Page 10 - Modern Spatiotemporal Geostatistics

PREFACE

"If an old rule of thumb from the publishing
industry is to be believed, every equation included in
a book halves the number sold." Economist, Jan. 2-8, 1999

Stochastic characterization of spatial and temporal attributes began as a col-
lection of mathematical concepts and methods developed originally (mostly
in the 1930's through 1950's) by A.N. Kolmogorov, H. Wold, N. Wiener,
A.M. Yaglom, K. Ito, I.M. Gel'fand, L.S. Gandin, B. Matern, P. Whittle, and
others. G. Matheron coined the term "geostatistics" to refer to these develop-
ments, brought them together, modified them in some cases, and then applied
them systematically in the mining exploration context. Rapid commercial suc-
cess allowed Matheron to establish the Fontainebleau Research Center in the
late 1960's outside Paris. Later, geostatistical techniques were used in other
disciplines as well, including hydrogeology, petroleum engineering, and envi-
ronmental sciences. Geostatistics was introduced in the 1970's in Canada and
the United States by geostatisticians including M. David, A.G. Journal, and
R.A. Olea. References to selected publications of the above researchers may
be found in the bibliography at the end of this book.
It is widely recognized that the techniques of classical geostatistics, which
have been used for several decades, have reached their limit and the time has
come for some alternative approaches to be given a chance. In fact, many
researchers and practitioners feel that they may soon be faced with some kind
of law of diminishing returns for geostatistics, inasmuch as the problems of
the rapidly developing new scientific fields are becoming more complex, and
seemingly fewer new geostatistical concepts and methods are available for their
solution.
With these concerns in mind, this book is an introduction to the funda-
mentals of modern spatiotemporal geostatistics. Modern geostatistics is viewed
in the book as a group of spatiotemporal concepts and methods which are the
products of the advancement of the epistemic status of stochastic data analy-
sis. The latter is considered from a novel perspective promoting the view that
ix