Tackling Climate Change with Machine Learning

Tackling Climate Change with Machine Learning

David Rolnick111D.R. conceived and edited this work, with P.L.D., L.H.K., and K.K. Authors P.L.D., L.H.K., K.K., A.L., K.S., A.S.R., N.M-D., N.J., A.W-B., A.L., T.M., and E.D.S. researched and wrote individual sections. S.K.M., K.P.K., C.G., A.Y.N., D.H., J.C.P., F.C., J.C., and Y.B. contributed expert advice. Correspondence to drolnick@seas.upenn.edu. , Priya L. Donti, Lynn H. Kaack, Kelly Kochanski, Alexandre Lacoste,
Kris Sankaran, Andrew Slavin Ross, Nikola Milojevic-Dupont, Natasha Jaques,
Anna Waldman-Brown, Alexandra Luccioni, Tegan Maharaj, Evan D. Sherwin,
S. Karthik Mukkavilli, Konrad P. Kording, Carla Gomes, Andrew Y. Ng,
Demis Hassabis, John C. Platt, Felix Creutzig, Jennifer Chayes, Yoshua Bengio
University of Pennsylvania, Carnegie Mellon University, ETH Zürich, University of Colorado Boulder,
Element AI, Mila, Université de Montréal, Harvard University,
Mercator Research Institute on Global Commons and Climate Change, Technische Universität Berlin,
Massachusetts Institute of Technology, Cornell University, Stanford University,
DeepMind, Google AI, Microsoft Research

Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help. Here we describe how machine learning can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we identify high impact problems where existing gaps can be filled by machine learning, in collaboration with other fields. Our recommendations encompass exciting research questions as well as promising business opportunities. We call on the machine learning community to join the global effort against climate change.


The effects of climate change are increasingly visible.111For a layman’s introduction to the topic of climate change, see [romm2018climate, archer2010climate]. Storms, droughts, fires, and flooding have become stronger and more frequent [field2012managing]. Global ecosystems are changing, including the natural resources and agriculture on which humanity depends. The 2018 intergovernmental report on climate change estimated that the world will face catastrophic consequences unless global greenhouse gas emissions are eliminated within thirty years [ipcc_global_2018]. Yet year after year, these emissions rise.

Addressing climate change involves mitigation (reducing emissions) and adaptation (preparing for unavoidable consequences). Both are multifaceted issues. Mitigation of greenhouse gas (GHG) emissions requires changes to electricity systems, transportation, buildings, industry, and land use. Adaptation requires climate modeling, risk prediction, and planning for resilience and disaster management. Such a diversity of problems can be seen as an opportunity: there are many ways to have an impact.

In recent years, machine learning (ML) has been recognized as a broadly powerful tool for technological progress. Despite the growth of movements applying ML and AI to problems of societal and global good222See the AI for social good movement (e.g. [hager2019artificial, berendt2019ai]), ML for the developing world [de2018machine], and the computational sustainability movement (e.g. [kelling2018computational, joppa2017case, lassig2016computational, gomes2009computational, dietterich2009machine]). Faghmous and Kumar presented an overview of climate change problems from the perspective of big data [faghmous2014big], and Kaack recently presented an overview of ML applications to climate mitigation [kaack2019challenges]. Climate informatics specifically considers the problem of applying ML to climate modeling [monteleoni2013climate, karpatne2017big], which we consider in §LABEL:sec:_climate_prediction. Ford et al. also call for applications of big data to climate change adaptation domains including vulnerability assessment, early warning, and monitoring and evaluation [ford2016opinion], topics which we consider in §LABEL:sec:societal-impacts., there remains the need for a concerted effort to identify how these tools may best be applied to climate change. Many ML practitioners wish to act, but are uncertain how. On the other side, many fields have begun actively seeking input from the ML community.

This paper aims to provide an overview of where machine learning can be applied with high impact in the fight against climate change, through either effective engineering or innovative research. The solutions we highlight include climate mitigation and adaptation, as well as meta-level tools that enable other solutions. In order to maximize the relevance of our recommendations, we have consulted experts across many fields (see Acknowledgments) in the preparation of this paper.








RL &











Electricity Systems LABEL:sec:electricity-systems LABEL:sec:electricity-lowCarbon
LABEL:sec:electricity-systems LABEL:sec:electricity-lowCarbon
LABEL:sec:electricity-developing LABEL:sec:electricity-lowCarbon LABEL:sec:electricity-lowCarbon
Buildings & Cities LABEL:sec:distr LABEL:sec:cities LABEL:sec:buildings-cities LABEL:sec:buildings-cities LABEL:sec:bldgopt LABEL:sec:indv LABEL:sec:cities LABEL:sec:buildings-cities
LABEL:sec:demandresponse LABEL:sec:demandresponse LABEL:sec:industry
Farms & Forests
LABEL:sec:agriculture LABEL:sec:forests
CO Removal LABEL:subsubsec:_sequestration LABEL:subsubsec:_sequestration LABEL:subsubsec:_sequestration LABEL:subsec:dac
Climate Prediction LABEL:sec:_climate_models_-_params LABEL:sec:_climate_prediction LABEL:sec:_climate_models_-_ml+science LABEL:sec:_climate_prediction
Societal Impacts
LABEL:subsub:infrastructure LABEL:subsub:social_systems LABEL:subsub:infrastructure LABEL:subsub:ecology LABEL:subsub:social_systems
Solar Geoengineering LABEL:subsub:aerosol-modeling LABEL:subsub:planetary-control
Tools for Individuals LABEL:sec:personal_carbon_footprint LABEL:sec:personal_carbon_footprint LABEL:sec:household_energy_impact LABEL:sec:behavior_change LABEL:sec:household_energy_impact LABEL:sec:personal_carbon_footprint LABEL:sec:household_energy_impact LABEL:sec:household_energy_impact
Tools for Society LABEL:sec:policydesign
LABEL:sec:policydesign LABEL:sec:toolsforsociety LABEL:sec:policydesign
Education LABEL:sec:climate-ed LABEL:sec:aied
Finance LABEL:sec:climate-analytics LABEL:sec:finance LABEL:sec:climate-analytics
Table 1: Climate change solution domains, along with areas of ML that are relevant to each. Rows of the table correspond to sections of this paper. This table should not be seen as comprehensive.

Who is this paper written for?

We believe that our recommendations will prove valuable to several different audiences (detailed below). In our writing, we have assumed some familiarity with basic terminology in machine learning, but do not assume any prior familiarity with application domains (such as agriculture or electric grids).

Researchers and engineers: We identify many problems that require conceptual innovation and can advance the field of ML, as well as being highly impactful. For example, we highlight how weather models afford an exciting domain for interpretable ML (see §LABEL:sec:_climate_models_-_params). We encourage researchers and engineers across fields to use their expertise in solving urgent problems relevant to society.

Entrepreneurs and investors: We identify many problems where existing ML techniques could have a major impact without further research, and where the missing piece is deployment. We realize that some of the recommendations we offer here will make valuable startups and nonprofits. For example, we highlight techniques for providing fine-grained solar forecasts for power companies (see §LABEL:sec:electricity-variable), tools for helping reduce personal energy consumption (see §LABEL:sec:behavior_change), and predictions for the financial impacts of climate change (see §LABEL:sec:finance). We encourage entrepreneurs and investors to fill what is currently a wide-open space.

Corporate leaders: We identify problems where ML can lead to massive efficiency gains if adopted at scale by corporate players.333Approximate cost-benefit analyses for some of these are considered e.g. in [hawken2017drawdown]. For example, we highlight means of optimizing supply chains to reduce waste (see §LABEL:sec:supplychains) and software/hardware tools for precision agriculture (see §LABEL:sec:agriculture). We encourage corporate leaders to take advantage of opportunities offered by ML to benefit both the world and the bottom line.

Local and national governments: We identify problems where ML can improve public services, help gather data for decision-making, and guide plans for future development. For example, we highlight intelligent transportation systems (see §LABEL:sec:TReducing, LABEL:sec:modalshift), techniques for automatically assessing the energy consumption of buildings in cities (see §LABEL:sec:bldginfrastructure), and tools for improving disaster management (see §LABEL:subsub:crisis). We encourage governments to consult ML experts while planning infrastructure and development, as this can lead to better, more cost-effective outcomes. We further encourage public entities to release data that may be relevant to climate change mitigation and adaptation goals.

How to read this paper

The paper is broken into sections according to application domain (see Table 1). To help the reader, we have also included the following flags at the level of individual solutions.

  • High Leverage denotes bottlenecks that domain experts have identified in climate change mitigation or adaptation and that we believe to be particularly well-suited to tools from ML. These solutions may be especially fruitful for ML practitioners wishing to have an outsized impact, though applications not marked with this flag are also valuable and should be pursued.

  • Long-term denotes solutions that will have their primary impact after 2040. Such solutions are neither more nor less important than short-term solutions – both are necessary.

  • High Risk denotes solutions that are risky in one of the following ways: (i) the technology involved is uncertain and may ultimately not succeed, (ii) there is uncertainty as to the impact on GHG emissions (for example, the Jevons paradox may apply444The Jevons paradox in economics refers to a situation where increased efficiency nonetheless results in higher overall demand. For example, autonomous vehicles could cause people to drive far more, so that overall GHG emissions could increase even if each ride is more efficient. In such cases, it becomes especially important to make use of specific policies, such as carbon pricing, to direct new technologies and the ML behind them. See also the literature on rebound effects and induced demand.), or (iii) there is the potential for unwanted side effects (negative externalities).

These flags should not be taken as definitive; they represent our understanding of more rigorous analyses within the domains we consider, combined with our subjective evaluation of the potential role of ML in these various applications.

Despite the length of the paper, we cannot cover everything. There will certainly be many solutions that we have not considered, or that we have erroneously dismissed. We look forward to seeing where future work leads.

A call for collaboration

All of the problems we highlight in this paper require collaboration across fields. As the language used to refer to problems often varies between disciplines, we have provided keywords and background reading within each section of the paper. Finding collaborators and relevant data can sometimes be difficult; for additional resources, please visit the website that accompanies this paper (https://www.climatechange.ai/).

Collaboration makes it easier to develop effective solutions. Working with domain experts reduces the chance of using powerful tools when simple tools will do the job, of working on a problem that isn’t actually relevant to practitioners, of overly simplifying a complex issue, or of failing to anticipate risks.

Collaboration can also help ensure that new work reaches the audience that will use it. To be impactful, ML code should be accessible and published using a language and a platform that are already popular with the intended users. For maximal impact, new code can be integrated into an existing, widely used tool.

We emphasize that machine learning is not a silver bullet. The applications we highlight are impactful, but no one solution will “fix” climate change. There are also many areas of action where ML is inapplicable, and we omit these entirely. Furthermore, technology alone is not enough – technologies that would reduce climate change have been available for years, but have largely not been adopted at scale by society. While we hope that ML will be useful in reducing the costs associated with climate action, humanity also must decide to act.

Comments 0
Request Comment
You are adding the first comment!
How to quickly get a good reply:
  • Give credit where it’s due by listing out the positive aspects of a paper before getting into which changes should be made.
  • Be specific in your critique, and provide supporting evidence with appropriate references to substantiate general statements.
  • Your comment should inspire ideas to flow and help the author improves the paper.

The better we are at sharing our knowledge with each other, the faster we move forward.
The feedback must be of minimum 40 characters and the title a minimum of 5 characters
Add comment
Loading ...
This is a comment super asjknd jkasnjk adsnkj
The feedback must be of minumum 40 characters
The feedback must be of minumum 40 characters

You are asking your first question!
How to quickly get a good answer:
  • Keep your question short and to the point
  • Check for grammar or spelling errors.
  • Phrase it like a question
Test description