Climate Informatics

Overview:


The threat of climate change is one of the greatest challenges currently facing society. Given my undergraduate studies and longstanding interest in climate change, and inspired by the success of Bioinformatics, I wanted to use machine learning to shed light on climate change. Understanding climate change is an urgent challenge. Meanwhile, climate science is an extremely data-rich field, especially considering the massive amounts of simulation output from physics-driven climate models, providing a lens into the distant past and distant future. A multi-model ensemble of these climate models is used by the Intergovernmental Panel on Climate Change (IPCC) to inform their reports to the United Nations. Climate scientists are interested in ways to address the large ensemble spread (disagreement in predictions).


As it turned out, my past work on algorithms for online learning from non-stationary (time-varying) data, with access to expert predictors, proved to be very helpful in combining and robustifying the ensemble predictions. Our online learning algorithm, which updates weights over experts (climate models), while simultaneously learning the level of non-stationarity, significantly outperformed the multi-model (non-adaptive) mean, the standard technique in climate science. This provided a proof of concept that machine learning has something to offer the field of climate science; our work received the best paper award at a NASA conference and was discussed at an Expert Meeting of the IPCC. This momentum helped launch the field of climate informatics; I co-founded the International Workshop on Climate Informatics which turned 5 in 2015 and has attracted climate scientists and data scientists from over 19 countries and 30 states.


Since then, we have developed online learning algorithms that handle both spatial and temporal non-stationarity, along with multi-resolution structure, leading to improved performance for multi-model ensemble prediction. We have also demonstrated an unorthodox application of topic modeling to discover climate phenomena from data, providing a data-driven approach to defining and detecting extreme climate and weather events. There are a range of other problems on which machine learning can make an impact, and we encourage both machine learning researchers and climate scientists to get involved. The climate informatics endeavor is an exciting experiment in building a new interdisciplinary research field.


Video and slides from our NIPS 2014 Tutorial, “Climate Change: Challenges for Machine Learning.”


Research profile in Planet Forward.


For more information and materials, including data sets, tutorials, and workshop information, please see the Climate Informatics website.


Workshops: Climate Informatics turned 5 in 2015, and to celebrate, we launched the first Climate Informatics Hackathon! The sixth workshop, plus hackathon, will take place in September 2016.


  1. Bullet  Climate Informatics 2016: September 22-23, National Center for Atmospheric Research (NCAR), Boulder, CO.

  2. Bullet  Climate Informatics 2015: September 24-25, National Center for Atmospheric Research (NCAR), Boulder, CO.

  3. Bullet  Climate Informatics 2014: September 25-26, National Center for Atmospheric Research (NCAR), Boulder, CO.

  4. Bullet  Climate Informatics 2013: September 26-27, National Center for Atmospheric Research (NCAR), Boulder, CO.

  5. Bullet  Climate Informatics 2012: September 20-21, National Center for Atmospheric Research (NCAR), Boulder, CO.

  6. Bullet  The First International Workshop on Climate Informatics: August 26th 2011, at the New York Academy of Sciences, New York, NY.


Publications and conference/workshop presentations (by our group):

  1. Bullet  Scott McQuade, Claire Monteleoni, “Multi-Task Learning from a Single Task: Can Different Forecast Periods be Used to Improve Each Other?” In The Fifth International Workshop on Climate Informatics, The National Center for Atmospheric Research, 2015. Spotlight and poster presentation by McQuade.

  2. Bullet  Mahesh Mohan, Cheng Tang, Claire Monteleoni, Timothy DelSole, and Benjamin Cash, “Seasonal Prediction Using Unsupervised Feature Learning and Regression.” In The Fifth International Workshop on Climate Informatics, The National Center for Atmospheric Research, 2015. Spotlight and poster presentation by Mohan and Tang.

  3. Bullet  Timothy DelSole, Claire Monteleoni, Scott McQuade, Michael K. Tippett, Kathleen Pegion, and J. Shukla, “Tracking Seasonal Prediction Models.” In The Fifth International Workshop on Climate Informatics, The National Center for Atmospheric Research, 2015. Spotlight and poster presentation by McQuade.

  4. Bullet  A. Banerjee and C. Monteleoni, “Climate Change: Challenges for Machine Learning,” Invited Tutorial at NIPS 2014. Oral presentation by Banerjee and Monteleoni. [Slides]

  5. Bullet  C. Tang and C. Monteleoni, “Detecting Extreme Events from Climate Time-Series via Topic Modeling,” In The Fourth International Workshop on Climate Informatics, The National Center for Atmospheric Research, 2014. Oral and poster presentation by Tang.

  6. Bullet  “Machine Learning Techniques for Combining Multi-Model Climate Projections,” Invited talk, New Approaches for Pattern Recognition and Change Detection, session at American Geophysical Union (AGU) Fall Meeting, 2013. Oral presentation by Monteleoni.

  7. Bullet  S. McQuade and C. Monteleoni, “MRF-Based Spatial Expert Tracking of the Multi-Model Ensemble,” in New Approaches for Pattern Recognition and Change Detection, session at American Geophysical Union (AGU) Fall Meeting, 2013. Oral presentation by McQuade.

  8. Bullet  M. Ghafarianzadeh and C. Monteleoni, “Climate Prediction via Matrix Completion,” in Workshop on Machine Learning for Sustainability, NIPS 2013.  Poster presentation by Ghafarianzadeh.

  9. Bullet  M. Ghafarianzadeh and C. Monteleoni, “Climate Prediction via Matrix Completion,” in Workshop for Women in Machine Learning (WiML), collocated with NIPS 2013.  Poster presentation by Ghafarianzadeh.

  10. Bullet  “Climate Informatics: Recent Advances and Challenge Problems for Machine Learning in Climate Science,” Invited talk, Discovery Informatics: AI Takes a Science-Centered View on Big Data, AAAI Fall Symposium
    Series, 2013. Oral presentation by Monteleoni.

  11. Bullet  C. Monteleoni, G. A. Schmidt, and S. McQuade, “Climate Informatics: Accelerating Discovery in Climate Science with Machine Learning,” IEEE Computing in Science and Engineering (CISE) Magazine, Special Issue on Machine Learning. Sept.–Oct. 2013 (vol. 15 no. 5) pp. 32–40, 2013. Invited.

  12. Bullet  “Machine Learning Techniques for Combining Multi-Model Climate Projections,” Invited talk, The Third International Workshop on Climate Informatics, The National Center for Atmospheric Research, 2013. Oral presentation by Monteleoni.

  13. Bullet  S. McQuade and C. Monteleoni, “MRF-Based Spatial Expert Tracking of the Multi-Model Ensemble,“ The Third International Workshop on Climate Informatics, The National Center for Atmospheric Research, 2013. Poster presentation by McQuade.

  14. Bullet  M. Ghafarianzadeh and C. Monteleoni, “Climate Prediction via Matrix Completion,” The Third International Workshop on Climate Informatics, The National Center for Atmospheric Research, 2013. Poster presentation by Ghafarianzadeh.

  15. Bullet  M. Ghafarianzadeh and C. Monteleoni, “Climate Prediction via Matrix Completion” to appear in the Late-Breaking Papers Track, at the Twenty-Seventh Conference on Artificial Intelligence (AAAI), lightning oral and poster presentation by Ghafarianzadeh, Bellevue, WA, July 2013.

  16. Bullet  C. Monteleoni, G.A. Schmidt, F. Alexander, A. Niculescu-Mizil, K. Steinhaeuser, M. Tippett, A. Banerjee, M.B. Blumenthal, A.R. Ganguly, J.E. Smerdon, and M. Tedesco, “Climate Informatics,” to appear in Computational Intelligent Data Analysis for Sustainable Development; Data Mining and Knowledge Discovery Series. Yu, T., Chawla, N., and Simoff, S. (Eds.), CRC Press, Taylor & Francis Group. Chapter 4, pp. 81–126, 2013. Invited.

  17. Bullet  S. McQuade and C. Monteleoni, “Global Climate Model Tracking using Geospatial Neighborhoods,” In The Second International Workshop on Climate Informatics, The National Center for Atmospheric Research, 2012. Poster and spotlight oral presentation by McQuade.

  18. Bullet  S. McQuade and C. Monteleoni, “Global Climate Model Tracking using Geospatial Neighborhoods,” in the Computational Sustainability and AI Special Track, at the Twenty-Sixth Conference on Artificial Intelligence (AAAI), oral and poster presentation by McQuade, Toronto, July 2012.

  19. Bullet  S. McQuade and C. Monteleoni, “Global Climate Model Tracking using Geospatial Neighborhoods,” in poster presentation by McQuade, The Learning Workshop (Snowbird), April 2012. 

  20. Bullet  “Climate Informatics,” Invited talk, Workshop on Machine Learning for Sustainability, oral presentation by Monteleoni, NIPS 2011.

  21. Bullet  C. Monteleoni, G. Schmidt, S. Saroha, and E. Asplund, “Tracking Climate Models” in Journal of Statistical Analysis and Data Mining: Special Issue on Best of CIDU 2010, Volume 4, Issue 4, pp. 72–392, August 2011. Invited.

  22. Bullet  “Tracking Climate Models:  Advances in Climate Informatics,” Invited talk, The Second IEEE ICDMWorkshop on Knowledge Discovery from Climate Data: Prediction, Extremes, and Impacts, The 10th IEEE International Conference on Data Mining (ICDM), oral presentation by Monteleoni, Sydney, Australia , December 2010.

  23. Bullet  C. Monteleoni, G. Schmidt, and S. Saroha, “Tracking Climate Models”  In NASA Conference on Intelligent Data Understanding (CIDU), oral presentation by Monteleoni, October 2010.  Awarded Best Application Paper.

  24. Bullet  C. Monteleoni, S. Saroha, and G. Schmidt, “Tracking Climate Models”  In The Learning Workshop, oral presentation by Monteleoni, Snowbird, April 2010.

  25. Bullet  C. Monteleoni, S. Saroha, and G. Schmidt, “Can machine learning techniques improve forecasts?”  In Intergovernmental Panel on Climate Change (IPCC) Expert Meeting on Assessing and Combining Multi Model Climate Projections, poster presentation by Schmidt, Boulder, January 2010.

  26. Bullet  C. Monteleoni, S. Saroha, and G. Schmidt, “Tracking Climate Models”  In Temporal Segmentation: Perspectives from Statistics, Machine Learning, and Signal Processing, Workshop at Neural Information Processing Systems, poster presentation by Saroha, Vancouver, December 2009.              


Sponsors (past and present):

  1. Bullet  National Science Foundation (multiple grants linked here).

  2. Bullet  The Earth Institute, Columbia University

  3. Bullet  LDEO/GISS Climate Center

  4. Bullet  Information Science and Technology Center, Los Alamos National Laboratory

  5. Bullet  Department of Statistics, Columbia University

  6. Bullet  The New York Academy of Sciences

  7. Bullet  NEC Labs America

  8. Bullet  Yahoo! Research

  9. Bullet  National Center for Atmospheric Research (NCAR)

  10. Bullet  The Climate Corporation

  11. Bullet  Cray Inc.

  12. Bullet  NVIDIA