The Probability Perturbation Method: A New Look at Bayesian Inverse Modeling

By Jef Caers, T. Hoffman. 2006

154 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Environmental Engineering, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/906614fdd3382108fcdf806bf74e556cb70b5435

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Philippe Renard
2. Gregoire Mariethoz
3. Niklas Linde
4. A. Alcolea
5. Tapan Mukerji
6. Julien Straubhaar
7. Jef Caers
8. Denis Allard

In Environmental Engineering

1. Philippe Renard
2. Gregoire Mariethoz
3. Jef Caers
4. Niklas Linde
5. Julien Straubhaar
6. Tapan Mukerji
7. Denis Allard
8. A. Alcolea

In Statistical and Nonlinear Physics

1. Philippe Renard
2. A. Alcolea
3. Gregoire Mariethoz
4. Tapan Mukerji
5. Niklas Linde
6. Denis Allard
7. Satomi Suzuki
8. Michael Justin O'Sullivan

Citations in the corpus

• A comparison of seven methods for the inverse modelling of groundwater flow. Application to the characterisation of well catchments (2009, methodology): “MP geostatistics is embedded in the Probability Perturbation Method [20,21,72], a novel technique capable of accommodating heads as conditioning data.”
• Bayesian inverse problem and optimization with iterative spatial resampling (2010, methodology): “In the class of prior‐driven methods, one can find the probability perturbation method [Caers and Hoffman, 2006] and the blocking moving window [Alcolea and Renard, 2010].”
• Connectivity metrics for subsurface flow and transport (2013, methodology): “[80] used the probability perturbation inverse method [81] and multiple-point statistics [40] to analyze on the same site the anomalous pressure signals observed in six observation wells during a pumping test.”
• Geological realism in hydrogeological and geophysical inverse modeling: A review (2015, methodology): “The probability perturbation method (PPM) is similar to the gradual deformation method in principle but offers a different perspective [15,17].”
• The Direct Sampling method to perform multiple‐point geostatistical simulations (2010, methodology): “It has also been applied with inversemodeling techniques [Alcolea and Renard, 2010; Caers and Hoffman, 2006; Ronayne et al., 2008;Mariethoz et al., 2010].”
• Blocking Moving Window algorithm: Conditioning multiple‐point simulations to hydrogeological data (2010, methodology): “[5] In the context of inverse problem, MP geostatistics has been embedded in the Probability Perturbation Method, PPM hereinafter [Caers, 2003; Caers and Hoffman, 2006; Hu, 2008].”
• Bayesian calibration of a large‐scale geothermal reservoir model by a new adaptive delayed acceptance Metropolis Hastings algorithm (2011, methodology): “…developed by Duan et al. [1992], Yapo et al. [1998], Karpouzos et al. [2001], and Vrugt et al. [2003]; pilot points methods [RamaRao et al., 1995; Cooley, 2000]; the probability perturbation method [Caers and Hoffman, 2006]; and the Bayesian filtering technique of Lehikoinen et al. [2010].”
• A Distance-based Prior Model Parameterization for Constraining Solutions of Spatial Inverse Problems (2008, methodology): “A practical algorithm for solving inverse problems under a training image-based prior model, termed probability perturbation method, was proposed in Caers (2003), and was later framed within a Bayesian context in Caers and Hoffman (2006) .”