Building 5, St Priest campus Machine Learning in Montpellier, Theory & Practice Time-series datasets are central in numerous fields of science and engineering, such as biomedicine, Earth observation, and network analysis. Extensive research exists on state-space models (SSMs), which are powerful mathematical tools that allow for probabilistic and interpretable learning on time series. Estimating the model parameters in SSMs is arguably one of the most complicated tasks, and the inclusion of prior knowledge is known to both ease the interpretation but also to complicate the inferential tasks. In this talk, I will introduce a novel joint graphical modeling framework called DGLASSO (Dynamic Graphical Lasso) [1], that bridges the static graphical Lasso model [2] and the causal-based graphical approach for the linear-Gaussian SSM in [3]. I will also present a new inference method within the DGLASSO framework that implements an efficient block alternating majorization-minimization algorithm. The algorithm's convergence is established by departing from modern tools from nonlinear analysis. Experimental validation on synthetic and real weather variability data showcases the effectiveness of the proposed model and inference algorithm. Machine Learning in Montpellier, Theory & Practice

Room Zénith, Maison de la Télédétection Machine Learning in Montpellier, Theory & Practice Artificial Intelligence has been instrumental in advancing science in the past decade, and enabling a “fourth paradigm” for science. Can AI be equally effective for advancing scientific discoveries related to sustainability? In this talk, I will revisit some of the grand challenges related to understanding and modelling sustainability problems: what makes such problems apart from other scientific endeavors? Then, we will identify together with the audience some of the challenges and opportunities that AI can be useful and impactful. Machine Learning in Montpellier, Theory & Practice

Room 109, Building 9, St Eloi campus Machine Learning in Montpellier, Theory & Practice Biodiversity is under severe pressure, as many different disturbance events threaten terrestrial and marine ecosystems with varying impacts. Therefore, habitat distribution modelling, which aims to quantify the statistical links between environmental covariates and an habitat’s occurrence, is increasingly relevant. Herein, we present two different approaches to guide investment, management and regulatory decisions. Firstly, a framework based on tabular data, which experiments with different network architectures, feature encodings, hyperparameter tuning and noise addition strategies to identify the optimal model for habitat classification based on plant species composition. Secondly, we introduce Pl@ntBERT, which leverages sophisticated natural language processes based on transformers (i.e., models with attention components able to learn contextual relations between categorical and numerical features). In particular, since they reinforce each other, the pipeline makes use of both masked language modelling and text classification. The first step helps to get a statistical understanding of the plant species composition (the language in which the model is trained in). Then, subsequent training is used to assign an habitat type to sentences describing vegetation plots. The fine-tuning of a pretrained foundation model on in-domain data shows significant upgrade. Notably, it clearly outperforms previous state-of-the-art methods by pushing the accuracy score on a large database containing millions of European samples. Finally, our results showcase that flora is a strong marker of habitat type and doesn't need to be coupled with environmental spatial data to train neural networks with high predictive power. Looking forward to seeing you. Machine Learning in Montpellier, Theory & Practice