"The predominant predictive tools are climate models, known as General Circulation Models (GCMs) or Earth System Models (ESMs). These models inform local and national government decisions), help people calculate their climate risks (see Policy, Markets, and Decision Science and Climate Change Adaptation) and allow us to estimate the potential impacts of solar geoengineering [and exploring Earth System response to different emission future scenarios, and under differnet assumptions]. Recent trends have created opportunities for ML to advance the state-of-the-art in climate prediction. First, new and cheaper satellites are creating petabytes of climate observation data. Second, massive climate modeling projects are generating petabytes of simulated climate data. Third, climate forecasts are computationally expensive (some simulations have taken three weeks to run on NCAR supercomputers), while ML methods are becoming increasingly fast to train and run, especially on next-generation computing hardware. As a result, climate scientists have recently begun to explore ML techniques, and are starting to team up with computer scientists to build new and exciting applications."
Machine Learning Application Areas
ML, and climate science
- Collecting data for climate models: Assimilation of diverse sources can improve climate models, and machine learning can transform raw sensor output into more relevant derived data. Relevant applications include sensor calibration and analyzing information in remote sensing data. Well-curated benchmark datasets have the potential to advance several geoscience problems.
- Accelerating climate models: Physical constraints are key ingredients for cloud, aerosol, ice sheet, and sea level models. Traditional solutions to these physics-based models are computationally expensive, but machine learning components can help alleviate the most problematic bottlenecks.
- Working with climate models: Climate models can be extremely complex, and climate predictions are often made using the outputs of 20+ climate models. ML can help streamline existing climate models. For instance, ML can help identify and leverage relationships between variables within climate models, in order to streamline these models. ML can also help intelligently combine the outputs of multiple climate models in order to simplify computation with these ensembles.
Forecasting extreme events
- Storm tracking: While climate models can forecast long-term changes in the climate system, separate systems are required to detect specific extreme weather phenomena, like cyclones, atmospheric rivers, and tornadoes. Identifying extreme events in climate model outputs can inform scientific understanding of where and when these events may occur. ML can help classify, detect, and track climate-related extreme events such as hurricanes in climate model outputs.
- Local forecasts: Storms, droughts, fires, floods, and other extreme events are expected to become stronger and more frequent as climate change progresses. Machine learning can be used to refine what are otherwise coarse-grained forecasts (e.g., generated from climate or weather prediction models) of these extreme weather events. These high-resolution forecasts can guide improvements in system robustness and resilience.
- Introduction to climate dynamics and climate modeling (2010): A technical treatment of the climate system, energy balance, climate modeling, and climate perturbations. Available here.
- Principles of Planetary Climate (2010): An introduction to the physics of climate, with examples in python.
- Intergovernmental Panel on Climate Change (IPCC) Assessment Reports (e.g., AR5) and the IPCC Special Report Global Warming of 1.5 ºC
- Oxford Research Encyclopedia of Climate Science: A collection of articles on the climate systems, impacts of climate change, and the methods used in climate science.
Online Courses and Course Materials
- An Introduction to Climate Modeling (2014): A video lesson from Climate Literacy's Youtube channel. Available here.
Conferences, Journals, and Professional Organizations
- American Geosciences Union (AGU) Fall Meeting: A yearly conference organised by the AGU, usually takes place in December, location varies across different states of the USA. Website here.
- European Geosciences Union (EGU) General Assembly: A yearly conference organised by the EGU, usually takes place in April or Early May in Vienna, Austria. Website here.
- International Meeting on Statistical Climatology (IMSC): Meetings occurring approximately every three years, usually around June or July, in different locations worldwide. IMSC is organised by statisticians, climatologists and atmospheric scientists aiming to transfer knowledge among different communities (e.g., see the previous meeting)
- Climate Informatics (CI): annual workshop series, usually occurring in September in different locations worldwide (e.g., see the previous meetings).
Applications of Machine Learning in different domains of climate science appear in various climate-related journals, such as:
- Bulletin of the American Meteorological Society (BAMS): A journal published by the Americal Meteorological Society (AMS). Available here.
- Earth System Dynamics (ESD): An open-access journal of the European Geophysical Union. Available here.
- Environmental Research Letters (ERL): An open-access journal from IOPscience publishing group. Available here.
- Environmental Data Science: A new open-access interdisciplinary journal. Available here.
- Geophysical Research Letters (GRL): A journal of the American Geophysical Union. Available here.
- Journal of Climate: A journal published by the Americal Meteorological Society (AMS). Available here.
- Proceedings of the National Academy of Sciences (PNAS): A wide-reaching journal often featuring climate science. Available here.
- Springer Nature journals: Often feature climate science topics, recently also with applications of machine learning -e.g., Nature Climate Change, Nature Geoscience, Nature Communications (open access), Communications Earth and Environment (open access), npj Climate and Atmospheric Science (open access).
Major societies and organizations
- American Geophysical Union (AGU): An organization supporting work across the geophysical sciences. Website here.
- Climate Informatics (CI): An organization dedicated to computing in climate science. Website here.
- European Geosciences Union (EGU): An organization supporting research in Earth, planetary, and space science in Europe. Website here.
- Intergovernmental Panel on Climate Change (IPCC): A United Nations body that assesses climate change and provides policy-relevant information. IPCC provides Assessment Reports and Special Reports that provide a comprehensive summary of the state-of-the-art developments and findings. Website here.
Libraries and Tools
- Pangeo: An open source python package for geoscience applications, available here.
- Pangeo also maintains a list of packages useful for atmospheric, ocean, and climate science.
The largest climate prediction datasets are ensembles of many climate simulations. These include simulations with varied physics, architectures, or initial conditions, and they are used to explore the range of possible climate futures. The largest ensembles include:
- The Coupled Model Intercomparison Project (CMIP): A gateway to climate models in use and development, available here. CMIP is associated with the Earth System Grid Federation, which also provides data analysis tools and tutorials: https://esgf.llnl.gov/
- The CESM Large Ensemble: Read about it in The Community Earth System Model (CESM) Large Ensemble Project. Available here.
- Google Cloud Weather and Climate Datasets: Petabyte-scale weather and climate datasets from sources like NOAA’s NEXRAD and NASA/USGS’s Landsat, made available for free as part of Google Cloud’s Public Datasets Program. Available here.
- EARTHDATA: NASA's gateway to earth science data. Data are available at multiple levels of processing. Available here.
The Earth and climate science community is also working to create benchmark datasets: https://is-geo.org/benchmarks/.
- Rolnick, David; Donti, Priya L.; Kaack, Lynn H.; Kochanski, Kelly; Lacoste, Alexandre; Sankaran, Kris; Ross, Andrew Slavin; Milojevic-Dupont, Nikola; Jaques, Natasha; Waldman-Brown, Anna; Luccioni, Alexandra (2019-11-05). "Tackling Climate Change with Machine Learning". arXiv:1906.05433 [cs, stat].
- IPCC (2018). Global warming of 1.5C. An IPCC special report on the impacts of global warming of 1.5C above pre-industrial levels and related global greenhouse gas emission pathways, in the context of strengthening the global response to the threat of climate change, sustainable development, and efforts to eradicate poverty.
- IPCC (2014). IPCC. Climate Change 2014: Mitigation of Climate Change. Contribution of Working Group III to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change.
- IPCC (2014). Climate Change 2014: Synthesis Report. Contribution of Working Groups I, II and III to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change.
- "Earth Observation Gateway".
- "NASA EarthData".
- "Coupled Model Intercomparison Project (CMIP)".
- Carman, T (2017). "Position paper on high performance computing needs in Earth system prediction". NOAA Institutional Repository.
- "The Community Earth System Model (CESM) Large Ensemble project". 2015. Cite journal requires
- Goosse, Hugues (2015). Climate system dynamics and modeling. New York, NY: Cambridge University Press. ISBN 978-1-107-08389-9.
- Pierrehumbert, Raymond T. (2010). Principles of planetary climate. Cambridge ; New York: Cambridge University Press. ISBN 978-0-521-86556-2. OCLC 601113992.
- "Oxford Research Encyclopedia of Climate Science". Oxford Research Encyclopedia of Climate Science. Retrieved 2020-11-19.
- "5.1 Introduction to Climate Modeling - YouTube". www.youtube.com. Retrieved 2020-09-24.