Identification of internal structures in an active volcano is mandatory to quantify the physical processes preceding eruptions. We propose a fully unsupervised Bayesian inversion method that uses the point compound dislocation model as a complex source of deformation, to dynamically identify the substructures activated during magma migration. We applied this method at Piton de la Fournaise. Using 7‐day moving trends of Global Navigation Satellite System (GNSS) data preceding the June 2014 eruption, we compute a total of 15 inversion models of 2.5 million forward problems each, without a priori information. Obtained source shapes (dikes, prolate ellipsoids, or pipes) show magma migration from 7–8 km depth to the surface, drawing a mechanical “tomography” of the magma pathway. Our results also suggest source geometries compatible with observed eruptive fissures and seismicity distribution. In case of finite magma volume involved in final dike injection, source volume estimates from this method allow forecasting volumes of erupted lava.
Over the past decade, neural networks have been successful at making predictions from biological sequences, especially in the context of regulatory genomics. As in other fields of deep learning, tools have been devised to extract features such as sequence motifs that can explain the predictions made by a trained network. Here we intend to go beyond explainable machine learning and introduce SEISM, a selective inference procedure to test the association between these extracted features and the predicted phenotype. In particular, we discuss how training a one-layer convolutional network is formally equivalent to selecting motifs maximizing some association score. We adapt existing sampling-based selective inference procedures by quantizing this selection over an infinite set to a large but finite grid. Finally, we show that sampling under a specific choice of parameters is sufficient to characterize the composite null hypothesis typically used for selective inference-a result that goes well beyond our particular framework. We illustrate the behavior of our method in terms of calibration, power and speed and discuss its power/speed trade-off with a simpler data-split strategy. SEISM paves the way to an easier analysis of neural networks used in regulatory genomics, and to more powerful methods for genome wide association studies (GWAS).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.