The Sentinel-2 mission of the European Space Agency (ESA) Copernicus program provides multispectral remote sensing data at decametric spatial resolution and high temporal resolution. The objective of this work is to evaluate the ability of Sentinel-2 time-series data to enable classification of an inherent biophysical property, in terms of accuracy and uncertainty estimation. The tested inherent biophysical property was the soil texture. Soil texture classification was performed on each individual Sentinel-2 image with a linear support vector machine. Two sources of uncertainty were studied: uncertainties due to the Sentinel-2 acquisition date and uncertainties due to the soil sample selection in the training dataset. The first uncertainty analysis was achieved by analyzing the diversity of classification results obtained from the time series of soil texture classifications, considering that the temporal resolution is akin to a repetition of spectral measurements. The second uncertainty analysis was achieved from each individual Sentinel-2 image, based on a bootstrapping procedure corresponding to 100 independent classifications obtained with different training data. The Simpson index was used to compute this diversity in the classification results. This work was carried out in an Indian cultivated region (84 km², part of Berambadi catchment, in the Karnataka state). It used a time-series of six Sentinel-2 images acquired from February to April 2017 and 130 soil surface samples, collected over the study area and characterized in terms of texture. The classification analysis showed the following: (i) each single-date image analysis resulted in moderate performances for soil texture classification, and (ii) high confusion was obtained between neighboring textural classes, and low confusion was obtained between remote textural classes. The uncertainty analysis showed that (i) the classification of remote textural classes (clay and sandy loam) was more certain than classifications of intermediate classes (sandy clay and sandy clay loam), (ii) a final soil textural map can be produced depending on the allowed uncertainty, and iii) a higher level of allowed uncertainty leads to increased bare soil coverage. These results illustrate the potential of Sentinel-2 for providing input for modeling environmental processes and crop management.

There is a need for the up‐to‐date assessment of desertification/land degradation maps that are dynamic in nature at different scales for comprehensive planning and preparation of action plans. This paper aims to develop the desertification vulnerability index (DVI) and predict the different desertification processes operating in Anantapur District, India, based on machine language techniques. Climate, land use, soil, and socioeconomic parameters were used to prepare DVI by a multivariate index model. The computed DVI along with climate, terrain, and soil properties was used as explanatory variable to predict the desertification processes by using a random forest model. About 14.2% of the area was created as a training dataset in 9 places for modeling and remaining area was tested for prediction of desertification processes. We used desertification status map (DSM) of Anantapur District prepared under Desertification status mapping of India–2nd cycle as a reference dataset for calculation of accuracy indices. Kappa and classification accuracy index were calculated for training and validation datasets. We recorded overall accuracy rate and kappa index of 85.5% and 75.8% for training datasets and 71.0% and 51.8% for testing datasets. The results of variable importance analysis of random forest model showed that DVI was the most important predictor followed by potential evapotranspiration and Normalized Difference Vegetation Index for prediction of desertification processes. The results from this work given new insight into using the existing knowledge on prediction of desertification in unvisited areas and also quick update of DSM maps.