See RealClimate‘s “Statistics and Climate“. 

For some reason having to do with the mechanics of the site, the following comment was considered a “duplicate”.

@tmb, The core of geostatistics is kriging, and it is a standard technique in much Oceanography, as well as other climate-related science.  See, for example, Glover, Jenkins, Doney, Modeling Methods for Marine Science, Cambridge University Press, 2011. Von Storch and Zwiers specifically leave Geostatistics aside on page ix of their text, something I’ve always felt to be a shortcoming. BTW, check out Banerjee, Carlin, Gelfand, Hierarchical Modeling and Analysis for Spatial Data, Chapman & Hall/CRC, 2004.

I therefore put it here.