Landslide susceptibility assessment serves as a critical scientific reference for geohazard control, land use, and sustainable development planning. The existing research has not fully considered the potential impact of the spatial agglomeration and dispersion of landslides on assessments. This issue may cause a systematic evaluation bias when the field investigation data are insufficient, which is common due to limited human resources. Accordingly, this paper proposes two novel strategies, including a clustering algorithm and a preprocessing method, for these two ignored features to strengthen assessments, especially in high-susceptibility regions. Multiple machine learning models are compared in a case study of the city of Bijie (Guizhou Province, China). Then we generate the optimal susceptibility map and conduct two experiments to test the validity of the proposed methods. The primary conclusions of this study are as follows: (1) random forest (RF) was superior to other algorithms in the recognition of high-susceptibility areas and the portrayal of local spatial features; (2) the susceptibility map incorporating spatial feature messages showed a noticeable improvement over the spatial distribution and gradual change of susceptibility, as well as the accurate delineation of critical hazardous areas and the interpretation of historical hazards; and (3) the spatial distribution feature had a significant positive effect on modeling, as the accuracy increased by 5% and 10% after including the spatial agglomeration and dispersion consideration in the RF model, respectively. The benefit of the agglomeration is concentrated in high-susceptibility areas, and our work provides insight to improve the assessment accuracy in these areas, which is critical to risk assessment and prevention activities.

Global warming is exacerbating flood hazards, making the robustness of flood risk management a critical issue. Without considering future scenarios, flood risk analysis built only on historical knowledge may not adequately address the coming challenges posed by climate change. A comprehensive risk analysis framework based on both historical inundations and future projections to tackle uncertainty is still lacking. In this view, a scenario-based, data-driven risk analysis framework that for the first time integrates recent historical floods and future risk trends is here presented, consisting of flood inundation-prone and high-risk zones. Considering the Poyang Lake Eco-Economic Zone (PLEEZ) in China as the study area, we reproduced historical inundation scenarios of major flood events by using Sentinel-1 imagery from 2015 to 2021, and used them to build the risk baseline model. The results show that 11.7% of the PLEEZ is currently exposed to the high-risk zone. In the SSP2-RCP4.5 scenario, the risk would gradually decrease after peaking around 2040 (with a 19.3% increase in high-risk areas), while under the traditional fossil fuel-dominated development pathway (SSP5-RCP8.5), the risk peak would occur with a higher intensity about a decade earlier. The attribution analysis results reveal that the intensification of heavy rainfall is the dominant driver of future risk increase and that the exploitation of unused land such as wetlands induces a significant increase in risk. Finally, a hierarchical panel of recommended management measures was developed. We hope that our risk analysis framework inspires newfound risk awareness and provides the basis for more effective flood risk management in river basins.

Landslide on the Qinghai-Tibet Plateau (QTP) is expected to be more affected by climate change due to the sensitivity of this unique climatic and geomorphological area to variations in temperature and precipitation. As an important response signal to climate change, a systematic framework for the assessment of landslide hazard and risk in QTP is necessary to investigate the potential impacts of climate change on landslides and related exposures.The study aims to establish an integrated model that synthesizes spatial and temporal landslide prediction, using statistical analysis, machine learning, and quantitative methods. The temporal landslide prediction is made by means of empirical rainfall thresholds, based on satellite rainfall estimates, whose feasibility for defining landslide-triggering rainfall thresholds was proved by several studies.A well-documented hazard database of the QTP provided by the China Geological Survey (4519 records from 2001 to 2022) indicates that landslides occurred here are mostly induced by rainfall from April to October, with an obvious seasonal characteristic, resulting in fatalities, damage, and affected population. According to the database, 3542 landslides are associated to a rainfall trigger. Based on the satellite-based rainfall product of CHIRPS (Climate Hazards Group InfraRed Precipitation with Station data, version 2.0 final) daily data, we find that the rainfall of the occurrence day and the antecedent rainfall over the seven days before the landslides are significant indicators for the rainfall induced hazard. Using the frequentist method, the event duration-cumulated event rainfall (ED) thresholds at different non-exceedance probabilities for landslide triggering are calculated for the whole QTP area and for different environmental subdivisions within it. The thresholds show a robust definition with low parameter uncertainty. This is the first attempt to define empirical rainfall thresholds for landslide occurrence specifically for the QTP.Given the long-term of the used database, temporal and spatial analyses are conducted, to search for variations in the rainfall triggering conditions according to landslide locations and time of occurrence. Variations in the seasonal distribution and in the annual trends (using 5-year moving windows from 2007 to 2002) are evaluated. The impact of variations in rainfall patterns due to climate change making the landscape of the QTP more prone to landslides during the recent-most ten years is demonstrated by the gradual change of thresholds with lower intercepts and slopes. That means, for a certain rainfall duration, there is a tendency of lower rainfall threshold to trigger a landslide.The thresholds here defined are further combined with landslide susceptibility map based on Random Forest to derive a landslide hazard map for the interested area.