Software pipeline for the high-resolution estimation of air temperatures and probabilistic heat hazards in urban regions

To address this, the proposed architecture employs a two-branch fusion approach: a temporal branch that encodes lagged meteorological sequences (such as ERA5 data) and a spatial convolutional branch that processes local geospatial embedding patches. Rather than outputting single deterministic values, the model utilizes quantile regression to estimate conditional predictive distributions for daily minimum and maximum air temperatures.

This probabilistic approach enables the generation of uncertainty-aware temperature maps and allows for the direct derivation of critical heat hazard event probabilities, specifically tropical nights and hot days. The accompanying open-source codebase includes the complete machine learning pipeline and trained models.