Predicting soil erosion susceptibility associated with climate change scenarios in the Central Highlands of Sri Lanka

Predictive modeling of diazinon residual concentration in soils contaminated with potentially toxic elements: a comparative study of machine learning approaches

The widespread use of pesticides, including diazinon, poses an increased risk of environmental pollution and detrimental effects on biodiversity, food security, and water resources. In this study, we investigated the impact of Potentially Toxic Elements (PTE) including Zn, Cd, V, and Mn on the degradation of diazinon in three different soils. We investigated the capability and performance of four machine learning models to predict residual pesticide concentration, including adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR), radial basis function (RBF), and multi-layer perceptron (MLP). We employed a 10-fold cross-validation mechanism to evaluate the models. Moreover, performance validation of selected algorithms through the coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE) and mean square error (MSE) confirm that the SVR and ANFIS with lower RMSE, MSE, and a higher R2 can simulate the degradation process better than other models. The result showed that both SVR and ANFIS approaches worked well for the data set, but the SVR technique is more accurate than the fuzzy model for estimating pesticide concentration in soil in the presence of PTE. Vanadium appeared to be the best option for the degradation of diazinon. The models predicted the performance of V2+ for diazinon degradation with R2 and RMSE of 0.99 and 2.18 m g . k g - 1 for SVR and, 0.99, and 1.30 for the ANFIS model for the training set. Finally, the high accuracy of the models was confirmed.

Prediction of soil erosion and sediment yield in an ungauged basin based on land use land cover changes

Soil erosion is a significant problem in the agriculture sector and the environment globally. Susceptible soil erosion zones must be identified and erosion rates evaluated to decrease land degradation problems and increase crop productivity by protecting soil fertility. Therefore, a research study has been carried out in the Ponnaniyar River basin, an ungauged tributary of the Cauvery basin in India, primarily used for agriculture. The main purpose of this study is to assess soil erosion (SE) and sediment yield (SY) for the future in an ungauged basin by utilizing the projected land use/land cover (LULC) map of the study area. Additionally, Landsat 8 satellite dataset was only used for the classification and prediction of LULC to eliminate the variation between the resolution, bands and its wavelength of different satellites datasets. To achieve the goals of this study, three phases were followed. First, the LULC of the study area was classified using a Random Trees Classifier (RTC), a machine learning technique, followed by the projection of land cover using a Cellular Automata-based Artificial Neural Network (CA-ANN) model. The driving factors for this model include digital elevation model (DEM), slope, distance to roads, settlements, and water bodies. The accuracy level of the projected LULC map was determined by comparing it with the classified LULC map of the study area, and the results showed an overall accuracy (OA) of 85.35 percentage and a kappa coefficient (K) of 0.74, respectively. Second, the projected LULC map was used in the land management factor (C) and conversation practice factor (P) of the Revised Universal Soil Loss Equation (RUSLE) model to assess soil erosion. The model was integrated with the sediment delivery ratio (SDR) to estimate sediment yield within the study area. The accuracy of the generated erosion map based on the classified and projected LULC for the year 2022 was determined using the receiver operating characteristic curve (ROC) curve, and it was found to be in satisfactory agreement. Finally, for effective soil and water conservation measures, the basin was divided into 13 sub-watersheds (SWs) using terrain analysis in geographical information system (GIS). The SWs were prioritized based on the mean soil loss in the 4-year interval from 2014 to 2030 and integrated using the weighted average method to determine the final prioritization. From these findings, SW 11, SW 9, SW 12, and SW 1 are extremely affected by soil erosion, and immediate implementation of water harvesting structures is required for soil conservation. Also, this research might be useful for decision-makers and policymakers in land management.

Spatiotemporal evolution of soil water erosion in Ningxia grassland based on the RUSLE-TLSD model

Accurate assessment of grassland soil erosion before and after grazing exclusion and revealing its driving mechanism are the basis of grassland risk management. In this study, the long-term soil erosion in Ningxia grassland was simulated by integrating and calibrating the transport limited sediment delivery (TLSD) function with the revised universal soil loss equation (RUSLE) model. The differential mechanisms of soil loss were explored using the GeoDetector method, and the relative effects of precipitation changes (PC) and human activities (HA) on grassland soil erosion were investigated using double mass curves. The measured sediment discharges from six hydrological stations verified that the RUSLE-TLSD model could reliably simulate water erosion in Ningxia. From 1988 to 2018, the water erosion rate of grassland in Ningxia ranged from 74.98 to 14.98 t⋅ha-1⋅a-1, showing an overall downward trend. July to September is the period with the highest of water erosion. The slope is the dominant factor influencing the spatial distribution of water erosion. After grazing exclusion, the net water erosion rate in Ningxia grassland and sub-regions decreased significantly. The double mass curves results show that human activities were the main driver of net erosion reduction. The focus of water erosion control in Ningxia is to control soil erosion in different terrains and protect grassland with slopes greater than 10°.

Impacts of land use/land cover and soil property changes on soil erosion in the black soil region, China

Soil erosion (SE) is seriously threatening grain production and the ecological environment in the black soil region. Understanding the impact of changes in land use/land cover (LULC) and soil properties on SE is critical for agricultural sustainability and soil management. However, the contribution of soil property changes to SE is often ignored in existing studies. This study analyzed changes in LULC and soil properties from 1980 to 2020 in the black soil region, China. Then, the revised universal soil loss equation was used to explore the spatiotemporal changes of SE from 1980 to 2020. Finally, the contribution of LULC change and soil property change to SE was separated by scenario comparison. The results showed that cropland increased (by 24,157 km²) at the expense of grassland and forest from 1980 to 2020. Sand in cropland decreased by 21.95%, while the silt, clay, and SOC increased by 21.37%, 1.43%, and 15.38%, respectively. Soil erodibility in cropland increased greatly (+9.85%), while in forest and grassland decreased (-6.05% and -4.72%). LULC change and soil properties change together aggravated SE in the black soil region. LULC change and soil property change resulted in a 22% increase in SE, of which LULC change resulted in a 14% increase, and soil property change resulted in an 8% increase. Agricultural development policy was the main reason driving LULC change. The combination of LULC change, climatic factors, and long-term tillage resulted in changes in soil properties. Ecosystem management and policy can reduce SE through vegetation restoration and soil improvement. This study can provide important references for soil conservation and agricultural development in the black soil region.

Predicting soil erosion potential under CMIP6 climate change scenarios in the Chini Lake Basin, Malaysia

Climate change and soil erosion are very associated with environmental defiance which affects the life sustainability of humans. However, the potency effects of both events in tropical regions are arduous to be estimated due to atmospheric conditions and unsustainable land use management. Therefore, several models can be used to predict the impacts of distinct climate scenarios on human and environmental relationships. In this study, we aimed to predict current and future soil erosion potential in the Chini Lake Basin, Malaysia under different Climate Model Intercomparison Project-6 (CMIP6) scenarios (e.g., SSP2.6, SSP4.5, and SSP8.5). Our results found the predicted mean soil erosion values for the baseline scenario (2019-2021) was around 50.42 t/ha year. The mining areas recorded the highest soil erosion values located in the southeastern part. The high future soil erosion values (36.15 t/ha year) were obtained for SSP4.5 during 2060-2080. Whilst, the lowest values (33.30 t/ha year) were obtained for SSP2.6 during 2040-2060. According to CMIP6, the future soil erosion potential in the study area would reduce by approximately 33.9% compared to the baseline year (2019-2021). The rainfall erosivity factor majorly affected soil erosion potential in the study area. The output of the study will contribute to achieving the United Nations' 2030 Agenda for Sustainable Development.