GPU-Accelerated Deep Learning for Heatwave Prediction and Urban Heat Risk Assessment

TL;DR

This paper introduces a GPU-accelerated deep learning framework for accurate next-day urban heatwave prediction and risk assessment, demonstrated with Sarajevo data, improving speed and accuracy over traditional methods.

Contribution

It presents a novel GPU-based deep learning approach, specifically ConvLSTM models with mixed loss, for urban heat prediction and risk mapping, enhancing efficiency and accuracy.

Findings

ConvLSTM with mixed loss achieved MAE=0.2293, RMSE=0.3089, R2=0.8877

Using longer temporal series and more variables improves results

GPU implementation reduces execution time significantly

Abstract

Heatwaves are an important problem in cities, and climate change makes this problem more difficult. In this paper, we present a GPU-based deep learning framework for next-day prediction of urban thermal conditions and for heat risk assessment. The study was carried out in Sarajevo by using MODIS land surface temperature data and Open-Meteo forecast data. We tested several models, including convolutional models and spatiotemporal models. Among them, ConvLSTM with a mixed loss function gave the best results. The obtained values were MAE = 0.2293, RMSE = 0.3089, and R2 = 0.8877. The experiments also showed that results can be improved by using longer temporal series and additional meteorological variables. Since the framework was implemented on a GPU and trained with mixed precision, the execution time was reduced. Based on the predicted temperature fields, it was also possible to combine hazard information with exposure and vulnerability data in order to generate city heat risk maps. The proposed framework can be used as a practical basis for city heat analysis.