Research Article
Fire Net: A Deep Learning-Based CNN Model for Wildfire Detection Using Satellite Images
@INPROCEEDINGS{10.4108/eai.28-4-2025.2357846, author={Peer Mohamed Appa M A Y and Jones Andrew E and Sundar Raj B and Vishnu Priyan C}, title={Fire Net: A Deep Learning-Based CNN Model for Wildfire Detection Using Satellite Images}, proceedings={Proceedings of the 4th International Conference on Information Technology, Civil Innovation, Science, and Management, ICITSM 2025, 28-29 April 2025, Tiruchengode, Tamil Nadu, India, Part I}, publisher={EAI}, proceedings_a={ICITSM PART I}, year={2025}, month={10}, keywords={wildfire detection firenet deep learning data preprocessing binary classification convolutional neural networks satellite imagery}, doi={10.4108/eai.28-4-2025.2357846} }- Peer Mohamed Appa M A Y
Jones Andrew E
Sundar Raj B
Vishnu Priyan C
Year: 2025
Fire Net: A Deep Learning-Based CNN Model for Wildfire Detection Using Satellite Images
ICITSM PART I
EAI
DOI: 10.4108/eai.28-4-2025.2357846
Abstract
This project delivers an efficient and reliable approach for detecting wildfires using Satellite Imagery. The model is build using CONVOLUTIONAL NEURAL NETWORK that automatically classifies satellite images as either wildfire detected or normal region. The FireNet model is completely built from scratch with multiple convolution and pooling layers which extracts information from the images followed by dense layers to classify the images. The model is compiled using Adam optimizer and to enhance binary classification accuracy. Trained on a dataset of Satellite images FireNet achieves an accuracy of 92and handling wildfires. The planned system will operate continuously by processing the satellite images and identi- fying wildfires in real-time. Furthermore, the images can be re-used again to improve the model and accuracy of the predication.
