Workshop 2018

Thank you to the University of California (our co-sponsor) and all the presenters and attendees for helping to make the DSI's Inaugural Workshop a huge success!

Read more about the event.

Day 1 | Day 2 | Posters

Session 1: Applications

• Yuriy Ayzman (LLNL): Transfer Learning Applications toward ICF Capsule Manufacturing
• Anh Tran (UCLA): Bayesian Model Averaging for Estimating the Temperature Distribution in a Steam Methane Reforming Furnace
• Jian-Qiao Sun (UCM): A Neural Network–Evolutionary Computational Framework for Aircraft Engine Remaining Useful Life
• Cheng Ding (LBL): Deep Learning Based Predictive Modeling of EHR Data for Suicide Prevention
• Yong Han (LLNL): Application of Machine Learning, Computer Vision and Data Analytics for Materials Science

Session 2: Cognitive Simulation

• Brian Spears (LLNL): Learning-Based Predictive Models: A New Approach to Integrating Large-Scale Simulations and Experiments
• Luc Peterson (LLNL): Machine Learning Aided Discovery of a New NIF Design
• Harsh Bhatia (LLNL): Enabling Multiscale Simulations of RAS Biology using Machine Learning

Session 3: Neural Networks

• Jayaraman J. Thiagarajan (LLNL): Modeling Time-Varying Data: Attention, Generative Models and Beyond
• Brian Bartoldson (LLNL): An Interpretable Multimodal Retrieval Tool
• Kelli Humbird (LLNL): Deep Jointly-Informed Neural Networks
• Ryan Goldhahn (LLNL): Robust Decentralized Signal Processing and Distributed Control of Autonomous Sensor Networks

Session 4: Uncertainty Quantification

• Jim Gaffney (LLNL): Calibration of Radiation-Hydrodynamics Simulations using Data from Inertial Confinement Fusion Experiments
• Kathleen Schmidt (LLNL): Parameter Subset Selection for Mixed-Effects Models
• Peter Hatfield (University of Oxford, LLNL): Machine Learning and Algorithmic Approaches in ICF Capsule Design

Session 5: Space/Other Applications

• Michael Schneider (LLNL): Probabilistic Modeling to Measure Dark Energy
• Adam Kellerman (UCLA): Real-Time Data-Assimilative Hindcast and Forecast of Earth's Electron Radiation Belts: Research to Applications
• Andreas Zoglauer (UCB, BIDS): Lessons Learned from Applying Machine Learning to the Data Analysis Pipeline of the COSI Telescope
• Benjamin Nachman (LBL): Deep Learning with the Largest Scientific Dataset: Modern Machine Learning for High Energy Physics

Session 6: Biological Sciences Applications

• Paul Gamble (Lab41): Biollante
• Gerald Quon (UCD): Deep Domain Adaptation Networks Predict Changes in Cell State Under Stimulus
• Aram Avila-Herrera (LLNL): Search Strategies for Antimicrobial Resistance Associated Genes

Session 7: Computer Vision 

• Rushil Anirudh (LLNL): Interpreting Deep Neural Networks using Graph Signal Analysis
• Shusen Liu (LLNL): Visual Exploration of Latent Spaces in Deep Neural Network Models
• Luke Jaffe (LLNL): Remote Sensor Design for Automated Visual Recognition
• Laura Kegelmeyer (LLNL): Evolution of Machine Learning for NIF Optics Inspection (OI)

Session 8: Methods 

• Anna Matsekh (LANL): Machine Learning for Memory Reduction in the Implicit Monte Carlo Simulations of the Thermal Radiative Transfer
• Thomas Desautels (LLNL): Controlling a Sepsis Simulation with PILCO, a Model-Learning Controller
• Tenzing Joshi (LBL): Detection and Identification of Radiological Sources with Non-Negative Matrix Factorization
• Gerald Friedland (LLNL, UCB): One Bit Matters: Explaining Adversarial Examples as the Abuse of Redundancy

Session 9: Applied Statistics

• Bruno Sanso (UCSC): Inferring Release Characteristics from an Atmospheric Dispersion Model 
• Giuliana Pallotta (LLNL): Improving Predictions of Radiological Surface Contamination Uncertainty via an Ensemble of Simulations
• Abel Rodriguez (UCSC): Spherical Factor Analysis for Binary Data: A Look at the Conservative Revolt in the US House of Representatives
• William Dawson (LLNL): Bayesian Sensor Fusion in Centralized and Decentralized Networks

Session 10: Precision Medicine

• Ya Ju Fan (LLNL): Distinguishing between Normal and Cancer Cells Using Autoencoder Node Saliency
• Brenden Petersen (LLNL): Deep Reinforcement Learning and Simulation as a Path toward Precision Medicine
• Stewart He (LLNL): Semi Supervised Feature Learning for Tumor Growth Prediction
• Kevin McLoughlin (LLNL): Deep Learning to Accelerate Cancer Drug Discovery

Session 11: Security

• Eddy Banks (LLNL): ADAPD – Advanced Data Analytics for Proliferation Detection
• Mateusz Monterial (LLNL): Machine Learning Approach to Improving Performance with Portal Monitors
• Felipe Mejia (Lab41): Challenges in Secure Machine Learning
• Margaret Arno (LLNL): A Multimodal-Deep Learning System for the Retrieval of Open Source Data on Nuclear Proliferation Activities

Session 12: Tools and Infrastructure

• Dani Ushizima (UCB, BIDS): Deep Learning for Image Search: Characterization, Retrieval and Ranking of Multi-Modal Data
• Amanda Minnich (LLNL): Utilizing Container Technology to Streamline Data Science
• Tim Moon (LLNL): Scalable Deep Learning Training for Scientific Applications
• Daniel Fedor-Thurman (LLNL): HPCrypt: End-to-End Data Protection for HPC

• Brandyn Ward (UCSC): A Comparison of Generative Models for the Detection and Identification of Gaseous Chemical Plumes in Hyperspectral Imagery
• Connor Amorin (LLNL, UMass Amherst): A Hybrid Deep Learning Architecture for Classification of Microscopic Damage on NIF Optics
• Bin Chen, Yufang Jin, Brown Patrick (UCD): An Automatic Mapping of Tree Crops Planting Age using Landsat Time Series Stacks and Google Earth Engine
• Timothy La Fond, Geoff Sanders, Christine Klymko, Van Emden Henson (LLNL): An Ensemble Framework for Detecting Community Changes in Dynamic Networks
• V.M. Castillo (LLNL), B. Kustowski (LLNL), Y. Mubarka (LLNL, UCSD): Asynchronous Method for Active Learning on HPC for Efficient Exploration of Complex Systems
• Jason Bernstein, Kathleen Schmidt, David Rivera, Nathan Barton, Jeffrey Florando, Ana Kupresanin (LLNL): Bayesian Comparison of Material Strength Model Predictiveness
• Xuanyu Mao, Antoine M. Snijders, Jian-Hua Mao, Hang Chang (LBL): Biomedical Data to Knowledge: An integrative study for brain tumor research
• Danny Yeap, Paul Hichwa, Maneeshin Y. Rajapakse, Fauna Fabia, Nicholas J. Kenyon, Cristina E. Davis (UCD): Chemical Detection using Differential Mobility Spectrometry Plots
• Rebecca K Lindsey (LLNL), Nir Goldman (LLNL, UCD), Sorin Bastea (LLNL), Laurence E. Fried (LLNL): ChIMES: Machine-Learned Force Fields for Quantum-Accurate Reactive Simulation
• Haoyu Niu, Tiebiao Zhao, YangQuan Chen (UCM): Data Science in Agriculture Enabled by Low-Cost Remote Sensing Drones: Opportunity and Challenges
• A.R. Gonçalves, A.P de Oliveira, P. Ray, B. Soper, D. Widemann (LLNL); J. Nygard, M. Nygard (Cancer Registry of Norway): Deep Entity Embeddings for Cancer Survival Prediction
• J. O’Leary (UCB), K. Sawlani (Lam Research Corp.), A. Mesbah (UCB): Deep Learning for Semiconductor Defect Classification
• Alexander M. Petersen, Emmanuel M. Vincent, Anthony LeRoy Westerling (UCM): Discrepancy in Scientific Authority and Media Visibility of Climate Change Scientists and Contrarians
• J. Kallman, D. Domyancic, B. Gallagher, M. Jiang, A. Toreja (LLNL): DISTLR [Directed Intelligent System for Targeted Lagrangian Relaxation] First Results in KULL
• Samuel N. Araya, Anna Fryjoff-Hun, Andreas Anderson, Joshua H. Viers, Teamrat A. Ghezzehei (UCM): Estimating Soil Moisture from Unmanned Aerial Vehicle and Machine Learning
• N.E. Marks, M. Fitzgerald (LLNL), S.P. LaMont (LANL), J.D. Borgardt (Juniata College): Exercising National Nuclear Forensics Libraries – Details on the Creation and Implementation of the Galaxy Serpent 3 Data Set
• Naoya Maruyama (LLNL), Nikoli Dryden (LLNL, UIUC), Tim Moon (LLNL), Brian Van Essen (LLNL), Mark Snir (UIUC): Generalized Distributed-Memory Convolutional Neural Networks for Large-Scale Parallel Systems
• Camila Zanette, Caitlin C. Bannan, Christopher I. Bayly, Josh Fass, Michael K. Gilson, Michael R. Shirts, John D. Chodera, David L. Mobley (UCI): Learned Chemical Perception of Force Field Typing Rules using Monte Carlo Sampling
• Chyi-Shin Chen, Akash Narani, Todd Pray, Deepti Tanjore (LBL): Machine Learning Can De-Risk Bio-Based Production: Predictive Modeling in R
• H. Guillon, C.F. Byrne, B. Lane, S. Sandoval-Solis, G. Pasternack, H. Dahlke (UCD): Machine Learning Meets Eco-Hydraulics – Exhaustively Mapping the Channel Geometry of California Rivers and Streams
• Matteo Busi, Aditya K. Mohan, Alex A. Dooraghi, Kyle M. Champley, Harry E. Martz (LLNL); Ulrik L. Olsen (Technical University of Denmark): Material Characterization using Spectral X-ray CT
• Jian Hao Miao, Janesh Chhabra, Yu Zhang (UCSC): Medium-Term Wind Power Forecasting via Recurrent Neural Networks
• Bradley Harris, Jiali Zhang, Austen Bernardi, Hai Yu, Lan Na, Bo Chen, Xi Chen, Gang-Yu Liu, Roland Faller (UCD): Molecular Dynamics Simulation of Tetrasaccharide Assemblies in the Context of 3D Nanoprinting
• Steven A. Magana-Zook (LLNL): Nuclear Explosion Monitoring with Machine Learning: A LSTM Approach to Seismic Event Discrimination
• Jinlong Wu (LBL, Virginia Tech), Jianxun Wang (Virginia Tech), Heng Xiao (Virginia Tech): Physics-Informed Machine Learning for Data-Driven Turbulence Modeling
• Rafael Zamora-Resendiz, Silvia Crivelli (LBL): Protein Structure Classification using Spatial Graph Convolutional Neural Networks
• D. Rivera, J. Bernstein, K. Schmidt, N. Barton, A. Kupresanin, J. Florando (LLNL): Quantifying Uncertainty in Materials Strength
• Sam Ade Jacobs, Nikoli Dryden, Tim Moon, Brian Van Essen, Stewart He, Jonathan Allen (LLNL): Scaling Deep Learning for Cancer Drug Discovery on HPC Systems
• Derek D. Jensen, Donald D. Lucas, Katherine A. Lundquist, Lee G. Glascoe (LLNL): Sensitivity of a Bayesian Source-Term Estimation Model to Spatiotemporal Sensor Resolution
• Youngsoo Choi, Bill Arrighi (LLNL): Space-Time Reduced Order Model for Dynamic Systems
• Xingchen Yu, Abel Rodriguez (UCSC): Spherical Latent Factor Model
• Claudia Wehrhahn (UCSC), Abel Rodriguez (UCSC),  Christopher Paciorek (UCB): The NIMBLE Environment for Statistical Computing
• Daniel Laney, Frank Di Natale, Kathleen Dyer, Joseph Eklund, Rebecca Haluska, Nathan Greco, Esteban Pauli, Matthew Larsen, Walt Nissen, Jessica Semler (LLNL): The Workflow Project at LLNL
• Sisi Song, Abel Rodriguez, Gordon Keller, Mircea Teodorescu (UCSC): Trajectory Planning for Autonomous Vehicles for Optimal Environmental Monitoring
• Bogdan Kustowski, Jim Gaffney, Brian Spears, Gemma Anderson (LLNL): Transfer Learning for the Calibration of the ICF Simulations
• V. Dumont (UCB), T. Bowen (UCB, SSL), R. Roglans (UCB, SSL), J. Wurtele (UCB), D. Budker (UCB, LBL): Understand the Magnetic Pulse of Cities