Solar Geoengineering: Difference between revisions

modify intro
(→‎Relevant Groups and Organizations: --> add SCoPEx pointer)
(modify intro)
Line 1:
''This page is about the intersection of solar geoengineering and machine learning. For an overview of solar geoengineering as a whole, please see the [https://en.wikipedia.org/wiki/Solar_radiation_management Wikipedia page] on this topic.''
 
Solar geoengineering (also known as "solar radiation management") refers of proposals aimed at increasing the amount of heat the Earth releases, in order to counteract global warming caused by the greenhouse effect. In particular, solar geoengineering proposals seek to "reflect a small fraction of sunlight back into space or increase the amount of solar radiation that escapes back into space to cool the planet."<ref name=":0">{{Cite web|title=Geoengineering|url=https://geoengineering.environment.harvard.edu/geoengineering|website=geoengineering.environment.harvard.edu|access-date=2020-12-07|language=en}}</ref> Examples of such proposals include attempting to make clouds brighter so they reflect back more sunlight; installing sun shields in space; and scattering aerosols into the stratosphere in order to scatter a small amount of sunlight.<ref name=":0" />
 
It is worth noting that solar geoengineering proposals come with many uncertainties and risks (regarding both implementation and effects), as well as governance challenges and ethical considerations.<ref name=":1">{{Cite web|url=https://royalsociety.org/topics-policy/publications/2009/geoengineering-climate/|title=Geoengineering the climate: science, governance and uncertainty {{!}} Royal Society|website=royalsociety.org|language=en-gb|access-date=2020-12-19}}</ref> In addition, since solar geoengineering proposals do not address the amount of CO<sub>2</sub> or other greenhouse gases in the atmosphere, they do not necessarily address issues related to rising CO<sub>2</sub> levels, such as ocean acidification.<ref name=":1" /> As a result, solar geoengineering proposals are widely considered to be very much a "last resort" for addressing climate change.<ref>{{Cite journal|last=Victor|first=David G.|last2=Morgan|first2=M. Granger|last3=Apt|first3=Jay|last4=Steinbruner|first4=John|date=2009|title=The Geoengineering Option - A Last Resort against Global Warming|url=https://heinonline.org/HOL/Page?handle=hein.journals/fora88&id=278&div=&collection=|journal=Foreign Affairs|volume=88|pages=64}}</ref>
Solar engineering proposals come with many uncertainties, risks, and governance challenges. For instance, [TODO finish]
 
Although it has been argued that the "hardest and most important problems raised by solar geoengineering are non-technical,"<ref>{{Cite journal|last=Sugiyama|first=Masahiro|last2=Ishii|first2=Atsushi|last3=Asayama|first3=Shinichiro|last4=Kosugi|first4=Takanobu|date=2018-04-26|title=Solar Geoengineering Governance|url=http://dx.doi.org/10.1093/acrefore/9780190228620.013.647|journal=Oxford Research Encyclopedia of Climate Science|doi=10.1093/acrefore/9780190228620.013.647}}</ref> there are a number of technical problems that remain to be addressed, some of which may (speculatively) benefit from machine learning.<ref name=":2" />
 
== Machine Learning Application Areas ==
There are a number of speculative applications of machine learning to solar geoengineering. (For more details on these problem areas, see the chapter on Solar Geoengineering in the paper "Tackling Climate Change with Machine Learning."<ref name=":2">{{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>)
 
* '''Designing aerosols''': Many solar geoengineering proposals rely on injecting aerosol particles into the atmosphere to partially reflect sunlight. ML can (speculatively) accelerate the search for new aerosols that are chemically nonreactive but still reflective, cheap, and easy to keep aloft. (See also the page on [[Accelerated Science|accelerated science]].)