TEACHING & OTHER
RESOURCES
Climate Impact Lab: Adaptation Inventory
The Adaptation Inventory offers a repository of adaptation programs that have enhanced climate resilience and reduced climate-related damages. The Inventory is designed to help policymakers and researchers identify evidence-based policies and programs that may mitigate the socio-economic impacts of climate risk. It is updated regularly, provides an interactive tool, and enables metadata downloads.
Multi-task Observation using SAtellite Imagery and Kitchen Sinks (MOSAIKS)
MOSAIKS is a task-agnostic approach to linking satellite imagery and machine learning for prediction of ground conditions at scale. More information can be found here and our API hosting downloadable imagery features is here. In collaboration with CEGA and the Togo AI Lab, are writing a digital textbook on MOSAIKS and related Earth embeddings that can be found here. The textbook should make it easy to get going with your own imagery-based predictions in R or Python!
stagg:: A data pre-processing R package for climate impacts analysis
stagg is an R package that transforms raw gridded climate data into tabular administrative-level variables intended for use in climate econometrics analyses. Flexible options let users control specifications like nonlinear transformations, weighted spatial aggregation, and temporal aggregation with a few lines of code. Our GitHub package is here and our published paper is here. Tyler Liddell made some additional helpful resources: here is a cheatsheet and and here is a scientific poster. It's a work in progress -- please send us feedback!
EDS 222: Statistics for Environmental Data Science
This course is a core class in the Masters of Environmental Data Science program at the Bren School. We cover fundamental statistical concepts and tools, and then apply and expand upon those tools to learn some temporal and spatial statistical methods that are particularly helpful in environmental data science. Our course website is here, and all slides and labs are available on the course GitHub.
