skip to main content

Title: Deep Learning for Climate Models of the Atlantic Ocean
A deep neural network is trained to predict sea surface temperature variations at two important regions of the Atlantic ocean, using 800 years of simulated climate dynamics based on the first-principles physics models. This model is then tested against 60 years of historical data. Our statistical model learns to approximate the physical laws governing the simulation, providing significant improvement over simple statistical forecasts and comparable to most state-of-the-art dynamical/conventional forecast models for a fraction of the computational cost.
Authors:
; ;
Award ID(s):
1920304
Publication Date:
NSF-PAR ID:
10273992
Journal Name:
AAAI Spring Symposium: MLPS, 2020
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract This project is funded by the US National Science Foundation (NSF) through their NSF RAPID program under the title “Modeling Corona Spread Using Big Data Analytics.” The project is a joint effort between the Department of Computer & Electrical Engineering and Computer Science at FAU and a research group from LexisNexis Risk Solutions. The novel coronavirus Covid-19 originated in China in early December 2019 and has rapidly spread to many countries around the globe, with the number of confirmed cases increasing every day. Covid-19 is officially a pandemic. It is a novel infection with serious clinical manifestations, including death, and it has reached at least 124 countries and territories. Although the ultimate course and impact of Covid-19 are uncertain, it is not merely possible but likely that the disease will produce enough severe illness to overwhelm the worldwide health care infrastructure. Emerging viral pandemics can place extraordinary and sustained demands on public health and health systems and on providers of essential community services. Modeling the Covid-19 pandemic spread is challenging. But there are data that can be used to project resource demands. Estimates of the reproductive number (R) of SARS-CoV-2 show that at the beginning of the epidemic, each infectedmore »person spreads the virus to at least two others, on average (Emanuel et al. in N Engl J Med. 2020, Livingston and Bucher in JAMA 323(14):1335, 2020). A conservatively low estimate is that 5 % of the population could become infected within 3 months. Preliminary data from China and Italy regarding the distribution of case severity and fatality vary widely (Wu and McGoogan in JAMA 323(13):1239–42, 2020). A recent large-scale analysis from China suggests that 80 % of those infected either are asymptomatic or have mild symptoms; a finding that implies that demand for advanced medical services might apply to only 20 % of the total infected. Of patients infected with Covid-19, about 15 % have severe illness and 5 % have critical illness (Emanuel et al. in N Engl J Med. 2020). Overall, mortality ranges from 0.25 % to as high as 3.0 % (Emanuel et al. in N Engl J Med. 2020, Wilson et al. in Emerg Infect Dis 26(6):1339, 2020). Case fatality rates are much higher for vulnerable populations, such as persons over the age of 80 years (> 14 %) and those with coexisting conditions (10 % for those with cardiovascular disease and 7 % for those with diabetes) (Emanuel et al. in N Engl J Med. 2020). Overall, Covid-19 is substantially deadlier than seasonal influenza, which has a mortality of roughly 0.1 %. Public health efforts depend heavily on predicting how diseases such as those caused by Covid-19 spread across the globe. During the early days of a new outbreak, when reliable data are still scarce, researchers turn to mathematical models that can predict where people who could be infected are going and how likely they are to bring the disease with them. These computational methods use known statistical equations that calculate the probability of individuals transmitting the illness. Modern computational power allows these models to quickly incorporate multiple inputs, such as a given disease’s ability to pass from person to person and the movement patterns of potentially infected people traveling by air and land. This process sometimes involves making assumptions about unknown factors, such as an individual’s exact travel pattern. By plugging in different possible versions of each input, however, researchers can update the models as new information becomes available and compare their results to observed patterns for the illness. In this paper we describe the development a model of Corona spread by using innovative big data analytics techniques and tools. We leveraged our experience from research in modeling Ebola spread (Shaw et al. Modeling Ebola Spread and Using HPCC/KEL System. In: Big Data Technologies and Applications 2016 (pp. 347-385). Springer, Cham) to successfully model Corona spread, we will obtain new results, and help in reducing the number of Corona patients. We closely collaborated with LexisNexis, which is a leading US data analytics company and a member of our NSF I/UCRC for Advanced Knowledge Enablement. The lack of a comprehensive view and informative analysis of the status of the pandemic can also cause panic and instability within society. Our work proposes the HPCC Systems Covid-19 tracker, which provides a multi-level view of the pandemic with the informative virus spreading indicators in a timely manner. The system embeds a classical epidemiological model known as SIR and spreading indicators based on causal model. The data solution of the tracker is built on top of the Big Data processing platform HPCC Systems, from ingesting and tracking of various data sources to fast delivery of the data to the public. The HPCC Systems Covid-19 tracker presents the Covid-19 data on a daily, weekly, and cumulative basis up to global-level and down to the county-level. It also provides statistical analysis for each level such as new cases per 100,000 population. The primary analysis such as Contagion Risk and Infection State is based on causal model with a seven-day sliding window. Our work has been released as a publicly available website to the world and attracted a great volume of traffic. The project is open-sourced and available on GitHub. The system was developed on the LexisNexis HPCC Systems, which is briefly described in the paper.« less
  2. Abstract

    In grassland ecosystems, it is well known that increasing plant species diversity can improve ecosystem functions (i.e., ecosystem responses), for example, by increasing productivity and reducing weed invasion. Diversity-Interactions models use species proportions and their interactions as predictors in a regression framework to assess biodiversity and ecosystem function relationships. However, it can be difficult to model numerous interactions if there are many species, and interactions may be temporally variable or dependent on spatial planting patterns. We developed a new Diversity-Interactions mixed model for jointly assessing many species interactions and within-plot species planting pattern over multiple years. We model pairwise interactions using a small number of fixed parameters that incorporate spatial effects and supplement this by including all pairwise interaction variables as random effects, each constrained to have the same variance within each year. The random effects are indexed by pairs of species within plots rather than a plot-level factor as is typical in mixed models, and capture remaining variation due to pairwise species interactions parsimoniously. We apply our novel methodology to three years of weed invasion data from a 16-species grassland experiment that manipulated plant species diversity and spatial planting pattern and test its statistical properties in a simulationmore »study.Supplementary materials accompanying this paper appear online.

    « less
  3. Despite its importance in electron transfer reactions and radiation chemistry, there has been disagreement over the fundamental nature of the hydrated electron, such as whether or not it resides in a cavity. Mixed quantum/classical simulations of the hydrated electron give different structures depending on the pseudopotential employed, and ab initio models of computational necessity use small numbers of water molecules and/or provide insufficient statistics to compare to experimental observables. A few years ago, Kumar et al. (J. Phys. Chem. A 2015, 119, 9148) proposed a minimalist ab initio model of the hydrated electron with only a small number of explicitly treated water molecules plus a polarizable continuum model (PCM). They found that the optimized geometry had four waters arranged tetrahedrally around a central cavity, and that the calculated vertical detachment energy and radius of gyration agreed well with experiment, results that were largely independent of the level of theory employed. The model, however, is based on a fixed structure at 0 K and does not explicitly incorporate entropic contributions or the thermal fluctuations that should be associated with the room-temperature hydrated electron. Thus, in this paper, we extend the model of Kumar et al. by running Born−Oppenheimer molecular dynamics (BOMD)more »of a small number of water molecules with an excess electron plus PCM at room temperature. We find that when thermal fluctuations are introduced, the level of theory chosen becomes critical enough when only four waters are used that one of the waters dissociates from the cluster with certain density functionals. Moreover, even with an optimally tuned range-separated hybrid functional, at room temperature the tetrahedral orientation of the 0 K first-shell waters is entirely lost and the central cavity collapses, a process driven by the fact that the explicit water molecules prefer to make H-bonds with each other more than with the excess electron. The resulting average structure is quite similar to that produced by a noncavity mixed quantum/classical model, so that the minimalist 4-water BOMD models suffer from problems similar to those of noncavity models, such as predicting the wrong sign of the hydrated electron’s molar solvation volume. We also performed BOMD with 16 explicit water molecules plus an extra electron and PCM. We find that the inclusion of an entire second solvation shell of explicit water leads to little change in the outcome from when only four waters were used. In fact, the 16-water simulations behave much like those of water cluster anions, in which the electron localizes at the cluster surface, showing that PCM is not acceptable for use in minimalist models to describe the behavior of the bulk hydrated electron. For both the 4- and 16-water models, we investigate how the introduction of thermal motions alters the predicted absorption spectrum, vertical detachment energy, and resonance Raman spectrum of the simulated hydrated electron. We also present a set of structural criteria that can be used to numerically determine how cavity-like (or not) a particular hydrated electron model is. All of the results emphasize that the hydrated electron is a statistical object whose properties are inadequately captured using only a small number of explicit waters, and that a proper treatment of thermal fluctuations is critical to understanding the hydrated electron’s chemical and physical behavior.« less
  4. Viewing neural network models in terms of their loss landscapes has a long history in the statistical mechanics approach to learning, and in recent years it has received attention within machine learning proper. Among other things, local metrics (such as the smoothness of the loss landscape) have been shown to correlate with global properties of the model (such as good generalization performance). Here, we perform a detailed empirical analysis of the loss landscape structure of thousands of neural network models, systematically varying learning tasks, model architectures, and/or quantity/quality of data. By considering a range of metrics that attempt to capture different aspects of the loss landscape, we demonstrate that the best test accuracy is obtained when: the loss landscape is globally well-connected; ensembles of trained models are more similar to each other; and models converge to locally smooth regions. We also show that globally poorly-connected landscapes can arise when models are small or when they are trained to lower quality data; and that, if the loss landscape is globally poorly-connected, then training to zero loss can actually lead to worse test accuracy. Our detailed empirical results shed light on phases of learning (and consequent double descent behavior), fundamental versus incidentalmore »determinants of good generalization, the role of load-like and temperature-like parameters in the learning process, different influences on the loss landscape from model and data, and the relationships between local and global metrics, all topics of recent interest.« less
  5. Table of Contents: Foreword by the CI 2016 Workshop Chairs …………………………………vi Foreword by the CI 2016 Steering Committee ..…………………………..…..viii List of Organizing Committee ………………………….……....x List of Registered Participants .………………………….……..xi Acknowledgement of Sponsors ……………………………..…xiv Hackathon and Workshop Agenda .………………………………..xv Hackathon Summary .………………………….…..xviii Invited talks - abstracts and links to presentations ………………………………..xxi Proceedings: 34 short research papers ……………………………….. 1-135 Papers 1. BAYESIAN MODELS FOR CLIMATE RECONSTRUCTION FROM POLLEN RECORDS ..................................... 1 Lasse Holmström, Liisa Ilvonen, Heikki Seppä, Siim Veski 2. ON INFORMATION CRITERIA FOR DYNAMIC SPATIO-TEMPORAL CLUSTERING ..................................... 5 Ethan D. Schaeffer, Jeremy M. Testa, Yulia R. Gel, Vyacheslav Lyubchich 3. DETECTING MULTIVARIATE BIOSPHERE EXTREMES ..................................... 9 Yanira Guanche García, Erik Rodner, Milan Flach, Sebastian Sippel, Miguel Mahecha, Joachim Denzler 4. SPATIO-TEMPORAL GENERATIVE MODELS FOR RAINFALL OVER INDIA ..................................... 13 Adway Mitra 5. A NONPARAMETRIC COPULA BASED BIAS CORRECTION METHOD FOR STATISTICAL DOWNSCALING ..................................... 17 Yi Li, Adam Ding, Jennifer Dy 6. DETECTING AND PREDICTING BEAUTIFUL SUNSETS USING SOCIAL MEDIA DATA ..................................... 21 Emma Pierson 7. OCEANTEA: EXPLORING OCEAN-DERIVED CLIMATE DATA USING MICROSERVICES ..................................... 25 Arne N. Johanson, Sascha Flögel, Wolf-Christian Dullo, Wilhelm Hasselbring 8. IMPROVED ANALYSIS OF EARTH SYSTEM MODELS AND OBSERVATIONS USING SIMPLE CLIMATE MODELS ..................................... 29 Balu Nadiga, Nathanmore »Urban 9. SYNERGY AND ANALOGY BETWEEN 15 YEARS OF MICROWAVE SST AND ALONG-TRACK SSH ..................................... 33 Pierre Tandeo, Aitor Atencia, Cristina Gonzalez-Haro 10. PREDICTING EXECUTION TIME OF CLIMATE-DRIVEN ECOLOGICAL FORECASTING MODELS ..................................... 37 Scott Farley and John W. Williams 11. SPATIOTEMPORAL ANALYSIS OF SEASONAL PRECIPITATION OVER US USING CO-CLUSTERING ..................................... 41 Mohammad Gorji–Sefidmazgi, Clayton T. Morrison 12. PREDICTION OF EXTREME RAINFALL USING HYBRID CONVOLUTIONAL-LONG SHORT TERM MEMORY NETWORKS ..................................... 45 Sulagna Gope, Sudeshna Sarkar, Pabitra Mitra 13. SPATIOTEMPORAL PATTERN EXTRACTION WITH DATA-DRIVEN KOOPMAN OPERATORS FOR CONVECTIVELY COUPLED EQUATORIAL WAVES ..................................... 49 Joanna Slawinska, Dimitrios Giannakis 14. COVARIANCE STRUCTURE ANALYSIS OF CLIMATE MODEL OUTPUT ..................................... 53 Chintan Dalal, Doug Nychka, Claudia Tebaldi 15. SIMPLE AND EFFICIENT TENSOR REGRESSION FOR SPATIOTEMPORAL FORECASTING ..................................... 57 Rose Yu, Yan Liu 16. TRACKING OF TROPICAL INTRASEASONAL CONVECTIVE ANOMALIES ..................................... 61 Bohar Singh, James L. Kinter 17. ANALYSIS OF AMAZON DROUGHTS USING SUPERVISED KERNEL PRINCIPAL COMPONENT ANALYSIS ..................................... 65 Carlos H. R. Lima, Amir AghaKouchak 18. A BAYESIAN PREDICTIVE ANALYSIS OF DAILY PRECIPITATION DATA ..................................... 69 Sai K. Popuri, Nagaraj K. Neerchal, Amita Mehta 19. INCORPORATING PRIOR KNOWLEDGE IN SPATIO-TEMPORAL NEURAL NETWORK FOR CLIMATIC DATA ..................................... 73 Arthur Pajot, Ali Ziat, Ludovic Denoyer, Patrick Gallinari 20. DIMENSIONALITY-REDUCTION OF CLIMATE DATA USING DEEP AUTOENCODERS ..................................... 77 Juan A. Saenz, Nicholas Lubbers, Nathan M. Urban 21. MAPPING PLANTATION IN INDONESIA ..................................... 81 Xiaowei Jia, Ankush Khandelwal, James Gerber, Kimberly Carlson, Paul West, Vipin Kumar 22. FROM CLIMATE DATA TO A WEIGHTED NETWORK BETWEEN FUNCTIONAL DOMAINS ..................................... 85 Ilias Fountalis, Annalisa Bracco, Bistra Dilkina, Constantine Dovrolis 23. EMPLOYING SOFTWARE ENGINEERING PRINCIPLES TO ENHANCE MANAGEMENT OF CLIMATOLOGICAL DATASETS FOR CORAL REEF ANALYSIS ..................................... 89 Mark Jenne, M.M. Dalkilic, Claudia Johnson 24. Profiler Guided Manual Optimization for Accelerating Cholesky Decomposition on R Environment ..................................... 93 V.B. Ramakrishnaiah, R.P. Kumar, J. Paige, D. Hammerling, D. Nychka 25. GLOBAL MONITORING OF SURFACE WATER EXTENT DYNAMICS USING SATELLITE DATA ..................................... 97 Anuj Karpatne, Ankush Khandelwal and Vipin Kumar 26. TOWARD QUANTIFYING TROPICAL CYCLONE RISK USING DIAGNOSTIC INDICES .................................... 101 Erica M. Staehling and Ryan E. Truchelut 27. OPTIMAL TROPICAL CYCLONE INTENSITY ESTIMATES WITH UNCERTAINTY FROM BEST TRACK DATA .................................... 105 Suz Tolwinski-Ward 28. EXTREME WEATHER PATTERN DETECTION USING DEEP CONVOLUTIONAL NEURAL NETWORK .................................... 109 Yunjie Liu, Evan Racah, Prabhat, Amir Khosrowshahi, David Lavers, Kenneth Kunkel, Michael Wehner, William Collins 29. INFORMATION TRANSFER ACROSS TEMPORAL SCALES IN ATMOSPHERIC DYNAMICS .................................... 113 Nikola Jajcay and Milan Paluš 30. Identifying precipitation regimes in China using model-based clustering of spatial functional data .................................... 117 Haozhe Zhang, Zhengyuan Zhu, Shuiqing Yin 31. RELATIONAL RECURRENT NEURAL NETWORKS FOR SPATIOTEMPORAL INTERPOLATION FROM MULTI-RESOLUTION CLIMATE DATA .................................... 121 Guangyu Li, Yan Liu 32. OBJECTIVE SELECTION OF ENSEMBLE BOUNDARY CONDITIONS FOR CLIMATE DOWNSCALING .................................... 124 Andrew Rhines, Naomi Goldenson 33. LONG-LEAD PREDICTION OF EXTREME PRECIPITATION CLUSTER VIA A SPATIO-TEMPORAL CONVOLUTIONAL NEURAL NETWORK .................................... 128 Yong Zhuang, Wei Ding 34. MULTIPLE INSTANCE LEARNING FOR BURNED AREA MAPPING USING MULTI –TEMPORAL REFLECTANCE DATA .................................... 132 Guruprasad Nayak, Varun Mithal, Vipin Kumar« less