Evaluating Drought Effects on Soil: Innovative Soil Salinity Monitoring via SAR Data, Sentinel-2 Imagery, and Machine Learning Algorithms in Kerkennah Archipelago

Abstract

The Kerkennah archipelago in Tunisia is one of the most vulnerable areas where the influence of climate change is undeniable. Soil salinization has emerged as a major consequence of climate variation on this island. In this study, remote sensing techniques were implemented to develop a model for predicting soil salinity from satellite images. Machine learning algorithms, Sentinel-1 and Sentinel-2 data, and ground truth measurements were used to estimate soil salinity. Several algorithms were considered to achieve accurate findings. These algorithms are categorized as polynomial regression, random forest regression, exponential regression, and linear regression. The results demonstrate that exponential regression is the pre-eminent algorithm for estimating soil salinity with high predictive accuracy of R2 = 0.75 and RMSE = 0.47 ds/m. However, spatiotemporal soil salinity maps reveal distinct and clear distribution patterns, highlighting salty areas (i.e., sebkhas) and agricultural parcels. Thus, through the model, we explore areas of moderately high salinity within agricultural lands that could be affected by irrigation practices. The present work demonstrates a reliable model for soil salinity monitoring in the Kerkennah archipelago and inspires more successful technologies such as remote sensing and machine learning to improve the estimation of soil salinity in climate-affected vulnerable areas.

Keywords

• climate change
• soil salinity
• Sentinel-1
• Sentinel-2
• machine learning
• NDVI