Abstract. 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.
Barthel et al. (Mon,) studied this question.