Explainable artificial intelligence (XAI) focuses on creating methods to provide transparency in how complex machine learning models make decisions. A key approach in XAI is feature attribution, which breaks down the model's predictions into the contributions of individual input features. In this presentation, we address feature attribution within the framework of Gaussian process regression (GPR). We present a principled approach that incorporates model uncertainty into the attribution process, expanding existing methods. Despite the GPR's flexibility and non-parametric nature, we demonstrate that interpretable, closed-form expressions for feature attributions can still be derived. Using integrated gradients as the attribution technique, we show that these attributions follow a Gaussian process distribution, effectively capturing the uncertainty inherent in the model. Through both theoretical and experimental validations, we show the robustness and versatility of this approach. Moreover, in applicable cases, the exact GPR attributions are not only more precise but also computationally more efficient than commonly used approximation methods.

The world’s forests are undergoing significant changes due to loss and degradation, emphasizing the need for Near Real-Time (NRT) monitoring to prevent further damage. Traditional monitoring methods using optical imagery are hindered by cloud coverage, while newer Synthetic Aperture Radar (SAR) systems, although operational in all weather conditions, face challenges such as sensitivity to soil moisture and the need for spatial filtering to reduce speckle effects. These limitations affect the detection of small-scale forest loss, especially in seasonally variable regions like dry forests and savannas. This paper presents a SAR-based forest disturbance detection method using Bayesian inference. Unlike traditional methods, this approach maintains the native resolution of the data by avoiding spatial filtering. Forest disturbance is modelled as a change-point detection problem within a non-filtered Sentinel-1 time series, where each new observation updates the probability of forest loss by leveraging prior information and a data model. This sequential adaptation ensures robustness against variations and trends, making it effective in monitoring disturbances across diverse forest types, including areas affected by seasonality. The proposed method was tested against other NRT monitoring systems for the year 2020, using small validation polygons (under 1 hectare) in the Brazilian Amazon and Cerrado savanna. Results demonstrate significant improvements in detecting small-scale disturbances and drastically reduced false alarm rates in both biomes. Notably, in the seasonality-sensitive Cerrado, our solution completely outperforms the leading and only existing optical technology.

Bayesian optimization is a commonly employed method for optimizing expensive, black-box functions, leveraging statistical surrogate models to identify optimal query points while maintaining a balance between exploration and exploitation in the search space. Traditionally, this approach assumes the target function remains constant over time. However, recent advancements have introduced a framework for time-varying Bayesian optimization, capable of addressing dynamic, non-stationary functions. In this presentation, we explore a time-varying approach using dynamic random feature-based Gaussian processes that evolve a linear model's parameters to capture function changes over time. Our proposed mechanism enables the acquisition function to dynamically adjust the exploration-exploitation trade-off in response to these changes. We demonstrate the effectiveness of our method through comparisons with baseline time-varying Bayesian optimization algorithms on both a synthetic example and a localization problem based on simulated data.

In this communication we develop a new full Slepian-Bangs formula adapted to observations on Lie Groups (LGs) distributed according to a Gaussian distribution on LGs (CGD), where both the LG mean and LG covariance depend on an unknown LG parameter. This formulation, which can be seen as a generalization on LGs of the full Slepian-Bangs formula for the Euclidean Gaussian distribution, is obtained using LG tools and properties of the CGD. A closed-form expression is then obtained for a modified Wahba’s problem where the observations'covariance matrix depends on the unknown rotation matrix. Such expression is validated through numerical simulations.

Space-based remote sensing facilitates the determination of greenhouse gas concentrations, enhancing the comprehension of carbon fluxes at the Earth’s surface in the context of climate change. High-resolution spectrometers, such as the CNES/UKSA MicroCarb and the upcoming ESA Copernicus Carbon Dioxide Monitoring (CO2M) spectrometers, are crucial tools for this purpose. These instruments require a precise calibration, especially regarding the relative approximation errors of the Instrument Spectral Response Functions (ISRFs). To ease ISRF estimation, parametric models such as Gaussian and Super-Gaussian models have been investigated. However, these models cannot always take into account the diversity of ISRF shapes that are encountered in practical applications. For example, in MicroCarb simulations, the expected performance is not always achieved by these two conventional ISRF estimation methods, even when there is no spectral and radiometric errors. This paper investigates a novel approach based on the sparse representation of ISRFs in a dictionary. This method decomposes the spectral responses of interest as sparse linear combinations of atoms belonging to a dictionary, which are built using representative ISRFs. This new method can be applied both for on-ground ISRF denoising, and in-flight ISRF estimation through the resolution of an appropriate inverse problem. Experiments conducted using realistic simulated datasets associated with the MicroCarb instrument are used to evaluate the performance of the proposed method for on-ground and in-flight ISRF estimation, yielding promising estimation performance compared to the state of the art.

Le domaine de l’observation de l’Espace s’intéresse de près aux signaux très basse fréquence, car ils fournissent d’importantes informations quant à la naissance et aux premiers jours de l’Univers. A ce jour, les interféromètres observant ces signaux se situent à la surface de la Terre, dans des zones arides. Malheureusement, ces signaux sont très sensibles aux interférences terrestres ainsi qu’à l’ionosphère, et sont donc difficilement observables. Une solution à ce problème serait d’observer les signaux directement depuis l’Espace, en déployant un essaim de nanosatellites en orbite autour de la Lune. Cet essaim constitue un Système Spatial Distribué (DSS), fonctionnant en tant qu’interféromètre, dont l’orbite lunaire le préserve des interférences terrestres et de l’ionosphère. Cependant, la configuration de l’essaim de nanosatellites en interféromètre spatial est un défi de taille en termes de communication, notamment en raison de l’absence d’infrastructure dans l’Espace et du volume de données d’observation à propager au sein du système. L’objectif de la thèse est donc de définir une configuration d’architecture fiable, répondant aux contraintes conjointes d’un réseau MANET et d’un système distribué. La thèse commence par caractériser le réseau de l’essaim de nanosatellites et met en avant sa forte hétérogénéité. Ensuite, elle propose des algorithmes permettant de répartir équitablement la charge du réseau, en se basant sur des techniques de division de graphe, et compare les performances de ces algorithmes sur des critères d’équité. Enfin, elle évalue la sensibilité du système aux pannes en termes de robustesse (résistance aux pannes) et de résilience (maintien du fonctionnement en présence de pannes) et étudie l’impact de la division de graphe sur la fiabilité globale de l’essaim. Les algorithmes de division développés dans cette thèse devront garantir la Qualité de Service (QoS) essentielle au bon fonctionnement d’un interféromètre spatial. Pour atteindre cet objectif, des solutions de routage pertinentes devront être minutieusement étudiées et intégrées, afin de s’assurer qu’elles répondent aux exigences strictes de performance et de fiabilité de cette application avancée.

Le domaine de l’observation de l’Espace s’intéresse de près aux signaux très basse fréquence, car ils fournissent d’importantes informations quant à la naissance et aux premiers jours de l’Univers. A ce jour, les interféromètres observant ces signaux se situent à la surface de la Terre, dans des zones arides. Malheureusement, ces signaux sont très sensibles aux interférences terrestres ainsi qu’à l’ionosphère, et sont donc difficilement observables. Une solution à ce problème serait d’observer les signaux directement depuis l’Espace, en déployant un essaim de nanosatellites en orbite autour de la Lune. Cet essaim constitue un Système Spatial Distribué (DSS), fonctionnant en tant qu’interféromètre, dont l’orbite lunaire le préserve des interférences terrestres et de l’ionosphère. Cependant, la configuration de l’essaim de nanosatellites en interféromètre spatial est un défi de taille en termes de communication, notamment en raison de l’absence d’infrastructure dans l’Espace et du volume de données d’observation à propager au sein du système. L’objectif de la thèse est donc de définir une configuration d’architecture fiable, répondant aux contraintes conjointes d’un réseau MANET et d’un système distribué. La thèse commence par caractériser le réseau de l’essaim de nanosatellites et met en avant sa forte hétérogénéité. Ensuite, elle propose des algorithmes permettant de répartir équitablement la charge du réseau, en se basant sur des techniques de division de graphe, et compare les performances de ces algorithmes sur des critères d’équité. Enfin, elle évalue la sensibilité du système aux pannes en termes de robustesse (résistance aux pannes) et de résilience (maintien du fonctionnement en présence de pannes) et étudie l’impact de la division de graphe sur la fiabilité globale de l’essaim. Les algorithmes de division développés dans cette thèse devront garantir la Qualité de Service (QoS) essentielle au bon fonctionnement d’un interféromètre spatial. Pour atteindre cet objectif, des solutions de routage pertinentes devront être minutieusement étudiées et intégrées, afin de s’assurer qu’elles répondent aux exigences strictes de performance et de fiabilité de cette application avancée.

Location-based services, safety-critical applications, and modern intelligent transportation systems require reliable, continuous, and precise positioning, navigation, and timing (PNT) information. Global Navigation Satellite Systems (GNSS) are the main source of positioning data in open sky conditions; however, their vulnerabilities to radio interferences and signal propagation limit their use in challenging environments. Consequently, enhancing conventional GNSS-based PNT solutions to incorporate additional sensing modalities and exploit other available signals of opportunity has become necessary for continuous and reliable navigation. Articles in the special issue span detection methods, estimation algorithms, signal optimization, and the application of machine learning, providing comprehensive insights into enhancing navigation and positioning accuracy.

Forests worldwide have undergone significant transformations due to forest loss, highlighting the critical need for real-time forest monitoring to prevent further vegetation loss and facilitate prompt interventions. Traditionally, forest loss monitoring relied on optical imagery, which is obstructed by its susceptibility to cloud coverage, especially in tropical regions. In recent times, Synthetic Aperture Radar (SAR)-based systems have emerged to enable all-weather operability. However, SAR-based approaches encounter challenges, such as the alterations in backscatter caused by factors like soil moisture variations. Moreover, accurately detecting small-scale disturbances remains problematic for SAR systems, partly due to the spatial filtering techniques employed to mitigate the effects of speckle. Additionally, monitoring forest loss in regions characterized by pronounced seasonality in backscatter signals, such as dry forests and savannas, poses limitations, resulting in substantial under-monitoring of these extensive carbon sinks. This study introduces an unsupervised SAR-based method for detecting forest loss, employing Bayesian inference through an infinite state Markov chain.