Launched by Georges Matheron at the Mining Bureau of Algeria, then at the BRGM and the CEA, geostatistics has rapidly expanded with the creation of the Centre for geostatistical and mathematical morphology at the Ecole des Mines de Paris in 1967. The strong growth of the centre has led to its division into two new centres, the Centre for Geostatistics and the Centre for Mathematical Morphology.

 From the very start, the aim was to develop theoretical and methodological elements to meet the needs of the industrial world. At the very beginning, applications concerned exclusively mining industry, but they rapidly expanded to oil and other fields as meteorology, sea mapping, halieutics, air, water and soil pollution, etc.

 Theoretically speaking, first and until roughly 1985, geostatistics mainly focused on Gaussian random functions (or linear methods, which take place in a much broader frame, but we know they have good properties in the Gaussian case). Works were then oriented towards non-Gaussian random functions, in particular for the conditional simulation of random sets, for example to represent lithologic facies.

 Over the past decade, works mainly concern coupling with other approaches and application to new fields :

  • geostatistics and data assimilation ;
  • integration of digital simulators in the study of exposure to noise or radio electric waves ;
  • application to polluted soils, air and water quality (with the definition of random functions on a river system) ;
  • stochastic genetic models ;
  • extreme values in a spatial context.