Explore the vast range of titles available.

Rainfall–runoff modeling has been of great importance for flood control and water resource management. However, the selection of hydrological models is challenging to obtain superior simulation performance especially with the rapid development of machine learning techniques. Three models under different categories of machine learning methods, including support vector regression (SVR), extreme gradient boosting (XGBoost), and the long-short term memory neural network (LSTM), were assessed for simulating daily runoff over a mountainous river catchment. The performances with different input scenarios were compared. Additionally, the joint multifractal spectra (JMS) method was implemented to evaluate the simulation performances during wet and dry seasons. The results show that: (1) LSTM always obtained a higher accuracy than XGBoost and SVR; (2) the impacts of the input variables were different for different machine learning methods, such as antecedent streamflow for XGBoost and rainfall for LSTM; (3) XGBoost showed a relatively high performance during dry seasons, and the classification of wet and dry seasons improved the simulation performance, especially for LSTM during dry seasons; (4) the JMS analysis indicated the advantages of a hybrid model combined with LSTM trained with wet-season data and XGBoost trained with dry-season data.

The frequent occurrence of typhoons causes geological disasters, such as debris flow and landslide, by bringing extreme rainfall events. Due to the lack of data collection on extreme rainfall events caused by typhoons, the relationship between rainfall patterns and debris flow has not been deeply studied. Therefore, based on hourly rainfall data during typhoons in Wenzhou from 1980 to 2017, this study used a variety of methods to classify the rainfall events and analyze the characteristics of typhoon-induced rainfall events and their impacts on the probability of debris-flow occurrence. Three classification techniques, including dynamic time warping, K-Means cluster, and self-organizing maps, are applied with two ways to normalize rainfall records, including dimensionless rainfall density curves and dimensionless rainfall cumulation curves, for extracting rainfall patterns from recorded 1 h rainfall data. The rainfall patterns are then used for the estimation of typhoon-induced debris-flow occurrence probability. Results show that different methods present different rainfall patterns. The probability of debris flows varies with different patterns of rainfall events. The research results help deepen the understanding of typhoon rainfall events and debris-flow disaster prevention in the region and contribute to regional flood control and disaster reduction.

In the context of increasingly severe climate change, studying the relationship between climate factors and vegetation dynamics is crucial for ecological conservation and sustainable development. This study focuses on the Oujiang River Basin from 1981 to 2022, aiming to quantitatively model the interactions among temperature, precipitation, the NDVI, and the LAI. Addressing the lack of approaches for forecasting high-resolution LAI data and existing LAI data that are usually interpreted from NDVI data, we proposed a two-step inversion framework: first, modeling the response of the NDVI to climate variables; second, predicting the LAI using the NDVI as a mediating variable. By integrating long-term remote sensing datasets (GIMMS and MODIS NDVI) with meteorological data and applying trend analysis, spatial correlation analysis, and clustering techniques (K-Means and Possibilistic C-Means), we identified spatial heterogeneity in vegetation response patterns. The study results showed that (1) climate factors have a distinctly spatially heterogeneous impact on the NDVI and LAI; (2) temperature is identified as the dominant factor in most regions; and (3) the LAI prediction model based on the climate factors NDVI and NDVI–LAI relationships shows good accuracy in the medium-to-high range of the LAI, with an R2 value ranging from 0.516 to 0.824. This study provides a scalable approach to improve LAI estimation and monitor vegetation dynamics in complex terrain under changing climate conditions.

Geohazards such as collapses, landslides, and debris flows result from complex interactions between human activities and environmental conditions. However, a quantitative understanding of their coupling mechanisms remains challenging. This study developed a machine learning-based classification framework​ for multi-geohazard susceptibility mapping (GSM) in Zhejiang Province, China, to address this gap. The study employed XGBoost, AdaBoost, and Random Forest to construct individual models for each geohazard, using a comprehensive set of geomorphologic, geological, environmental, hydrological, and anthropogenic factors. The XGBoost model achieved Area Under the Curve (AUC) values greater than 0.9 for all geohazards, and was selected as the optimal model for GSM. Results show: (1) Topographic position index (TPI) and distance to roads are the most influential factors, with dominant roles varying by geohazard—TPI primarily controls debris flows, while collapses are more driven by road proximity. (2) Anthropogenic factors account for 15.9%–33.8% of importance across geohazards. (3) The dependence plots and heatmap of interaction values reveal the impact of human–natural factor coupling mechanisms on geohazards. The study provides a quantitative and interpretable analysis of human–natural environment coupling, offering insights for risk management and spatial planning in densely populated coastal regions under climate change.

Many hydrological models incorporate vegetation-related parameters to describe hydrological processes more precisely. These parameters should adjust dynamically in response to seasonal changes in vegetation. However, due to limited information or methodological constraints, vegetation-related parameters in hydrological models are often treated as fixed values, which restricts model performance and hinders the accurate representation of hydrological responses to vegetation changes. To address this issue, a vegetation-related dynamic-parameter framework is applied on the Xinanjiang (XAJ) model, which is noted as Eco-XAJ. The dynamic-parameter framework establishes the regression between the Normalized Difference Vegetation Index (NDVI) and the evapotranspiration parameter K. Two routing methods are used in the models, i.e., the unit hydrograph (XAJ-UH and Eco-XAJ-UH) and the Linear Reservoir (XAJ-LR and Eco-XAJ-LR). The original XAJ model and the modified Eco-XAJ model are applied to the Ou River Basin, with detailed comparisons and analyses conducted under various scenarios. The results indicate that the Eco-XAJ model outperforms the original model in long-term discharge simulations, with the NSE increasing from 0.635 of XAJ-UH to 0.647 of Eco-XAJ-UH. The Eco-XAJ model also reduces overestimation and incorrect peak flow simulations during dry seasons, especially in the year 1991. In drought events, the modified model significantly enhances water balance performance. The Eco-XAJ-UH outperforms the XAJ-UH in 9 out of 16 drought events, while the Eco-XAJ-LR outperforms the XAJ-LR in 14 out of 16 drought events. The results demonstrate that the dynamic-parameter model, in regard to vegetation changes, offers more accurate simulations of hydrological processes across different scenarios, and its parameters have reasonable physical interpretations.

We present a 1970–2020 dataset of daily maximum coastal water levels reconstructed for 23 tide gauges along China’s coast. The product combines storm-surge residuals predicted with an Informer-based deep learning workflow (benchmarked against LSTM, CNN-LSTM, and ConvLSTM) with astronomical tides estimated by UTide from historical observations. Predictors are drawn from ERA5 reanalysis and multi-source tide-gauge records are used for training and validation. For each station, the model with best validation skill generates residuals combined with tidal harmonics to form daily maxima. Across stations, the reconstruction attains a mean correlation coefficient of 0.81 and RMSE of 11.7 cm for daily maxima; for events above the 95th percentile, the mean correlation is 0.68 and RMSE is typically below 20 cm. The release includes metadata, data splits, and skill metrics for transparency and reuse. This dataset enables spatiotemporal analyses of extreme coastal water levels and coastal hazard mitigation in regions with sparse observations. Daily maxima are computed as the sum of the maximum tide and maximum surge. This serves as an upper bound, as the peaks of tide and surge rarely coincide. Using hourly data, we estimate a mean non-coincidence bias of 14.9 cm (14.8%). Additionally, station-specific statistics are provided for user adjustment.

Hydrological and climatic data at finer temporal resolutions are considered essential to model hydrological processes, especially for short duration flood events. Parameter transferability is an essential approach to obtain sub-daily hydrological simulations at many regions without sub-daily data. In this study, the objective is to investigate temporary dependency of parameter sensitivity for different flood types, which contributes to research into parameter transferability. This study is conducted in a medium-sized basin using a distributed hydrological model, DHSVM. Thirty-six flood events in the period of 04/12/2006–07/01/2013 in the Jinhua River basin, China, are classified into three flood types (FF: flash flood, SRF: short rainfall flood and LRF: long rainfall flood) by using the fuzzy decision tree method. The results show that SRF is the dominant flood type in the study area, followed by LRF and FF. Runoff simulations of FF and SRF are more sensitive to parameter perturbations than those of LRF. Sensitive parameters are highly dependent on temporal resolutions. The temporary dependency of LRF is the highest, followed by SRF and FF. More attention should be payed to sensitive and highly temporal dependent parameters in a subsequent parameter transfer process. Further study into this result is required to test the applicability.

This study presents an approach that integrates remote sensing evapotranspiration into multi-objective calibration (i.e., runoff and evapotranspiration) of a fully distributed hydrological model, namely a distributed hydrology–soil–vegetation model (DHSVM). Because of the lack of a calibration module in the DHSVM, a multi-objective calibration module using ε-dominance non-dominated sorted genetic algorithm II (ε-NSGAII) and based on parallel computing of a Linux cluster for the DHSVM (εP-DHSVM) is developed. The module with DHSVM is applied to a humid river basin located in the mid-west of Zhejiang Province, east China. The results show that runoff is simulated well in single objective calibration, whereas evapotranspiration is not. By considering more variables in multi-objective calibration, DHSVM provides more reasonable simulation for both runoff (NS: 0.74% and PBIAS: 10.5%) and evapotranspiration (NS: 0.76% and PBIAS: 8.6%) and great reduction of equifinality, which illustrates the effect of remote sensing evapotranspiration integration in the calibration of hydrological models.

Evapotranspiration (ET) is an important element in the water and energy cycle. Potential evapotranspiration (PET) is an important measurement of ET. Its accuracy has significant influence on agricultural water management, irrigation planning, and hydrological modelling. However, whether current PET models are applicable under climate change or not, is still a question. In this study, five frequently used PET models were chosen, including one combination model (the FAO Penman-Monteith model, FAO-PM), two temperature-based models (the Blaney-Criddle and the Hargreaves models) and two radiation-based models (the Makkink and the Priestley-Taylor models), to estimate their appropriateness in the historical and future periods under climate change impact on the Yarlung Zangbo river basin, China. Bias correction methods were not only applied to the temperature output of Global Climate Models (GCMs), but also for radiation, humidity, and wind speed. It was demonstrated that the results from the Blaney-Criddle and Makkink models provided better agreement with the PET obtained by the FAO-PM model in the historical period. In the future period, monthly PET estimated by all five models show positive trends. The changes of PET under RCP8.5 are much higher than under RCP2.6. The radiation-based models show better appropriateness than the temperature-based models in the future, as the root mean square error (RMSE) value of the former models is almost half of the latter models. The radiation-based models are recommended for use to estimate PET under climate change in the Yarlung Zangbo river basin.

The streamflow recession analysis, always following a power law, depicts the storage-release relation in catchments. However, the understanding of hydrological recession dynamics is still insufficient. Here, a total of 80 nearly natural catchments from the reference hydrologic networks (RHNs) in the UK were selected to explore the changes and the controlling factors of recession slope curve parameters by utilizing trend analysis methods, the self-organizing map, and k-means clustering algorithms. The results demonstrated that (i) the estimation of event-scale recession parameters was sensitive to different combinations of recession extraction and fitting methods. Particularly, the combination of Brutsaert extraction and the linear regression method always obtained robust estimations of recession parameters. (ii) Changes of annual median recession parameters showed a clear spatial distribution pattern, indicating the climate-driven impact on recession processes. Up to 17 catchments in Scotland showed significant changes in recession processes, always displaying increasing trends in the recession coefficient and decreasing trends in the recession exponent. (iii) The recession exponent strongly depended on the base-flow index, rock permeability, arable area, and temporal distribution of rainfall. Additionally, the spatial patterning of recession processes further provided some insights for facilitating the understanding of the hydrological recession process.