Skip to main content

Conference Program

CompSust DC 2022 will take place online.

Friday, March 11, 2022

11:00am – 12:05pm10:00am – 11:05am8:00am – 9:05am Opening Talk
Opening Keynote Presentation:
Dr. Volodymyr Kuleshov (Cornell Tech)
12:05pm – 12:15pm11:05am – 11:15am9:05am – 9:15am Break
12:15pm – 1:15pm11:15am – 12:15pm9:15am – 10:15am
Presentations Group 1
  • From a Bag of Bagels to Bandit-Data Driven Optimization
    Zheyuan Ryan Shi
    ~15 minutes
  • Local Damages from Hurricanes: Application of Machine Learning with Satellite Data
    Katie Kolodner
    ~15 minutes
  • Pollution from Freight Trucks in the Contiguous United States: Public Health Damages and Implications for Environmental Justice
    Priyank Lathwal et al.
    ~15 minutes
  • Robust Reinforcement Learning for Wildlife Conservation
    Lily Xu
    ~15 minutes
1:15pm – 2:00pm12:15pm – 1:00pm10:15am – 11:00am Lunch Break
2:00pm – 2:30pm1:00pm – 1:30pm11:00am – 11:30am Invited Talk: Ritwik Gupta (University of California, Berkeley)
2:30pm – 3:30pm1:30pm – 2:30pm11:30am – 12:30pm Keynote Presentation:
Dr. Claire Monteleoni (University of Colorado, Boulder)
3:30pm – 3:45pm2:30pm – 2:45pm12:30pm – 12:45pm Break
3:45pm – 4:45pm2:45pm – 3:45pm12:45pm – 1:45pm
Presentations Group 2
  • Task-Informed Meta-Learning
    Gabriel Tseng
    ~15 minutes
  • Modeling Numerical Quantities to Extract Measurements from Climate Text Sources
    Daniel Spokoyny
    ~15 minutes
  • Toward Semantic Mapping for Natural Environments
    David Russell
    ~15 minutes
  • ML for structural health monitoring
    Ishan Khurjekar
    ~15 minutes

Saturday, March 12, 2022

11:00am – 11:45am10:00am – 10:45am8:00am – 8:45am
Presentations Group 3
  • ElephantBook: A Semi-Automated Human-in-the-Loop System for Elephant Re-Identification
    Peter Kulits
    ~15 minutes
  • Monitoring Social Insect Activity with Minimal Human Supervision
    Tarun Sharma / Julian Wagner
    ~15 minutes
  • Conserving Biodiversity via Adjustable Robust Optimization
    Yingxiao Ye et al.
    ~15 minutes
11:45am – 12:00pm10:45am – 11:00am8:45am – 9:00am Break
12:00pm – 1:15pm11:00am – 12:15pm9:00am – 10:15am Networking on
1:15pm – 2:00pm12:15pm – 1:00pm10:15am – 11:00am Lunch Break
2:00pm – 3:00pm1:00pm – 2:00pm11:00am – 12:00pm Keynote Presentation:
Dr. Arun Majumdar (Stanford University)
3:00pm – 3:15pm2:00pm – 2:15pm12:00pm – 12:15pm Break
3:15pm – 4:00pm2:15pm – 3:00pm12:15pm – 1:00pm
Presentations Group 4
  • Towards Geographically-Transferable Deep Learning Models for Human Mobility
    Massimiliano Luca
    ~15 minutes
  • Dynamic marginal emission factors via implicit differentiation
    Lucas F Valenzuela et al.
    ~15 minutes
  • Principled Algorithms for Online Resource Allocation and Dispatch in Communities
    Geoffrey Pettet
    ~15 minutes
4:00pm – 5:00pm3:00pm – 4:00pm1:00pm – 2:00pm Closing Keynote:
Dr. Victor Anton (
5:00pm4:00pm2:00pm Closing Remarks

Keynote speakers

Dr. Volodymyr Kuleshov

Dr. Volodymyr Kuleshov (Cornell Tech)

Towards a sustainable food supply chain powered by artificial intelligence

Abstract: About 30–40% of food produced worldwide is wasted. This represents a $165B loss to the US economy and poses major environmental problems: for example, it is estimated that food waste contributes to up to 25% of all greenhouse gas emissions. This talk explores how artificial intelligence can be used to automate decisions across the food supply chain in order to reduce waste and increase access to nutritious and affordable food. We describe how supply chain automation can be cast as a model-based control problem and present novel planning algorithms that benefit from a principled treatment of model uncertainty. We also describe how these algorithms can be deployed within an intelligent decision support system that assists supermarket operators in performing perishable inventory management. This system is currently deployed across hundreds supermarkets in the US (handling ~2% of US produce volume) and has led to waste reductions of up to 50%. We hope that this talk will bring the food waste problem to the attention of the machine learning community.

Bio: Volodymyr Kuleshov is an Assistant Professor at the Jacobs Technion-Cornell Institute at Cornell Tech and in the Computer Science Department at Cornell University. He obtained his bachelor's in Mathematics and Computer Science from McGill University, and his Ph.D. in Computer Science from Stanford University, where he was the recipient of the Arthur Samuel Best Thesis Award.

Kuleshov's research interests are in the field of machine learning and its applications in scientific discovery, health, and sustainability. His work has been featured in Nature Biotechnology, Nature Medicine, Nature Communications and Scientific American, and was awarded an NSERC Post-Graduate Fellowship and a Stanford Graduate Fellowship. He is the co-founder and Chief Technologist at Afresh, a startup focused on automating the food supply chain using AI in order to reduce food waste.

Dr. Claire Monteleoni

Dr. Claire Monteleoni (University of Colorado, Boulder)

Deep Unsupervised Learning for Climate Informatics

Abstract: Despite the scientific consensus on climate change, drastic uncertainties remain. Crucial questions about regional climate trends, changes in extreme events, such as heat waves and mega-storms, and understanding how climate varied in the distant past, must be answered in order to improve predictions, assess impacts and vulnerability, and inform mitigation and sustainable adaptation strategies. Machine learning can help answer such questions and shed light on climate change. I will give an overview of our climate informatics research, focusing on challenges in learning from spatiotemporal data, along with semi- and unsupervised deep learning approaches to studying rare and extreme events, and precipitation and temperature downscaling.

Bio: Claire Monteleoni is an Associate Professor, and the Associate Chair for Inclusive Excellence, in the Department of Computer Science at the University of Colorado Boulder, and the founding Editor in Chief of Environmental Data Science, a Cambridge University Press journal, launched in December 2020. She joined CU Boulder in 2018, following positions at University of Paris-Saclay, CNRS, George Washington University, and Columbia University. She completed her PhD and Masters in Computer Science at MIT and was a postdoc at UC San Diego. She holds a Bachelor's in Earth and Planetary Sciences from Harvard. Her research on machine learning for the study of climate change helped launch the interdisciplinary field of Climate Informatics. In 2011, she co-founded the International Conference on Climate Informatics, which turned 10 years old in 2020, and has attracted climate scientists and data scientists from over 20 countries and 30 U.S. states. She gave an invited tutorial: Climate Change: Challenges for Machine Learning, at NeurIPS 2014.

Dr. Arun Majumdar

Dr. Arun Majumdar (Stanford University)

Energy, Climate and Sustainability: The Defining Issue of the 21st Century

Abstract: The 20th Century was marked by dramatic innovations in medical care, transportation, food production, communications, computing, aerospace technology and the built environment. This has led to remarkable improvements in our quality of life, brought billions of people out of poverty, and has supported a four-fold increase in global population and seven-fold increase in GDP per capita. The fundamental infrastructure to enable these historic changes was energy. The use of fossil fuels and the associated greenhouse gas emissions has made this 20th century approach unsustainable. We are now witnessing a global economy undergo a once-in-a-century shift to chart a sustainable course. Will this happen sufficiently fast to address climate change? What are the innovations needed? How can computing enable and empower this transition? Will it happen uniformly around the world? What are the roles of academic institutions, government, business, and non-profits? This talk will explore these issues in depth and breadth and take stock of the opportunities and challenges that lie ahead of us.

Bio: Dr. Arun Majumdar is the Jay Precourt Provostial Chair Professor at Stanford University, a faculty member of the Department of Mechanical Engineering.

From 2009 to 2012, Dr. Majumdar served as the Founding Director of ARPA-E and from March 2011 to June 2012 as the Acting Under Secretary of Energy. After leaving Washington, Dr. Majumdar was the VP for Energy at Google.

Dr. Majumdar is a member of the National Academy of Sciences, National Academy of Engineering and the American Academy of Arts and Sciences. He also served as the Vice Chairman of the Advisory Board to the US Secretary of Energy, Dr. Ernest Moniz, was a Science Envoy for the US Department of State. He currently serves as the Chair of Advisory Board of the US Secretary of Energy, Jennifer Granholm, as well as on the advisory board of numerous energy businesses and non-profits.

Dr. Majumdar received his BS in Mechanical Engineering in 1985 from the Indian Institute of Technology, Bombay, and his Ph.D. from the University of California, Berkeley in 1989.

Dr. Victor Anton

Dr. Victor Anton (Founder and CEO of — Using artificial intelligence to accelerate wildlife conservation

Abstract: While Artificial Intelligence (AI) is revolutionising multiple aspects of our lives, there is limited uptake of AI in supporting ecological well-being and protecting the nearly 1 million species currently threatened with extinction. is a New Zealand not-for-profit aiming to bridge this gap between computer sciences and wildlife conservation worldwide. This presentation will provide an overview of how combines machine learning, community science, and environmental education to provide accurate and timely information to biologists and conservation managers. From developing open-source machine learning models and data analysis apps to creating educational activities about AI and wildlife conservation. works to democratise the use of AI and enhance current conservation efforts.

Bio: Victor has extensive experience in conservation biology, wildlife monitoring and ecological modeling. He discovered the strengths and limitations of machine learning for conservation while working with camera traps during his PhD at Victoria University of Wellington, New Zealand. Since then, he has worked with numerous research institutions, governments and communities around the world to translate big data into scientific discoveries and better conservation management practices.

Steering Committee