ALBERT

Description: Knowledge of the spatial distribution of dust aerosols and their effects on crops is important for policy formulation and food security. This study aims to investigate the impact of dust source susceptibility areas (DSSA) on the loss of agricultural crop and corresponding water consumption in terms of Water Footprint in the Great Salt Desert, Iran. To this goal, MODIS satellite images during the 2005–2020 period were used to identify dust sources and 135 dust source zones were identified. Machine learning algorithm viz. Random Forest (RF), generalized linear model (GLM), and Artificial neural network (ANN) were tested to reproduce DSSA. The best method was RF and applied to calculate and classify DSSA in five risk levels from very low to very high. The amount of wheat production under high risk of DSSA was estimated using the average crop yield from recent years using agriculture statistics. We calculated the loss of crops and corresponding water consumption for three scenarios, assuming a typical loss of 20, 40, and 60% of the wheat production for better crop loss estimation. Finally, the spatial relationships between wheat farmland and high-risk DSSA were assessed using ordinary least squares regression (OLS) and geographically weighted regression (GWR) at sub-watershed scale. The area of wheat cultivation in high and very high risk of DSSA is 10188.04 km2, which is 36% of all agricultural land for wheat in the region. Loss of wheat crop to DSSA meant that 1270.58 to 3811 million m3 water used for the production of wheat were lost, corresponding to 2%, to 7% of lost water compared to the total water consumption for wheat production in the study area.

Description: Land degradation is a cause of many social, economic, and environmental problems. Therefore identification and monitoring of high-risk areas for land degradation are necessary. Despite the importance of land degradation due to wind and water erosion in some areas of the world, the combined study of both types of erosion in the same area receives relatively little attention. The present study aims to create a land degradation map in terms of soil erosion caused by wind and water erosion of semi-dry land. We focus on the Lut watershed in Iran, encompassing the Lut Desert that is influenced by both monsoon rainfalls and dust storms. Dust sources are identified using MODIS satellite images with the help of four different indices to quantify uncertainty. The dust source maps are assessed with three machine learning algorithms encompassing the artificial neural network (ANN), random forest (RF), and flexible discriminant analysis (FDA) to map dust sources paired with soil erosion susceptibility due to water. We assess the accuracy of the maps from the machine learning results with the area under the curve (AUC) of the receiver operating characteristic (ROC) metric. The water and aeolian soil erosion maps are used to identify different classes of land degradation risks. The results show that 43 % of the watershed is prone to land degradation in terms of both aeolian and water erosion. Most regions (45 %) have a risk of water erosion and some regions (7 %) a risk of aeolian erosion. Only a small fraction (4 %) of the total area of the region had a low to very low susceptibility for land degradation. The results of this study underline the risk of land degradation for in an inhabited region in Iran. Future work should focus on land degradation associated with soil erosion from water and storms in larger regions to evaluate the risks also elsewhere.