Search

Flood susceptibility modeling is crucial for rapid flood forecasting, disaster reduction strategies, evacuation planning, and decision-making. Machine learning (ML) models have proven to be effective tools for assessing flood susceptibility. However, most previous studies have focused on individual models or comparative performance, underscoring the unique strengths and weaknesses of each model. In this study, we propose a stacking ensemble learning algorithm that harnesses the strengths of a diverse range of machine learning models. The findings reveal the following: (1) The stacking ensemble learning, using RF-XGB-CB-LR model, significantly enhances flood susceptibility simulation. (2) In addition to rainfall, key flood drivers in the study area include NDVI, and impervious surfaces. Over 40% of the study area, primarily in the northeast and southeast, exhibits high flood susceptibility, with higher risks for populations compared to cropland. (3) In the northeast of the study area, heavy precipitation, low terrain, and NDVI values are key indicators contributing to high flood susceptibility, while long-duration precipitation, mountainous topography, and upper reach vegetation are the main drivers in the southeast. This study underscores the effectiveness of ML, particularly ensemble learning, in flood modeling. It identifies vulnerable areas and contributes to improved flood risk management. [ABSTRACT FROM AUTHOR]

In frequency analysis of annual maximum flood series (AMFS), it is mechanism‐based and significant to incorporate the information of the underlying "ordinary" daily streamflow events for improving accuracy of flood risk estimation and appropriate management. In previous studies related to flood nonstationarity, the classical norming constants method (C‐NCM) has been used to derive statistical parameters of annual maximum flood distribution from daily streamflow distribution. However, C‐NCM does not flexibly consider the feasible range of the scale parameter of annual maximum flood distributions, which can result in the inability to provide sufficient and reliable models to fit AMFS. This paper aims to investigate the potential of two alternative norming constants methods in fitting annual maximum floods, namely the Hall's norming constants method (H‐NCM) and the Fisher and Tippetts' norming constants method (FT‐NCM) respectively. A comparative study of these three methods was carried out using hydrological streamflow series of 77 stations in the Yangtze and Yellow River basins, China. The results found that H‐NCM outperforms both C‐NCM and FT‐NCM for the stations with relatively low‐skewness coefficient of AMFS. Therefore, H‐NCM is recommended to prioritize for practical applications when considering daily streamflow rather than small samples of flood events. Furthermore, if the skewness coefficient exceeds Cs,Gumbel≈1.14, the overall modelling performance of these three methods is significantly deteriorated. This can provide some reference for the applicability of the norming constants method in flood frequency analysis. [ABSTRACT FROM AUTHOR]

Relative little is known about the interaction between climate change and groundwater. Analysis of aquifer response to climatic variability could improve the knowledge related to groundwater resource variations and therefore provides guidance on water resource management. In this work, seasonal and annual variations of groundwater levels in Kumamoto plain (Japan) and their possible interactions with climatic indices and El Niño Southern Oscillation (ENSO) were analyzed statistically. Results show the following: (1) The water level in the recharge area mainly fluctuates at 1- and 2-year periods, whereas the significant periodicity for water level oscillation in the coastal aquifer is 0.5 year. (2) The aquifer water levels are possibly influenced by variability in precipitation, air temperature, barometric pressure, humidity variances and ENSO. Relative high correlations and large proportions of similarities in wavelet power patterns were found between these variables and water levels. (3) Aquifer response to climatic variances was evaluated using cross wavelet transform and wavelet coherence. In recharging aquifers, the ENSO-induced annual variations in precipitation, air temperature, humidity and barometric pressure affect aquifer water levels. The precipitation, air temperature and humidity respond to ENSO with a 4-, 6- and 8-month time lag, respectively, whereas the ENSO imparts weak influence on the barometric pressure. Significant biennial variation of water levels during 1991-1995 is caused primarily by precipitation and humidity variations. In the coastal aquifer, the 0.5-year variability in ENSO is transferred by precipitation, barometric pressure and humidity to aquifer water levels, and the precipitation/humidity influence is more significant comparing with the barometric pressure. Copyright © 2014 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

• Dramatic variation in water level of two semi-arid-region great lakes was analyzed. • Effects on lake level decrease in order of runoff, lake evaporation, and rainfall. • Lake evaporation change may mitigate or aggravate the desiccation of great lakes. • ENSO contributed less than 6% of inter-annual variation in Hulun Lake. Global warming and drying have caused desiccation of lakes in arid and semi-arid regions worldwide, and the mechanisms underlying sharp decreases in water level of great lakes in arid and semi-arid regions in recent decades require elucidation. Using a combination of multiple statistical and modeling methods, we extracted multi-decadal trends from water level time series (~1960–2017) of the two largest lakes in northern China, and explored the influences of hydro-meteorological factors on the multi-decadal and inter-annual variation in lake water level. The hydrology components of the Hulun Lake basin varied with greater amplitude than those of the Qinghai Lake basin, with water level decreases of 5.3 (1991–2011) and 3.1 (1961–2004) m in Hulun Lake and Qinghai Lake, respectively. River runoff influenced multi-decadal changes in water level of the two great lakes most, followed by lake surface evaporation and precipitation at the lake surface. Lake surface evaporation, driven by potential evaporation and lake area dynamics, was the largest hydrology component of the two great lakes. Lake surface evaporation mitigated the decline of Hulun Lake over 1995–2011, while it aggravated the decline of Qinghai Lake over 1990–2005. Although El Niño–Southern Oscillation significantly affected various hydro-meteorological factors, it contributed less than 6% of inter-annual variation in Hulun Lake, and no significant effect on the variation in Qinghai Lake was found. Pan evaporation was negatively correlated with precipitation and land evapotranspiration in both great lake basins. [ABSTRACT FROM AUTHOR]