Groundwater is essential for water resources but faces over-extraction and supply-demand imbalance. Precisely comprehending alterations in groundwater is crucial for sustainable development. Groundwater levels demonstrate a delayed reaction to meteorological circumstances, frequently neglected in current research, diminishing predictive accuracy. This study investigates the lag effect of precipitation and evapotranspiration on groundwater forecasting in Hebei Province, China. We performed a lag analysis utilizing long-term data to ascertain correlations between groundwater levels and climatic variables. Two groundwater prediction models using the random forest algorithm were developed, one incorporating the lag effect and the other excluding it. The Shapley Additive exPlanations (SHAP) method assessed the significance of each element and its influence on model variations. Research reveals a notable lag in groundwater response: shallow groundwater reacts to precipitation after 4.55 months and to evapotranspiration after 9.21 months; deep groundwater responds after 5.91 and 9.63 months, respectively. The inclusion of the lag effect resulted in higher accuracy of the model, with an average reduction of 35.7% in MAE and 18.20% in RMSE. The improved model more accurately captured the influence of meteorological factors on groundwater levels, potentially providing more scientific decision support for the rational allocation and sustainable use of water resources.

Under intensifying climate change impacts, accurate quantification of population exposure to urban flooding has become an imperative component of risk mitigation strategies, particularly when considering the dynamic nature of human mobility patterns. Previous assessments relying on neighborhood block-scale population estimates derived from conventional census data have been constrained by significant spatial aggregation errors. This study presents methodological advancements through the integration of social sensing data analytics, enabling unprecedented spatial resolution at the building scale while capturing real-time population dynamics. We developed an agent-based simulation framework that incorporates (1) building-based urban environment, (2) hydrodynamic flood modeling outputs, and (3) empirically grounded human mobility patterns derived from multi-source geospatial big data. The implemented model systematically evaluates transient population exposure through spatiotemporal superposition analysis of flood characteristics and human occupancy patterns across different urban functional zones in Lishui City, China. Firstly, multi-source points of interest (POIs) data are aggregated to acquire activated time of buildings, and an urban environment system at the building scale is constructed. Then, with population, buildings, and roads as the agents, and population behavior rules, activity time of buildings, and road accessibility as constraints, an agent-based model in an urban flood scenario is designed to dynamically simulate the distribution of population. Finally, the population dynamics of urban flood exposure under a flood scenario with a 50-year return is simulated. We found that the traditional exposure assessment method at the block scale significantly overestimated the exposure, which is four times of our results based on building scale. The proposed method enables a clearer portrayal of the disaster occurrence process at the urban local level. This work, for the first time, incorporates multi-source social sensing data and the triadic relationship between human activities, time, and space in the disaster process into flood exposure assessment. The outcomes of this study can contribute to estimate the susceptibility to urban flooding and formulate emergency response plans.