Bastian Steinhoff-Knopp

Soil erosion is one of the main threats to agricultural productivity and environmental sustainability worldwide. Detailed and consistent field data on erosion features are essential for a better understanding of erosion processes, identifying driving factors and supporting the development and evaluation of suitable soil erosion mitigation strategies and soil erosion prediction tools. Existing digital mapping solutions are often limited in terms of standardisation, flexibility and ease of use. The Qfield plugin EroMapper is a new open-source tool designed to support standardised and efficient field mapping of soil erosion features by water erosion. The plugin provides a modular, tool-based workflow for recording linear, sheet and combined erosion features, as well as soil material depositions, overland water flow and land management practices. The observations are easy to map and stored in a predefined GeoPackage structure, ensuring consistency between field data collection and subsequent analyses. An accompanying Python-based post-processing script systematically derives key parameters, such as affected area, erosion or deposition volume, mass and average depth of linear erosion features. Mapped features can be linked to geospatial parcel geometries for aggregation. The workflow enables reproducible data processing and assigns unique identifiers to all mapped features. Overall, the plugin workflow provides a robust and flexible solution for long-term field monitoring of soil erosion by water, the documentation of erosion events and supports further analysis and modelling applications.

Modelling soil erosion by water is essential for developing effective mitigation strategies and preventing on- and off-site damages in agricultural areas. So far, complex artificial neural networks have rarely been applied in small-scale soil erosion modelling, and their potential still remains unclear. This study compares the performance of different neural network architectures for modelling soil erosion by water at a small spatial scale in agricultural cropland. The analysis was based on erosion rate data (in t ha⁻¹ yr⁻¹) at a 5 m × 5 m resolution, derived from a 20-year monitoring programme, and covers 458 ha of cropland across seven investigation areas in northern Germany. Nineteen predictor variables related to topography, climate, management, and soil properties were selected as inputs to assess their interrelationships with observed erosion patterns. A single-layer neural network (SNN), a deep neural network (DNN), and a convolutional neural network (CNN) were applied and evaluated against a random forest (RF) model used as a benchmark. A leave-one-area-out validation was applied to evaluate how well the models generalize to areas withheld entirely during training. While all models tended to underestimate high erosion rates, they often successfully captured the underlying spatial patterns. All tested models exhibited comparable root mean squared errors (RMSE: 2.2 t ha⁻¹ yr⁻¹). With respect to mean absolute error (MAE), the neural network models achieved slightly lower values (MAE: 0.9 t ha⁻¹ yr⁻¹) than the random forest model (MAE: 1.0 t ha⁻¹ yr⁻¹). Clearer differences between models were observed for the F₁ scores, which reflect performance across soil loss classes. Here, the CNN achieved the highest F₁ score (0.46) among the tested models. This study demonstrates the potential of complex neural networks to capture erosion patterns at the field-to-landscape scale and provides insights into the relevance of the chosen predictor variables, as well as key modelling limitations, such as the underestimation of very high erosion rates in unseen areas. It also highlights the need for more comprehensive datasets to improve generalization capabilities of the models.

Accurately modelling soil erosion by water is essential for developing effective mitigation strategies and preventing on- and off-site damages in agricultural areas. So far, complex artificial neural networks have rarely been applied in small-scale soil erosion modelling, and their potential still remains unclear. This study compares the performance of different neural network architectures for modelling soil erosion by water at a small spatial scale in agricultural cropland. The analysis is based on erosion rate data at a 5 m × 5 m resolution, derived from a 20-year monitoring programme, and covers 458 hectares of cropland across six investigation areas in northern Germany. Nineteen predictor variables related to topography, climate, management and soil properties were selected as inputs to assess their interrelationships with observed erosion patterns and to predict continuous soil erosion rates. A single-layer neural network (SNN), a deep neural network (DNN), and a convolutional neural network (CNN) were applied and evaluated against a random forest (RF) model used as a benchmark. All machine learning models have successfully captured spatial patterns of soil erosion, with the CNN consistently outperforming the others across all evaluation metrics. The CNN achieves the lowest root mean squared error (RMSE: 1.05) and mean absolute error (MAE: 0.41), outperforming the RF (RMSE: 1.31, MAE: 0.58) and the SNN (RMSE: 1.48, MAE: 0.63), while the DNN performs similarly to the CNN with a slightly higher RMSE (1.1) and MAE (0.45). The CNN notably outperforms the other three approaches when evaluating their capability to accurately predict soil erosion within given classes, achieving a weighted mean F1 score of 0.7. A permutation importance analysis identified the digital elevation model as the most influential predictor variable across all models, contributing between 15 % and 18.3 %, while USLE C and R factors also had significant importance. Overall, these findings highlight the potential of complex neural networks for predicting spatially explicit rates of soil erosion by water.

Accurately modelling soil erosion by water is essential for developing effective mitigation strategies and preventing on- and off-site damages in agricultural areas. So far, complex artificial neural networks have rarely been applied in small-scale soil erosion modelling, and their potential still remains unclear. This study compares the performance of different neural network architectures for modelling soil erosion by water at a small spatial scale in agricultural cropland. The analysis is based on erosion rate data at a 5 m × 5 m resolution, derived from a 20-year monitoring programme, and covers 458 hectares of cropland across six investigation areas in northern Germany. Nineteen predictor variables related to topography, climate, management and soil properties were selected as inputs to assess their interrelationships with observed erosion patterns and to predict continuous soil erosion rates. A single-layer neural network (SNN), a deep neural network (DNN), and a convolutional neural network (CNN) were applied and evaluated against a random forest (RF) model used as a benchmark. All machine learning models have successfully captured spatial patterns of soil erosion, with the CNN consistently outperforming the others across all evaluation metrics. The CNN achieves the lowest root mean squared error (RMSE: 1.05) and mean absolute error (MAE: 0.41), outperforming the RF (RMSE: 1.31, MAE: 0.58) and the SNN (RMSE: 1.48, MAE: 0.63), while the DNN performs similarly to the CNN with a slightly higher RMSE (1.1) and MAE (0.45). The CNN notably outperforms the other three approaches when evaluating their capability to accurately predict soil erosion within given classes, achieving a weighted mean F1 score of 0.7. A permutation importance analysis identified the digital elevation model as the most influential predictor variable across all models, contributing between 15 % and 18.3 %, while USLE C and R factors also had significant importance. Overall, these findings highlight the potential of complex neural networks for predicting spatially explicit rates of soil erosion by water.

Accurately modelling soil erosion by water is essential for developing effective mitigation strategies and preventing on- and off-site damages in agricultural areas. So far, complex artificial neural networks have rarely been applied in small-scale soil erosion modelling, and their potential still remains unclear. This study compares the performance of different neural network architectures for modelling soil erosion by water at a small spatial scale in agricultural cropland. The analysis is based on erosion rate data at a 5 m × 5 m resolution, derived from a 20-year monitoring programme, and covers 458 hectares of cropland across six investigation areas in northern Germany. Nineteen predictor variables related to topography, climate, management and soil properties were selected as inputs to assess their interrelationships with observed erosion patterns and to predict continuous soil erosion rates. A single-layer neural network (SNN), a deep neural network (DNN), and a convolutional neural network (CNN) were applied and evaluated against a random forest (RF) model used as a benchmark. All machine learning models have successfully captured spatial patterns of soil erosion, with the CNN consistently outperforming the others across all evaluation metrics. The CNN achieves the lowest root mean squared error (RMSE: 1.05) and mean absolute error (MAE: 0.41), outperforming the RF (RMSE: 1.31, MAE: 0.58) and the SNN (RMSE: 1.48, MAE: 0.63), while the DNN performs similarly to the CNN with a slightly higher RMSE (1.1) and MAE (0.45). The CNN notably outperforms the other three approaches when evaluating their capability to accurately predict soil erosion within given classes, achieving a weighted mean F1 score of 0.7. A permutation importance analysis identified the digital elevation model as the most influential predictor variable across all models, contributing between 15 % and 18.3 %, while USLE C and R factors also had significant importance. Overall, these findings highlight the potential of complex neural networks for predicting spatially explicit rates of soil erosion by water.

Accurately modelling soil erosion by water is essential for developing effective mitigation strategies and preventing on- and off-site damages in agricultural areas. So far, complex artificial neural networks have rarely been applied in small-scale soil erosion modelling, and their potential still remains unclear. This study compares the performance of different neural network architectures for modelling soil erosion by water at a small spatial scale in agricultural cropland. The analysis is based on erosion rate data at a 5 m × 5 m resolution, derived from a 20-year monitoring programme, and covers 458 hectares of cropland across six investigation areas in northern Germany. Nineteen predictor variables related to topography, climate, management and soil properties were selected as inputs to assess their interrelationships with observed erosion patterns and to predict continuous soil erosion rates. A single-layer neural network (SNN), a deep neural network (DNN), and a convolutional neural network (CNN) were applied and evaluated against a random forest (RF) model used as a benchmark. All machine learning models have successfully captured spatial patterns of soil erosion, with the CNN consistently outperforming the others across all evaluation metrics. The CNN achieves the lowest root mean squared error (RMSE: 1.05) and mean absolute error (MAE: 0.41), outperforming the RF (RMSE: 1.31, MAE: 0.58) and the SNN (RMSE: 1.48, MAE: 0.63), while the DNN performs similarly to the CNN with a slightly higher RMSE (1.1) and MAE (0.45). The CNN notably outperforms the other three approaches when evaluating their capability to accurately predict soil erosion within given classes, achieving a weighted mean F1 score of 0.7. A permutation importance analysis identified the digital elevation model as the most influential predictor variable across all models, contributing between 15 % and 18.3 %, while USLE C and R factors also had significant importance. Overall, these findings highlight the potential of complex neural networks for predicting spatially explicit rates of soil erosion by water.

Accurately modelling soil erosion by water is essential for developing effective mitigation strategies and preventing on- and off-site damages in agricultural areas. So far, complex artificial neural networks have rarely been applied in small-scale soil erosion modelling, and their potential still remains unclear. This study compares the performance of different neural network architectures for modelling soil erosion by water at a small spatial scale in agricultural cropland. The analysis is based on erosion rate data at a 5 m × 5 m resolution, derived from a 20-year monitoring programme, and covers 458 hectares of cropland across six investigation areas in northern Germany. Nineteen predictor variables related to topography, climate, management and soil properties were selected as inputs to assess their interrelationships with observed erosion patterns and to predict continuous soil erosion rates. A single-layer neural network (SNN), a deep neural network (DNN), and a convolutional neural network (CNN) were applied and evaluated against a random forest (RF) model used as a benchmark. All machine learning models have successfully captured spatial patterns of soil erosion, with the CNN consistently outperforming the others across all evaluation metrics. The CNN achieves the lowest root mean squared error (RMSE: 1.05) and mean absolute error (MAE: 0.41), outperforming the RF (RMSE: 1.31, MAE: 0.58) and the SNN (RMSE: 1.48, MAE: 0.63), while the DNN performs similarly to the CNN with a slightly higher RMSE (1.1) and MAE (0.45). The CNN notably outperforms the other three approaches when evaluating their capability to accurately predict soil erosion within given classes, achieving a weighted mean F1 score of 0.7. A permutation importance analysis identified the digital elevation model as the most influential predictor variable across all models, contributing between 15 % and 18.3 %, while USLE C and R factors also had significant importance. Overall, these findings highlight the potential of complex neural networks for predicting spatially explicit rates of soil erosion by water.

Recent studies show that machine learning methods (ML) have a high potential to model various soil erosion processes. The main focus of this research is on qualitative modelling (risk classes, binary occurrence) on smaller scales e.g., probability maps for gully erosion. In this study, we used four machine learning methods to reproduce spatial explicit information on soil loss rates in a 5 m resolution obtained in the Lower Saxonian (Germany) soil erosion monitoring program in the years 2000 - 2020. The monitoring data includes information on soil loss by water erosion (sheet and rill erosion) on 465 ha of cropland in northern Germany derived by continuous erosion feature mapping after erosive rainfall events (see Steinhoff-Knopp & Burkhard (2018) for methods and results). We applied the ML methods Random Forest (RF), a Single-Layer Neural Network (SLNN), a Deep Neural Network with multiple hidden layers (DNN) and a Convolutional Neural Network (CNN) to reproduce the mapped soil loss rates. Prediction variables included are up to 19 soil, land use, rainfall and DEM-derived topographic parameters. All ML methods were able to reproduce the soil erosion patterns. The comparison between the different models shows that the CNN model outperforms all other tested models in nearly all metrics. Its RMSE of 1.05 and MAE of 0.41 are significantly lower than those of the RF (RMSE: 1.31, MAE: 0.58) and SLNN (RMSE: 1.48, MAE: 0.63). Only the DNN performs similarly, with a slightly higher RMSE of 1.1 and MAE of 0.58. However, the classification performance of the RF, DNN, and CNN models is comparable, with F1 scores ranging from 0.68 to 0.70 and AUC values between 0.92 and 0.94. Additionally, the permutation importance was calculated to assess the influence of the predictor variables. In all four models, the variable with the highest importance is the DEM. Its importance ranges from 15% to 18.3%, depending on the model. All models also strongly rely on USLE C and R factors. Our findings emphasize the high potential of ML-driven erosion predictions and will be rolled out to predict soil erosion rates on cropland in northern Germany.Steinhoff-Knopp, B. and Burkhard, B.: Soil erosion by water in Northern Germany: long-term monitoring results from Lower Saxony, CATENA, 165, 299–309, https://doi.org/10.1016/j.catena.2018.02.017, 2018.

Soil compaction and soil erosion by water are among the top 5 threats to agricultural soils in Europe. Soil compaction has a direct impact on soil erosion, for instance by reducing infiltration rates. Therefore, measures directly addressing soil compaction (e.g. optimized field traffic and reduced wheel load) have an impact on soil erosion by water. In addition, measures such as crop rotation management, including cover crop management, allow combined effects on soil erosion and soil compaction. Currently, no evidence at regional scale is available that indicates which measures can generate this co-benefit and which regions having a high risk of soil erosion and compaction can benefit from those measures. Modelling exercises provide the option for generating this information and are tested here in a regional scale case study.As a first step, we identified cropland with a combined risk of soil compaction and soil erosion by water in Lower Saxony (northern Germany). To this end, we derived typical crop rotations for 2017 to 2021 based on high-resolution crop type maps for three soil regions in the study area. Depending on the crop rotations and farm size, typical machinery equipment was defined and field work dates were derived according to phenological data. This data was combined with three weather scenarios using real observational data (dry: 2020, wet: 2017, intermediate: 2004). We employed the USLE (Universal Soil Loss Equation) and the SaSCiA-model (Spatially explicit Soil Compaction risk Assessment) to model soil erosion and soil compaction risk for the different weather scenarios and the three typical crop rotations in the soil regions. The results help to identify regions with combined risk for soil erosion and soil compaction. The next step will be the analysis of measures addressing both degradation processes.