Gaussian processes can be used as a supervised learning technique for classification as well as regression. An example of a classification task would be to recognize handwritten digits, whereas an example of a regression problem would be to learn the inverse dynamics of a robot arm (Fig. 1(a)). For the latter, the task is to obtain a mapping from the state of the arm (given by the positions, ve...

A linear relationship between ERS-2 SAR backscattering coe cient (s0 ) and volumetric soil moisture was determined at both ends of a rainfall gradient in Israel. A Normalized radar Backscatter soil Moisture Index (NBMI) was derived and related strongly to soil moisture concentration. This index may allow the mapping of soil moisture conditions over large areas with C band SAR data.

The present paper proposes a method for the evaluation of soil evaporation, using soil moisture estimations based on radar satellite measurements. We present firstly an approach for the estimation and monitoring of soil moisture in a semi-arid region in North Africa, using ENVISAT ASAR images, over two types of vegetation covers. The first mapping process is dedicated solely to the monitoring o...

Examples from the Murray–Darling basin in Australia are used to illustrate different methods of disaggregation of reconnaissance-scale maps. One approach for disaggregation revolves around the de-convolution of the soil–landscape paradigm elaborated during a soil survey. The descriptions of soil map units and block diagrams in a soil survey report detail soil–landscape relationships or soil top...

The COsmic-ray Soil Moisture Observing System (COSMOS) rover may be useful for validating satellite-based estimates of near-surface soil moisture, but the accuracy with which the rover can measure 0to 5-cm soil moisture has not been previously determined. Our objectives were to calibrate and validate a COSMOS rover for mapping 0to 5-cm soil moisture at spatial scales suitable for evaluating sat...

Images of representative clayey bare fields were chosen from a high spatial resolution hyperspectral dataset that was acquired with the prototypal airborne Hyper SIM-GA sensor from Selex Galileo simultaneously with ground soil spectral signatures and the collection of samples. After both the pre-processing and calibration of the SIM-GA data, the mapping procedure was developed using the 2-2.45 ...

The goal of accurately mapping soil variability preceded GPS-aided agriculture, and has been a challenging aspect of precision agriculture since its inception. Many studies have found the range of spatial dependence is shorter than the distances used in most grid sampling. Other studies have examined variability within government soil surveys and concluded that they have limited utility in many...

It is well known that the world is rich with soil data resulting from the efforts of past soil surveys. However, the majority of these data is largely unused. These legacy soil data come in the form of soil maps, soil survey reports, soil profile descriptions, and/or in the format of antiquated “card catalogue”. These data provide many benefits including soil information preservation or as a ma...