritree

It is hard these days not to encounter examples of machine learning out in the world. Chances are, if your phone unlocks using facial recognition or if you’re using voice commands to control your phone, you are likely using machine learning algorithms — in particular deep neural networks.

What makes these algorithms so powerful is that they learn relationships between high-level concepts we wish to find in an image (faces) or sound wave (words) with sets of low-level patterns (lines, shapes, colors, textures, individual sounds), which represent them in the data. Furthermore, these low-level patterns and relationships do not have to be conceived of or hand-designed by humans, but instead are learned directly from examples of the data. Not having to come up with new patterns to find for each new problem is why deep neural networks have been able to advance the state of the art for so many different types of problems: from analyzing video for self-driving cars to assisting robots in learning how to manipulate objects.

Here at Fermilab, there has been a lot of effort in having these deep neural networks help us analyze the data from our particle detectors so that we can more quickly and effectively use it to look for new physics. These applications are a continuation of the high-energy physics community’s long history in adopting and furthering the use of machine learning algorithms.

Recently, the MicroBooNE neutrino experiment published a paper describing how they used convolutional neural networks — a particular type of deep neural network — to sort individual pixels coming from images made by a particular type of detector known as a liquid-argon time projection (LArTPC) chamber. The experiment designed a convolutional neural network called U-ResNet to distinguish between two types of pixels: those that were a part of a track-like particle trajectory from those that were a part of a shower-like particle trajectory.

This plot shows a comparison of U-ResNet performance on data and simulation, where the true pixel labels are provided by a physicist. The sample used is 100 events that contain a charged-current neutrino interaction candidate with neutral pions produced at the event vertex. The horizontal axis shows the fraction of pixels where the prediction by U-ResNet differed from the labels for each event. The error bars indicate only a statistical uncertainty.

Track-like trajectories, made by particles such as a muon or proton, consist of a line with small curvature. Shower-like trajectories, produced by particles such as an electron or photon, are more complex topological features with many branching trajectories. This distinction is important because separating these type of topologies is known to be difficult for traditional algorithms. Not only that, shower-like shapes are produced when electrons and photons interact in the detector, and these two particles are often an important signal or background in physics analyses.

MicroBooNE researchers demonstrated that these networks not only performed well but also worked in a similar fashion when presented with simulated data and real data. The latter is the first time this has been demonstrated for data from LArTPCs.

Showing that networks behave the same on simulated and real data is critical, because these networks are typically trained on simulated data. Recall that these networks learn by looking at many examples. In industry, gathering large “training” data sets is an arduous and expensive task. However, particle physicists have a secret weapon — they can create as much simulated data as they want, since all experiments produce a highly detailed model of their detectors and data acquisition systems in order to produce as faithful a representation of the data as possible.

However, these models are never perfect. And so a big question was, “Is the simulated data close enough to the real data to properly train these neural networks?” The way MicroBooNE answered this question is by performing a Turing test that compares the performance of the network to that of a physicist. They demonstrated that the accuracy of the human was similar to the machine when labeling simulated data, for which an absolute accuracy can be defined. They then compared the labels for real data. Here the disagreement between labels was low, and similar between machine and human (See the top figure. See the figure below for an example of how a human and computer labeled the same data event.) In addition, a number of qualitative studies looked at the correlation between manipulations of the image and the label provided by the network. They showed that the correlations follow human-like intuitions. For example, as a line segment gets shorter, the network becomes less confident if the segment is due to a track or a shower. This suggests that the low-level correlations being used are the same physically motivated correlations a physicist would use if engineering an algorithm by hand.

This example image shows a charged-current neutrino interaction with decay gamma rays from a neutral pion (left). The label image (middle) is shown with the output of U-ResNet (right) where track and shower pixels are shown in yellow and cyan color respectively.

Demonstrating this simulated-versus-real data milestone is important because convolutional neural networks are valuable to current and future neutrino experiments that will use LArTPCs. This track-shower labeling is currently being employed in upcoming MicroBooNE analyses. Furthermore, for the upcoming Deep Underground Neutrino Experiment (DUNE), convolutional neural networks are showing much promise toward having the performance necessary to achieve DUNE’s physics goals, such as the measurement of CP violation, a possible explanation of the asymmetry in the presence of matter and antimatter in the current universe.

FNAL LBNF/DUNE from FNAL to SURF, Lead, South Dakota, USA

FNAL DUNE Argon tank at SURF

Surf-Dune/LBNF Caverns at Sanford

SURF building in Lead SD USA

The more demonstrations there are that these algorithms work on real LArTPC data, the more confidence the community can have that convolutional neural networks will help us learn about the properties of the neutrino and the fundamental laws of nature once DUNE begins to take data.

Science paper:
A Deep Neural Network for Pixel-Level Electromagnetic Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
https://arxiv.org/abs/1808.07269

Victor Genty, Kazuhiro Terao and Taritree Wongjirad are three of the scientists who analyzed this result. Victor Genty is a graduate student at Columbia University. Kazuhiro Terao is a physicist at SLAC National Accelerator Laboratory. Taritree Wongjirad is an assistant professor at Tufts University.

See the full article here .

five-ways-keep-your-child-safe-school-shootings

Please help promote STEM in your local schools.

Stem Education Coalition

Fermi National Accelerator Laboratory (Fermilab), located just outside Batavia, Illinois, near Chicago, is a US Department of Energy national laboratory specializing in high-energy particle physics. Fermilab is America’s premier laboratory for particle physics and accelerator research, funded by the U.S. Department of Energy. Thousands of scientists from universities and laboratories around the world
collaborate at Fermilab on experiments at the frontiers of discovery.

FNAL/MINERvA

FNAL DAMIC

FNAL Muon g-2 studio

FNAL Short-Baseline Near Detector under construction

FNAL Mu2e solenoid

Dark Energy Camera [DECam], built at FNAL

FNAL DUNE Argon tank at SURF

FNAL/MicrobooNE

FNAL Don Lincoln

FNAL/MINOS

FNAL Cryomodule Testing Facility

FNAL Minos Far Detector

FNAL LBNF/DUNE from FNAL to SURF, Lead, South Dakota, USA

FNAL/NOvA experiment map

FNAL NOvA Near Detector

FNAL ICARUS

FNAL Holometer

From Breakthrough Listen via Science Alert: “Astronomers Have Detected an Astonishing 72 New Mystery Radio Bursts From Space “

From Breakthrough Listen Project

via

Science Alert

11 SEP 2018
MICHELLE STARR

A massive number of new signals have been discovered coming from the notorious repeating fast radio source FRB 121102 – and we can thank artificial intelligence for these findings.

Researchers at the search for extraterrestrial intelligence (SETI) project Breakthrough Listen applied machine learning to comb through existing data, and found 72 fast radio bursts that had previously been missed.

Fast radio bursts (FRBs) are among the most mysterious phenomena in the cosmos. They are extremely powerful, generating as much energy as hundreds of millions of Suns. But they are also extremely short, lasting just milliseconds; and most of them only occur once, without warning.

This means they can’t be predicted; so it’s not like astronomers are able to plan observations. They are only picked up later in data from other radio observations of the sky.

Except for one source. FRB 121102 is a special individual – because ever since its discovery in 2012, it has been caught bursting again and again, the only FRB source known to behave this way.

Because we know FRB 121102 to be a repeating source of FRBs, this means we can try to catch it in the act. This is exactly what researchers at Breakthrough Listen did last year. On 26 August 2017, they pointed the Green Bank Telescope in West Virginia at its location for five hours.

In the 400 terabytes of data from that observation, the researchers discovered 21 FRBs using standard computer algorithms, all from within the first hour. They concluded that the source goes through periods of frenzied activity and quiescence.

But the powerful new algorithm used to reanalyse that August 26 data suggests that FRB 121102 is a lot more active and possibly complex than originally thought. Researchers trained what is known as a convolutional neural network to look for the signals, then set it loose on the data like a truffle pig.

It returned triumphant with 72 previously undetected signals, bringing the total number that astronomers have observed from the object to around 300.

“This work is only the beginning of using these powerful methods to find radio transients,” said astronomer Gerry Zhang of the University of California Berkeley, which runs Breakthrough Listen.

“We hope our success may inspire other serious endeavours in applying machine learning to radio astronomy.”

The new result has helped us learn a little more about FRB 121102, putting constraints on the periodicity of the bursts. It suggests that, the researchers said, there’s no pattern to the way we receive them – unless the pattern is shorter than 10 milliseconds.

See the full article here .

five-ways-keep-your-child-safe-school-shootings

Please help promote STEM in your local schools.

Stem Education Coalition

Listen

Breakthrough Listen is the largest ever scientific research program aimed at finding evidence of civilizations beyond Earth. The scope and power of the search are on an unprecedented scale:

The program includes a survey of the 1,000,000 closest stars to Earth. It scans the center of our galaxy and the entire galactic plane. Beyond the Milky Way, it listens for messages from the 100 closest galaxies to ours.

The instruments used are among the world’s most powerful. They are 50 times more sensitive than existing telescopes dedicated to the search for intelligence.

CSIRO/Parkes Observatory, located 20 kilometres north of the town of Parkes, New South Wales, Australia

UCSC Lick Automated Planet Finder telescope, Mount Hamilton, CA, USA

GBO radio telescope, Green Bank, West Virginia, USA

The radio surveys cover 10 times more of the sky than previous programs. They also cover at least 5 times more of the radio spectrum – and do it 100 times faster. They are sensitive enough to hear a common aircraft radar transmitting to us from any of the 1000 nearest stars.

We are also carrying out the deepest and broadest ever search for optical laser transmissions. These spectroscopic searches are 1000 times more effective at finding laser signals than ordinary visible light surveys. They could detect a 100 watt laser (the energy of a normal household bulb) from 25 trillion miles away.

Listen combines these instruments with innovative software and data analysis techniques.

The initiative will span 10 years and commit a total of $100,000,000.

From MIT News: “Taking machine thinking out of the black box”

From MIT News

September 5, 2018
Anne McGovern | Lincoln Laboratory

Members of a team developing Adaptable Interpretable Machine Learning at Lincoln Laboratory are: (l-r) Melva James, Stephanie Carnell, Jonathan Su, and Neela Kaushik. Photo: Glen Cooper.

Adaptable Interpretable Machine Learning project is redesigning machine learning models so humans can understand what computers are thinking.

Software applications provide people with many kinds of automated decisions, such as identifying what an individual’s credit risk is, informing a recruiter of which job candidate to hire, or determining whether someone is a threat to the public. In recent years, news headlines have warned of a future in which machines operate in the background of society, deciding the course of human lives while using untrustworthy logic.

Part of this fear is derived from the obscure way in which many machine learning models operate. Known as black-box models, they are defined as systems in which the journey from input to output is next to impossible for even their developers to comprehend.

“As machine learning becomes ubiquitous and is used for applications with more serious consequences, there’s a need for people to understand how it’s making predictions so they’ll trust it when it’s doing more than serving up an advertisement,” says Jonathan Su, a member of the technical staff in MIT Lincoln Laboratory’s Informatics and Decision Support Group.

Currently, researchers either use post hoc techniques or an interpretable model such as a decision tree to explain how a black-box model reaches its conclusion. With post hoc techniques, researchers observe an algorithm’s inputs and outputs and then try to construct an approximate explanation for what happened inside the black box. The issue with this method is that researchers can only guess at the inner workings, and the explanations can often be wrong. Decision trees, which map choices and their potential consequences in a tree-like construction, work nicely for categorical data whose features are meaningful, but these trees are not interpretable in important domains, such as computer vision and other complex data problems.

Su leads a team at the laboratory that is collaborating with Professor Cynthia Rudin at Duke University, along with Duke students Chaofan Chen, Oscar Li, and Alina Barnett, to research methods for replacing black-box models with prediction methods that are more transparent. Their project, called Adaptable Interpretable Machine Learning (AIM), focuses on two approaches: interpretable neural networks as well as adaptable and interpretable Bayesian rule lists (BRLs).

A neural network is a computing system composed of many interconnected processing elements. These networks are typically used for image analysis and object recognition. For instance, an algorithm can be taught to recognize whether a photograph includes a dog by first being shown photos of dogs. Researchers say the problem with these neural networks is that their functions are nonlinear and recursive, as well as complicated and confusing to humans, and the end result is that it is difficult to pinpoint what exactly the network has defined as “dogness” within the photos and what led it to that conclusion.

To address this problem, the team is developing what it calls “prototype neural networks.” These are different from traditional neural networks in that they naturally encode explanations for each of their predictions by creating prototypes, which are particularly representative parts of an input image. These networks make their predictions based on the similarity of parts of the input image to each prototype.

As an example, if a network is tasked with identifying whether an image is a dog, cat, or horse, it would compare parts of the image to prototypes of important parts of each animal and use this information to make a prediction. A paper on this work: “This looks like that: deep learning for interpretable image recognition,” was recently featured in an episode of the “Data Science at Home” podcast. A previous paper, “Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions,” used entire images as prototypes, rather than parts.

The other area the research team is investigating is BRLs, which are less-complicated, one-sided decision trees that are suitable for tabular data and often as accurate as other models. BRLs are made of a sequence of conditional statements that naturally form an interpretable model. For example, if blood pressure is high, then risk of heart disease is high. Su and colleagues are using properties of BRLs to enable users to indicate which features are important for a prediction. They are also developing interactive BRLs, which can be adapted immediately when new data arrive rather than recalibrated from scratch on an ever-growing dataset.

Stephanie Carnell, a graduate student from the University of Florida and a summer intern in the Informatics and Decision Support Group, is applying the interactive BRLs from the AIM program to a project to help medical students become better at interviewing and diagnosing patients. Currently, medical students practice these skills by interviewing virtual patients and receiving a score on how much important diagnostic information they were able to uncover. But the score does not include an explanation of what, precisely, in the interview the students did to achieve their score. The AIM project hopes to change this.

“I can imagine that most medical students are pretty frustrated to receive a prediction regarding success without some concrete reason why,” Carnell says. “The rule lists generated by AIM should be an ideal method for giving the students data-driven, understandable feedback.”

The AIM program is part of ongoing research at the laboratory in human-systems engineering — or the practice of designing systems that are more compatible with how people think and function, such as understandable, rather than obscure, algorithms.

“The laboratory has the opportunity to be a global leader in bringing humans and technology together,” says Hayley Reynolds, assistant leader of the Informatics and Decision Support Group. “We’re on the cusp of huge advancements.”

Melva James is another technical staff member in the Informatics and Decision Support Group involved in the AIM project. “We at the laboratory have developed Python implementations of both BRL and interactive BRLs,” she says. “[We] are concurrently testing the output of the BRL and interactive BRL implementations on different operating systems and hardware platforms to establish portability and reproducibility. We are also identifying additional practical applications of these algorithms.”

Su explains: “We’re hoping to build a new strategic capability for the laboratory — machine learning algorithms that people trust because they understand them.”

See the full article here .

five-ways-keep-your-child-safe-school-shootings
Please help promote STEM in your local schools.

Stem Education Coalition

The mission of MIT is to advance knowledge and educate students in science, technology, and other areas of scholarship that will best serve the nation and the world in the twenty-first century. We seek to develop in each member of the MIT community the ability and passion to work wisely, creatively, and effectively for the betterment of humankind.