No abstract

Soil texture is an important property that controls the mobility of the water and nutrients in soil. This study examined the capability of machine learning (ML) models in estimating soil texture fractions using different combinations of remotely sensed data from Sentinel-1 (S1), Sentinel-2 (S2), and terrain-derived covariates (TDC) across two contrasting agroecological regions in Southwest Germany, Kraichgau and the Swabian Alb. Importantly, we tested the predictive power of three different ML models: the random forest (RF), the support vector machine (SVM), and extreme gradient boosting (XGB) coupled with the remote sensing data covariates. As expected, ML model performance was not consistent regarding the input covariates, soil texture fractions, and study regions. For example, in the Swabian Alb, the SVM model performed the best for the sand content with S2 + TDC (RMSE = 3.63%, R2 = 0.42), and XGB best predicted the clay content with S1 + S2 + TDC (RMSE = 6.84%, R2 = 0.64). In Kraichgau, the best models for sand (RMSE = 7.54%, R2 = 0.79) and clay contents (RMSE = 6.14%, R2 = 0.48) were obtained using XGB and SVM, respectively. Moreover, the results indicated that TDC were critical in estimating soil texture fractions, especially in Kraichgau, which indicated that topography plays an important role in defining the spatial distribution of soil properties. In contrast, the contribution of remote sensing data better predicted the silt and clay content in the Swabian Alb. The transferability of a region-specific model to the other region was low as indicated by poor predictive performance. The resulting soil-texture-fraction maps could be a significant source of information for efficient land resource management and environmental monitoring. Nonetheless, further research to evaluate the added value of the Sentinel imagery and to better analyze the spatial transferability of machine learning models is highly recommended.

Meandering rivers are among the most dynamic Earth-surface systems, which generally appear in fertile valleys, the most valuable lands for agriculture and human settlement. Landsat time series and morphological parameters are complementary tools for exploring river dynamics. Karun River is the most effluent and largest meandering river in Iran, which keeps the Karun’s basin economy, agriculture, and industrial sections alive; hence, investigating morphological changes in this river is essential. The morphological characteristics of Karun have undergone considerable changes over time due to several tectonic, hydrological, hydraulic, and anthropogenic factors. This study has identified and analyzed morphological changes in Karun River using a time series of Landsat imagery from 1985–2015. On that basis, morphological dynamics, including the river’s active channel width, meander’s neck length, water flow length, sinuosity index, and Cornice central angle, were quantitatively investigated. Additionally, the correlation between the stream power and morphological factors was explored using the data adopted from the hydrometric stations. The results show that the dominant pattern of the Karun River, due to the sinuosity coefficient, is meandering, and the majority of the river falls in the category of developed meander rivers. Moreover, the number of arteries reduced in an anabranch pattern, and the river has been migrating towards the downstream and eastern sides since 1985. This phenomenon disposes a change in the future that can be hazardous to the croplands and demands specific considerations for catchment management.

No abstract

No abstract