RTSEvo v1.0: a retrogressive thaw slump evolution model

Abstract. Widespread thermal degradation in permafrost regions is accelerating the development of retrogressive thaw slumps (RTS), which threaten ecological stability and infrastructure. Existing RTS modeling studies, however, are largely confined to static susceptibility mapping, lacking the capacity to predict their spatiotemporal evolution. To bridge this gap, we developed a new dynamic RTS evolution model (RTSEvo) that couples three modules: (1) a time-series forecast of regional RTS area, (2) a machine-learning module for pixel-level probability mapping, and (3) a constrained spatial allocation module that simulates RTS expansion by integrating neighborhood effects, stochasticity, and a novel retrogressive erosion factor. Validated using 2021 and 2022 manually interpreted RTS maps of the Beiluhe Basin, the model successfully simulated RTS growth, with the Logistic Regression-based model showing superior stability and accuracy. An interesting finding is that predictive skill is significantly enhanced by integrating process-based rules with statistical probability. The inclusion of a novel retrogressive erosion factor, which mechanistically simulates headwall retreat, proved critical, improving model performance by over 29.3% as measured by the Figure of Merit. The primary innovation of this study is the successful realization of a regional-scale dynamic simulation and prediction of RTS. This model offers a more robust scientific tool for RTS-related risk mitigation strategies.