The Women in Data Science (WiDS) Datathon 2023, organized by the WiDS Worldwide team at Stanford University, and Harvard University IACS focused on longer-term weather forecasting to help communities adapt to extreme weather events caused by climate change.
The dataset was created in collaboration with Climate Change AI (CCAI). Participants were required to submit forecasts of temperature and precipitation for one year.
I decided to use XGBoost, a tree ensemble model consisting of a set of classification and regression trees (CART), to forecast climate data. Below is my step-by-step process to generate my submission to the WiDS Datathon 2023 climate data forecasting challenge:
