Machine learning for research on climate change adaptation policy integration: an exploratory UK case study
Understanding how climate change adaptation is integrated into existing policy sectors and organizations is critical to ensuretimely and effective climate actions across multiple levels and scales. Studying climate change adaptation policy has becomeincreasingly difficult, particularly given the increasing volume of potentially relevant data available, the validity of existingmethods handling large volumes of data, and comprehensiveness of assessing processes of integration across all sectors andpublic sector organizations over time. This article explores the use of machine learning to assist researchers when conductingadaptation policy research using text as data. We briefly introduce machine learning for text analysis, present the steps of trainingand testing a neural network model to classify policy texts using data from the UK, and demonstrate its usefulness with quantitative and qualitative illustrations. We conclude the article by reflecting on the merits and pitfalls of using machine learning in our case study and in general for researching climate change adaptation policy.
R. Biesbroek, S. Badloe, I. N. Athanasiadis, Machine learning for research on climate change adaptation policy integration: an exploratory UK case study, Regional Environmental Change, 20:85, 2020, doi:10.1007/s10113-020-01677-8.
You might also enjoy (View all publications)
- Mixing process-based and data-driven approaches in yield prediction
- Combining telecom data with heterogeneous data sources for traffic and emission assessments - an agent-based approach
- A weakly supervised framework for high-resolution crop yield forecasts