Accurate time series forecasting is fundamental to geohazard early warning, yet remains a major challenge. Conventional in situ geotechnical monitoring remains costly and spatially constrained, whereas deep learning applied to remote sensing data has become increasingly prevalent but often suffers from opacity of model decision-making. To address this issue, we propose a Transformer-based forecasting framework, namely PatchTST-Fusion, adapted for multivariate Multi-Temporal Interferometric Synthetic Aperture Radar (MT-InSAR) time series. The framework integrates model interpretability analysis through TimeSHAP, providing temporal and feature-level attributions across the input sequence. Landslide deformation time series are first derived from Copernicus Sentinel-1 SAR data. Variational Mode Decomposition is then applied to decompose the non-linear signals into trend, seasonal, and noise components. The denoised displacement series are modeled and forecast using the proposed PatchTST-Fusion, which incorporates rainfall and reservoir water level fluctuations as feature-level drivers. Application to the Daping landslide cluster in the Three Gorges Reservoir Area in China demonstrates that our method captures both the long-term and transient non-linear coupling between deformation and its triggers, surpassing state-of-the-art models including CNN-BiGRU-Attention, Informer and original PatchTST with 7–55% improvements in MAE and 10–52% improvements in RMSE. Beyond predictive gains, feature attribution of environmental triggers via TimeSHAP reveals that rainfall and reservoir regulation exert temporally distinct influences on slope kinematics, with high relative importance concentrated in specific periods and characteristic lagged responses. This interpretable framework provides both enhanced forecasting accuracy and process-based insights, offering a broadly applicable tool for landslide early warning in reservoir regions.

Accurately assessing cloud feedback on global warming is essential for producing reliable climate projections. Linear regression analysis is a widely used method for this purpose, offering a straightforward approach for examining the relationship between cloud radiative effects and global-mean surface temperature. However, the El Niño–Southern Oscillation (ENSO) can significantly contribute to these estimates, which is often overlooked due to ENSO's relatively short periodicity (2–7 years). Using 72 years of reanalysis data and 150 years of simulations by 11 global climate models, this study demonstrates that, over a large portion of the low- to mid-latitude oceans, ENSO can contribute up to a few W m⁻² K⁻¹ to the regression-based cloud feedback estimates over decades and even centuries. Through a detailed spatial and temporal analysis, our findings underscore the importance of accounting for and removing ENSO's influence to improve the accuracy of cloud feedback assessments in the context of global warming.

Cloud feedback remains the dominant source of uncertainty in climate projections, highlighting the necessity of rigorous cloud-based evaluations of climate models. Current assessments rely predominantly on cloud climatology and responses to internal variability, leaving cloud changes driven by historical warming largely unassessed. Here, we identify an emergent trend mode in total cloud cover (CLT) across multiple reanalysis products that is closely linked to global mean surface temperature. Using this warming-linked mode as the primary benchmark, we evaluate 13 CMIP6 AMIP simulations (1979–2014). While the models adequately capture global warming and internal variability in both temperature and CLT, this CLT trend mode is systematically absent in the simulations. Diagnostic regression reveals that this absence is characterized by a substantial underestimation of the response amplitude and large-scale spatial mismatches. This systematic deficiency points to shared structural limitations in current atmospheric models. Addressing this specific discrepancy offers a targeted pathway to constrain the forced cloud response, thereby reducing cloud feedback uncertainties in future climate projections.

Accurately assessing the cloud feedback to global warming is essential for producing reliable climate projections. Linear regression analysis is a widely used method for this purpose, offering a straightforward approach for examining the relationship between cloud radiative effects and global mean surface temperature. However, the El Niño–Southern Oscillation (ENSO) can introduce a significant bias in these estimations, which is often overlooked due to ENSO’s relatively short periodicity. Using 72 years of reanalysis data and 150 years of simulations by 12 global climate models, this study demonstrates that ENSO can produce a bias of comparable magnitude to the estimated cloud feedback, over decades and even centuries. By providing a detailed spatial and temporal analysis of this bias, our findings underscore the importance of accounting for and removing the ENSO’s influence to improve the accuracy of cloud feedback assessment in the context of global warming.

Long-term satellite observations of cloud amount provide critical constraints on climate sensitivity and are essential for reducing uncertainties in climate projections. Different cloud types exert distinct radiative effects and exhibit divergent responses to warming. Yet, their relative contributions to trends in total cloud amount remain inadequately quantified. This study analyzes 17 years (2003–2019) of MODIS observations and reveals that, although global and zonal (60°S–60°N) mean trends in total cloud amount are weak, significant local signals persist. Trend decomposition demonstrates that free-tropospheric cloud occurrence dominates the magnitude of total cloud amount trends, whereas low-level cloud (LowC) size primarily dictates their spatial distribution. Nevertheless, this LowC size signal is substantially suppressed by an opposing LowC occurrence signal, resulting in a significant decoupling between LowC and total cloud amounts. To address the inherent limitations of passive satellite retrievals, we further utilize ERA5 reanalysis data. This data further indicates that approximately half of the trend in LowC occurrence arises from cloud overlap biases unresolved by passive satellite sensors. Correcting for this bias should yield a coherent shift in LowC amount trends over most oceans, suggesting that passive satellite retrievals may have systematically obscured the response of low-level clouds to recent climate change.

Accurately assessing the cloud feedback to global warming is essential for producing reliable climate projections. Linear regression analysis is a widely used method for this purpose, offering a straightforward approach for examining the relationship between cloud radiative effects and global mean surface temperature. However, the El Niño–Southern Oscillation (ENSO) can introduce a significant bias in these estimations, which is often overlooked due to ENSO’s relatively short periodicity. Using 72 years of reanalysis data and 150 years of simulations by 12 global climate models, this study demonstrates that ENSO can produce a bias of comparable magnitude to the estimated cloud feedback, over decades and even centuries. By providing a detailed spatial and temporal analysis of this bias, our findings underscore the importance of accounting for and removing the ENSO’s influence to improve the accuracy of cloud feedback assessment in the context of global warming.