Geostatistics Toronto 2021 : : Quantitative Geology and Geostatistics / / edited by Sebastian Alejandro Avalos Sotomayor, Julian M. Ortiz, R. Mohan Srivastava.

• Superior document: Springer Proceedings in Earth and Environmental Sciences,
• Author: Avalos Sotomayor, Sebastian Alejandro.
• TeilnehmendeR: Ortiz, Julian M.; Srivastava, R. Mohan.
• Place / Publishing House: Cham : : Springer International Publishing :, Imprint: Springer,, 2023.
• Year of Publication: 2023
• Edition: 1st ed. 2023.
• Language: English
• Series: Springer Proceedings in Earth and Environmental Sciences,
• Physical Description: 1 online resource (282 pages)

This open access book provides state-of-the-art theory and application in geostatistics. Geostatistics Toronto 2021 includes 28 short abstracts, 18 extended abstracts, and 7 full articles in the fields of geostatistical theory, multi-point statistics, earth sciences, mining, optimal drilling, domains, seismic, classification uncertainty risk, and artificial intelligence and machine learning. All contributions were presented at the 11th International Geostatistics Congress held in virtually at Toronto, Canada, from July 12-16, 2021. This book is valuable to researchers, scientists, and practitioners in geology, mining, petroleum, geometallurgy, mathematics, and statistics.

Table of Contents

A Geostatistical Heterogeneity Metric For Spatial Feature Engineering -- Iterative Gaussianisation For Multivariate Transformation -- Comparing And Detecting Stationarity And Dataset Shift -- Simulation Of Stationary Gaussian Random Fields With A Gneiting Spatio-Temporal Covariance -- Spectral Simulation Of Gaussian Vector Random Fields On The Sphere -- Geometric And Geostatistical Modeling Of Point Bars -- Application Of Reinforcement Learning For Well Location Optimization -- Compression-Based Modelling Honouring Facies Connectivity In Diverse Geological Systems -- Spatial Uncertainty In Pore Pressure Models At The Brazilian Continental Margin -- The Suitability Of Different Training Images For Producing Low Connectivity, High Net:Gross Pixel-Based Mps Models -- Probabilistic Integration Of Geomechanical And Geostatistical Inferences For Mapping Natural Fracture Networks.