Deep learning models for enhanced forest-fire prediction at Mount Kilimanjaro, Tanzania: Integrating satellite images, weather data and human activities data

Abstract

Forest fires (FFs) are a growing threat to ecosystems and human settlements, particularly in vulnerable regions such as Mount Kilimanjaro, Tanzania. Accurate and timely fire prediction is essential to mitigate these risks and improve fire management strategies. This study develops and evaluates advanced Deep Learning (DL) models for FF prediction by integrating spatiotemporal vegetation indices, environmental data, and human activity indicators. Specifically, Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNNs), and Convolutional Long Short-Term Memory (ConvLSTM) models were employed to analyze Sentinel-2 satellite imagery and weather data, along with anthropogenic factors such as beekeeping, tourism, agriculture, and deforestation rates. Leveraging this diverse, high-dimensional dataset, the ConvLSTM model engineered to capture intricate spatial and temporal relationships delivered superior performance, achieving an AUROC of 0.9785 and Accuracy 98.08%, surpassing the LSTM and CNN models. Integrating human-induced activities with environmental data, these models provide accurate and actionable predictions for fire management in high-risk areas. This study demonstrates the potential of ConvLSTM in developing operational tools for early fire detection, streamlining data-driven decision-making, improving resource allocation, and guiding preventive strategies in fire-prone regions such as Mount Kilimanjaro.