Understanding the mechanism of gully erosion in the alpine region through an interpretable machine learning approach.

In the alpine region, climate warming has led to the retreat of glaciers, snow cover, and permafrost. This has intensified water cycling, soil erosion, and increased the occurrence of natural disasters in the alpine region. This study investigated the Lhasa River Basin in the southern Tibetan Plateau, serving as a representative case study of a typical alpine basin, with a specific focus on gully erosion. Based on field investigations and interpretation using high-resolution satellite remote sensing images, the Random Forest (RF) algorithm was applied to evaluate gully erosion susceptibility on watershed level. The Shapley Additive Interpretation method was then used to interpret the RF model and gain deeper insights into the influencing variables of gully erosion. The results showed that the RF model achieved an area under the receiver operating characteristic (AUC) accuracy of 0.99 and 0.98 for the training and testing datasets, respectively, indicating an outstanding performance of the model. The resulting susceptibility map based on the RF model shows that areas with moderate and higher levels of gully erosion susceptibility are covering 50 % of the basin. The model interpretation results indicated that elevation, slope, permafrost, rainstorm, silt loam topsoil, human activity, stream power, and vegetation were the explaining variables with the highest importance for gully erosion occurrence. Different variables are characterized by specific thresholds promoting gully erosion such as: i) elevations higher than 4950 m, ii) slopes steeper than 13.5°, iii) extreme rainstorms longer than 11 days per year, iv) silt loam topsoil, v) presence of permafrost, vi) stream power index higher than 1.2, and vii) normalized difference vegetation index (NDVI) lower than 0.25. Our findings provide the scientific basis to improve soil erosion control in such highly vulnerable alpine area.

Assessment of gully influencing factors and susceptibility using remote sensing-based frequency ratio method in Sunshui River Basin, Southwest China.

Gully erosion is a serious global environmental problem associated with land degradation and ecosystem security. Examining the influencing factors of gullies and determining susceptibility hold significance in environmental sustainability. The study evaluates the spatial distribution, influencing factors, and susceptibility of gullies in the Sunshui River Basin in Sichuan Province, Southwest China. The frequency ratio method supported by satellite images and the gully inventory dataset (1614 gully head points) with different influencing factors were applied to assess the distribution and susceptibility of gullies. Additionally, gully head points were grouped into a training set (70%, 1130 points) and a test set (30%, 484 points). Spatial distribution results indicated that most gullies are located in the middle and upper part of the basin, characterized by moderate elevation (2100-3300 m), steep slopes (11.63-27.34°), abandoned farmland, and Cambisols soil, and fewer gullies are located in lower part characterized by lower elevation, gentle slopes, and low vegetation coverage. Land use and land cover influence on susceptibility is significantly greater than other factors with a prediction rate of 33.9, especially farmland abandonment, while the occurrence of gullies is also more often on southwest-orientated slopes. Gully susceptibility highlighted that the study area affected by the very low, low, moderate, high, and very high susceptibilities to these gullies covered an area of about 16%, 23%, 32%, 26%, and 3% of the total basin respectively, which indicates 61% of the study area is susceptible to gully erosion. Moderate to high susceptibility is situated in the upper and middle part, consistent with the spatial distribution of gullies in the basin, and very high susceptibility (3%) is distributed in both the lower and upper parts of the basin. These results have important implications for soil loss control, land planning, and integrated watershed management in the mountainous areas of Southwest China.

Gully regulates snowmelt runoff, sediment and nutrient loss processes in Mollisols region of Northeast China.

Gully is a prominent indicator of land degradation in agroecosystems, functioning as a crucial pathway connecting upslopes to downstream channels. However, little is known about how gully regulates runoff, sediment, and nutrient loss processes in the catchment during snowmelt. In this study, we monitored these processes in situ at both the gully head (the upslope accumulated catchment of the gully head, CGH) and outlet of two representative and typical gully-dominated catchments (F1 and F2) during snowmelt in Mollisols region of Northeast China. Our results showed that runoff discharge of CGH and outlet exhibited a multi-peak trend during snowmelt, driven by the transition from snow melting to soil thawing. This transition resulted in distinct runoff patterns in both CGH and outlet, with significant differences in their response to air temperature. The total runoff yield of CGH accounted for 57.8 % in F1 and 40.6 % in F2 of the total runoff yield of the outlet. Notably, the peak sediment concentration displayed a marked lag compared to the peak runoff discharge, primarily dominated by the increased sensitivity of gully erosion after the thawing of gully slopes. Gully erosion was the main source of sediment yield in the catchment, contributing 98.2 % in F1 and 96.6 % in F2. Furthermore, nutrient concentrations exhibited a decreasing trend during snowmelt. The comparison of high nutrient concentrations in CGH and relatively low nutrient concentrations in outlet highlighted the gully's role in intercepting and diluting runoff nutrients. Hysteresis analysis confirmed the differential contribution of CGH and gully to nutrient sources. CGH accounting for 50.9 % and 93.3 % of runoff TN and runoff TP loss, while contributing only 8.3 % and 5.8 % to sediment TN and sediment TP loss, respectively. These findings offer valuable insights for effective erosion control and nonpoint source pollution management in gully-dominated agroecosystems during snowmelt.

Prioritising gully remediation in a Great Barrier Reef catchment: An approach using two independent methods of assessing erosion activity in 22,300 gullies.

The strategic reduction and remediation of degraded land is a global environmental priority. This is a particular priority in the Great Barrier Reef catchment area, Australia, where gully erosion a significant contributor to land degradation and water quality deterioration. Urgent action through the prioritisation and remediation of gully erosion sites is imperative to safeguard this UNESCO World Heritage site. In this study, we analyze a comprehensive dataset of 22,311 mapped gullies within a 3480 km2 portion of the lower Burdekin Basin, northeast Australia. Utilizing high-resolution lidar datasets, two independent methods - Minimum Contemporary Estimate (MCE) and Lifetime Average Estimate (LAE) - were developed to derive relative erosion rates. These methods, employing different data processing approaches and addressing different timeframes across the gully lifetime, yield erosion rates varying by up to several orders of magnitude. Despite some expected divergence, both methods exhibit strong, positive correlations with each other and additional validation data. There is a 43% agreement between the methods for the highest yielding 2% of gullies, although 80.5% of high-yielding gullies identified by either method are located within a 1 km proximity of each other. Importantly, distributions from both methods independently reveal that ∼80% of total volume of gully erosion in the study area is produced from only 20% of all gullies. Moreover, the top 2% of gullies generate 30% of the sediment loss and the majority of gullies do not significantly contribute to the overall catchment sediment yield. These results underscore the opportunity to achieve significant environmental outcomes through targeted gully management by prioritising a small cohort of high yielding gullies. Further insights and implications for management frameworks are discussed in the context of the characteristics of this cohort. Overall, this research provides a basis for informed decision-making in addressing gully erosion and advancing environmental conservation efforts.

Analyzing gully erosion and deposition patterns in loess tableland: Insights from small baseline subset interferometric synthetic aperture radar (SBAS InSAR).

The fragile Loess Plateau of China suffers substantial gully erosion. It is imperative to elucidate gully erosion patterns for implementing effective erosion control strategies. However, high spatiotemporal resolution quantification of gully dynamics remains limited across the Loess Plateau landscape. We utilized the small baseline subset interferometric synthetic aperture radar (SBAS InSAR) technique to investigate the phenomenon of gully erosion and deposition on the Dongzhiyuan tableland, which sits within the vast expanse of the Loess Plateau in China, over the period spanning 2020-2022. The tableland edges subsided while gully bottoms uplifted due to sedimentation. Low elevations underwent active deformation. Slope, aspect, and curvature modulated uplift and subsidence patterns by affecting runoff and sediment transport. Gentle downstream slopes displayed enhanced sedimentation. Southern gullies showed pronounced uplift compared to northern gullies. Heavy rainfall triggered extensive erosion followed by rapid uplift, reflecting an adaptive oscillation between erosion and deposition. Basin hydrology correlated with spatial patterns of deformation. Vegetation cover above 60 % of the maximum substantially increased InSAR error. Our study reveals intricate spatiotemporal behaviors of erosion and deposition in loess gullies using time-series InSAR. The findings provide new insights into gully geomorphology and evolution, and our study quantifies gully erosion and deposition patterns at high spatiotemporal resolution, enabling identification of the most vulnerable areas and prioritization of conservation efforts.

Interpretability of simple RNN and GRU deep learning models used to map land susceptibility to gully erosion.

Gully erosion possess a serious hazard to critical resources such as soil, water, and vegetation cover within watersheds. Therefore, spatial maps of gully erosion hazards can be instrumental in mitigating its negative consequences. Among the various methods used to explore and map gully erosion, advanced learning techniques, especially deep learning (DL) models, are highly capable of spatial mapping and can provide accurate predictions for generating spatial maps of gully erosion at different scales (e.g., local, regional, continental, and global). In this paper, we applied two DL models, namely a simple recurrent neural network (RNN) and a gated recurrent unit (GRU), to map land susceptibility to gully erosion in the Shamil-Minab plain, Hormozgan province, southern Iran. To address the inherent black box nature of DL models, we applied three novel interpretability methods consisting of SHaply Additive explanation (SHAP), ceteris paribus and partial dependence (CP-PD) profiles and permutation feature importance (PFI). Using the Boruta algorithm, we identified seven important features that control gully erosion: soil bulk density, clay content, elevation, land use type, vegetation cover, sand content, and silt content. These features, along with an inventory map of gully erosion (based on a 70 % training dataset and 30 % test dataset), were used to generate spatial maps of gully erosion using DL models. According to the Kolmogorov-Smirnov (KS) statistic performance assessment measure, the simple RNN model (with KS = 91.6) outperformed the GRU model (with KS = 66.6). Based on the results from the simple RNN model, 7.4 %, 14.5 %, 18.9 %, 31.2 % and 28 % of total area of the plain were classified as very-low, low, moderate, high and very-high hazard classes, respectively. According to SHAP plots, CP-PD profiles, and PFI measures, soil silt content, vegetation cover (NDVI) and land use type had the highest impact on the model's output. Overall, the DL modelling techniques and interpretation methods used in this study proved to be helpful in generating spatial maps of soil erosion hazard, especially gully erosion. Their interpretability can support watershed sustainable management.

Remote sensing and nuclear techniques for high-resolution mapping and quantification of gully erosion in the highly erodible area of the Malcanska River Basin, Eastern Serbia.

Gully erosion leads to the formation of deep and wide channels that increase the risk of soil loss, flooding, and water pollution. In addition, this process reduces the productivity and viability of agricultural land and natural ecosystems. Preventing gully erosion is critical for maintaining ecological balance and preserving natural resources in certain areas. This paper presents a methodology integrating remote sensing and nuclear techniques to study gully erosion. The morphometric characterization of gullies using 360-degree camera photogrammetry was introduced as a new method in erosion research. This approach aims to investigate the suitability of unmanned aerial vehicle and terrestrial photogrammetry for modeling gullies, to study the variability of erosion processes in gullies at a small scale, and to compare the differences in erosion intensity between nearby gullies. The study's objectives include identifying the effective and economical method for gullies monitoring and providing a starting point for controlling and safeguarding gullies. Mainly erosion process was detected in the studied gullies, while deposition was identified at only 2 out of 39 sampling locations. The results showed an average soil redistribution rate of 16.2 t ha-1 yr-1 and coefficients of variation of 32%, 59%, and 91% for three investigated gullies. It was determined that aerial photogrammetry methods were not practical under the conditions prevailing in the study area. Highly detailed 3D models of the gullies were created using 360-degree photogrammetry. It was confirmed that the micro-relief obtained by photogrammetric modeling is an essential contribution to erosion research. The 360-degree camera photogrammetry serves as a reliable tool for analyzing the morphology of gullies and, in perspective, tracking changes in gully systems over time or monitoring the effectiveness of the applied protection measures.

Gully erosion mapping based on hydro-geomorphometric factors and geographic information system.

Delineation of areas susceptible to gully erosion with high accuracy and low cost using significant factors and statistical model is essential. In the present study, a gully susceptibility erosion map (GEM) was developed using hydro-geomorphometric parameters and geographic information system in western Iran. For this aim, a geographically weighted regression (GWR) model was applied, and its results compared to frequency ratio (FreqR) and logistic regression (LogR) models. Almost twenty effective parameters on gully erosion were detected and mapped in the ArcGIS®10.7 environment. These layers and gully inventory maps (375 gully locations) were prepared using aerial photographs, Google Earth images, and field surveys divided into 70% and 30% (263 and 112 samples) ArcGIS®10.7. The GWR, FreqR, and LogR models were developed to generate gully erosion susceptibility maps. The area under the receiver/relative operating characteristic curve (AUC-ROC) was calculated to validate the generated maps. Based on the LogR model results, soil type (SOT), rock unit (RUN), slope aspect (SLA), Altitude (ALT), annual average precipitation (AAP), morphometric position index (MPI), terrain surface convexity (TSC), and land use (LLC) factors were the most critical conditioning parameters, respectively. The AUC-ROC results show the accuracy of 84.5%, 79.1%, and 78% for GWR, LogR, and FreqR models, respectively. The results show high performance for the GWR compared to LogR and FreqR multivariate and bivariate statistic models. The application of hydro-geomorphological parameters has a significant role in the gully erosion susceptibility zonation. The suggested algorithm can be used for natural hazards and human-made disasters such a gully erosion on a regional scale.

A data driven gully head susceptibility map of Africa at 30 m resolution.

Predicting gully erosion at the continental scale is challenging with current generation models. Moreover, datasets reflecting gully erosion processes are still rather scarce, especially in Africa. This study aims to bridge this gap by collecting an extensive dataset and developing a robust, empirical model that predicts gully head density at high resolution for the African continent. We developed a logistic probability model at 30 m resolution that predicts the likelihood of gully head occurrence using currently available GIS data sources. To calibrate and validate this model, we used a new database of 31,531 gully heads, mapped over 1216 sites across Africa. The exact location of all gully heads was manually mapped by trained experts using high-resolution imagery available from Google Earth. This allowed the extraction of detailed information at the gully head scale, such as the local soil surface slope. Variables included in our empirical model are topography, climate, vegetation, soil characteristics and tectonic context. They are consistent with our current process-based understanding of gully formation and evolution. The model shows that gully occurrences mainly depend on slope steepness, soil texture and vegetation cover and to a lesser extent on rainfall intensity and tectonic activity. The combination of these factors allows for robust and fairly reliable predictions of gully head occurrences, with Areas Under the Curve for validation around 0.8. Based on these results, we present the first gully head susceptibility map for Africa at a 30 m resolution.

Optimizing machine learning algorithms for spatial prediction of gully erosion susceptibility with four training scenarios.

Gully erosion causes high soil erosion rates and is an environmental concern posing major risk to the sustainability of cultivated areas of the world. Gullies modify the land, shape new landforms, and damage agricultural fields. Gully erosion mapping is essential to understand the mechanism, development, and evolution of gullies. In this work, a new modeling approach was employed for gully erosion susceptibility mapping (GESM) in the Golestan Dam basin of Iran. The measurements of 14 gully erosion (GE) factors at 1042 GE locations were compiled in a spatial database. Four training datasets comprised of 100%, 75%, 50%, and 25% of the entire database were used for modeling and validation (for each data set in the common 70:30 ratio). Four machine learning models-maximum entropy (MaxEnt), general linear model (GLM), support vector machine (SVM), and artificial neural network (ANN)- were employed to check the usefulness of the four training scenarios. The results of random forest (RF) analysis indicated that the most important GE effective factors were distance from the stream, elevation, distance from the road, and vertical distance of the channel network (VDCN). The receiver operating characteristic (ROC) was used to validate the results. Our study showed that the sample size influenced the performance of the four machine learning algorithms. However, the ANN had a lower sensitivity to the reduction of sample size. In addition, validation results revealed that ANN (AUROC = 0.85.7-0.90.4%) had the best performance based on all four sample data sets. The results of this research can be useful and valuable guidelines for choosing machine learning methods when a complete gully inventory is not available in a region.

Gully erosion prediction method from geoenvironmental data and supervised machine learning techniques.

Predictive models are statistical representations that indicate, based on the historical data analysis, the probability of triggering a given phenomenon in the future. In geosciences, such models have been essential to predict the occurrence of adverse phenomena commonly associated with environmental disasters, such as gully erosion. Therefore, this paper presents a method for producing gully erosion predictive models based on geoenvironmental data and machine learning techniques. The method's effectiveness test was produced in a region of approximately 40,000 km² in southeastern Brazil and compared the predictive performance of four models designed with different machine learning algorithms. The results demonstrated that the technique is capable of producing models with high predictive ability, with emphasis on the random forest algorithm, which, in addition to having achieved the highest levels of accuracy, also produced highly realistic maps for the study area.•The method is straightforward and may be applied to predict other geological processes.•The application of the method does not require knowledge of programming language.•The models produced achieved high predictive performance.

Gully erosion vulnerability modelling, estimation of soil loss and assessment of gully morphology: a study from cratonic part of eastern India.

A highly visible form of soil erosion is gully, a significant geomorphological feature, resulting from water erosion and causing land degradation and deterioration. In arid and semi-arid environment, gully erosion is conceived as an important source of sediment supply washing out the top fertile soil and exposing lower soil layers. The present study is conducted on the lateritic terrain of Rupai watershed of eastern plateau fringe of India, where water erosion is a serious concern. In order to prepare a gully erosion vulnerability mapping, the analytical hierarchy process (AHP) model coupled with geospatial technology is adopted taking into account thirteen bio-physical factors. It is revealed that around 49% area of the watershed belongs to high to very high gully erosion vulnerability zone (GEVZ) followed by moderate risk zone of 31.64%. This model is validated performing an accuracy assessment, which is calculated to be 90.91%, and the value of Kappa co-efficient is 0.86. It is imperative to estimate the average annual soil loss alongside of delineating GEVZ; thus, the revised universal soil loss equation (RUSLE) model is used with geospatial technology. It unveils that the average estimated soil loss of the watershed varies from < 15 to 431 t ha-1 y-1. Around 29% of the study area experiences high to very high (57 to > 147 t ha-1 y-1) soil erosion risk, where 68% area endures low level of soil erosion risk (< 15 t ha-1 y-1). The study of gully morphology depicts gully depth ranging from < 1 to 5 m (small to medium gully) with V and U shapes. Results obtained from this study may help in planning and management of land use and soil erosion conservation.

An experimental investigation of the erosion process and morphological characteristics of the tile-back type slope with non-uniform slopes based on a 3D reconstruction method.

Tile-back type slopes comprise ephemeral gullies (EGs) and hillslopes; they are a unique and widely distributed micro-landform in the Loess Plateau region of China. Gully erosion from these landforms is a serious issue, but the micro-landform makes the erosion process and its estimation complex. Quantifying soil erosion processes and their distribution characteristics at different positions on tile-back type slopes will provide a clearer picture for ecological restoration to control further soil degradation. This study investigated the erosion process of tile-back type slope with non-uniform slopes using a 3D photo-reconstruction method during eight successive simulated rainfall events. The results showed that EG erosion began with a chain of intermittent headcuts. When the accumulated rainfall reached 76 mm, serious collapses dramatically increased the amount of sediment by 216% after the first rainfall (cumulative rainfall was about 15 mm). We quantified the sediment contribution of EG erosion (46.20%), rill erosion (35.62%), and inter-rill erosion (18.18%) to total soil loss. The erosion area of the steep slope section and extremely steep slope section accounted for 33.26% and 66.74% of the total erosion area, respectively. Moreover, sediment amounts significantly correlated with morphological parameters, particularly the amount of EG erosion and maximum gully depth, with a correlation coefficient of 0.98. Cumulative gully length and erosion area had the greatest effect on rill erosion, with a correlation coefficient of 0.97. These results provide insight into the qualitative and quantitative understanding of EG erosion process on Loess Plateau of China and an important reference for the rational arrangement of EG control measures.

Influence of Topographic Factors on the Characteristics of Gully Systems in Mountainous Areas of Ningnan Dry-Hot Valley, SW China.

A gully system is an important indicator that reflects the development of regional topography and landforms, and topography is one of the most important factors affecting the development of gullies. However, at present, research on the impact of topography on the development of gully systems in the mountainous area of Ningnan dry-hot valley still needs to be strengthened. In order to study the characteristics of gullies and the influence of topography on the development of gully systems, based on both the visual interpretation of remote sensing images and field investigations, five topographic factors (elevation, slope gradient, aspect, relief, and dissection) were employed and three gully erosion indexes (gully length, density, and frequency) were calculated. The geographical information system was used in this study to carry out the spatial analysis, Ward's hierarchical clustering and correlation analysis. Results showed that the development of gully systems is greatly affected by the degree of relief and dissection, and there is a significant positive correlation (p < 0.01; p < 0.05), while elevation, slope gradient and aspect have little influence on it. Analysis of the gully systems showed that the gully erosion is the most intense in the area with an elevation of 2800−3200 m and slope gradients ≥ 38°. Furthermore, the degree of erosion on shady slopes was greater than that on sunny slopes. These results will help us to understand the spatial distribution and formation of gully systems in mountainous areas.

Identifying sensitivity of factor cluster based gully erosion susceptibility models.

The present study has attempted to address the issue of sensitivity of different clusters of factors towards gully erosion in the Mayurakshi river basin. Firstly, the gully erosion susceptibility of the basin area has been mapped by integrating using 18 parameters divided into four factor-cluster, viz. erodibility, erosivity, resistance, and topographical cluster, with the help of four machine learning (ML) models such as random forest (RF), gradient boost (GBM), extreme gradient boost (XGB), and support vector machine (SVM). Results show that almost 20% and 25% of the upper catchment of the basin belongs to extreme and high gully erosion susceptibility. Among the applied algorithms, RF is appeared as the best performing model. The spatial association of factor cluster-based models with the final susceptibility model is found the highest for the erosivity cluster, followed by the erodibility cluster. From the sensitivity analysis, it becomes clear that geology and soil texture are dominant contributing factors to gully erosion susceptibility. The geological formation of unclassified granite gneiss and geomorphological formation of denudational origin pediment-pediplain complex is dominant over the entire upper catchment of the basin, and therefore, can be considered regional factors of importance. Since the study has figured out the different grades of susceptible areas with dominant factors and factor cluster, it would be useful for devising planning for gully erosion check measures. From economic particularly food security purpose, it is very essential since it is concerned with precious soil loss and negative effects on agriculture.

A Multi-Criteria Framework for Identification of Gully Developmental Stages Based on UAV Data-A Case Study in Yuanmou County, Yunnan Province, SW China.

Gully erosion is a common form of soil erosion in dry-hot valleys, and it often brings serious land degradation. A multi-criteria method integrating the characteristics of the longitudinal profile (LP), the cross profile (CP) and the knickpoints of gullies was applied to identify the development stage of gullies in Yuanmou County, Yunnan Province, in southwestern China. Firstly, based on the high-resolution data sources produced by an unmanned aerial vehicle (UAV), 50 gullies were selected as the typical ones in Tutujiliangzi and Shadi village. The LPs were extracted, and their morphological indices, information entropy and fitting functions were calculated. The morphological characteristics of the CPs and the presence or absence of knickpoints were recorded. The results show that the period of the gullies in Tutujiliangzi and Shadi is dominated by the deep incision period and the equilibrium adjustment period, which means that most gullies are in the period of the severe erosion stage. Among the gullies, 13 LPs' morphological index is between 0.636 and 0.933, and the morphology of the LP presents an upward convex shape; the cross profiles are mainly V-shaped and U-shaped. Thirty-two LPs' morphological index is between 1.005~2.384, which presents a slightly concave shape; the cross profiles are mainly repeated U-shapes. The remaining five LPs have a morphological index of 0.592, 0.462, 1.061, 1.344 and 0.888, respectively; the LPs of upstream and downstream are different. The LPs of the Tutujiliangzi gullies are nearly straight lines and slightly concave, while those of the Shadi village gullies are convex and nearly straight lines. The knickpoints and step-pools in Shadi village are more developed, while the gullies in Tutujiliangzi develop more rapidly. This study shows that in counties with similar conditions, these conditions such as temperature and precipitation, local topographic changes, soil properties and vegetation conditions have obvious effects on the development of gullies.

Understanding land degradation induced by gully erosion from the perspective of different geoenvironmental factors.

Complex interrelationships between landscape-level geoenvironmental factors and natural phenomena have rendered land degradation control measures ineffective. For control to be effective, this study argues that the interactions between different geoenvironmental factors and gully erosion (as an indicator of land degradation) should be more fully investigated and spatially mapped. To do so, gully locations of the Konduran watershed, Iran, were detected in the field and modeled in response to seventeen geoenvironmental factors using three machine learning methods, i.e., multivariate adaptive regression splines (MARS), random forest (RF), regularized random forest (RRF), and Bayesian generalized linear model (Bayesian GLM). The models' performance was validated, the relationship of gully occurrence with each factor was quantified, the probability of gully erosion (i.e., land degradation) was retrospectively estimated, and the spatially explicit maps of land degradation susceptibility were produced. Based on the area under the receiver operating characteristic curve (AUC), the RRF and MARS models with AUC = 0.98 achieved the greatest goodness-of-fit with the training dataset, whereas the RF model with AUC = 0.83 showed the greatest ability in predicting future gully occurrences. Further scrutinization using the sensitivity and specificity metrics demonstrated the efficiency of the RF model for correctly classifying the gully (sensitivity-training = 92%; sensitivity-validation = 90%) and non-gully (specificity-training = 95%; specificity-validation = 68%) pixels. Nearly 13% of the study area ended up being the hardest hit region due to their general characteristics of distance from roads and rives, altitude, and normalized difference vegetation index (NDVI) that were identified as the most influential factors in gully erosion occurrence. Given the resolution quality and reliable predictive accuracy, our spatially explicit maps of land susceptibility to gully erosion can be used by authorities and urban planners for identifying the target areas for rehabilitation and making more informed decisions for infrastructure development. Although our study was strictly focused on a certain region, our recommendations and implications are of global significance.

Modelled estimates of fine sediment and particulate nutrients delivered from the Great Barrier Reef catchments.

The eWater Source modelling framework has been modified to support the Great Barrier Reef (GBR) Dynamic SedNet catchment modelling concept, which is used to simulate fine sediment and particulate nutrient generation, loss, and transport processes across GBR catchments. Catchment scale monitored data sets are used to calibrate and evaluate models. Model performance is assessed qualitatively and quantitatively. Modelling predicts that approximately half of generated sediment is delivered to the GBR lagoon; the remainder is deposited on floodplains, trapped in reservoirs or lost through other minor processes (e.g. irrigation extractions). Gullies are the major source of sediment, with comparable contributions from hillslopes and streambanks. Hillslope sources are considered the major source of particulate nutrients across the GBR catchments. We demonstrate that using locally developed, customised models coupled with a complementary monitoring program can produce credible modelled estimates of pollutant loads and provide a platform for testing catchment scale assumptions and scenarios.

May agricultural terraces induce gully erosion? A case study from the Black Soil Region of Northeast China.

Terracing of hillslopes is usually regarded as an effective measure to control soil erosion. Although it is often stressed that proper terrace construction and regular terrace maintenance are of great significance to prevent erosion on terraced hillslopes, examples of terrace-induced gully erosion are scarce. Field observations on terraced and partly abandoned hillslopes in the Black Soil Region of Northeast China, a region heavily affected by gully erosion since the middle of the 20th century, indicated that gully formation might be caused by terraces. In order to understand the impact of terracing on gully erosion, we selected several gullies to investigate the cause and timing of their triggering. We used a combination of field mapping, high-resolution digital terrain models, multi-temporal aerial photograph interpretation and interviews with local farmers. Our results showed that several gullies developed after terracing. Improper terrace design caused runoff concentration along terraces and ridges with mean inclination of 3.8%, which resulted in gully incision due to overtopping of terraces at low spots or due to the uncontrolled release of concentrated flow to adjoining unterraced hillslopes. The same processes are responsible for the persistent gully activity after abandonment and vegetation recovery. Furthermore, we showed how terraces affected gully morphology. Finally, we suggested appropriate countermeasures to stop further soil loss and land degradation on abandoned terraced hillslopes in NE China. Our findings are important as they demonstrate how poorly designed terraces may not only be ineffective but may even aggravate gully erosion.

Novel Ensemble Approach of Deep Learning Neural Network (DLNN) Model and Particle Swarm Optimization (PSO) Algorithm for Prediction of Gully Erosion Susceptibility.

This study aims to evaluate a new approach in modeling gully erosion susceptibility (GES) based on a deep learning neural network (DLNN) model and an ensemble particle swarm optimization (PSO) algorithm with DLNN (PSO-DLNN), comparing these approaches with common artificial neural network (ANN) and support vector machine (SVM) models in Shirahan watershed, Iran. For this purpose, 13 independent variables affecting GES in the study area, namely, altitude, slope, aspect, plan curvature, profile curvature, drainage density, distance from a river, land use, soil, lithology, rainfall, stream power index (SPI), and topographic wetness index (TWI), were prepared. A total of 132 gully erosion locations were identified during field visits. To implement the proposed model, the dataset was divided into the two categories of training (70%) and testing (30%). The results indicate that the area under the curve (AUC) value from receiver operating characteristic (ROC) considering the testing datasets of PSO-DLNN is 0.89, which indicates superb accuracy. The rest of the models are associated with optimal accuracy and have similar results to the PSO-DLNN model; the AUC values from ROC of DLNN, SVM, and ANN for the testing datasets are 0.87, 0.85, and 0.84, respectively. The efficiency of the proposed model in terms of prediction of GES was increased. Therefore, it can be concluded that the DLNN model and its ensemble with the PSO algorithm can be used as a novel and practical method to predict gully erosion susceptibility, which can help planners and managers to manage and reduce the risk of this phenomenon.