Jump to content

Climate Change Adaptation: Difference between revisions

 
(22 intermediate revisions by 6 users not shown)
''This page is about the intersection of climate change adaptation and machine learning. For an overview of climate change adaptation as a whole, please see the [https://en.wikipedia.org/wiki/Climate_change_adaptation Wikipedia page] on this topic.''[[File:Societal-adaptation.png|thumb|A summary of the different domains within which machine learning can support climate adaptation. Figure from "Tackling Climate Change with Machine Learning."<ref name=":0">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). [http://arxiv.org/abs/1906.05433 "Tackling Climate Change with Machine Learning"]. ''arXiv:1906.05433 [cs, stat].''</ref>]]
[[File:Societal-adaptation.png|thumb|A summary of the different domains within which machine learning can support climate adaptation.]]
Climate change adaptation refers to changes that can increase the resilience and robustness of earth and social systems. A system is resilient if it can gracefully recover from climate impacts, and it is robust if it has the impacts themselves are minimal.
Changes in the atmosphere have impacts on the ground. The expected societal impacts of climate change include prolonged ecological and socioeconomic stresses as well as brief, but severe, societal disruptions. For example, impacts could include both gradual decreases in crop yield and localized food shortages. If we can anticipate climate impacts well enough, then we can prepare for them by asking:
 
* How do we reduce vulnerability to climate impacts?
* How do we support rapid recovery from climate-induced disruptions?
 
A wide variety of strategies have been put forward, from robust power grids to food shortage prediction, and while this is good news for society, it can be overwhelming for an ML practitioner hoping to contribute. Fortunately, a few critical needs tend to recur across strategies – it is by meeting these needs that machine learning has the greatest potential to support societal adaptation. From a high level, these involve
 
Three ways that machine learning can support adaptation are highlighted in the paper "Tackling Climate Change with Machine Learning,"<ref name=":0" /><blockquote>
* Sounding alarms: Identifying and prioritizing the areas of highest risk, by using evidence of risk from historical data.
* Providing annotation: Extracting actionable information or labels from unstructured raw data.
* Promoting exchange: Making it easier to share resources and information to pool and reduce risk.
</blockquote>
== Data ==
Satellite imagery are used for ecological and social observation. Some public sources include,
 
== Machine Learning Application Areas ==
* [https://github.com/chrieke/awesome-satellite-imagery-datasets awesome-satellite-imagery-datasets]: A github repository of accessible satellite imagery data.
*
 
=== Infrastructure ===
There have also been competitions revolving around climate change adaptation issues,
 
*'''[[Predictive Maintenance|Predictive maintenance]]''': The increased weather extremes associated with climate change can create increased stresses on physical infrastructure, like roads and power lines. Machine learning can support targeted, just-in-time maintenance by isolating components at risk of near-term failure.
* [https://app.wandb.ai/wandb/droughtwatch/benchmark DroughtWatch] revolves around drought monitoring in Kenya.
*'''Risk and vulnerability assessment''': Better knowledge of where and on what time scale impacts will be felt can support prioritization of resources for societal adaptation.
* [https://www.drivendata.co/case-studies/promoting-digital-financial-services-in-tanzania/ Promoting Digital Financial Services in Tanzania] describes an attempt to mobile money effort to improve financial inclusion and resilience.
* The [https://zindi.africa/competitions/ibm-malaria-challenge IBM Malaria Challenge] is a competition around Improved disease surveillance and response, which is motivated by the spread of vector borne disease resulting from climate change.
 
===Societal Systems===
This competition describes an attempt to use mobile money effort to improve financial inclusion and resilience.
 
*'''[[Food Security|Food security]]''': By affecting rainfall and the timing of growing seasons, climate change poses a risk to food security. Machine learning can support information gathering around food supply chains, providing early warnings about -- and triggering preventative action around -- famines.
Improved disease surveillance and response is an important part of adaptation – here is one competition with this goal in mind.
*'''Public health''': Climate change can increase the range of vector-borne disease and exacerbate the severity and frequency of heatwaves. Both pose public health hazards, and machine learning can support risk assessment and outreach to vulnerable populations.
 
=== Methods and SoftwareCrisis ===
 
*'''Annotating disaster maps''': During crisis situations, relief organizations rely on detailed maps -- these are often the most reliable sources of information about the locations of schools, hospitals, and highways, for example. Machine learning can accelerate what are otherwise manual mapping processes.
== Recommended Readings ==
*'''Delivering alerts''': Machine learning can support situational awareness during crises, distilling large volumes of raw information (e.g., from social media or weather forecasts) into forms that can guide action.
 
== RecommendedBackground Readings ==
* Quinn, J. et al. Computational sustainability and artificial intelligence in the developing world<ref>{{Cite journal|last=Quinn|first=John|last2=Frias-Martinez|first2=Vanessa|last3=Subramanian|first3=Lakshminarayan|date=2014-09-29|title=Computational Sustainability and Artificial Intelligence in the Developing World|url=http://dx.doi.org/10.1609/aimag.v35i3.2529|journal=AI Magazine|volume=35|issue=3|pages=36|doi=10.1609/aimag.v35i3.2529|issn=0738-4602}}</ref> (2014).
* Gomes, C. et al., Computational sustainability: Computing for a better world and a sustainable future. (2019)
* Agrawal, A., and Perrin, N. Climate adaptation, local institutions and rural livelihoods. (2009)
* Shi, L. et al. Roadmap towards justice in urban climate adaptation research. (2016)
 
=== CommunityPrimers ===
 
*'''Chapter 20: "Adaptation Planning and Implementation" in the IPCC Fifth Assessment Report (2014)'''<ref>Abeysinghe A, Denton F, Bhadwal S, Burton I, Gao Q, Leal W, Lemos MF, Masui T, O'brien K, Van Ypersele JP, Warner K, and Wilbanks T, 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 [Core Writing Team, R.K. Pachauri and L.A. Meyer (eds.)]. IPCC, Geneva, Switzerland, 151 pp. 2014</ref>: An overview of current understanding on climate impacts and risks.
=== Journals and conferences ===
* Quinn, J. et al. '''Computational sustainability and artificial intelligence in the developing world (2014)'''<ref>{{Cite journal|last=Quinn|first=John|last2=Frias-Martinez|first2=Vanessa|last3=Subramanian|first3=Lakshminarayan|date=2014-09-29|title=Computational Sustainability and Artificial Intelligence in the Developing World|url=http://dx.doi.org/10.1609/aimag.v35i3.2529|journal=AI Magazine|volume=35|issue=3|pages=36|doi=10.1609/aimag.v35i3.2529|issn=0738-4602}}</ref>: (2014)A review describing the use of machine learning in problems related to health, food security, and mobility in the developing world.
*'''Computational sustainability: Computing for a better world and a sustainable future (2019)'''<ref>{{Citation|last=Schneider|first=Sabrina|title=The Impacts of Digital Technologies on Innovating for Sustainability|date=2019|url=http://dx.doi.org/10.1007/978-3-319-97385-2_22|work=Palgrave Studies in Sustainable Business In Association with Future Earth|pages=415–433|place=Cham|publisher=Springer International Publishing|isbn=978-3-319-97384-5|access-date=2020-08-28}}</ref>: An overview of the goals and techniques used in the field of computational sustainability.
 
== Online Courses and Course Materials ==
* [https://channels.plos.org/rtcc PLOS Responding to Climate Change]
 
* [https://acmcompass.org/ ACM Compass]
== Conferences, Journals, and Professional Organizations ==
* [https://www.itu.int/en/ITU-T/AI/2018/Pages/default.aspx AI for Good Global Summit]
 
* [https://www.thelancet.com/climate-and-health Lancet Health and Climate Change]
=== Journals andMajor conferences ===
 
* '''ACM Compass''': An annual conference focused on computing for sustainable societies. Website [https://acmcompass.org/ here].
 
* '''AI for Good Global Summit''': An annual conference organized by the UN ITU. Website [https://www.itu.int/en/ITU-T/AI/2018/Pages/default.aspx here].
 
=== Major journals ===
 
*'''PLOS Responding to Climate Change''': A channel from the open access journal PLOS dedicated to responses to climate change. Journal website [https://channels.plos.org/rtcc here].
*'''Lancet Health and Climate Change''': An initiative by the journal Lancet disseminating research on climate change and public health. Journal website [https://www.thelancet.com/climate-and-health here].
 
=== Societies and organizations ===
 
=== PastLibraries and upcomingTools events ===
{{SectionStub}}
 
== Data ==
== Important considerations ==
Satellite imagery are used for ecological and social observation. Some public sources include,
 
* [https://github.com/chrieke/awesome-satellite-imagery-datasets '''awesome-satellite-imagery-datasets''']: A github repository of accessible satellite imagery data.
== Next steps ==
* [https://github.com/cloudtostreet/MODIS_GlobalFloodDatabase '''Global Flood Database''']: A github repository that includes code and supporting data for the Global Flood Database.
 
There have also been competitions revolving around climate change adaptation issues,
 
* [https://app.wandb.ai/wandb/droughtwatch/benchmark '''DroughtWatch''']: revolvesPrediction aroundfor drought monitoring in Kenya.
* [https://www.drivendata.co/case-studies/promoting-digital-financial-services-in-tanzania/ '''Promoting Digital Financial Services in Tanzania''']: describesImproving anefficiency attemptof tomoney mobile moneyservices effortfor toimprovement improveof financial inclusion and resilience.
* The [https://zindi.africa/competitions/ibm-malaria-challenge '''IBM Malaria Challenge''']: is a competition aroundMachine Improvedlearning disease surveillance and response, which is motivated by the spread of vector borne disease resulting from climate change.
 
Improved disease surveillance and response is an important part of adaptation – here is one competition with this goal in mind.
 
== References ==
 
[[category:Application areasProblem_domains]]
Cookies help us deliver our services. By using our services, you agree to our use of cookies.