2026-10-15T02:37:51Z https://data.mendeley.com/oai

oai:data.mendeley.com/nwzcm9ckrt.2 2025-07-21T15:51:54Z

Tanim, Sharia Arfin A Diffusion Model-Generated Forest Fire Dataset Mendeley Data This dataset consists of 2,204 AI-generated images, created using a Stable Diffusion model. The images are organized into two distinct folders: Fire: Contains 1,102 images depicting synthetic representations of forest fires. Non-Fire: Contains 1,102 images showing various forest scenes without any fire activity. Each image has a resolution of 150x150 pixels, optimized for use in machine learning tasks such as classification, detection, and environmental monitoring. Purpose The dataset is intended to aid research and development in areas such as: Forest fire detection and prevention using AI. Benchmarking deep learning models for image classification tasks. Studying the environmental impact of forest fires. Key Features Generated with Stable Diffusion, ensuring high-quality and varied synthetic visuals. Balanced dataset structure (equal representation of fire and non-fire images). Small image size (150x150), suitable for lightweight model training and testing. When using this dataset, please cite the following paper: Alam, G. M. I., Tasnia, N., Biswas, T., Hossen, M. J., Tanim, S. A., & Miah, M. S. U. (2025). Real-Time Detection of Forest Fires Using FireNet-CNN and Explainable AI Techniques. IEEE Access. Object Detection Image Classification Imdadul Alam, Gazi Mohammad Tasnia, Naima Biswas, Tapu Hossen, Md. Jakir Ullah Miah, Md Saef Dataset doi:10.17632/nwzcm9ckrt.2 oai:data.mendeley.com/nwzcm9ckrt.2 Creative Commons Attribution 4.0 International http://creativecommons.org/licenses/by/4.0 https://data.mendeley.com/datasets/nwzcm9ckrt 2025-07-21T15:51:54Z