E
Eric Laloy
Researcher at Université catholique de Louvain
Publications - 75
Citations - 2120
Eric Laloy is an academic researcher from Université catholique de Louvain. The author has contributed to research in topics: Markov chain Monte Carlo & Bayesian inference. The author has an hindex of 17, co-authored 67 publications receiving 1531 citations. Previous affiliations of Eric Laloy include University of California, Irvine & Ghent University.
Papers
More filters
Journal ArticleDOI
High-dimensional posterior exploration of hydrologic models using multiple-try DREAM (ZS) and high-performance computing
TL;DR: MT‐DREAM(ZS), which combines the strengths of multiple‐try sampling, snooker updating, and sampling from an archive of past states is introduced, which is especially designed to solve high‐dimensional search problems and receives particularly spectacular performance improvement over other adaptive MCMC approaches when using distributed computing.
Journal ArticleDOI
Training-Image Based Geostatistical Inversion Using a Spatial Generative Adversarial Neural Network
Abstract: Probabilistic inversion within a multiple‐point statistics framework is often computationally prohibitive for high‐dimensional problems. To partly address this, we introduce and evaluate a new training‐image based inversion approach for complex geologic media. Our approach relies on a deep neural network of the generative adversarial network (GAN) type. After training using a training image (TI), our proposed spatial GAN (SGAN) can quickly generate 2‐D and 3‐D unconditional realizations. A key characteristic of our SGAN is that it defines a (very) low‐dimensional parameterization, thereby allowing for efficient probabilistic inversion using state‐of‐the‐art Markov chain Monte Carlo (MCMC) methods. In addition, available direct conditioning data can be incorporated within the inversion. Several 2‐D and 3‐D categorical TIs are first used to analyze the performance of our SGAN for unconditional geostatistical simulation. Training our deep network can take several hours. After training, realizations containing a few millions of pixels/voxels can be produced in a matter of seconds. This makes it especially useful for simulating many thousands of realizations (e.g., for MCMC inversion) as the relative cost of the training per realization diminishes with the considered number of realizations. Synthetic inversion case studies involving 2‐D steady state flow and 3‐D transient hydraulic tomography with and without direct conditioning data are used to illustrate the effectiveness of our proposed SGAN‐based inversion. For the 2‐D case, the inversion rapidly explores the posterior model distribution. For the 3‐D case, the inversion recovers model realizations that fit the data close to the target level and visually resemble the true model well.
Journal ArticleDOI
Efficient posterior exploration of a high‐dimensional groundwater model from two‐stage Markov chain Monte Carlo simulation and polynomial chaos expansion
TL;DR: In this paper, the authors report on two strategies for accelerating posterior inference of a highly parameterized and CPU-demanding groundwater flow model using generalized polynomial chaos (gPC) theory and dimensionality reduction.
Journal ArticleDOI
HESS Opinions: Incubating deep-learning-powered hydrologic science advances as a community
Chaopeng Shen,Eric Laloy,Amin Elshorbagy,Adrian Albert,Jerad D. Bales,Fi-John Chang,Sanmay Ganguly,Kuolin Hsu,Daniel Kifer,Zheng Fang,Kuai Fang,Dongfeng Li,Xiaodong Li,Wen-Ping Tsai +13 more
TL;DR: This paper suggests that DL-based methods can open up a complementary avenue toward knowledge discovery in hydrologic sciences, and suggests that integrating process-based models with DL models will help alleviate data limitations.
Journal ArticleDOI
Inversion using a new low-dimensional representation of complex binary geological media based on a deep neural network
TL;DR: This work uses a deep neural network of the variational autoencoder type to construct a parametric low-dimensional base model parameterization of complex binary geological media and finds that the dimensionality reduction (DR) approach outperforms principle component analysis (PCA), optimization-PCA, and discrete cosine transform (DCT) DR techniques for unconditional geostatistical simulation of a channelized prior model.