Ecological potential assessment and land use area estimation of agricultural lands based on multi-time images of Sentinel-2 using ANP-WLC and GIS in Bastam, Iran.

Abstract

The use of land-based ecological potential is a key management factor in achieving sustainable development and conserving soil and water resources. The purpose of this study is to use multi-time images of Sentinel-2 to determine the area of agricultural lands and evaluate their ecological potential in Bastam, Semnan Province, Iran. Therefore, in the first step, the most common agricultural lands (including apricot and grape orchards), field crops (including wheat and forage maize), and their phenological period were determined. Then, the information was classified using, namely support vector machine, maximum likelihood, and minimum distance. In the next step, soil, topography, and climate data were extracted according to expert opinions and the analysis of the basin's natural potential. The ecological evaluation models of the region were applied to homogeneous units, and after calculating the ecological potential index by the integrated ANP-WLC model, the ecological potential map was generated. The results of the land use classification showed that the support vector machine model and the minimum distance, respectively, had the best and worst performance with kappa coefficient of 0.82 and 0.61. The highest area of cultivated lands (3423 hectares) was estimated for wheat and the lowest (738 hectares) for forage maize. Moreover, the results of the ecological potential evaluation showed that 60% of apricot orchards, and 40.19% of the wheat fields, were in the class of good ecological potential. Overall, 2290 hectares were in the poor class, and 4030 hectares in the excellent class in terms of ecological potential.