Geostatistics

By Emmanouil A. Varouchakis. Spatiotemporal Analysis of Extreme Hydrological Events, 2019

167 citations recorded by the source corpus.

Abstract Geostatistics has been well established and developed during the last three decades and is widely applied in environmental research and technology. Geostatistics is a subdiscipline of spatial statistics. It includes a set of statistical methods that concern random variables with spatial and/or temporal variability (random fields). These variables represent physical quantities with economic or environmental importance. The methods are based on the assumption that the spatiotemporal variability includes a random component that has space–time correlation. Therefore statistical measures such as mean value, variance, standard deviation, spatiotemporal dependence, etc., are used to extract any useful information from the available data. Geostatistics deals with distributions in which the spatial and/or temporal dependence is the primary characteristic. Geostatistical analysis aims to estimate the statistical parameters that determine the spatial and/or temporal distribution and dependence of the relevant variables. This procedure is called parameter inference. These parameters are used to estimate (interpolate) the variables at desired spatiotemporal locations where no measurements are available. This chapter describes the basic mathematical background of geostatistics and presents a complete methodological guide for geostatistical analysis of physical variables.

Subfields: Artificial Intelligence, Environmental Engineering, Soil Science

View Paper: https://www.semanticscholar.org/paper/8bba5ea55a687cd4ec61bffe230817a9c7748d60

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

In Environmental Engineering

In Soil Science

Citations in the corpus

An Improved Multi-Output Gaussian Process RNN with Real-Time Validation for Early Sepsis Detection (2017, methodology): “This model is also equivalent to the well-known Linear Model of Coregionalization (Journel and Huijbregts (1978)).”
Continual Multi-task Gaussian Processes (2019, methodology): “Future research lines are, for instance, to employ convolutional processes (CPs) or non-linear mappings as the mixing operator in the multi-output GP model as an alternative to the LMC.”