IntheArt

2024

GeoTS: A time series classification framework to identify geological formations

Shwetha Salimath, Centrale-Supelec

Lundi 16 décembre à 11h30, CEA-Saclay, Orme-des merisiers, Bat 709, salle Rubin

Studying the lithography of the Earth's subsurface in geoscience involves analyzing different geological formations to model and characterize reservoirs. This process uses drilled well measurements to connect specific geological formations or tops. Reservoir modeling is essential in geothermal, mineral mining, oil and gas, and carbon storage. Traditional well correlation algorithms are time-consuming and costly, but Deep Learning (DL) models have shown promising results. This paper presents GeoTS, a Python library that employs advanced time series classification DL models for well correlation. It uses drilling trajectory depth and gamma-ray well logs as inputs, predicting the depths of formations' tops. Gamma-ray signatures around these depths are extracted, cleaned, and clustered using Dynamic Time Warping (DTW) and machine learning models like HDBSCAN and OPTICS. The implementation includes various deep learning architectures (FCN, InceptionTime, XceptionTime, XCM, LSTM-FCN) and new models (LSTM-2dCNN, LSTM-XCM). The results indicate faster computation and higher accuracy than industry benchmarks, making this the first open-source benchmark for the well correlation task, to our knowledge.

 

Towards fast and scalable uncertainty quantification for scientific imaging

Tobias Liaudat, Irfu/Dedip

Vendredi 31 mai  Jeudi 28 novembre à 11h30, CEA-Saclay, Orme-des merisiers, Bat 709, salle Rubin

The last decade brought us substantial progress in computational imaging techniques for current and next-generation interferometric telescopes, such as the SKA. Imaging methods have exploited sparsity and more recent deep learning architectures with remarkable results.  Despite good reconstruction quality, obtaining reliable uncertainty quantification (UQ) remains a common pitfall of most imaging methods. The UQ problem can be addressed by reformulating the inverse problem in the Bayesian framework. The posterior probability density function provides a comprehensive understanding of the uncertainties. However, computing the posterior in high-dimensional settings is an extremely challenging task. Posterior probabilities are often computed with sampling techniques, but these cannot yet cope with the high-dimensional settings from radio imaging. 

 

This work proposes a method to address uncertainty quantification in radio-interferometric imaging with data-driven (learned) priors for very high-dimensional settings. Our model uses an analytic physically motivated model for the likelihood and exploits a data-driven prior learned from data. The proposed prior can encode complex information learned implicitly from training data and improves results from handcrafted priors (e.g., wavelet-based sparsity-promoting priors). We exploit recent advances in neural-network-based convex regularisers for the prior that allow us to ensure the log-concavity of the posterior while still being expressive. We leverage probability concentration phenomena of log-concave posterior functions that let us obtain information about the posterior avoiding the use of sampling techniques. Our method only requires the maximum-a-posteriori (MAP) estimation and evaluations of the likelihood and prior potentials. We rely on convex optimisation methods to compute the MAP estimation, which are known to be much faster and better scale with dimension than sampling strategies. The proposed method allows us to compute local credible intervals, i.e., Bayesian error bars, and perform hypothesis testing of structure on the reconstructed image. We demonstrate our method by reconstructing simulated radio-interferometric images and carrying out fast and scalable uncertainty quantification.

 

Rôles de l'IA dans le cancer du sein pour le dépistage à partir de mammographies et pour la prédiction de la réponse à la chimiothérapie néoadjuvante à partir d’IRM

Frédérique Frouin, institut curie

Mardi 30 avril à 11h30, CEA-Saclay, Orme-des merisiers, Bat 709, salle Cassini

L’exposé portera dans un premier temps sur l’utilisation possible des méthodes d’intelligence artificielle pour le dépistage du cancer du sein à partir de mammographies, domaine pour lequel les données d’apprentissage sont nombreuses. Dans un second temps, à partir de notre expérience de recherche, nous montrerons comment dans des domaines beaucoup plus restreints, nous avons pu utiliser des outils d’IA pour tenter de mieux prédire la réponse à la chimiothérapie néoadjuvante et nous identifierons un certain nombre de difficultés qui limitent l’impact de ces outils à l’heure actuelle.