Enhancing Wildfire Forecasting Through Multisource Spatio-Temporal Data, Deep Learning, Ensemble Models and Transfer Learning

TL;DR

This paper introduces a novel wildfire prediction method combining multisource spatiotemporal data, deep learning, ensemble models, and transfer learning to improve forecast accuracy and understand key influencing factors.

Contribution

It presents a new integrated approach leveraging transfer learning and ensemble models with multisource data for wildfire forecasting.

Findings

Effective integration of multisource data improves wildfire prediction accuracy.

Transfer learning enhances model performance with limited real-time data.

Identified key weather and human activity factors influencing wildfires.

Abstract

This paper presents a novel approach in wildfire prediction through the integration of multisource spatiotemporal data, including satellite data, and the application of deep learning techniques. Specifically, we utilize an ensemble model built on transfer learning algorithms to forecast wildfires. The key focus is on understanding the significance of weather sequences, human activities, and specific weather parameters in wildfire prediction. The study encounters challenges in acquiring real-time data for training the network, especially in Moroccan wildlands. The future work intends to develop a global model capable of processing multichannel, multidimensional, and unformatted data sources to enhance our understanding of the future entropy of surface tiles.