Machine Learning and Artificial Intelligence to Advance Earth System Science: Opportunities and Challenges: Proceedings of a Workshop (2022)
Chapter: Appendix C: Workshop Agenda
Appendix C: Workshop Agenda
Machine Learning and Artificial Intelligence to Advance Earth System Science: Opportunities and Challenges—A Workshop
February 7, 10, and 11, 2022 | 1:00-4:00 pm (All times EST)
Workshop Goal: This workshop will consider the opportunities and challenges of using machine learning and artificial intelligence (ML/AI) to advance Earth system science, including their ethical development and use. The workshop will convene Earth system science experts, ML and AI researchers, social and behavioral scientists, ethicists, and decision makers across sectors to explore how these approaches can contribute to improving understanding, analysis, modeling, prediction, and decision making. Workshop discussions will examine state-of-the-art approaches for using ML/AI for Earth system science, consider challenges and ways to mitigate risks of using ML/AI, and identify future opportunities to accelerate progress.
| 1:00 pm | Welcome and Opening Remarks |
| Ruby Leung, Planning Committee Chair, Pacific Northwest National Laboratory |
Session 1: Overview of State-of-the-Art Use of ML/AI for Earth System Science
Moderators: Amy McGovern, University of Oklahoma, and Ruby Leung, PNNL
Session 1 will provide a broad overview of how ML/AI are currently being used for Earth system science, remaining conceptual and technical challenges, and opportunities to address those challenges.
| 1:10 pm | 20-minute talk followed by discussion |
| Peter Dueben, European Centre for Medium-Range Weather Forecasts | |
| 1:40 pm | Break |
Session 2: Emerging Approaches for Using and Interpreting ML/AI
Moderators: Patrick Heimbach, UT Austin, and Aarti Singh, CMU
Session 2 will consider unique challenges in Earth system science that emerging ML/AI approaches can help to address. Specific approaches will include integrating physics, expert knowledge, multiple modalities of data, and ML/AI techniques; explainable AI and interpretable ML; and data assimilation.
| 1:45 pm | 12-minute talks followed by discussion |
|
|
|
| 2:45 pm | Break |
Session 3: Emerging Opportunities from Social and Human Engineered Systems
Moderators: Ann Bostrom, UW, and Ruby Leung, PNNL
Session 3 panelists will discuss opportunities for using ML/AI to understand social and human engineered systems, and the prospects for using ML/AI to integrate social and human engineered system science into Earth system science.
| 3:00 pm | 5-minute panelist remarks followed by discussion |
|
|
| 3:50 pm | Closing Remarks and Plans for Day 2 |
| Amy McGovern, University of Oklahoma | |
| 4:00 pm | Adjourn |
| 1:00 pm | Welcome and Opening Remarks |
| Ruby Leung, Committee Chair, Pacific Northwest National Laboratory | |
| 1:10 pm | Recap of Workshop Day 1 |
| Patrick Heimbach, UT Austin, and Diego Melgar, U of Oregon |
Session 1: Responsible and Ethical Use and JEDI Issues for ML/AI in Weather, Climate, and Earth System Science
Moderators: Amy McGovern, University of Oklahoma, and Ann Bostrom, UW
Session 1 panelists will consider what ethical standards should guide Earth system science, and how such standards relate to the lenses of justice, equity, diversity, and inclusion (JEDI). Panelists will also discuss potential biases in ML/AI for Earth system science and promising ways to avoid those biases.
| 1:20 pm | 5-minute panelist remarks followed by discussion |
|
|
| 2:10 pm | Break |
Session 2: Workforce Development Capacity and Skill Sets
Moderators: Diego Melgar, U of Oregon, and Amy McGovern, University of Oklahoma
Session 2 conversationalists will discuss gaps in education for those working at the intersection of ML/AI and Earth system science, needs and strategies for the private sector and academia in workforce development, the role of continued education in the current workforce, and capacity building at earlier educational stages.
| 2:20 pm | Brief introductions followed by conversation |
|
Session 3: Challenges and Opportunities for Earth Science Technology and Data
Moderators: Patrick Heimbach, UT Austin, and Laure Zanna, NYU
Session 3 panelists will consider open data, standards, and platforms to facilitate open science for ML/AI and Earth system science as well as technology development, funding models, and education challenges and opportunities for Earth system science technology and data.
| 3:00 pm | 5-minute panelist remarks followed by discussion |
|
|
| 3:50 pm | Closing Remarks and Plans for Day 3 |
| Laure Zanna, NYU | |
| 4:00 pm | Adjourn |
| 1:00 pm | Welcome and Opening Remarks |
| Ruby Leung, Committee Chair, Pacific Northwest National Laboratory | |
| 1:10 pm | Recap of Workshop Day 2 |
| Ruby Leung, PNNL, and Ann Bostrom, UW |
Session 1: Using ML/AI for Data-Driven Decision Making
Moderators: Ann Bostrom, UW, and Diego Melgar, University of Oregon
Session 1 speakers will discuss the role of ML/AI at the interface of predictive physical models and real-time decision making, handling uncertainties, and the remaining scientific, engineering, societal, and ethical challenges in this space.
| 1:20 pm | 12-minute talks followed by discussion |
|
|
| 2:20 pm | Break |
Session 2: Novel Funding Mechanisms, Partnerships, and Knowledge Transfer Between Academia, Industry, Nonprofits, and Government
Moderators: Aarti Singh, CMU, and Laure Zanna, NYU
Session 2 conversationalists will consider funding opportunities, effective mechanisms, and creative new approaches to facilitate partnerships and knowledge transfer among academia, industry, nonprofits, and government to advance ML/AI for Earth system science.
| 2:40 pm | Brief introductions followed by conversation |
|
|
| 3:40 pm | Summary of Workshop Day 3 |
| Aarti Singh, CMU, and Amy McGovern, University of Oklahoma | |
| 3:50 pm | Closing Remarks |
| Ruby Leung, Committee Chair, Pacific Northwest National Laboratory | |
| 4:00 pm | Adjourn |
