Climate Modeling and Analysis: Difference between revisions

From Climate Change AI Wiki
Content added Content deleted
VisualWikitext
mNo edit summary
No edit summary
Line 1: Line 1:
''This page is about the intersection of climate science and machine learning in the context of climate change adaptation. For an overview of climate science as a whole, please see the [https://en.wikipedia.org/wiki/Climatology Wikipedia page] on this topic.''[[File:Clim prediction.png|thumb|The main avenues through which machine learning can support climate science, as described in <ref>{{Cite journal|title=Tackling Climate Change with Machine Learning|url=https://arxiv.org/pdf/1906.05433.pdf#page=63&zoom=100,109,256}}</ref>.]]
''This page is about the intersection of climate science and machine learning in the context of climate change adaptation. For an overview of climate science as a whole, please see the [https://en.wikipedia.org/wiki/Climatology Wikipedia page] on this topic.''[[File:Clim prediction.png|thumb|The main avenues through which machine learning can support climate science, as described in "Tackling Climate Change with Machine Learning." <ref name=":0">{{Cite journal|last=Rolnick|first=David|last2=Donti|first2=Priya L.|last3=Kaack|first3=Lynn H.|last4=Kochanski|first4=Kelly|last5=Lacoste|first5=Alexandre|last6=Sankaran|first6=Kris|last7=Ross|first7=Andrew Slavin|last8=Milojevic-Dupont|first8=Nikola|last9=Jaques|first9=Natasha|last10=Waldman-Brown|first10=Anna|last11=Luccioni|first11=Alexandra|date=2019-11-05|title=Tackling Climate Change with Machine Learning|url=http://arxiv.org/abs/1906.05433|journal=arXiv:1906.05433 [cs, stat]}}</ref>]]
The first global warming prediction was made in 1896, when Arrhenius estimated that burning fossil fuels could eventually release enough CO2 to warm the Earth by 5°C. The fundamental physics underlying those calculations has not changed, but our predictions have become far more detailed and precise. 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<ref>{{Cite book|url=https://www.ipcc.ch/sr15/|title=Global warming of 1.5C. An IPCC special report on the impacts of global warming of 1.5C above
As described in "Tackling Climate Change with Machine Learning,"<ref name=":0" /><blockquote>The first global warming prediction was made in 1896, when Arrhenius estimated that burning fossil fuels could eventually release enough CO2 to warm the Earth by 5°C. The fundamental physics underlying those calculations has not changed, but our predictions have become far more detailed and precise. 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<ref>{{Cite book|url=https://www.ipcc.ch/sr15/|title=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
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|author=IPCC|coauthors=|date=October 2018.}}</ref><ref>{{Cite book|url=https://www.ipcc.ch/report/ar5/wg3/|author=IPCC|title=IPCC. Climate Change 2014: Mitigation of Climate Change. Contribution of Working Group III to the Fifth
global response to the threat of climate change, sustainable development, and efforts to eradicate poverty|author=IPCC|coauthors=|date=October 2018.}}</ref><ref>{{Cite book|url=https://www.ipcc.ch/report/ar5/wg3/|author=IPCC|title=IPCC. Climate Change 2014: Mitigation of Climate Change. Contribution of Working Group III to the Fifth
Line 7: Line 7:


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<ref>{{Cite web|url=https://earth.esa.int/eogateway/}}</ref><ref>{{Cite web|url=earthdata.nasa.gov}}</ref>. Second, massive climate modeling projects are generating petabytes of simulated climate data<ref>{{Cite web|url=cmip.llnl.gov}}</ref>. Third, climate forecasts are computationally expensive<ref>{{Cite journal|title=Position paper on high performance computing needs in Earth system prediction|last=Carman|first=T|coauthors=T Clune, F Giraldo, M Govett, B Gross, A Kamrathe, T Lee, D McCarren, J Michalakes, S Sandgathe,
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<ref>{{Cite web|url=https://earth.esa.int/eogateway/}}</ref><ref>{{Cite web|url=earthdata.nasa.gov}}</ref>. Second, massive climate modeling projects are generating petabytes of simulated climate data<ref>{{Cite web|url=cmip.llnl.gov}}</ref>. Third, climate forecasts are computationally expensive<ref>{{Cite journal|title=Position paper on high performance computing needs in Earth system prediction|last=Carman|first=T|coauthors=T Clune, F Giraldo, M Govett, B Gross, A Kamrathe, T Lee, D McCarren, J Michalakes, S Sandgathe,
and T Whitcomb|url=https://repository.library.noaa.gov/view/noaa/14319|year=2017}}</ref> (some simulations have taken three weeks to run on NCAR supercomputers<ref>{{Cite journal|title=The Community Earth System Model (CESM) Large Ensemble project|year=2015|url=https://journals.ametsoc.org/bams/article/96/8/1333/69450}}</ref>), 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.
and T Whitcomb|url=https://repository.library.noaa.gov/view/noaa/14319|year=2017}}</ref> (some simulations have taken three weeks to run on NCAR supercomputers<ref>{{Cite journal|title=The Community Earth System Model (CESM) Large Ensemble project|year=2015|url=https://journals.ametsoc.org/bams/article/96/8/1333/69450}}</ref>), 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.</blockquote>


== Machine Learning Application Areas ==
== Machine Learning Application Areas ==

=== Uniting data, ML, and climate science ===

* Data for climate models
* Accelerating climate models
* Working with climate models

=== Forecasting extreme events ===

* Storm tracking
* Local forecasts


== Background Readings ==
== Background Readings ==
Some textbook length introductions to climate science include,


=== Textbooks ===
*''[http://www.climate.be/textbook/ Introduction to climate dynamics and climate modeling]''


*'''Introduction to climate dynamics and climate modeling (2010)'''<ref>{{Cite book|title=Climate system dynamics and modeling|last=Goosse|first=Hugues|date=2015|publisher=Cambridge University Press|isbn=978-1-107-08389-9|location=New York, NY}}</ref>: A technical treatment of the climate system, energy balance, climate modeling, and climate perturbations. Available [http://www.climate.be/textbook/contents.html here].
Other resources include,


=== Other ===
*[https://www.youtube.com/watch?v=XGi2a0tNjOo&feature=youtu.be An Introduction to Climate Modeling], a video lesson from Climate Literacy's Youtube channel

*'''An Introduction to Climate Modeling (2014)'''<ref>{{Cite web|url=https://www.youtube.com/watch?v=XGi2a0tNjOo&feature=youtu.be|title=5.1 Introduction to Climate Modeling - YouTube|website=www.youtube.com|access-date=2020-09-24}}</ref>: A video lesson from Climate Literacy's Youtube channel. Available [https://www.youtube.com/watch?v=XGi2a0tNjOo&feature=youtu.be here].


== Online Courses and Course Materials ==
== Online Courses and Course Materials ==
Line 25: Line 37:


=== Journals and conferences ===
=== Journals and conferences ===
Climate science is a journal field. Noteworthy research appears in journals such as the [https://journals.ametsoc.org/bams Bulletin of the American Meteorological Society], [https://agupubs.onlinelibrary.wiley.com/journal/19448007 Geophysical Research Letters] and the [https://www.pnas.org/ Proceedings of the National Academy of Sciences].
Climate science is a journal field. Noteworthy research appears in journals such as

* '''Bulletin of the American Meteorological Society''': A journal published by the AMS. Available [https://journals.ametsoc.org/bams here].
* '''Geophysical Research Letters''': The journal of the American Geophysical Union. Available [https://agupubs.onlinelibrary.wiley.com/journal/19448007 here].
* '''Proceedings of the National Academy of Sciences''': A wide-reaching journal often featuring climate science. Available [https://www.pnas.org/ here].


=== Societies and organizations ===
=== Societies and organizations ===


*'''American Geophysical Union''': An organization supporting work across the geophysical sciences. Website [https://www.agu.org/ here].
*[https://www.agu.org/ AGU]
*[http://climateinformatics.org/ Climate Informatics]
*'''Climate Informatics''': An organization dedicated to computing in climate science. Website [http://climateinformatics.org/ here].


=== Past and upcoming events ===
=== Past and upcoming events ===


*[https://www.agu.org/fall-meeting AGU Fall Meeting 2020]
*'''AGU Fall Meeting''': A yearly conference organized by the American Geophysical Union. Website [https://www.agu.org/fall-meeting here].


== Libraries and Tools ==
== Libraries and Tools ==
[https://pangeo.io/ Pangeo] supports open source scientific python for geoscience applications.
'''Pangeo''': An open source python package for geoscience applications, available [https://pangeo.io/ here].


* Pangeo also maintains a list of packages useful for [https://github.com/pangeo-data/awesome-open-climate-science atmospheric, ocean, and climate science].
* Pangeo also maintains a list of packages useful for [https://github.com/pangeo-data/awesome-open-climate-science atmospheric, ocean, and climate science].

Revision as of 03:44, 24 September 2020

This page is about the intersection of climate science and machine learning in the context of climate change adaptation. For an overview of climate science as a whole, please see the Wikipedia page on this topic.

The main avenues through which machine learning can support climate science, as described in "Tackling Climate Change with Machine Learning." [1]

As described in "Tackling Climate Change with Machine Learning,"[1]

The first global warming prediction was made in 1896, when Arrhenius estimated that burning fossil fuels could eventually release enough CO2 to warm the Earth by 5°C. The fundamental physics underlying those calculations has not changed, but our predictions have become far more detailed and precise. 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[2][3][4]), 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. 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[5][6]. Second, massive climate modeling projects are generating petabytes of simulated climate data[7]. Third, climate forecasts are computationally expensive[8] (some simulations have taken three weeks to run on NCAR supercomputers[9]), 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

Uniting data, ML, and climate science

  • Data for climate models
  • Accelerating climate models
  • Working with climate models

Forecasting extreme events

  • Storm tracking
  • Local forecasts

Background Readings

Textbooks

  • Introduction to climate dynamics and climate modeling (2010)[10]: A technical treatment of the climate system, energy balance, climate modeling, and climate perturbations. Available here.

Other

  • An Introduction to Climate Modeling (2014)[11]: A video lesson from Climate Literacy's Youtube channel. Available here.

Online Courses and Course Materials

Community

Journals and conferences

Climate science is a journal field. Noteworthy research appears in journals such as

  • Bulletin of the American Meteorological Society: A journal published by the AMS. Available here.
  • Geophysical Research Letters: The journal of the American Geophysical Union. Available here.
  • Proceedings of the National Academy of Sciences: A wide-reaching journal often featuring climate science. Available here.

Societies and organizations

  • American Geophysical Union: An organization supporting work across the geophysical sciences. Website here.
  • Climate Informatics: An organization dedicated to computing in climate science. Website here.

Past and upcoming events

  • AGU Fall Meeting: A yearly conference organized by the American Geophysical Union. Website here.

Libraries and Tools

Pangeo: An open source python package for geoscience applications, available here.

Data

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:

N.B. Climate model data is typically presented in netcdf4 format. These may be smoothly converted to csv files or pandas dataframes, but be aware that the data lies on irregular 3D spherical grids.

The Earth and climate science community is also working to create benchmark datasets: https://is-geo.org/benchmarks/.

References

  1. ↑ 1.0 1.1 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].
  2. ↑ IPCC (October 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. line feed character in |title= at position 94 (help); Check date values in: |date= (help)
  3. ↑ 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. line feed character in |title= at position 104 (help)
  4. ↑ 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. line feed character in |title= at position 97 (help)
  5. ↑ https://earth.esa.int/eogateway/. Missing or empty |title= (help)
  6. ↑ [earthdata.nasa.gov earthdata.nasa.gov] Check |url= value (help). Missing or empty |title= (help)
  7. ↑ [cmip.llnl.gov cmip.llnl.gov] Check |url= value (help). Missing or empty |title= (help)
  8. ↑ Carman, T (2017). "Position paper on high performance computing needs in Earth system prediction". Unknown parameter |coauthors= ignored (|author= suggested) (help); line feed character in |coauthors= at position 97 (help); Cite journal requires |journal= (help)
  9. ↑ "The Community Earth System Model (CESM) Large Ensemble project". 2015. Cite journal requires |journal= (help)
  10. ↑ Goosse, Hugues (2015). Climate system dynamics and modeling. New York, NY: Cambridge University Press. ISBN 978-1-107-08389-9.
  11. ↑ "5.1 Introduction to Climate Modeling - YouTube". www.youtube.com. Retrieved 2020-09-24.
Retrieved from "https://wiki.climatechange.ai/wiki/Climate_Modeling_and_Analysis?oldid=5079"