Dates: August 18-20, 2020. (Daily times: 9:30am-12:30 and 1:30-4:30pm CDT)
Format: 100% virtual, open to public - available as zoom webinar and as YouTube live stream.
Please click here for information on our 2nd Annual KGML workshop, coming in August 2021!
Workshop Synopsis Workshop Booklet Background Agenda (includes slides & recorded presentations) Organizers
Join the KGML Community Google Group: Members can share and receive announcements of future events, new papers, talks, resources, open positions, funding opportunities, etc. When you click the link above to join, you MAY see a "you do not have access" message, please click the Join Group button to add yourself to the group. You can also contact kgmlworkshop@umn.edu to be added directly to the email list, or if you have any questions or issues. This is a moderated list and you will be able to select the level of emails you want to receive (each email / abridged / digest / no email), and messages are only visible to members of the group (by email or by visiting the online message board). Please see the KGML Community Code of Conduct here.
Quicklinks to session details: Introduction Aquatic Sciences Hydrology Weather/Climate Translational Biology Closing Panel
The inaugural workshop took place August 18-20, 2020 virtually over zoom. Over 1000 people registered from over 30 countries, and a variety of topics and vibrant discussions were recorded and are available to watch here: https://z.umn.edu/kgmlworkshopyoutube.
If you would like to receive emails of future events, please Opt-in for KGML emails here.
This workshop is part of a 2-year conceptualization project funded by the NSF's Harnessing the Data Revolution (HDR) program involving researchers from the University of Minnesota, University of Wisconsin, Penn State, Colorado State University, and the University of Virginia. This project aims to develop a framework that uses the unique capability of data science models to automatically learn patterns and models from data, without ignoring the treasure of accumulated scientific knowledge. Specifically, the project builds the foundations of knowledge-guided machine learning (KGML) by exploring several ways of bringing scientific knowledge and machine learning models together using pilot applications from four domains: aquatic ecodynamics, climate and weather, hydrology, and translational biology. For more information, please see the project website.
The workshop will include invited talks and panel discussions by data scientists (researchers in data mining, machine learning, and statistics) and researchers from four application areas (aquatic sciences, hydrology, atmospheric science, and translational biology) to discuss challenges, opportunities, and early progress in bringing scientific knowledge to machine learning. In doing so, it aims to foster interdisciplinary collaborations and interactions among these communities. The expected outcomes are the identification and greater understanding of challenges and opportunities in knowledge guided machine learning.
Please see below for the general structure of the workshop; follow links (session title) under each session for specific details.
YOUTUBE LINKS: Part 1 (start to break), Part 2 (break to session end)
Session Chairs: Vipin Kumar and Michael Steinbach
SPEAKERS:
9:30-9:40 Welcome and Introduction, Vipin Kumar, University of Minnesota and NSF HDR PI (link to recorded introduction)
9:40-10:05 Vipin Kumar, University of Minnesota and NSF HDR PI: "Knowledge Guided Machine Learning: Challenges and Opportunities" (slides) (link to recorded presentation)
10:05- 10:30 Anuj Karpatne, Virginia Polytechnic Institute and State University: "Science-guided Machine Learning: Advances in An Emerging Paradigm Combining Scientific Knowledge with Machine Learning" (slides) (link to recorded presentation)
10:30- 10:55 Markus Reichstein, Max Planck Institute for Biogeochemistry: "Deep learning for a better understanding of the Earth System?" (link to recorded presentation)
10:55-11:10 BREAK
11:10-11:35 Arindam Banerjee, University of Minnesota: "Physics-guided Machine Learning for Sub-seasonal Climate Forecasting" (slides pdf) (link to recorded presentation)
11:35- 12:00 Laure Zanna, New York University: "Blending machine learning and physics for climate modeling" (slides) (link to recorded presentation)
12:00- 12:25 Ansu Chatterjee, University of Minnesota: "Deep Learning and Gaussian Processes: Some connections" (slides pdf) (link to recorded presentation)
YOUTUBE LINKS: Part 1(start to break), Part 2 (break to session end)
Session chairs: Paul Hanson and Hilary Dugan
SPEAKERS:
1:30-1:40 Paul Hanson University of Wisconsin, Madison: Introduction and opening of "Ecological knowledge guides machine learning: (i) process-guided phosphorus modeling, (ii) state-space modeling of lake oxygen dynamics” (slides) (link to recorded presentation)
1:40-2:00 Robert Ladwig, University of Wisconsin, Madison: Continuation and closing of "Ecological knowledge guides machine learning: (i) process-guided phosphorus modeling, (ii) state-space modeling of lake oxygen dynamics” (slides) (link to recorded presentation)
2:00-2:20 Alison Appling, United States Geological Survey: "Applications of knowledge-guided machine learning for water resources management" Note: This presentation is not publicly available. If you would like access to this recorded presentation, please contact kgmlworkshop@umn.edu.
2:20-2:40 Jared Willard, University of Minnesota: "Predicting Water Temperature Dynamics of Unmonitored Lake Systems with Meta Transfer Learning (MTL)" (slides) (link to recorded presentation)
2:40-3:00 Matt Ross, Colorado State University: "Matched-up, the importance of open-access training data for global-scale remote sensing of water quality" (slides) (link to recorded presentation)
3:00-3:10 BREAK
3:10-3:30 Sylvia Lee, Environmental Protection Agency: "Harnessing the literature, datasets, and models to understand continental-scale lake phosphorus recovery times" (slides) (link to recorded presentation)
3:30-3:50 Charuleka Varadharajan, Lawrence Berkeley National Laboratory: "Data-driven approaches to building efficient machine learning models for aquatic science and hydrology"(slides) (link to recorded presentation)
3:50-4:10 Xiaowei Jia, University of Pittsburgh: "Integrating Physics into Machine Learning for Monitoring Scientific Systems"(slides) (link to recorded presentation)
4:10-4:30 Panel Discussion Moderator: Hilary Dugan, University of Wisconsin, Madison (link to recorded panel)
YOUTUBE LINKS: Part 1(start to break), Part 2 (break to session end)
Session chairs: John Nieber and Chris Duffy
SPEAKERS:
9:30-9:40 Opening by Session Moderator, John Nieber, University of Minnesota (slides)(link to recorded presentation)
9:40-10:15 Grey Nearing, University of Alabama, Tuscaloosa: “What is the Role of Hydrological Science in the Age of Machine Learning?”(slides)(link to recorded presentation)
10:15-10:40 Chaopeng Shen, Pennsylvania State University: "From parameter calibration to parameter learning: Revolutionizing large-scale geoscientific modeling with big data" (slides) (link to recorded presentation)
10:40-11:05 Julian Koch, Geological Survey of Denmark and Greenland - Denmark: "Groundwater table modelling at high spatial resolution using machine learning and process-based models" (slides)(link to recorded presentation)
11:05-11:15 BREAK
11:15-11:35 Christopher Duffy, Pennsylvania State University: "Increasing the Value of Mechanistic Watershed Models Through Emulation and Machine Learning"(slides)(link to recorded presentation)
11:35-12:00 Xiang Li, Ankush Khandelwal, Shaoming Xu, University of Minnesota: "Physics Guided deep learning models for hydrology" (slides)(link to recorded presentation)
12:00-12:20 Michael J Friedel, Pacific Northwest National Laboratory: "Multiphysics-informed learning algorithm for vadose zone transport modeling – preliminary results" (link to recorded presentation)
12:20-12:30 Overall Questions and Session Summary
YOUTUBE LINKS: Part 1(start to break), Part 2 (break to session end)
Session chairs: Imme Ebert-Uphoff and Elizabeth Barnes
Session Schedule
1:30-2:00 Imme Ebert-Uphoff & Elizabeth Barnes , Colorado State University: "Overview of Knowledge-Guided Machine Learning for Weather and Climate" (slides) (link to recorded presentation)
2:00-2:20 Kirsten Mayer, Colorado State University: "Utilizing Interpretable Neural Networks for Subseasonal Prediction" (link to recorded presentation)
2:20-2:40 Marlene Kretschmer, Potsdam Institute for Climate Impact Research: "Causal inference and causal discovery to study teleconnection pathways" (slides)(link to recorded presentation)
2:40-2:50 BREAK
3:00-3:20 Maria Molina, University Corporation for Atmospheric Research: "Explaining Deep Learning Classification of Future Convective Storms" (slides)(link to recorded presentation)
3:20-3:40 Tom Beucler, University of California, Irvine: "Towards Physically-Consistent, Data-Driven Models of Convection" (slides) (link to recorded presentation)
3:40-4:00 Sherrie Wang, Stanford University: "Meta-learning for remote sensing" (slides) (link to recorded presentation)
4:00-4:30 Panel Questions and Discussion (link to recorded panel)
YOUTUBE LINKS: Part 1(start to break), Part 2 (break to session end)
Session Chairs: Aidong Zhang and Kevin Janes
SPEAKERS:
9:30-9:40: Introduction, Kevin Janes and Aidong Zhang (link to presentation)
9:40-10:05: Tandy Warnow, University of Illinois Urbana-Champaign: "Understanding Evolution through Massive Data and Computational Method Development"(slides) (link to presentation)
10:05-10:30: Amarda Shehu, George Mason University: "A Data-driven Journey in Macromolecular Structure, Dynamics, and Function" (slides) (link to presentation)
10:30-10:55 Cathy Wu, University of Delaware: "Integrative Text Mining and Semantic Computing for Data-Driven Biomedical Knowledge Discovery" (slides) (link to presentation)
10:55-11:10 BREAK
11:10-11:35: Madhav Marathe, University of Virginia: "Towards real-time computational epidemiology" (slides)(link to presentation)
11:35-12:00: Kevin Janes, University of Virginia: "Modeling and learning how cancer cells respond differently to oxidative stress" (slides) (link to presentation)
12:00-12:25: Aidong Zhang, Univeristy of Virginia: "Meta Learning for Cancer Prediction"(slides) (link to presentation)
YOUTUBE LINKS: https://www.youtube.com/watch?v=Z7H1AxLb1Ck
Moderators: Imme Ebert-Uphoff, Colorado State University & Paul Hanson, University of Wisconsin, Madison
Topic: Where do we go from here?
Elizabeth Barnes - Department of Atmospheric Science, Colorado State University
Chris Duffy - Department of Civil and Environmental Engineering, Pennsylvania State University
Hilary Dugan - Department of Integrative Biology, University of Wisconsin, Madison
Imme Ebert-Uphoff - Department of Electrical and Computer Engineering, Colorado State University
Paul Hanson - Center for Limnology, University of Wisconsin, Madison
Kevin Janes - School of Engineering & Applied Science, University of Virginia
Vipin Kumar - Department of Computer Science and Engineering, University of Minnesota
John Nieber - Department of Bioproducts and Biosystems Engineering, University of Minnesota
Michael Steinbach - Department of Computer Science and Engineering, University of Minnesota
Aidong Zhang - School of Engineering & Applied Science, University of Virginia
Quicklinks to session details: Introduction Aquatic Sciences Hydrology Weather/Climate Translational Biology Closing Panel