PulseTrendingJournal ClubResearchersJournalsExplore
Instagram
HomeTrendingJournal ClubExplore
Synapse
⌘+K
Synapse
June 4, 2026Applied Computing and GeosciencesOpen Access

Convolutional neural networks for wildfire spread and intensity prediction

View Full Paper
Ask AI
Bookmark
Share

Authors

MMMaryam MoradpourPKPankaj KumarGHGholam Ali Hoshyaripour

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates accurate wildfire prediction using CNNs, indicating potential advancement in forecasting technology.

Key Points

  • This study aims to develop a deep learning model using convolutional neural networks to predict wildfire spread and intensity under various environmental conditions.
  • Utilized a convolutional neural network trained on Weather Research and Forecasting (WRF) coupled with SFIRE simulation dataset.
  • Evaluated model performance using root mean square error (RMSE), mean absolute error (MAE), correlation coefficient (R2), and Structure–Amplitude–Location (SAL) method.
  • The model achieved an RMSE of 14.3 kW/m2 and MAE of 6.6 kW/m2, with a correlation coefficient of 84%.
  • CNN effectively reproduced wildfire spatial and temporal dynamics, closely aligning with reference simulations.
  • Demonstrated significantly lower computational costs compared to traditional models, suggesting a scalable forecasting solution.

Cite This Study

Moradpour et al. (2026) studied this question.

synapsesocial.com/papers/6a211591d499ed480b16ea40https://doi.org/10.1016/j.acags.2026.100355
View Full Paper
Ask AI
Bookmark
Share