Nowadays, a key challenge in Earth observation and human behavior analysis, is data management and processing. Data acquisition of natural and human environment produces every day a large set of information from which more and more knowledge must be extracted and classified. Thus classical approaches to manage and process these data can no longer be used. Big data and IA approaches seem more appropriate. However, to investigate their potential and to make significant improvements in specific domains, it is necessary to build multidisciplinary teams. This project proposed by University Savoie Mont Blanc gathers researchers from two laboratories working respectively in geophysics (ISTerre) and computer sciences (LISTIC). These two laboratories are used to work together in different projects where they bring their complementary expertise to develop advanced methods for the processing of large data sets. Both laboratories intend to develop and apply IA techniques to improve the understanding and modeling of complex situations observed by different sensors. Two specific contexts will be investigated: • The context of volcanology, with two PhD theses proposed on the analysis of volcanic activity by machine learning approaches, and on the integration of dynamic physical models into data driven methods to improve predictions; • The context of human activity with one PhD thesis proposed on the development of “wise objects” which can progressively learn on them-selves and detect changes in human behavior in different cases: at home in home automation and home care for elderly persons, or through energy consumption when using computers. The 3 PhD theses are proposed by ISTerre, by LISTIC and by a joint ISTerre-LISTIC supervision. All researchers involved in the project are working on Bourget-du-Lac and/or Annecy Campuses of research and teaching activities. The project will organize regular meetings in both laboratories with the 3 recruited PhD students, in order to share the developed tools and the experience acquired on investigated IA methods.

The systematic acquisition of and free access to Sentinel-1 A/B Synthetic Aperture Radar (SAR) images provide scientists with both opportunities and challenges for operational monitoring of Earth deformation by SAR image time series. In this project, the coordinator brings together, for the first time, Interferometry SAR, statistical learning, deep learning and geophysics skills in order to form an interdisciplinary team who aims to promote methodological development for operational Earth deformation monitoring and natural hazard prediction by SAR image time series. For this, we start from single look complex SAR image time series and deal with displacement estimation and natural hazard prediction problems by means of both statistics based learning and neural networks based learning approaches. First, we develop a recursive and robust multi-temporal InSAR method, allowing for efficient gradual integration of new arriving SAR images and considering non Gaussian properties of SAR image statistics, to estimate displacement velocity and displacement time series. Moreover, we propose a complete and original missing data imputation framework for SAR displacement time series based on statistical learning and deep learning. Second, we tackle, for the first time, the major issue of neural networks based physical parameters inversion and prediction from SAR derived displacement time series. We propose recursive neural network models, adapted to SAR displacement data specificity, in both supervised and semi-supervised learning frameworks. Prior physical knowledge will be incorporated into the neural networks in order to enhance the learning process and to improve the interpretability and explainability. A particular effort will be made on the understanding of the neural network functioning in order to ensure the accountability and then the actionability of the results for operational use. All previously developed methods will be applied to targets of geophysical interest, including volcanoes covered by Sentinel-1 A/B SAR images every 6 or 12 days and Alpine glaciers covered by Sentinel-1 A/B images every 6 days and by high resolution PAZ images every 11 days. The expected results consist of 1) advanced open access multi-temporal InSAR methods, providing complete and reliable displacement time series in line with the routine availability of SAR image time series 2) open access recursive neural network models with both linear and nonlinear functionalities, adapted to SAR displacement data specificity, providing temporal evolution of key geophysical parameters in line with the routine availability of SAR image time series 3) a dataset tutorial illustrating in detail the input and output of previously developed methods, together with open access to the datasets used for illustration.

Environment monitoring is crucial for understanding the relationship between climate change and changes in large scale earth structures such as glaciers and forests. For these big structures, monitoring temporal evolution or assessing resilience and adaptation of earth to changes requires the analysis of time series composed of images. When considering remote sensing imagery, analyzing such time series is actually facing dimensionality: observations are huge data both in time and space domains; in addition with intricacy when using coherent acquisition waves (radar imaging for instance). The challenge of remote sensing information science is then developing tools for handling dimensionality of data. The scientific objective of the PHOENIX project is to provide non-stationary multidimensional models for easing information mining and retrieval in long sequences of multisource/distributed image time series issued from recent constellations of satellites. These models will be used to characterize the evolution of earth structures such as glaciers and forests. The technical objective of the PHOENIX project is to provide resilience analysis from information modeling and retrieval in image time series of Alpine glaciers and Amazonian forests. This analysis will be performed through a general framework of random field time series, with two work packages (WP) dedicated to methodological developments. The first package, WP1, will address parsimonious parametric modeling of random field time series by using non-stationary fractionally differenced/integrated parameterizations. The second package, WP2, is dedicated to non-parametric methods for the analysis of random field time series: cumulant analysis and trend/stationary decompositions are some important topics addressed in this WP. The third package, WP3, will focus on the application of WP1 and WP2 methods to 2 kinds of mono/multi-channel earth observation satellite image time series: 1) Synthetic Aperture Radar images which cover large areas and are not impacted by meteorological variability, 2) Spectro-Visible images which can observe specific areas with a higher spatio-spectral resolution. WP3 requires High Performance Computing (HPC). HPC will deserve two types of architectures: a big cluster of CPU (USMB MUST, already operational, efficient for parallel computing on “large databases with small size data”, but limited for loading and processing huge data) and a specific scalable workstation with huge random access memory (ANR support requested) for loading and processing huge size image time series.

DIRECTA (Deep learnIng in REal time for the Cherenkov Telescope Array), as the name states, is a project to apply deep learning solutions based on convolutional neural networks (CNNs) to the Cherenkov Telescope Array (CTA), in real-time. It is a continuation of the GammaLearn project, that already demonstrated the applicability of CNNs to CTA data, and of the ACADA work package that is developing the real-time analysis for CTA using the standard reconstruction techniques. Its objective is the demonstration of the applicability of CNNs in real-time for CTA with a working proof-of-concept applied to the already observing Large-Sized Telescope 1 (LST-1) and later to the LST-2 and Mid-Sized Telescope 1 whose construction will start in 2023. It will greatly improve CTA's reconstruction performances in real-time necessary for the study of transient sources such as gamma-ray bursts and flaring active galactic nuclei, of the Lorentz Invariance Violation and of the Extragalactic Background Light.

The use of advanced technologies in industrial systems is expanding in view of: 1) the technical specificities that they allow to achieve, 2) the traceability of data that they offer and, 3) the relief of human operators from tedious or repetitive tasks that they make possible. The industrial systems of the Future (4.0) are characterised by an increase in their autonomy and a profusion of data produced and handled that can lead to poorly controlled decisions, which can lead to ethical dilemmas. Such decisions may concern an inappropriate use of data for the management of industrial systems or reactions, triggered by Artificial Intelligence, based on a partial vision of the system and having poorly controlled consequences on the various stakeholders. The ETHICS40 project focuses on the management of ethical issues during the operation of industrial systems of the Future. In partnership with the bearing manufacturer NTN-SNR, which is in the process of migrating to the Factory of the Future, it aims to develop a tool, a software prototype, called ETHICS4IF (Ethical Risk Assessment and Management for Industry of the Future), which will enable the identification and integration of ethical risks into the management and performance imrovement of industrial systems of the Future. As ethics is a concept derived from moral philosophy that is difficult to grasp in engineering, the ETHICS4IF tool will be the result of works led by a multidisciplinary team involving specialists in applied ethics. A definition of this notion of ethics applied to the operation of industrial systems of the Future and an identification of the associated risks will be proposed in a first step. In a second step, the taking into account of these risks in the mechanism of evaluation and continuous improvement of the performance of industrial systems will be made operational by proposing a concrete methodology to integrate the risks and their potential consequences. ETHICS4IF will be aimed at actors interacting with these systems (operators, managers, etc.). It will combine the different points of view associated with ethical risks (human, industrial system, company, society, environment). The ethical management rules and practices deduced from the risk analysis will be defined in accordance with the rules of ethics in place in the company and in compliance with the laws associated with the use of digital technology. Performance indicators related to the ethics associated with the operation of the industrial systems of the Future will be proposed and monitored in order to improve the handling of this dimension. The main deliverable of the project will consist of a software prototype encompassing the aspects mentioned. It will be accompanied by a set of rules and practices deduced from its application by the NTN-SNR partner as well as a feedback on the use of the tool and the management rules and practices, beyond the NTN-SNR case study. The tool will be fed, tested and used by the Company. A strategic committee made up of the project members, industrialists who are not competitors of NTN-SNR and a law office specialising in digital law will oversee the progress of this project. The ETHICS40 project responds to an important need of industrialists in their migration towards the Factory of the Future. It will provide the scientific community with a tool to help operationalise ethics in engineering and industrial engineering research.