Xiaoying Li

Climate warming and increasingly frequent hydroclimatic extremes are altering snowfall regimes and snow cover dynamics, with important implications for frozen‐ground stability. Yet the combined effects of snow cover and environmental controls on ground thermal conditions remain poorly constrained. Using meteorological observations and remote sensing data during 2005–2024, we applied a partial least‐squares path model (PLS‐PM) to quantify how snow cover dynamics and environmental factors jointly influence ground temperature based freezing indices (FI _GT ) across China's frozen‐ground regions. Snow cover characteristics and FI _GT trends showed strong spatial heterogeneity. The insulating effect of snow varied markedly among regions and was much stronger in the permafrost regions of Northeast China than on the Qinghai‐Tibet Plateau (QTP) or in seasonally frozen ground regions. Over the past two decades, FI _GT declined across all frozen ground regions. At 0 cm depth, the rate of decline was greatest in permafrost regions of Northeast China (−25 ± 22°C·d yr ⁻¹ ), followed by seasonally frozen ground (−7 ± 10°C·d yr ⁻¹ ) and QTP permafrost (−1 ± 7°C·d yr ⁻¹ ). Shallow‐soil FI _GT was mainly controlled by climatic change, snow insulation, and soil properties, whereas deeper soil FI _GT was increasingly governed by soil mediated effects. In regions with stable snow cover, snow exerted a stronger insulating influence on surface and shallow‐soil freezing; in regions with unstable snow cover, FI _GT was more strongly constrained by climatic background and geographic setting. The findings advance understanding of frozen‐ground sensitivity to changing snow regimes and provide a scientific basis for assessing ecological and hydrological risks under continued climate warming.

The degradation of marginal permafrost is a sensitive indicator of climate change, with far-reaching implications on regional ecosystems, hydrology, and infrastructure. Located near the southern limit of latitudinal permafrost (SLLP) in Eastern Asia, Northeast China has experienced pronounced permafrost retreat and persistent ground warming in recent decades. This study develops a physics-informed machine learning (PIML) framework that integrates the Temperature at the Top of Permafrost (TTOP) model, observed changes in land use and land cover (LULC), and climate projections from the Coupled Model Intercomparison Project 6 (CMIP6) to improve the understanding and prediction of permafrost dynamics in the region. Results indicate that, under the SSP5-8.5 scenario, permafrost extent may decline by more than 90 % by the end of the 21st century, primarily driven by a sharp reduction in the air freezing index (AFI), especially in high-latitude and high-elevation zones. Land use and cover changes (LUCC), particularly urban expansion and deforestation, further exacerbate ground thermal disturbances. Spatially, mountainous forested areas, such as the Da Xing’anling Mountains, exhibit relatively greater resilience to warming due to dense vegetation and complex topography that help buffer surface energy fluxes. Feature attribution analysis identifies surface temperature, snow cover duration, and vegetation as dominant drivers of permafrost stability, while Uniform Manifold Approximation and Projection (UMAP) clustering reveals distinct degradation trajectories across different land cover types. This study highlights the complex interplay of climatic and anthropogenic factors in permafrost evolution and demonstrates the utility of integrating physical modelling with machine learning to support ecological conservation and infrastructure risk management in cold regions environment.

The degradation of marginal permafrost is a sensitive indicator of climate change, with far-reaching implications on regional ecosystems, hydrology, and infrastructure. Located near the southern limit of latitudinal permafrost (SLLP) in Eastern Asia, Northeast China has experienced pronounced permafrost retreat and persistent ground warming in recent decades. This study develops a physics-informed machine learning (PIML) framework that integrates the Temperature at the Top of Permafrost (TTOP) model, observed changes in land use and land cover (LULC), and climate projections from the Coupled Model Intercomparison Project 6 (CMIP6) to improve the understanding and prediction of permafrost dynamics in the region. Results indicate that, under the SSP5-8.5 scenario, permafrost extent may decline by more than 90 % by the end of the 21st century, primarily driven by a sharp reduction in the air freezing index (AFI), especially in high-latitude and high-elevation zones. Land use and cover changes (LUCC), particularly urban expansion and deforestation, further exacerbate ground thermal disturbances. Spatially, mountainous forested areas, such as the Da Xing’anling Mountains, exhibit relatively greater resilience to warming due to dense vegetation and complex topography that help buffer surface energy fluxes. Feature attribution analysis identifies surface temperature, snow cover duration, and vegetation as dominant drivers of permafrost stability, while Uniform Manifold Approximation and Projection (UMAP) clustering reveals distinct degradation trajectories across different land cover types. This study highlights the complex interplay of climatic and anthropogenic factors in permafrost evolution and demonstrates the utility of integrating physical modelling with machine learning to support ecological conservation and infrastructure risk management in cold regions environment.

The degradation of marginal permafrost is a sensitive indicator of climate change, with far-reaching implications on regional ecosystems, hydrology, and infrastructure. Located near the southern limit of latitudinal permafrost (SLLP) in Eastern Asia, Northeast China has experienced pronounced permafrost retreat and persistent ground warming in recent decades. This study develops a physics-informed machine learning (PIML) framework that integrates the Temperature at the Top of Permafrost (TTOP) model, observed changes in land use and land cover (LULC), and climate projections from the Coupled Model Intercomparison Project 6 (CMIP6) to improve the understanding and prediction of permafrost dynamics in the region. Results indicate that, under the SSP5-8.5 scenario, permafrost extent may decline by more than 90 % by the end of the 21st century, primarily driven by a sharp reduction in the air freezing index (AFI), especially in high-latitude and high-elevation zones. Land use and cover changes (LUCC), particularly urban expansion and deforestation, further exacerbate ground thermal disturbances. Spatially, mountainous forested areas, such as the Da Xing’anling Mountains, exhibit relatively greater resilience to warming due to dense vegetation and complex topography that help buffer surface energy fluxes. Feature attribution analysis identifies surface temperature, snow cover duration, and vegetation as dominant drivers of permafrost stability, while Uniform Manifold Approximation and Projection (UMAP) clustering reveals distinct degradation trajectories across different land cover types. This study highlights the complex interplay of climatic and anthropogenic factors in permafrost evolution and demonstrates the utility of integrating physical modelling with machine learning to support ecological conservation and infrastructure risk management in cold regions environment.

The degradation of marginal permafrost is a sensitive indicator of climate change, with far-reaching implications on regional ecosystems, hydrology, and infrastructure. Located near the southern limit of latitudinal permafrost (SLLP) in Eastern Asia, Northeast China has experienced pronounced permafrost retreat and persistent ground warming in recent decades. This study develops a physics-informed machine learning (PIML) framework that integrates the Temperature at the Top of Permafrost (TTOP) model, observed changes in land use and land cover (LULC), and climate projections from the Coupled Model Intercomparison Project 6 (CMIP6) to improve the understanding and prediction of permafrost dynamics in the region. Results indicate that, under the SSP5-8.5 scenario, permafrost extent may decline by more than 90 % by the end of the 21st century, primarily driven by a sharp reduction in the air freezing index (AFI), especially in high-latitude and high-elevation zones. Land use and cover changes (LUCC), particularly urban expansion and deforestation, further exacerbate ground thermal disturbances. Spatially, mountainous forested areas, such as the Da Xing’anling Mountains, exhibit relatively greater resilience to warming due to dense vegetation and complex topography that help buffer surface energy fluxes. Feature attribution analysis identifies surface temperature, snow cover duration, and vegetation as dominant drivers of permafrost stability, while Uniform Manifold Approximation and Projection (UMAP) clustering reveals distinct degradation trajectories across different land cover types. This study highlights the complex interplay of climatic and anthropogenic factors in permafrost evolution and demonstrates the utility of integrating physical modelling with machine learning to support ecological conservation and infrastructure risk management in cold regions environment.

The degradation of marginal permafrost is a sensitive indicator of climate change, with far-reaching implications on regional ecosystems, hydrology, and infrastructure. Located near the southern limit of latitudinal permafrost (SLLP) in Eastern Asia, Northeast China has experienced pronounced permafrost retreat and persistent ground warming in recent decades. This study develops a physics-informed machine learning (PIML) framework that integrates the Temperature at the Top of Permafrost (TTOP) model, observed changes in land use and land cover (LULC), and climate projections from the Coupled Model Intercomparison Project 6 (CMIP6) to improve the understanding and prediction of permafrost dynamics in the region. Results indicate that, under the SSP5-8.5 scenario, permafrost extent may decline by more than 90 % by the end of the 21st century, primarily driven by a sharp reduction in the air freezing index (AFI), especially in high-latitude and high-elevation zones. Land use and cover changes (LUCC), particularly urban expansion and deforestation, further exacerbate ground thermal disturbances. Spatially, mountainous forested areas, such as the Da Xing’anling Mountains, exhibit relatively greater resilience to warming due to dense vegetation and complex topography that help buffer surface energy fluxes. Feature attribution analysis identifies surface temperature, snow cover duration, and vegetation as dominant drivers of permafrost stability, while Uniform Manifold Approximation and Projection (UMAP) clustering reveals distinct degradation trajectories across different land cover types. This study highlights the complex interplay of climatic and anthropogenic factors in permafrost evolution and demonstrates the utility of integrating physical modelling with machine learning to support ecological conservation and infrastructure risk management in cold regions environment.

The degradation of marginal permafrost is a sensitive indicator of climate change, with far-reaching implications on regional ecosystems, hydrology, and infrastructure. Located near the southern limit of latitudinal permafrost (SLLP) in Eastern Asia, Northeast China has experienced pronounced permafrost retreat and persistent ground warming in recent decades. This study develops a physics-informed machine learning (PIML) framework that integrates the Temperature at the Top of Permafrost (TTOP) model, observed changes in land use and land cover (LULC), and climate projections from the Coupled Model Intercomparison Project 6 (CMIP6) to improve the understanding and prediction of permafrost dynamics in the region. Results indicate that, under the SSP5-8.5 scenario, permafrost extent may decline by more than 90 % by the end of the 21st century, primarily driven by a sharp reduction in the air freezing index (AFI), especially in high-latitude and high-elevation zones. Land use and cover changes (LUCC), particularly urban expansion and deforestation, further exacerbate ground thermal disturbances. Spatially, mountainous forested areas, such as the Da Xing’anling Mountains, exhibit relatively greater resilience to warming due to dense vegetation and complex topography that help buffer surface energy fluxes. Feature attribution analysis identifies surface temperature, snow cover duration, and vegetation as dominant drivers of permafrost stability, while Uniform Manifold Approximation and Projection (UMAP) clustering reveals distinct degradation trajectories across different land cover types. This study highlights the complex interplay of climatic and anthropogenic factors in permafrost evolution and demonstrates the utility of integrating physical modelling with machine learning to support ecological conservation and infrastructure risk management in cold regions environment.

The degradation of marginal permafrost is a sensitive indicator of climate change, with far-reaching implications on regional ecosystems, hydrology, and infrastructure. Located near the southern limit of latitudinal permafrost (SLLP) in Eastern Asia, Northeast China has experienced pronounced permafrost retreat and persistent ground warming in recent decades. This study develops a physics-informed machine learning (PIML) framework that integrates the Temperature at the Top of Permafrost (TTOP) model, observed changes in land use and land cover (LULC), and climate projections from the Coupled Model Intercomparison Project 6 (CMIP6) to improve the understanding and prediction of permafrost dynamics in the region. Results indicate that, under the SSP5-8.5 scenario, permafrost extent may decline by more than 90 % by the end of the 21st century, primarily driven by a sharp reduction in the air freezing index (AFI), especially in high-latitude and high-elevation zones. Land use and cover changes (LUCC), particularly urban expansion and deforestation, further exacerbate ground thermal disturbances. Spatially, mountainous forested areas, such as the Da Xing’anling Mountains, exhibit relatively greater resilience to warming due to dense vegetation and complex topography that help buffer surface energy fluxes. Feature attribution analysis identifies surface temperature, snow cover duration, and vegetation as dominant drivers of permafrost stability, while Uniform Manifold Approximation and Projection (UMAP) clustering reveals distinct degradation trajectories across different land cover types. This study highlights the complex interplay of climatic and anthropogenic factors in permafrost evolution and demonstrates the utility of integrating physical modelling with machine learning to support ecological conservation and infrastructure risk management in cold regions environment.

The degradation of marginal permafrost is a sensitive indicator of climate change, with far-reaching implications on regional ecosystems, hydrology, and infrastructure. Located near the southern limit of latitudinal permafrost (SLLP) in Eastern Asia, Northeast China has experienced pronounced permafrost retreat and persistent ground warming in recent decades. This study develops a physics-informed machine learning (PIML) framework that integrates the Temperature at the Top of Permafrost (TTOP) model, observed changes in land use and land cover (LULC), and climate projections from the Coupled Model Intercomparison Project 6 (CMIP6) to improve the understanding and prediction of permafrost dynamics in the region. Results indicate that, under the SSP5-8.5 scenario, permafrost extent may decline by more than 90 % by the end of the 21st century, primarily driven by a sharp reduction in the air freezing index (AFI), especially in high-latitude and high-elevation zones. Land use and cover changes (LUCC), particularly urban expansion and deforestation, further exacerbate ground thermal disturbances. Spatially, mountainous forested areas, such as the Da Xing’anling Mountains, exhibit relatively greater resilience to warming due to dense vegetation and complex topography that help buffer surface energy fluxes. Feature attribution analysis identifies surface temperature, snow cover duration, and vegetation as dominant drivers of permafrost stability, while Uniform Manifold Approximation and Projection (UMAP) clustering reveals distinct degradation trajectories across different land cover types. This study highlights the complex interplay of climatic and anthropogenic factors in permafrost evolution and demonstrates the utility of integrating physical modelling with machine learning to support ecological conservation and infrastructure risk management in cold regions environment.

The degradation of marginal permafrost is a sensitive indicator of climate change, with far-reaching implications on regional ecosystems, hydrology, and infrastructure. Located near the southern limit of latitudinal permafrost (SLLP) in Eastern Asia, Northeast China has experienced pronounced permafrost retreat and persistent ground warming in recent decades. This study develops a physics-informed machine learning (PIML) framework that integrates the Temperature at the Top of Permafrost (TTOP) model, observed changes in land use and land cover (LULC), and climate projections from the Coupled Model Intercomparison Project 6 (CMIP6) to improve the understanding and prediction of permafrost dynamics in the region. Results indicate that, under the SSP5-8.5 scenario, permafrost extent may decline by more than 90 % by the end of the 21st century, primarily driven by a sharp reduction in the air freezing index (AFI), especially in high-latitude and high-elevation zones. Land use and cover changes (LUCC), particularly urban expansion and deforestation, further exacerbate ground thermal disturbances. Spatially, mountainous forested areas, such as the Da Xing’anling Mountains, exhibit relatively greater resilience to warming due to dense vegetation and complex topography that help buffer surface energy fluxes. Feature attribution analysis identifies surface temperature, snow cover duration, and vegetation as dominant drivers of permafrost stability, while Uniform Manifold Approximation and Projection (UMAP) clustering reveals distinct degradation trajectories across different land cover types. This study highlights the complex interplay of climatic and anthropogenic factors in permafrost evolution and demonstrates the utility of integrating physical modelling with machine learning to support ecological conservation and infrastructure risk management in cold regions environment.