Soil organic carbon (SOC) stocks are a remarkable property for soil and environmental monitoring. The understanding of their dynamics in crop soils must go forward. The objective of this study was to determine the impact of temporal environmental controlling factors obtained by satellite images over the SOC stocks along soil depth, using machine learning algorithms. The work was carried out in São Paulo state (Brazil) in an area of 2577 km². We obtained a dataset of boreholes with soil analyses from topsoil to subsoil (0–100 cm). Additionally, remote sensing covariates (30 years of land use history, vegetation indexes), soil properties (i.e., clay, sand, mineralogy), soil types (classification), geology, climate and relief information were used. All covariates were confronted with SOC stocks contents, to identify their impact. Afterwards, the abilities of the predictive models were tested by splitting soil samples into two random groups (70 for training and 30% for model testing). We observed that the mean values of SOC stocks decreased by increasing the depth in all land use and land cover (LULC) historical classes. The results indicated that the random forest with recursive features elimination (RFE) was an accurate technique for predicting SOC stocks and finding controlling factors. We also found that the soil properties (especially clay and CEC), terrain attributes, geology, bioclimatic parameters and land use history were the most critical factors in controlling the SOC stocks in all LULC history and soil depths. We concluded that random forest coupled with RFE could be a functional approach to detect, map and monitor SOC stocks using environmental and remote sensing data.

Pedotransfer functions (PTFs) have been used to save time and cost in predicting certain soil properties, such as soil erodibility (K-factor). The main objectives of this study were to develop appropriate PTFs to predict the K-factor, and then compare new PTFs with Universal Soil Loss Equation (USLE) and the Revised Universal Soil Loss Equation (RUSLE) K-factor models. The K-factor was measured using 40 erosion plots under natural rainfall in Simakan Watershed, an area of 350 km² in central of Iran. The Regression Tree (RT) and Multiple Linear Regression (MLR) were used to develop PTFs for predicting the K-factor. The result showed that the mean of measured K was 0.01 t h MJ⁻¹ mm⁻¹. The mean K value predicted by USLE and RUSLE was 2.08 and 2.84 times more than the measured K, respectively. Although calcium carbonate was not considered in the original USLE and RUSLE K-factors, it appeared in the advanced PTFs due to its strong positive significant impact on aggregate stability and soil infiltration rate, resulting in decreased K-factor. The results also showed that the RT with R² = 0.84 had higher performance than developed MLR, USLE and RUSLE for the K estimation.

Land degradation by soil erosion is one of the most severe environmental issues that is greatly dependent on land use management. In this study, the effects of long-term land use management (including annual cultivated field (ACF), fallow field (FF), rangeland (R), and orchard field (OF)), soil depth (0–10 and 10–20 cm), and soil organic matter content (SOM) on wind- and water-erosion indices were investigated in calcareous soils of southern Iran. Soil samples were collected from four above-mentioned land-use types, and some soil properties and erosion indices were measured. Results showed that the most of soil aggregates stability indices in the surface layer (0–10 cm) of OF were higher than those in ACF, FF, and R, respectively, by nearly 39%, 32%, and 47% for dry mean weight diameter of aggregates (MWD_dry); 10%, 10%, and 48% for dry geometric mean weight diameter of aggregates (GMD_dry); 21%, 17%, and 15% for water-stable aggregates (WSA); and 11%, 16%, and 31% for aggregate stability index (ASI). Moreover, the mean of the soil wind erosion indicators in OF (0–10 cm) were lower than those in ACF, FF, and R, respectively, by nearly 18%, 24%, and 26%, for wind-erodible fraction (EF); 43%, 38%, and 49% for soil erodibility to wind erosion (K); and 36%, 32%, and 41% for wind erosion rate (ER). In ACF, despite the high clay content, some aggregate stability indices such as MWøD_dry and WSA were the lowest among studied land-use types which showed the negative effects of conventional tillage practices. Depth factor had only a significant effect on dust emission potential (DEP) in ACF, FF, and OF. In addition, there were significant and strong correlations between SOM and MWD_dry (r = 0.79), WSA (r = 0.77), EF (r = −0.85), K (r = 0.74), and ER (r = 0.74) in all datasets.

Soil salinization stands as a prominent global environmental challenge, necessitating enhanced assessment methodologies. This study is dedicated to refining soil salinity assessment in the Lake Urmia region of Iran, utilizing multi-year data spanning from 2015 to 2018. To achieve this objective, soil salinity was measured at 915 sampling points during the 2015–2018 timeframe. Simultaneously, remote sensing data were derived from surface reflectance data over the same study period. Four distinct scenarios were considered such as a newly developed spectral index (Scenario I), the newly developed index combined with other salt-based spectral indices from the literature (Scenario II), indirect spectral indices based on vegetation and soil characteristics (Scenario III), and the amalgamation of both direct and indirect spectral indices (Scenario IV). Linear Regression (LR), Support Vector Machine (SVM), and Random Forest (RF) were employed to assess soil salinity. The measured data divided to 75% of the data as the calibration dataset, while the remaining 25% constituted the validation dataset. The findings revealed a correlation between soil salinity and spectral indices from the literature, with a range of -0.53 to 0.51, while the newly developed spectral index exhibited a stronger correlation (r = 0.59). Furthermore, RF yielded superior results when using the newly developed spectral index (Scenario I). Overall, SVM emerged as the most effective model (ME = -9.678, R² = 0.751, and RPIQ = 1.78) when integrating direct and indirect spectral indices (Scenario IV). This study demonstrates the efficacy of combining machine learning techniques with a blend of newly developed and existing spectral indices from the literature for the monitoring of soil salinity, particularly in arid and semi-arid regions.

This study examines the effects of land use and slope aspect on soil erodibility (K-factor) and the fractal dimension (D) of soil particle size distribution (PSD) in calcareous soils at the watershed scale in western Iran. The study analyzed 113 soil samples collected from four land uses (slope-farmland, farmland, pasture, and woodland) at a depth of 0–20 cm, measuring common soil properties such as soil texture, soil organic matter (SOM), calcium carbonate (CaCO₃), pH, and cation exchange capacity (CEC). The PSD of soil samples was measured using the international system of soil size fractions, and the D for PSD was calculated. The K-factor was calculated using the RUSLE model. The results showed that the K-factor was highest in slope farmlands with SOM at 1.6% and lowest in woodlands at 0.02 Mg h MJ⁻¹ mm⁻¹ with SOM at 3.5%. The study also found that there were significant correlations between D and clay content (r = 0.52), sand content (r = −0.29), and CEC (r = 0.36). Woodland soils had the highest SOM content, with a mean D value of 2.895, significantly higher than the mean D value of slope farmland soils, which had the lowest SOM at 1.6%. The study concludes that woodland soils retain finer particles, particularly clay, resulting in lower soil loss and land degradation compared to other land uses. Finally, the study suggests that shady slope aspects (south aspect) contain more organic matter due to less solar radiation and higher soil water content, resulting in lower soil erodibility (0.02 Mg h MJ⁻¹ mm⁻¹) and higher D values compared to other slope aspects.