What question did this study set out to answer?

This research aims to improve wildfire prediction accuracy through advanced CNN architectures and Bayesian Optimization.

April 13, 2026

Empirical analytics of baseline and enhanced CNN architectures with frequency and RGB features using Bayesian Hyperparameter Optimization for wildfire prediction

Key Points

This research aims to improve wildfire prediction accuracy through advanced CNN architectures and Bayesian Optimization.
Developed wildfire prediction models using CNN architectures such as LeNet-5, AlexNet, and VGG16.
Applied both RGB images and FFT-based frequency-domain features for model training.
Utilized Bayesian Optimization with Tree-structured Parzen Estimator to optimize model parameters.
Evaluated model performance using accuracy and AUC-ROC metrics.
Modified LeNet-5 and AlexNet achieved accuracies of 97% and 96%, respectively, with frequency-domain features.
RGB-based modifications led to up to 98% accuracy in modified LeNet-5 and baseline VGG16.
Frequency-domain features combined with Bayesian Optimization significantly enhance wildfire prediction accuracy.

Abstract

Wildfires have caused long-term economic, ecological, and biological damage, highlighting the need for accurate prediction systems to protect forest wildlife and valuable non-timber resources such as medicinal plants, aromatic products, food, fodder, and fuelwood. This study proposes wildfire prediction models using frequency-domain analytics and Bayesian Optimization (BSO) in designing Convolutional Neural Network (CNN)-based deep learning models, including LeNet-5, AlexNet, and VGG16, applied to the DeepFire dataset. The models are trained and tested on both RGB images and Fast Fourier Transform (FFT)-based frequency-domain representations of fire and non-fire images. BSO, integrated with the Tree-structured Parzen Estimator (TPE), optimizes model parameters to effectively extract fire-related features. Model performance is evaluated using Accuracy and AUC-ROC metrics. Results indicate that BSO-based frequency-aware modified LeNet-5 and AlexNet achieve accuracies of 97% and 96%, respectively. Additionally, RGB-based BSO enhances performance, with modified LeNet-5 and baseline VGG16 reaching up to 98% accuracy. Overall, findings demonstrate that frequency-domain features combined with BSO significantly improve wildfire prediction, supporting ecological and biological conservation efforts.

Bookmark

Empirical analytics of baseline and enhanced CNN architectures with frequency and RGB features using Bayesian Hyperparameter Optimization for wildfire prediction

Key Points

Abstract

Cite This Study