In the context of global warming, landscapes with ice-rich permafrost, such as the Qinghai-Tibet Plateau (QTP), are highly vulnerable. The expansion of thermokarst lakes erodes the surrounding land, leading to collapses of various scales and posing a threat to nearby infrastructure and the environment. Assessing the susceptibility of thermokarst lakes in remote, data-scarce areas remains a challenging task. In this study, Landsat imagery and human-computer interaction were employed to improve the accuracy of thermokarst lake classification. The study also identified the key factors influencing the occurrence of thermokarst lakes, including the lake density, soil moisture (SM), slope, vegetation, snow cover, ground temperature, precipitation, and permafrost stability (PS). The results indicate that the most susceptible areas cover 19.02% of the QTP's permafrost region, primarily located in southwestern Qinghai, northeastern Tibet, and the Hoh Xil region. This study provides a framework for mapping the spatial distribution of thermokarst lakes and contributes to understanding the impact of climate change on the QTP.

Classifying a given landscape on the basis of its susceptibility to surface processes is a standard procedure in low to mid-latitudes. Conversely, these procedures have hardly been explored in periglacial regions. However, global warming is radically changing this situation and will change it even more in the future. For this reason, un-derstanding the spatial and temporal dynamics of geomorphological processes in peri-arctic environments can be crucial to make informed decisions in such unstable environments and shed light on what changes may follow at lower latitudes. For this reason, here we explored the use of data-driven models capable of recognizing locations prone to develop retrogressive thaw slumps (RTSs) and/or active layer detachments (ALDs). These are cryo-spheric hazards induced by permafrost degradation, and their development can negatively affect human set-tlements or infrastructure, change the sediment budget and release greenhouse gases. Specifically, we test a binomial Generalized Additive Modeling structure to estimate the probability of RST and ALD occurrences in the North sector of the Alaskan territory. The results we obtain show that our binary classifiers can accurately recognize locations prone to RTS and ALD, in a number of goodness-of-fit (AUCRTS = 0.83; AUCALD = 0.86), random cross-validation (mean AUCRTS = 0.82; mean AUCALD = 0.86), and spatial cross-validation (mean AUCRTS = 0.74; mean AUCALD = 0.80) routines. Overall, our analytical protocol has been implemented to build an open-source tool scripted in Python where all the operational steps are automatized for anyone to replicate the same experiment. Our protocol allows one to access cloud-stored information, pre-process it, and download it locally to be integrated for spatial predictive purposes.