Autonomous Satellite Wildfire Detection Using Hyperspectral Imagery and Neural Networks: A Case Study on Australian Wildfire

Abstract

One of the United Nations (UN) Sustainable Development Goals is climate action (SDG-13), and wildfire is among the catastrophic events that both impact climate change and are aggravated by it. In Australia and other countries, large-scale wildfires have dramatically grown in frequency and size in recent years. These fires threaten the world’s forests and urban woods, cause enormous environmental and property damage, and quite often result in fatalities. As a result of their increasing frequency, there is an ongoing debate over how to handle catastrophic wildfires and mitigate their social, economic, and environmental repercussions. Effective prevention, early warning, and response strategies must be well-planned and carefully coordinated to minimise harmful consequences to people and the environment. Rapid advancements in remote sensing technologies such as ground-based, aerial surveillance vehicle-based, and satellite-based systems have been used for efficient wildfire surveillance. This study focuses on the application of space-borne technology for very accurate fire detection under challenging conditions. Due to the significant advances in artificial intelligence (AI) techniques in recent years, numerous studies have previously been conducted to examine how AI might be applied in various situations. As a result of its special physical and operational requirements, spaceflight has emerged as one of the most challenging application fields. This work contains a feasibility study as well as a model and scenario prototype for a satellite AI system. With the intention of swiftly generating alerts and enabling immediate actions, the detection of wildfires has been studied with reference to the Australian events that occurred in December 2019. Convolutional neural networks (CNNs) were developed, trained, and used from the ground up to detect wildfires while also adjusting their complexity to meet onboard implementation requirements for trusted autonomous satellite operations (TASO). The capability of a 1-dimensional convolution neural network (1-DCNN) to classify wildfires is demonstrated in this research and the results are assessed against those reported in the literature. In order to enable autonomous onboard data processing, various hardware accelerators were considered and evaluated for onboard implementation. The trained model was then implemented in the following: Intel Movidius NCS-2 and Nvidia Jetson Nano and Nvidia Jetson TX2. Using the selected onboard hardware, the developed model was then put into practice and analysis was carried out. The results were positive and in favour of using the technology that has been proposed for onboard data processing to enable TASO on future missions. The findings indicate that data processing onboard can be very beneficial in disaster management and climate change mitigation by facilitating the generation of timely alerts for users and by enabling rapid and appropriate responses.

Trusted Autonomous Operations of Distributed Satellite Systems Using Optical Sensors

“…In recent years, there have been multiple instances of wildfires breaking out. A region in New South Wales that has a high risk of being affected by wildfires has been taken into consideration, and the analysis is currently taking place [ 50 ]. According to the initial findings of the investigation, the computed reconfiguration coverage for the Australian AOI is 95.9722%.…”

“…In Australia and other countries, large-scale forest fires have dramatically grown in rate of recurrence and size in recent years. In the past 15 years, there have been 18 wildfire events in Australia [ 50 ]. For the same, an iDSS, i.e., a constellation of satellites, is proposed as shown in Figure 6 with ISL to provide near-real-time disaster management.…”

Advancements in Forest Fire Prevention: A Comprehensive Survey

“…Such an approach holds great promise, particularly in terms of enhancing the performance of fire detection systems with respect to response time, surpassing the capabilities of architectures designed for general-purpose CPUs. In a recent study conducted by Thangavel et al [ 102 ], the feasibility of employing AI technologies directly on-board satellites for near real-time fire detection was examined and confirmed. The research demonstrated the successful utilization of a combination of specialized hardware, AI on-the-edge paradigms, and hyperspectral imagery.…”

Wildfire Detection Using Convolutional Neural Networks and PRISMA Hyperspectral Imagery: A Spatial-Spectral Analysis

“…The 1D-CNN architecture was described and exploited in previous works [30,35,36,39,[45][46][47]. Its input consists of pixel spectral signatures, represented as an array with a length of 230, defined by SWIR and VNIR PRISMA channels.…”

“…The quality of the information that can be extracted from PRISMA HS imagery was investigated in [29], where analytical methodologies were proposed to locate wildfires and estimate the temperature of active fire pixels. At the same time, we showed the possibility of implementing Trusted Autonomous Satellite Operations [30][31][32] by utilizing artificial intelligence [33,34] on-board satellites with astrionics for data processing [35][36][37]. For the purpose of providing real-time or near real-time disaster management, the same has been used in Distributed Satellite Systems [38][39][40].…”