Year: 2025
Type: conference-paper
Abstract: The critical need for sophisticated detection techniques has been highlighted by the rising frequency and intensity of wildfires in the US, especially in California.In 2023, wildfires caused 130 deaths nationwide, the highest since 1990.In January 2025, Los Angeles wildfires which included the Palisades and Eaton fires burnt approximately 40,000 acres and 12,000 buildings, and caused loss of human lives.The devastation underscores the urgent need for effective detection and prevention strategies.Deep learning models, such as Vision Transformers (ViTs), can enhance early detection by processing complex image data with high accuracy.However, wildfire detection faces challenges, including the availability of high-quality, real-time data.Wildfires often occur in remote areas with limited sensor coverage, and environmental factors like smoke and cloud cover can hinder detection.Additionally, training deep learning models is computationally expensive, and issues like false positives/negatives and scaling remain concerns.Integrating detection systems with real-time alert mechanisms also poses difficulties.In this work, we used the wildfire dataset consisting of 10.74 GB high-resolution images categorized into 'fire' and 'nofire' classes is used for training the ViT model.To prepare the data, images are resized to 224 x 224 pixels, converted into tensor format, and normalized using ImageNet statistics.The dataset is loaded with PyTorch's ImageFolder class, and DataLoader objects are used for batching and shuffling.A pre-trained ViT model (vit_base_patch16_224) is fine-tuned for binary classification "No Wildfire" vs. "Wildfire".Adam optimizer and CrossEntropyLoss are used to train the model.After training, evaluation of the test set shows the model achieves 96.10% accuracy and demonstrates ViT's effectiveness in wildfire detection.This approach provides a promising solution for real-time monitoring and post-event analysis, with improved response time and better accuracy.
Institution: University of Bridgeport
Language: English
Subfield: Safety, Risk, Reliability and Quality
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Awards: G540792204, G6057698366
OpenAlex ID: W4409905321