No abstract

Soil salinity is a widespread environmental hazard and the main causes of land degradation and desertification, especially in arid and semi-arid regions. The first step in finding such a solution is providing accurate information about the severity and extent of the salinity spread in affected areas; this can be done by mapping the electrical conductivity (EC) of the soil. Utilizing the potential of high-resolution satellite imagery along with remote sensing techniques is a promising method to map salinity, as it allows for large-scale monitoring and provides high accuracy and efficiency. This paper, therefore, aims at assessing soil salinity by mapping the EC of soils, using satellite imagery from the newly launched Sentinel-2 satellite as well as Landsat-8 data. A field study was carried out using those data, and various salt features were extracted that relate the EC values of field samples to satellite-derived salt features. The study used two different regression approaches MLP and SVR. Additionally, two feature selection algorithms, GA and SFS, were implemented on the data to improve model performance. The study concludes that the proposed method for modeling salinity and the mapping of soil EC can be considered an effective approach for soil salinity monitoring.

ABSTRACT:Soil salinity is one of the main causes of desertification and land degradation which has negative impacts on soil fertility and crop productivity. Monitoring salt affected areas and assessing land cover changes, which caused by salinization, can be an effective approach to rehabilitate saline soils and prevent further salinization of agricultural fields. Using potential of satellite imagery taken over time along with remote sensing techniques, makes it possible to determine salinity changes at regional scales. This study deals with monitoring salinity changes and trend of the expansion in different land cover types of Bakhtegan Salt Lake district during the last two decades using multi-temporal Landsat images. For this purpose, per-pixel trend analysis of soil salinity during years 2000 to 2016 was performed and slope index maps of the best salinity indicators were generated for each pixel in the scene. The results of this study revealed that vegetation indices (GDVI and EVI) and also salinity indices (SI-1 and SI-3) have great potential to assess soil salinity trends in vegetation and bare soil lands respectively due to more sensitivity to salt features over years of study. In addition, images of May had the best performance to highlight changes in pixels among different months of the year. A comparative analysis of different slope index maps shows that more than 76% of vegetated areas have experienced negative trends during 17 years, of which about 34% are moderately and highly saline. This percent is increased to 92% for bare soil lands and 29% of salt affected soils had severe salinization. It can be concluded that the areas, which are close to the lake, are more affected by salinity and salts from the lake were brought into the soil which will lead to loss of soil productivity ultimately.

No abstract