loess soil

LOESS, or locally weighted scatterplot smoothing, is one of many "modern" modeling methods that build on "classical" methods, such as linear and nonlinear least squares regression. Modern regression methods are designed to address situations in which the classical procedures do not perform well or cannot be effectively applied without undue labor. LOESS combines much of the simplicity of linear least squares regression with the flexibility of nonlinear regression. It does this by fitting simple models to localized subsets of the data to build up a function that describes the deterministic part of the variation in the data, point by point. In fact, one of the chief attractions of this method is that the data analyst is not required to specify a global function of any form to fit a model to the data, only to fit segments of the data.
See more at Wikipedia.org...

This article is about the geologic material. For the statistical technique see Local regression. Among the classifications of soil types, loess, from the German Löss or Löß, and ultimately from Swiss German lösch (loose), pronounced in several different ways in English (IPA: ]), it is a fine, silty, windblown (eolian) type of unconsolidated deposit. (The term sometimes refers to the soil derived from it.) It is derived from glacial deposits, where glacial activity has ground rocks very fine (rock flour). After drying, these deposits are highly susceptible to wind erosion, and downwind deposits may become very deep, even a hundred metres or more, as in areas of China and the midwestern United States. Loess deposits are geologically unstable by nature, and will erode even without being disturbed by humans; even well-managed loess farmland can experience dramatic erosion of well over 25 tonnes per hectare per year.
See more at Wikipedia.org...