Public Policy and Decision Science
TODO: add context regarding contribution to emissions, connection to ML, and selected readings (summarize)
Decision + Policy
When creating policies, decision-makers must often negotiate fundamental uncertainties in the underlying data. ML can help alleviate some of this uncertainty by extracting information from satellite imagery, sensors, social media posts, policy documents, and other sources (as detailed elsewhere in the paper).
Decision-makers often construct mathematical models to help them assess or trade off between different policy alternatives. ML can help provide new techniques for working with integrated assessment models, multi-objective optimization, and other models commonly used by decision-makers.
When creating new policies, decision-makers may wish to understand previous policies and analyze how these policies performed. ML can help on both fronts by analyzing the text of existing policies and by performing causal inference on historical data.
Carbon pricing and other market-based measures can incentivize the reduction of greenhouse gas emissions. ML can help predict prices in carbon markets and analyze the main drivers of these prices.
When designing market-based strategies, it is necessary to understand how effectively each strategy will reduce emissions, as well as how the underlying socio-technical system may be affected. ML can help assess the outcomes of market-based strategies to ensure they are effective and equitable.
TODO: Intro Paragraph
- World Bank ClimateSmart data portal
- Environmental Treaty Status Data Set, 2012 Release (1940–2012)
- Vulnerability to Climate Change Dataset
- CO2 “price” in European ETS (European Union Emissions Trading System (EU ETS) data from EUTL)
- IPCC Socio-Economic Baseline Data, v1 (1980, 1990, 1991, 1992, 1993, 1994, 1995, 2025)
- IPCC Fourth Assessment Report (AR4) Observed Climate Change Impacts, v1 (1970–2004)
Methods and Software
TODO: Intro par
- Carbon market simulation tool
- Python packages for multi-objective optimization:
- Evolutionary Multi-Objective Optimization (EMOO)
- Platypus - Multiobjective Optimization in Python: Platypus is a framework for evolutionary computing in Python with a focus on multiobjective evolutionary algorithms (MOEAs), providing optimization algorithms and analysis tools for multiobjective optimization.
- Matlab package for multi-objective optimization
- Resources for Effective Climate Decisions. (Ch. 4) Informing an Effective Response to Climate Change. (2010)
- Dryzek, J.S. et al., Climate Change and Society: Approaches and Responses. (2011)
- Holt, R.F. et al., Assessment and Decision-making for Climate Change: An Overview of Four Approaches (2012)
- Adge, N.W., Social Capital, Collective Action, and Adaptation to Climate Change. (2003)
- Intergovernmental Panel on Climate Change (IPCC). Social, Economic, and Ethical Concepts and Methods. (Ch. 3). (2014)
- World Health Organizaition. From Science to Policy: Developing Responses to Climate Change. (Ch. 12). Climate Change and Human Health - Risks and Responses. (1996)
- Roelich, K. and Giesekam, J. Decision making under uncertainty in climate change mitigation: introducing multiple actor motivations, agency and influence. (2018)
- Zambrano-Barragán, C. Decision Making and Climate Change Uncertainty: Setting the Foundations for Informed and Consistent Strategic Decisions. (2019)
- European Environmental Agency. Climate Change Policies (2016)
Markets and Pricing
- Kolk, K., Pinkse, J. Market Strategies for Climate Change. (2004)
- Anderson, S.E. et al. The Critical Role of Markets in Climate Change Adaptation. (2018)
- Center for Climate and Energy Solutions. Market-based strategies. (2019)