Spiller, Dario

Recent developments in Distributed Satellite Systems (DSS) have undoubtedly increased mission value due to the ability to reconfigure the spacecraft cluster/formation and incrementally add new or update older satellites in the formation. These features provide inherent benefits, such as increased mission effectiveness, multi-mission capabilities, design flexibility, and so on. Trusted Autonomous Satellite Operation (TASO) are possible owing to the predictive and reactive integrity features offered by Artificial Intelligence (AI), including both on-board satellites and in the ground control segments. To effectively monitor and manage time-critical events such as disaster relief missions, the DSS must be able to reconfigure autonomously. To achieve TASO, the DSS should have reconfiguration capability within the architecture and spacecraft should communicate with each other through an Inter-Satellite Link (ISL). Recent advances in AI, sensing, and computing technologies have resulted in the development of new promising concepts for the safe and efficient operation of the DSS. The combination of these technologies enables trusted autonomy in intelligent DSS (iDSS) operations, allowing for a more responsive and resilient approach to Space Mission Management (SMM) in terms of data collection and processing, especially when using state-of-the-art optical sensors. This research looks into the potential applications of iDSS by proposing a constellation of satellites in Low Earth Orbit (LEO) for near-real-time wildfire management. For spacecraft to continuously monitor Areas of Interest (AOI) in a dynamically changing environment, satellite missions must have extensive coverage, revisit intervals, and reconfiguration capability that iDSS can offer. Our recent work demonstrated the feasibility of AI-based data processing using state-of-the-art on-board astrionics hardware accelerators. Based on these initial results, AI-based software has been successively developed for wildfire detection on-board iDSS satellites. To demonstrate the applicability of the proposed iDSS architecture, simulation case studies are performed considering different geographic locations.

t This paper deals with detection and temperature analysis and of wildfires using PRISMA imagery. Precursore IperSpettrale della Missione Applicativa (Hyperspectral Precursor of the Application Mission, PRISMA) is a new hyperspectral mission by ASI (Agenzia Spaziale Italiana, Italian Space Agency) launched in 2019. This mission provides hyperspectral images with a spectral range of 400–2,500 nm and an average spectral resolution less than 12 nm and a spatial resolution of 30 m/pixel. This study focuses on the wildfire temperature estimation over the Bootleg Fire, US 2021. The analysis starts by considering the Hyperspectral Fire Detection Index (HFDI) which is used to analyze the informative content of the images, along with the analysis of some specific visible, near-infrared and shortwave-infrared bands. This first analysis is used as input to perform a temperature estimation of the areas with active wildfire. Surface temperature is retrieved using PRISMA radiance and a linear mixing model based on two background components (vegetation and burn scar) and two active fire components. PRISMA temperatures are compared with LST (Land Surface Temperature) products from NASA's ECOSTRESS and Landsat 8 which imaged the Bootleg Fire before and after PRISMA. A critical discussion of the results obtained with PRISMA is presented, followed by the advantages and limitation of the proposed approach.

In this work we present a segmentation study of wildfire scenarios using PRISMA hyperspectral data and a methodology based on convolutional neural networks and transfer learning. PRISMA (Precursore IperSpettrale della Missione Applicativa, Hyperspectral Precursor of the Application Mission) is the hyperspectral mission by ASI (Agenzia Spaziale Italiana, Italian Space Agency) launched in 2019 providing images with a spectral range of 0.4−2.5μm and an average spectral resolution less than 10 nm. We used the PRISMA hypercube acquired during the Australian bushfires of December 2019 in New South Wales to train a one-dimensional convolutional neural network and perform a transfer learning in the Bootleg Fire of July 2021 in the Fremont-Winema National Forest in Oregon. The generalization ability of the network is discussed and potential future applications are presented.

Wildfire temperature retrieval is of great interest as it helps to characterize wildfires effects and their potential impact on natural and built environments. For example, different temperatures of a fire are associated to different types of particles and gas emissions while studies have linked wildfires temperature to the degree of damage that fires cause to the landscape (severity). This study focuses on the wildfire temperature estimation by using PRecursore IperSpettrale della Missione operativA (PRISMA) data acquired over Log fire, US 2021. PRISMA is the new satellite launched on March 27th, 2019, by ASI (Italian Space Agency) and hosting an imaging spectrometer for acquisition of hyperspectal images. The optical sensor operates in the spectral range spanning between 400-2500nm with a spectral resolution ≤12 nm and a spatial resolution of 30m/px. Temperature is retrieved by using PRISMA radiance and a linear mixing model based on two background components (vegetation and burn scar) and up to two active fire components. The PRISMA retrieved temperatures are compared with the LST (Land Surface Temperature) products delivered by ECOsystem Spaceborne Thermal Radiometer Experiment (ECOSTRESS), a thermal sensor (5 bands at 8-12µm) which imaged the Logfire US close to the PRISMA passage. ln line with the literature, effects of saturation on temperature estimation has been investigated. In this way, a critical discussion of the results obtained with PRISMA will be to report advantages and limitation of the proposed approach.

The exacerbation of wildfires, attributed to the effects of climate change, presents substantial risks to ecological systems, infrastructure, and human well-being. In the context of the Sustainable Development Goals (SDGs), particularly those related to climate action, prioritizing the assessment and management of the occurrence and intensity of extensive wildfires is of utmost importance. In recent times, there has been a significant increase in the frequency and severity of widespread wildfires worldwide, affecting several locations, including Australia, Italy, and the United States of America. The presence of complex phenomena marked by limited predictability leads to significant negative impacts on biodiversity and human lives. The utilization of satellite-derived data with neural networks, such as convolutional neural networks (CNNs), is a potentially advantageous approach for augmenting the monitoring capabilities of wildfires. This research examines the generalization capability of four neural network models, namely the fully connected (FC), one-dimensional (1D) CNN, two-dimensional (2D) CNN, and three-dimensional (3D) CNN model. Each model’s performance, as measured by accuracy, recall, and F1 scores, is assessed through K-fold cross-validation. Subsequently, T-statistics and p-values are computed based on these metrics to conduct a statistical comparison among the different models, allowing us to quantify the degree of similarity or dissimilarity between them. By using training data from Australia and Sicily, the performances of the trained model are evaluated on the test dataset from Oregon. The results are promising, with cross-validation on the training dataset producing mean precision, recall, and F1 scores ranging between approximately 0.97 and 0.98. Especially, the fully connected model has superior generalization capabilities, whilst the 3D CNN offers more refined and less distorted classifications. However, certain issues, such as false fire detection and confusion between smoke and shadows, persist. The aforementioned methodologies offer significant perspectives on the capabilities of neural network technologies in supporting the detection and management of wildfires. These approaches address the crucial matter of domain transferability and the associated dependability of predictions in new regions. This study makes a valuable contribution to the ongoing efforts in climate change by assisting in monitoring and managing wildfires.

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.