Improved Active Fire Detection using Operational U-Nets

TL;DR

This paper introduces Operational U-Nets, a novel deep learning model using Self-ONN layers within a U-Net architecture, for improved early detection of active fires from satellite imagery, achieving better performance and efficiency.

Contribution

The paper presents a new deep learning architecture combining Self-ONN layers with U-Nets for more accurate and computationally efficient active fire detection.

Findings

Operational U-Nets outperform traditional methods in fire detection accuracy.

The approach significantly reduces computational complexity.

Preliminary results show improved early fire detection performance.

Abstract

As a consequence of global warming and climate change, the risk and extent of wildfires have been increasing in many areas worldwide. Warmer temperatures and drier conditions can cause quickly spreading fires and make them harder to control; therefore, early detection and accurate locating of active fires are crucial in environmental monitoring. Using satellite imagery to monitor and detect active fires has been critical for managing forests and public land. Many traditional statistical-based methods and more recent deep-learning techniques have been proposed for active fire detection. In this study, we propose a novel approach called Operational U-Nets for the improved early detection of active fires. The proposed approach utilizes Self-Organized Operational Neural Network (Self-ONN) layers in a compact U-Net architecture. The preliminary experimental results demonstrate that Operational U-Nets not only achieve superior detection performance but can also significantly reduce computational complexity.