Fragile Earth:

Theory Guided Data Science to Enhance Scientific Discovery

August 5th, 2019

Program

AUGUST 5

8:00 – 9:00 Research Paper, Track 1

8:00 – 8:10 Snehal More, Anuj Karpatne, Randolph H. Wynne and Valerie A. Thomas
Deep Learning for Forest Plantation Mapping in Godavari Districts of Andhra Pradesh, India Physics-aware Architecture of Neural Networks for Uncertainty Quantification: Application in Lake Temperature Modeling

8:10 – 8:20 Jiri Navratil, Alan King, Jesus Rios, Georgios Kollias, Ruben Torrado and Andres Codas
Accelerating Physics-Based Simulations Using Neural Network Proxies: An Application in Oil Reservoir Modeling

8:20 – 8:30 Nishant Yadav, Kate Duffy and Auroop R. Ganguly
Deep Learning Based Quantitative Precipitation Nowcasting

8:30 – 8:40 Xiaowei Jia, Jared Willard, Anuj Karpatne, Jordan Read, Jacob Zwart, Paul Hanson, Michael Steinbach and Vipin Kumar
Physics Guided Machine Learning for Modeling Engineered and Natural Systems

8:40 – 8:45 Arka Daw and Anuj Karpatne
Physics-aware Architecture of Neural Networks for Uncertainty Quantification: Application in Lake Temperature Modeling

8:45 – 8:50 Rutuja Gurav, Evangelos Papalexakis and Barry Barish
Multilinear Factorized Representations for LIGO Glitches in Label-scarce Settings

8:50 – 8:55 John Brandt
Text mining policy: Classifying forest and landscape restoration policy agenda with neural information retrieval

9:00 – 9:30 Keynote 1
Stefano Ermon, Stanford University
Measuring Economic Development from Space

9:30 – 10:00 Coffee Break

10:00 -10:30 Keynote 2
Jennifer Marsman, Microsoft
AI for Earth: Using machine learning to monitor, model, and manage natural resources

10:30 – 11:00 Research Paper, Track 2

10:30 – 10:40 Thomas Uriot
Learning with Sets in Multiple Instance Regression Applied to Remote Sensing

10:40 – 10:50 Kate Duffy, Thomas Vandal, Shuang Li, Sangram Ganguly, Ramakrishna Nemani and Auroop Ganguly
DeepEmSat: Deep Emulation for Satellite Data Mining

10:50 – 11:00 Adrian Albert, Emanuele Strano, Jasleen Kaur and Marta Gonzalez
Spatial sensitivity analysis for urban land use prediction with physics-constrained conditional generative adversarial networks

11:00 – 11:15 Keynote 3
Angel Hsu, Yale University
Seeking the Signal Through the Noise: Applied Data Science for Environment Decision Making

11:15 -11:55 Panel Discussion by John Brandt, World Resources Institute

Jane Fredrich – Cargill Inc.
Chid Apte – IBM Research
Aaron Bergstrom – University of North Dakota & Midwest Big Data Hub
Dennis Pamlin – RISE

11:55 -12:00 Closing Remarks – Naoki Abe, IBM Research

Noon – 17:00 Poster Session

All the speakers above will have a poster in this session. Additionally the following posters are also invited.

  • Poster 10: Spencer Schaber, José Gilson Regadas Filho, Ana Paula de Assis Maia and Rodrigo Uttpatel
    Data Mining for Poultry Farming Efficiency
  • Poster 11: Simone Bianco, Vito Paolo Pastore, Sujoy Biswas, Jennifer Fung and Thomas Zimmerman
    Monitoring Water Quality Using Plankton as Biosensor
  • Poster 12: Thomas Uriot
    Target-wise Kernel Mean Embedding in Multiple Instance Regression

AUGUST 6

19:00 – 21:30 Earth Day poster Session

The following papers alone are invited for this poster session.

  • Deep Learning for Forest Plantation Mapping in Godavari Districts of Andhra Pradesh, India
  • Accelerating Physics-Based Simulations Using Neural Network Proxies: An Application in Oil Reservoir Modeling
  • Deep Learning Based Quantitative Precipitation Nowcasting
  • Physics Guided Machine Learning for Modeling Engineered and Natural Systems
  • Learning with Sets in Multiple Instance Regression Applied to Remote Sensing
  • DeepEmSat: Deep Emulation for Satellite Data Mining
  • Spatial sensitivity analysis for urban land use prediction with physics-constrained conditional generative adversarial networks

Call for Papers

We are excited to announce the Fragile Earth workshop at KDD ’19, Earth Day in Anchorage on August 5th. FEED ’19 will bring together the research, industry, and policy community around enhancing scientific discovery in the earth sciences through the joint use of data, theory, and computation. Whether it is food security, water scarcity, energy use, land restoration,climate models, or the incorporation of theoretical thinking into data driven frameworks of scientific discovery, and related areas, we invite you to be part of the community!

We solicit three categories of papers: research papers, on-going work papers, and position/vision papers.

Research papers should be maximum 8 pages in length, on-going work papers maximum 6 pages and position or vision papers between 2 to 6 pages. All should follow the AMC template:

https://www.acm.org/publications/proceedings-template

Areas

  1. Paradigms for enhancing scientific discovery through theory guided data science.
  2. Empirical investigations at the intersection of the earth sciences/sustainability and data.
  3. Data-informed Food/Energy/Water/Earth Sciences policy discussions.
  4. Frameworks for helping the scientific and KDD communities to work together

Accepted papers will be allocated to three themed sessions and a poster session. We expect presentations to last 15-20 minutes (including questions), and will prioritize submissions based on relevance, scientific rigour, and potential for societal impact.

Workshop papers will not be published as a part of the SIGKDD 2019 Conference proceedings. However, for those authors interested in archival publications, we have a simultaneous submission policy with the Frontiers in Big Data journal. Authors of FEED 2019 submissions are optionally invited to submit the journal versions of their papers to the special issue “Big Data for Food, Energy and Water”. (Primarily solicited are journal ready versions of research papers, but those of position/vision papers will also be considered.)

The submission deadline is May 19th (for both the workshop and the journal). Information on the special issue, including the submission process, can be found here:

https://www.frontiersin.org/research-topics/8733/big-data-for-food-energy-and-water

Funding

We are pleased to announce funds to cover travel expenses of selected workshop participants, thanks to the seed funding we have been awarded by Cargill.

Cargill, a proud sponsor of the Fragile Earth workshop, is one of the largest food suppliers in the world producing Food Ingredients, Bio-Industrials, Animal Nutrition, Protein, Salt and Agricultural Supply Chain services. Cargill’s goal is to nourish the world in a safe, responsible and sustainable way and it has customers/partners in more than 125 countries in the world. The company has a number of initiatives using data science to help with sustainability, deforestation, water safety, energy/food waste, and safety. Cargill is thrilled to provide this support for emerging leaders in the area of data science for food energy and water as we work together to solve the associated challenges.

Organizers

KDD 2019

Naoki Abe

Distinguished Research Staff Member, IBM Research AI

KDD 2019

Kathleen Buckingham

Research Manager, World Resources Institute

KDD 2019

Bistra Dilkina

Associate Professor, CS, USC; Associate Director, USC Center for AI in Society (CAIS)

KDD 2019

Emre Eftelioglu

Applied Scientist at Amazon US

KDD 2019

James Hodson

CEO, AI for Good Foundation, Chief Science Officer, Cognism, Inc. Researcher, Jozef Stefan Institute, Artificial Intelligence Lab

Auroop Ganguly

Auroop R. Ganguly

Professor at Northeastern University in Boston, Director of the Sustainability and Data Sciences Laboratory (SDS Lab). A co-founder and the chief scientific adviser of risQ Inc.

KDD 2019

Ramakrishnan Kannan

CEO, AI for Good Foundation, Chief Science Officer, Cognism, Inc. Researcher, Jozef Stefan Institute, Artificial Intelligence Lab