Search

Abstract Traditional decomposition integration models decompose the original sequence into subsequences, which are then proportionally divided into training and testing periods for modeling. Decomposition may cause data aliasing, then the decomposed training period may contain part of the test period data. A more effective method of sample construction is sought in order to accurately validate the model prediction accuracy. Semi-stepwise decomposition (SSD), full stepwise decomposition (FSD), single model semi-stepwise decomposition (SMSSD), and single model full stepwise decomposition (SMFSD) techniques were used to create the samples. This study integrates Variational Mode Decomposition (VMD), African Vulture Optimization Algorithm (AVOA), and Least Squares Support Vector Machine (LSSVM) to construct a coupled rainfall prediction model. The influence of different VMD parameters α is examined, and the most suitable stepwise decomposition machine learning coupled model algorithm for various stations in the North China Plain is selected. The results reveal that SMFSD is relatively the most suitable tool for monthly precipitation forecasting in the North China Plain. Among the predictions for the five stations, the best overall performance is observed at Huairou Station (RMSE of 18.37 mm, NSE of 0.86, MRE of 107.2%) and Jingxian Station (RMSE of 24.74 mm, NSE of 0.86, MRE of 51.71%), while Hekou Station exhibits the poorest performance (RMSE of 25.11 mm, NSE of 0.75, MRE of 173.75%).

Understanding the value of ecosystem services (ESV) and the mechanisms that influence it is pivotal for upholding ecological equilibrium and fostering sustainable development in the densely populated regions of the Tibetan Plateau. In this study, we used several improved ESV calculation methods to describe the dynamic changes of ESV, and investigated the individual effects, synergistic effects, local spatial clustering patterns and spatial correlations of each factor using Geodetector and Geoda. The results reveal: (1) Over the past 35 years, ESV in the study area exhibited an overall increasing trend, with a total increase of 20.36 billion Chinese yuan. Grassland accounted for the largest proportion, approximately 60 %, playing a vital role in maintaining ecological balance. Climate regulation services had the highest share at around 24 %, with hydrological regulation and soil conservation services dominating. (2) Human activity, elevation, and temperature had the most significant impact on ESV in the Tibetan Plateau human activity intensive area, followed by Fractional Vegetation Cover (FVC) and precipitation. The synergistic effects of two factors indicated that the interaction between elevation and FVC exhibited a decreasing influence on ESV, while the interaction between human activity and temperature showed an increasing impact. (3) In medium to high-altitude areas and urban agglomeration zones, human activity and temperature had the most pronounced negative impact on ESV, highlighting the need for more effective land management and sustainable development plans. Elevation and annual precipitation showed a positive correlation with ESV, but beyond a certain elevation threshold, elevation and precipitation had an adverse effect on ESV. Similarly, in extremely high-altitude regions and water source areas like the Yellow River, ESV exhibited a positive correlation with temperature.

The assessment of wetland ecosystem services value can provide theoretical basis for regional social and economic development, ecological environment protection and other planning and measures. Based on the factors of hydrology, meteorology, society, economy, resources, environment and culture, the value of wetland ecosystem services in the Yellow River Delta was evaluated by the revised equivalent factor method. The results showed that from 2005 to 2020, the area of tidal flat wetland decreased by 54.35%, and aquaculture increased by 206.91%. The total value of wetland ecosystem services increased from 28.03 billion CNY to 35.77 billion CNY, an increase of 27.63%, showing an N-shaped change of "increase - decrease - increase" on the whole. The ecosystem service value per unit area was more in coastal areas and less in inland areas. From 2005 to 2020, the ecosystem service sensitivity coefficient of the Yellow River Delta wetland was all less than 1. Under the premise of rational development and utilization, it is predicted that the value of ecological services will continue to increase in the future.

This study delves into the hydrological cycle and drought characteristics of the Yi-Luo River Basin. By quantitatively assessing the impact of climate change on historical runoff variations in the basin, it provides a scientific basis for the rational planning of water and soil resources and the formulation of drought response strategies in the Yi-Luo River Basin. It offers more in-depth guidance for water resource management and ecological protection in the basin. Utilizing the SWAT model, a comprehensive assessment of the drought situation in the Yi-Luo River Basin from 1983 to 2023 was conducted. The study constructed a distributed hydrological model and a drought evaluation model for the basin, combined with GIS technology, to deeply analyze hydrological processes and drought characteristics. It was found that the drought phenomenon in the Yi-Luo River Basin has distinct seasonal and cyclical characteristics, with higher drought rates in summer and autumn due to insufficient precipitation, and a cyclical trend of increasing then decreasing and then increasing again since the 20th century. The spatial distribution characteristics of drought show that extreme and severe droughts are mainly concentrated in the middle reaches of the basin, especially in the Ruyang area, while the upper mountainous areas and downstream plains are generally characterized by mild drought. The distribution characteristics of drought duration indicate that the average duration of drought in the Yi-Luo River Basin is about 32 months, with severe and extreme droughts lasting about 16 months. Drought is more persistent in the middle reaches, while the upper and lower reaches have shorter drought periods. The spatial distribution characteristics of drought intensity show that the average drought intensity in the basin is 25, with higher drought intensity in the central and eastern parts facing more severe droughts. The impact of extreme droughts is relatively small in the upper and middle reaches and the northern part of the basin.

Abstract Temperature as an important indicator of climate change, accurate temperature prediction has important guidance and application value for agricultural production, energy management and disaster warning. Based on the advantages of CEEMDAN model in effectively extracting the time–frequency characteristics of nonlinear and nonsmooth signals, BO algorithm in optimizing the objective function within a limited number of iterations, and BiLSTM model in revealing the connection between the current data, the previous data and the future data, a monthly average temperature prediction model based on CEEMDAN–BO–BiLSTM is established. A CEEMDAN–BO–BiLSTM-based monthly average temperature prediction model is developed and applied to the prediction of monthly average temperature in Jinan City, Shandong Province. The results show that the constructed monthly mean temperature prediction model based on CEEMDAN–BO–BiLSTM is feasible; the constructed CEEMDAN–BO–BiLSTM model has an average absolute error of 1.17, a root mean square error of 1.43, an average absolute percentage error of 0.31%, which is better than CEEMDAN–BiLSTM, EMD–BiLSTM, and BiLSTM models in terms of prediction accuracy and shows better adaptability; the constructed CEEMDAN–BO–BiLSTM model illustrates that the model is not over-modeled and adds complexity using Friedman’s test and performance comparisons between model run speeds. The model provides insights for effective forecasting of monthly mean temperatures.

This study investigates the energy dynamics of sandstone subjected to failure in conditions typical of deep underground construction. Research was conducted using both standard triaxial compression and cyclic loading–unloading techniques at six distinct confining pressures, with the objective of elucidating the deformation and failure processes of rock materials. The tests demonstrated that, regardless of the stress path, sandstone primarily fails through shear under different confining pressures, which also reduces the formation of secondary cracks. The energy transformation observed during cyclic loading and unloading processes exhibits a distinctive peak-like distribution, marked by an inflection point that indicates changes in energy distribution. In the initial stages of the loading cycle, the energy profile of the rock increases, characterized by a condition in which the energy stored elastically exceeds the energy dissipated. Nevertheless, subsequent to reaching peak stress, there is a rapid transmutation of elastic strain energy into other forms, culminating in a pronounced elevation in the ratio of dissipated energy, which ultimately achieves a state of equilibrium influenced by the confining pressures. The study introduces the energy consumption ratio (Ke) as a metric for assessing rock damage accumulation and stability, noting a critical pattern where Ke decreases and then spikes at the rock’s failure point, with K = 1 identified as the critical threshold for failure. This comprehensive analysis illuminates the intricate relationship between energy distribution patterns and the stability of rock structures, thereby enhancing our understanding of failure mechanisms from an energetic perspective.

Abstract To improve the accuracy of runoff forecasting, a combined forecasting model is established by using the kernel extreme learning machine (KELM) algorithm optimised by the butterfly optimisation algorithm (BOA), combined with the variational modal decomposition method (VMD) and the complementary ensemble empirical modal decomposition method (CEEMD), for the measured daily runoff sequences at Jiehetan and Huayuankou stations and Gaochun and Lijin stations. The results show that the combined model VMD-CEEMD-BOA-KELM predicts the best. The average absolute errors are 30.02, 23.72, 25.75, 29.37, and the root mean square errors are 20.53 m3/s, 18.79 m3/s, 18.66 m3/s, and 21.87 m3/s, the decision coefficients are all above 90 percent, respectively, and the Nash efficiency coefficients are all more than 90%, from the above it can be seen that the method has better results in runoff time series prediction.

Abstract Enhancing flood forecasting accuracy, promoting rational water resource utilization and management, and mitigating river disasters all hinge on the crucial role of improving the accuracy of daily flow prediction. The coupled model of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Sample Entropy (SE), and Bidirectional Long Short-Term Memory (BiLSTM) demonstrates higher stability when faced with nonlinear and non-stationary data, stronger adaptability to various types and lengths of time series data by utilizing sample entropy, and significant advantages in processing sequential data through the BiLSTM network. In this study, in the context of predicting daily flow at the Huayuankou Hydrological Station in the lower reaches of the Yellow River, a coupled CEEMDAN–SE–BiLSTM model was developed and utilized. The results showed that the CEEMDAN–SE–BiLSTM coupled model achieved the utmost accuracy in prediction and optimal fitting performance. Compared with the CEEMDAN–SE–LSTM, CEEMDAN–BiLSTM, and BiLSTM coupled models, the root mean square error (RMSE) of this model is reduced by 42.77, 182.02, and 193.71, respectively; the mean absolute error (MAE) is reduced by 37.62, 118.60, and 126.67, respectively; and the coefficient of determination (R2) is increased by 0.0208, 0.1265, 0.1381.

Precipitation prediction is one of the important issues in meteorology and hydrology, and it is of great significance for water resources management, flood control, and disaster reduction. In this paper, a precipitation prediction model based on the empirical mode decomposition–variational mode decomposition–long short-term memory (EMD–VMD–LSTM) is proposed. This model is coupled with EMD, VMD, and LSTM to improve the accuracy and reliability of precipitation prediction by using the characteristics of EMD for noise removal, VMD for trend extraction, and LSTM for long-term memory. The monthly precipitation data from 2000 to 2019 in Luoyang City, Henan Province, China, are selected as the research object. This model is compared with the standalone LSTM model, EMD–LSTM coupled model, and VMD–LSTM coupled model. The research results show that the maximum relative error and minimum relative error of the precipitation prediction using the EMD–VMD–LSTM neural network coupled model are 9.64 and −7.52%, respectively, with a 100% prediction accuracy. This coupled model has better accuracy than the other three models in predicting precipitation in Luoyang City. In summary, the proposed EMD–VMD–LSTM precipitation prediction model combines the advantages of multiple methods and provides an effective way to predict precipitation. HIGHLIGHTS The EMD–VMD–LSTM coupling model can overcome the limitations of traditional LSTM.; In this paper, the method of quadratic decomposition of high-frequency components is used to reduce the volatility and non-stationarity of components.; In this paper, a novel rolling forecast method is used to predict precipitation.;

Abstract Rainfall forecasting is an important means for macro-control of water resources and prevention of future disasters. In order to achieve a more accurate prediction effect, this paper analyzes the applicability of the "full decomposition" and "stepwise decomposition" of the VMD (Variational mode decomposition) algorithm to the actual prediction service; The MAVOA (Modified African Vultures Optimization Algorithm) improved by Tent chaotic mapping is selected; and the DNC (Differentiable Neural Computer), which combines the advantages of recurrent neural networks and computational processing, is applied to the forecasting. The different VMD decompositions of the MAVOA-DNC combination together with other comparative models are applied to example predictions at four sites in the Huaihe River Basin. The results show that SMFSD (Single-model Fully stepwise decomposition) is the most effective, and the average Root Mean Square Error (RMSE) of the forecasts for the four sites of SMFSD-MAVOA-DNC is 9.02, the average Mean Absolute Error (MAE) of 7.13, and the average Nash-Sutcliffe Efficiency (NSE) of 0.94. Compared with the traditional VMD full decomposition, the RMSE is reduced by 7.42, the MAE is reduced by 4.83, and the NSE is increased by 0.05; the best forecasting results are obtained compared with other coupled models.

Abstract In order to enhance the simulation of BMPs (Best Management Practices) reduction effects in unmonitored watersheds, in this study, we combined the physically-based hydrological model Soil & Water Assessment Tool (SWAT) and the data-driven model Bi-directional Long Short-Term Memory (Bi-LSTM), using the very-high-resolution (VHR) Land Use and Land Cover (LULC) dataset SinoLC-1 as data input, to evaluate the feasibility of constructing a water environment model for the Ba-River Basin (BRB) in central China and improving streamflow prediction performance. In the SWAT-BiLSTM model, we calibrated the top five SWAT parameters sorted by P-Value, allowing SWAT to act as a transfer function to convert meteorological data into base flow and storm flow, serving as the data input for the Bi-LSTM model. This optimization improved the Bi-LSTM's learning process for the relationship between the target and explanatory variables. The daily streamflow prediction results showed that the hybrid model had 9 regions rated as "Very good," 2 as "Good," 2 as "Satisfactory," and 1 as "Unsatisfactory" among the 14 regions. The model achieved an NSE of 0.86, R2 of 0.85, and PBIAS of −2.71% for the overall daily streamflow prediction performance during the verification period of the BRB. This indicates that the hybrid model has high predictive accuracy and no significant systematic bias, providing a sound hydrodynamic environment for water quality simulation. The simulation results of different BMPs scenarios showed that in the scenarios with only one BMP measure, stubble mulch had the best reduction effect, with average reductions of 17.83% for TN and 36.17% for TP. In the scenarios with a combination of multiple BMP measures, the combination of stubble mulch, soil testing and formula fertilization, and vegetative filter strip performed the best, achieving average reductions of 42.71% for TN and 50.40% for TP. The hybrid model provides a novel approach to simulate BMPs' reduction effects in regions without measured hydrological data and has the potential for wide application in BMP-related decision-making.

Accurate prediction of monthly precipitation is crucial for effective regional water resources management and utilization. However, precipitation series are influenced by multiple factors, exhibiting significant ambiguity, chance, and uncertainty. In this research, we propose a combined model that integrates adaptive noise-complete ensemble empirical mode decomposition (CEEMDAN), variational modal decomposition method (VMD), and bidirectional long- and short-term memory (BILSTM) to enhance precipitation prediction. We apply this model to forecast precipitation in Fuzhou City and compare its performance with existing models, including CEEMD–long and short-term memory (LSTM), CEEMD–BILSTM, and CEEMDAN–BILSTM. Our findings demonstrate that the combined CEEMDAN–VMD–BILSTM quadratic decomposition model yields more accurate predictions and captures the real variation in precipitation series with greater fidelity. The model achieves an average relative error of 1.69%, at a lower level, and an average absolute error of 1.32 m, with a Nash–Sutcliffe efficiency coefficient of 0.92. Overall, the proposed quadratic decomposition model exhibits excellent applicability, stability, and superior predictive capabilities in monthly precipitation forecasting. HIGHLIGHTS Based on CEEMDAN to effectively reduce the reconstruction error of time series, VMD to effectively reduce the non-smoothness of precipitation time series with high complexity and strong non-linearity, and bidirectional long and short-term memory (BILSTM) model to effectively learn the long-term dependence in time series.; A combined model of adaptive noise-complete ensemble empirical modal decomposition (CEEMDAN), variational modal decomposition method (VMD) and bidirectional long and short-term memory (BILSTM) was constructed. which makes the prediction results more accurate and the coupled model can reflect the real changes of precipitation series in more reasonable details.;

Accurate runoff prediction is of great significance for flood prevention and mitigation, agricultural irrigation, and reservoir scheduling in watersheds. To address the strong non-linear and non-stationary characteristics of runoff series, a hybrid model of monthly runoff prediction, variational mode decomposition (VMD)–long short-term memory (LSTM)–Transformer, is proposed. Firstly, VMD is used to decompose the runoff series into multiple modal components, and the sample entropy of each modal component is calculated and divided into high-frequency and low-frequency components. The LSTM model is then used to predict the high-frequency components and the transformer to predict the low-frequency components. Finally, the prediction results are summed to obtain the final prediction results. The Mann–Kendall trend test method is used to analyze the runoff characteristics of the Miyun Reservoir, and the constructed VMD–LSTM–Transformer model is used to forecast the runoff of the Miyun Reservoir. The prediction results are compared and evaluated with those of VMD–LSTM, VMD–Transformer, empirical mode decomposition (EMD)–LSTM–Transformer, and empirical mode decomposition (EMD)–LSTM models. The results show that the Nash–Sutcliffe efficiency coefficient (NSE) value of this model is 0.976, mean absolute error (MAE) is 0.206 × 107 m3, mean absolute percentage error (MAPE) is 0.381%, and root mean squared error (RMSE) is 0.411 × 107 m3, all of which are better than other models, indicating that the VMD–LSTM–Transformer model has higher prediction accuracy and can be applied to runoff prediction in the actual study area. HIGHLIGHTS The VMD–LSTM–Transformer model proposed in this paper achieves higher accuracy in monthly runoff prediction compared to other models.; The VMD decomposition method used in the model improves the completeness and adequacy of time series decomposition.; By using LSTM and Transformer models for different frequency components, the proposed model achieves better prediction accuracy.;

Abstract Against the backdrop of accelerated global climate change and urbanization, the frequency and severity of flood disasters have been increasing. In recent years, influenced by climate change, the Hai-River Basin (HRB) has experienced multiple large-scale flood disasters. During the widespread extraordinary flood event from July 28th to August 1st, 2023, eight rivers witnessed their largest floods on record. These events caused significant damage and impact on economic and social development. The development of hydrological models with better performance can help researchers understand the impacts of climate change, provide risk information on different disaster events within watersheds, support decision-makers in formulating adaptive measures, urban planning, and improve flood defense mechanisms to address the ever-changing climate environment. This study examines the potential for enhancing streamflow simulation accuracy in the HRB located in Northeast China by combining the physically-based hydrological model with the data-driven model. Three hybrid models, SWAT-D-BiLSTM, SWAT-C-BiLSTM and SWAT-C-BiLSTM with SinoLC-1, were constructed in this study, in which SWAT was used as a transfer function to simulate the base flow and quick flow generation process based on weather data and spatial features, and BiLSTM was used to directly predict the streamflow according to the base flow and quick flow. In the SWAT-C-BiLSTM model, SWAT parameters with P values less than 0.4 in each hydrological station-controlled watershed were calibrated, while the SWAT-D-BiLSTM model did not undergo calibration. Additionally, this study utilizes both 30 m resolution land use and land cover (LULC) map and the first 1 m resolution LULC map SinoLC-1 as input data for the models to explore the impact on streamflow simulation performance. Among five models, the NSE of SWAT-C-BiLSTM with SinoLC-1 reached 0.93 and the R2 reached 0.95 during the calibration period, and both of them stayed at 0.92 even in the validation period, while the NSE and R2 of the other four models were all below 0.90 in the validation period. The potential impact of climate change on streamflow in the HRB was evaluated by using predicted data from five global climate models from CMIP6 as input for the best-performing SWAT-C-BiLSTM with SinoLC-1. The results indicate that climate change exacerbates the uneven distribution of streamflow in the HRB, particularly during the concentrated heavy rainfall months of July and August. It is projected that the monthly streamflow in these two months will increase by 34% and 49% respectively in the middle of this century. Furthermore, it is expected that the annual streamflow will increase by 5.6% to 9.1% during the mid-century and by 6.7% to 9.3% by the end of the century. Both average streamflow and peak streamflow are likely to significantly increase, raising concerns about more frequent urban flooding in the capital economic region within the HRB.

With global climate change and extreme weather events, water scarcity and environmental degradation are becoming increasingly prominent. Ecological replenishment is one important measure to enhance water quality in reservoirs. To address the severe pollution and ecological degradation problems of the Luhun Reservoir, this paper uses MIKE21 software to construct a coupled hydrodynamic-water quality model. Six recharge scenarios were designed to compare and explore the enhancement of reservoir water quality for these scenarios. The water quality status of these options was evaluated using the single-factor index method and the combined pollution index method. The results show that due to the ecological replenishment, the pollutant concentration leads the phenomenon of gradient diffusion to the center of the reservoir, and the average improvement rate of water quality is up to 40.22%. Schemes 2 and 5 have the lowest integrated pollution index. The most significant improvement in water quality was achieved at the same total recharge conditions, using 0.5 times the flow rate and two times the recharge time of the actual recharge project. The study results provide theoretical and technical support for the future management of the reservoir water environment. HIGHLIGHTS Verification of hydrodynamics and water quality in Luhun Reservoir using MIKE21 software.; The single-factor index method and the integrated pollution index method can accurately reflect the cleanliness of the watershed.; Using the actual project 0.5 times the flow rate and two times the recharge time can improve the water quality of Luhun Reservoir more effectively.;

Highly accurate rainfall prediction can provide a reliable scientific basis for human production and life. For the characteristics of occasional and sudden changes of rainfall in coastal hilly areas, this article chooses four cities in the eastern Zhejiang province as the object of the study and establishes a rainfall prediction model based on variational mode decomposition (VMD), reptile search algorithm (RSA), and differentiable neural computer (DNC). The VMD algorithm reduces the complexity of the sequence data; RSA is used to find the best-fit function; and DNC combines the advantages of the recurrent neural network and computational processing to improve the problem of memory forgetting of long short-term memory. To verify the prediction accuracy of the model, the prediction results are compared with the other three models, and the results show that the VMD–RSA–DNC model has the best prediction with the maximum and minimum relative errors of 9.62 and 0.17%, respectively, the average root-mean-square error of 5.43, the average mean absolute percentage error of 3.59%, and the average Nash–Sutcliffe efficiency of 0.95 for predicting four cities in the coastal hilly area. This study provides a new reference method for the construction of rainfall prediction models. HIGHLIGHTS Optimization of the differentiable neural computer (DNC) controller with reptile search algorithm (RSA) has a solid theoretical basis.; The coastal hilly area where plum rains and typhoons exist is selected for the study, and the prediction effect is better.; The coupled variational mode decomposition (VMD)–RSA–DNC model has higher prediction accuracy compared with other models.;

Water resources are vital to the development of human society, and mastering the law of runoff changes is the basis for achieving sustainable use of water resources. To study the impact of reservoir construction on the changes of downstream river runoff, this paper decomposes the runoff before and after reservoir construction using the CEEMDAN method based on the runoff data from the Huayuankou hydrological station. The fluctuation characteristics of each decomposition series of runoff before and after reservoir construction and the intra-annual variation pattern of runoff are also analyzed by combining multi-time information entropy and coefficient of variation. The results show that after the operation of the Xiaolangdi Reservoir, the annual runoff variation cycle tends to be flat, and the monthly runoff cycle is significantly reduced. After reservoir construction, the entropy values of each IMF and Res of runoff become larger, the complexity and randomness of runoff changes increase, and predictability decreases. Before and after the operation of the Xiaolangdi Reservoir, the coefficient of variation of runoff were 0.28–1 and 0.38–0.83, the distribution of runoff was more uniform, and the percentage of runoff in the flood season was reduced from 51.51 to 39.89%. HIGHLIGHTS Analysis of runoff data using CEEMDAN and multiscale information entropy.; Analysis from several perspectives, including inter- and intra-year perspectives.; Analysis of monthly runoff using dispersion coefficients and monthly runoff process lines.; The influence of the reservoir on the runoff of the lower Yellow River was studied.;

Abstract The accurate prediction of monthly runoff in the lower reaches of the Yellow River is crucial for the rational utilization of regional water resources, optimal allocation, and flood prevention. This study proposes a VMD-SSA-BiLSTM coupled model for monthly runoff volume prediction, which combines the advantages of Variational Modal Decomposition (VMD) for signal decomposition and preprocessing, Sparrow Search Algorithm (SSA) for BiLSTM model parameter optimization, and Bi-directional Long and Short-Term Memory Neural Network (BiLSTM) for exploiting the bi-directional linkage and advanced characteristics of the runoff process. The proposed model was applied to predict monthly runoff at GaoCun hydrological station in the lower Yellow River. The results demonstrate that the VMD-SSA-BiLSTM model outperforms both the BiLSTM model and the VMD-BiLSTM model in terms of prediction accuracy during both the training and validation periods. The Root-mean-square deviation of VMD-SSA-BiLSTM model is 30.6601, which is 242.5124 and 39.9835 lower compared to the BiLSTM model and the VMD-BiLSTM model respectively; the mean absolute percentage error is 5.6832%, which is 35.5937% and 6.3856% lower compared to the other two models, respectively; the mean absolute error was 19.8992, which decreased by 136.7288 and 25.7274 respectively; the square of the correlation coefficient (R 2 ) is 0.93775, which increases by 0.53059 and 0.14739 respectively; the Nash–Sutcliffe efficiency coefficient was 0.9886, which increased by 0.4994 and 0.1122 respectively. In conclusion, the proposed VMD-SSA-BiLSTM model, utilizing the sparrow search algorithm and bidirectional long and short-term memory neural network, enhances the smoothness of the monthly runoff series and improves the accuracy of point predictions. This model holds promise for the effective prediction of monthly runoff in the lower Yellow River.

Hebi is located in the northern part of China's Henan Province and is a typical receiving area for China's South-to-North Water Diversion Project. The assessment of habitat quality and water yield over a long time series is important for evaluating the stability of ecosystem services in Hebi and other receiving areas and for maintaining ecological security and promoting sustainable development. This paper aims to evaluate and dynamically analyse habitat quality and water yield in Hebi, and analyses the characteristics of changes in spatial and temporal patterns of land cover types, habitat quality and water yield in Hebi over the past 20 years, using 2000, 2005, 2010, 2015 and 2020 as horizontal years. The results indicate that: (1) During the study period, the overall land use type in Hebi City has been constantly changing, with the most significant conversion from arable land to other land types; combined with its landscape pattern index, Hebi City has a general characteristic of significant landscape fragmentation and complexity in land use. (2) Habitat quality in Hebi shows an overall trend towards better development, with water availability decreasing and then increasing; the zoning of ecosystem services in Hebi is divided into three classes: superior, good and general, with the area covered by the superior and general classes expanding year by year. (3) Correlation analysis by SPSS software shows that the correlation between habitat quality and landscape pattern index is greater than the correlation between habitat quality and climate change. Additionally, the correlation between water availability and climate change is greater than the correlation between water availability and landscape pattern index.

In recent years, with the growth of the population and the continuous expansion of agricultural land, non-point source (NPS) pollution has gradually become the primary cause of deteriorating water quality in the aquatic environment. Compared to point source pollution, NPS pollution is more diffuse, complex in its mechanisms, and challenging to pinpoint its sources. This study utilized the SWAT-Land Use Update Tool (SWAT-LUT) to dynamically update multi-year land use and land cover (LULC) data into the SWAT model to investigate the differences in nitrogen pollution sources in Jincheng City under different LULC scenarios. Two models were constructed in this study: SWAT-UNI, which utilized static 1997 LULC data, and SWAT-MULTI, which incorporated dynamic LULC data from 1997 to 2022. During the calibration period, SWAT achieved R2 and NSE values exceeding 0.82 for the daily streamflow simulation results, and these values remained above 0.76 during the validation period. Additionally, the Patch-generating Land Use Simulation (PLUS) model was employed to forecast the land use evolution in Jincheng City from 2022 to 2032 to explore the future response of NPS nitrogen pollution. From 1997 to 2022, significant changes were observed in agricultural land, forested land, and grassland areas within Jincheng City. Agricultural land and forested land increased by 3.29% and 4.71% of the total area of Jincheng City, respectively, while grassland decreased by 10.4%. In the prediction of land use evolution from 2022 to 2032, the evolutionary trends remained similar to previous patterns, albeit with a slightly decelerated pace. Simulation results indicated that the top three sources of nitrogen pollution in Jincheng City's water bodies in 1997 were atmospheric deposition (39.8%), nitrogen fertilizer application (29.8%), and soil nitrogen reservoirs (21.4%). With the continuous expansion of agricultural land, nitrogen pollution from nitrogen fertilizer application accounted for 35.6% of the TN (Total Nitrogen) load in water bodies in 2022, surpassing atmospheric deposition to become the dominant factor. The contribution of soil nitrogen reservoirs to nitrogen pollution in water bodies within Jincheng City showed a continuous upward trend over the twenty-five years, resulting in a total nitrogen load of 565.1 tons in 2022, ranking second and becoming a crucial aspect in pollution control efforts. Regarding seasonal distribution, the crop growing season (March to September) was identified as the critical period for controlling nitrogen pollution from nitrogen fertilizer application, while the autumn and winter seasons were crucial for controlling nitrogen pollution from atmospheric deposition and soil nitrogen reservoirs. The predictive results for future NPS nitrogen pollution indicate a continual increase in annual TN inflow into the river from nitrogen fertilizer application and soil nitrogen reservoirs, reaching 1841.6 tons in 2032, accounting for 65.2% of the total inflow. This research contributes to supporting decision-making for NPS pollution control measures in Jincheng City.

Runoff is one of the important hydrological variables of rivers, and its accurate prediction can provide a reliable basis for water resources system characterization and efficient utilization. In this paper, based on the advantages that the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) model can effectively overcome modal mixing and white noise interference, and the Auto-Regressive Integrated Moving Average (ARIMA) model can effectively overcome gradient disappearance and other problems, the coupled CEEMDAN–ARIMA prediction model is established, and the CEEMDAN–ARIMA model is used in the runoff prediction of the Lijin hydrological station in the lower Yellow River. The results show that the coupled CEEMDAN–ARIMA model has an R2 of 0.9398 and a Nash efficiency coefficient (NSE) of 0.918, with a prediction accuracy of Grade A. This shows that the CEEMDAN–ARIMA model has the ability to handle complex information in hydrological factor simulations, providing a new method for non-linear, non-stationary runoff prediction that has broad application prospects. HIGHLIGHTS A novel prediction model with the CEEMDAN–ARIMA method is proposed.; The highest point of the cumulative distance horizon is used as the dividing point between the training data and the predicted data.; The use of CEEMDAN to preprocess the data can effectively reduce the non-smoothness of the time series.; The prediction accuracy of the CEEMDAN–ARIMA model is better than NAR, ARIMA, and CEEMD–ARIMA models.;

The connectivity of urban water systems can enhance the connectivity of regional rivers, lakes, and water systems, which can improve the regional water environment and water ecology to a certain extent, and enhance the water disaster prevention capability. To scientifically evaluate the effect of water system connectivity in the comprehensive urban water system management project. In this study, a regional waterlogging model based on the coupling of ArcGis and SWMM is established. At the same time, the evaluation index system of water system connectivity effect of regional town water system comprehensive management project was constructed regarding PSR (“Pressure-Status-Response”) theory with structural connectivity, hydraulic connectivity and ecological and environmental improvement as the criteria, and the fuzzy evaluation method was used for analysis and evaluation. The results show that the improvement in the water environment is obvious after the water system is connected. The total length and area of rivers in the study area increased by 68.98% and 57.51%, respectively. River network density increased from 0.66 km/km2 to 0.69 km/km2, an increase of 4.55%; the regional water surface rate increased from 2.22% to 3.51%, an increase of 58.11%; the river frequency increased from 0.15/km2 to 0.29/km2, an increase of 93.33%. The water exchange capacity increased by 37.5% and the flow rate increased by 30%. All water systems have a better degree of connectivity and a better structure of river network water system. The decay rate of point source pollution increased by 40.61%, the water quality of rivers reached V standard, and the area covered by green areas increased to 32.29%. The evaluation grade of hydraulic characteristics and ecological environment indexes was “excellent”. The total evaluation set D=[0.5417,0.0791,0.2125,0] for the effect of water system connection in the study area. According to the principle of maximum affiliation, the improvement effect of the water system connection project in the study area is “excellent”.

As one of the important hydrological elements of rivers, flow is of great significance to the development and utilization of water resources and the ecological environment. Based on the excellent nonlinear processing capability of CEEMDAN and the advantages of BILSTM in time-series data modeling, a coupled CEEMDAN-BILSTM model is constructed for flow prediction, and the i-month flows from 1951 to 2016 are used to predict the i-month flows from 2017 to 2021. The results show that the CEEMDAN-BILSTM coupled model predicts the trend more closely with the actual data variation, and the minimum relative error is 0.56 and maximum 9.48, which are maintained within 10%, and the deterministic coefficients are all greater than 0.9, so the prediction accuracy is high. The flow in month i of 5 years was picked up by monthly predictions for 66 consecutive years, which provides a new way of thinking about the prediction of river flow. HIGHLIGHTS Predicting i-months in the 5 years of 2017–2021 by i-months in the 66 years of 1951–2016 can reduce the large flow volatility caused by the abundant and dry periods due to external conditions such as rainfall.; CEEMDAN can effectively improve the modal mixing problem of EMD method, and the decomposition process of CEEMDAN is complete.;

Abstract Accurate medium and long-term runoff forecasts play a vital role in guiding the rational exploitation of water resources and improving the overall efficiency of water resources use. Machine learning is becoming a common trend in time series forecasting research. Least squares support vector machine (LSSVM) and grey model (GM(1,1)) have received much attention in predicting rainfall and runoff in the last two years. “Decomposition-forecasting” has become one of the most important methods for forecasting time series data. Complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) decomposition method has powerful advantages in dealing with nonlinear data. Least squares support vector machine (LSSVM) has strong nonlinear fitting ability and good robustness. Gray model (GM(1,1)) can solve the problems of little historical data and low serial integrity and reliability. Based on their respective advantages, a combined CEEMDAN–LSSVM–GM(1,1) model was developed and applied to the runoff prediction of the lower Yellow River. To verify the reliability of the model, the prediction results were compared with the single LSSVM model, the CEEMDAN–LSSVM model and the CEEMDAN–support vector machines (SVM)–GM(1,1). The results show that the combined CEEMDAN–LSSVM–GM(1,1) model has a high accuracy and the prediction results are better than other models, which provides an effective prediction method for regional medium and long-term runoff prediction and has good application prospects.

Scientific precipitation predicting is of great value and guidance to regional water resources development and utilization, agricultural production, and drought and flood control. Precipitation is a nonlinear, non-smooth time series with significant stochasticity and uncertainty. In this paper, a complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) with long short-term memory (LSTM) model is developed for predicting annual precipitation in Zhengzhou city, China, which is compared with a single LSTM model, an ensemble empirical mode decomposition–LSTM model, a complementary ensemble empirical mode decomposition–LSTM model, and a CEEMDAN–autoregressive integrated moving average and a CEEMDAN–recurrent neural network model. The results show that the mean absolute percentage error, root mean square error, and coefficient of determination of the coupled CEEMDAN–LSTM model are 2.69%, 17.37 mm, and 0.9863, respectively. The prediction accuracy is significantly higher than that of the other five models, indicating that the proposed model has high prediction accuracy and can be used for annual precipitation forecasting in Zhengzhou city. HIGHLIGHTS The CEEMDAN method adds adaptive Gaussian white noise in the decomposition, which effectively reduces the reconstruction error.; LSTM can effectively overcome the gradient explosion problem of recurrent neural networks and has significant advantages in handling long time series data.; The CEEMDAN–LSTM coupled model has good learning ability in dealing with nonlinear and non-smooth hydrological factor sequences.;

The prediction of monthly precipitation is of great importance for regional water resources management and use. The monthly precipitation sequence is affected by various factors such as atmosphere, region and environment, and has obvious ambiguity, chance and uncertainty. CEEMD based on complementary ensemble empirical mode decomposition can effectively reduce the reconstruction error of time series, and bidirectional long short-term memory (BILSTM) model can effectively learn long-term dependencies in time series. A CEEMD-BILSTM (complementary integrated empirical mode decomposition-bidirectional long short-term memory) coupled model is constructed to predict the monthly precipitation in Zhengzhou, and the performances of the LSTM model, EEMD-LSTM model and EEMD-BILSTM model are compared. The CEEMD-BILSTM model has a maximum relative error of 7.28%, a minimum relative error of 0.00%, and an average relative error of 2.68%, with an RMS error of 2.6% and a coefficient of determination of 0.97 in predicting monthly precipitation in Zhengzhou, which is considered a good accuracy of the CEEMD-BILSTM model for predicting monthly precipitation in Zhengzhou. The model is better than the LSTM model, the EEMD-LSTM model, and the EEMD-BILSTM model and has better fitting ability. It also shows that it has strong nonlinear and complex process learning ability in the hydrological factor model of regional precipitation prediction. HIGHLIGHTS CEEMD is a novel data preprocessing method, which can effectively reduce the nonsmoothness of time series.; BILSTM models can efficiently learn long-term dependencies in time series.; CEEMD-BILSTM model has a higher prediction level, and the model is feasible for monthly precipitation prediction.;

Affected by urban construction and industrial discharge, the diffuse source pollution of river water environment in urban sections is becoming more and more serious. The use of numerical models can accurately and efficiently simulate the process of diffuse source pollution and analyze its evolution. Based on MIKE21, the urban river water environment model of the Bai river is constructed. After parameter calibration, it is proved that the model has high accuracy. Based on the discharge of this river section in 2018, the river diffuse source pollution is simulated under three hydrological conditions, and the BP neural network is used to simulate the river diffuse source pollution. Network assessment of water quality in dry years. The results showed that the four water quality indicators showed the spatial distribution characteristics of upstream>urban section>downstream, and the river water quality in the year showed the temporal distribution characteristics of flood season better than a non-flood season. The mean value of the coefficient of certainty R2 reaches 0.94 when comparing the simulated and measured values, which indicates that the model has high applicability and satisfactory fit. If the water quality of the water year does not meet the standard, the diffuse source pollution discharge should be reduced from May to October. This study can provide reference and guidance for urban river diffuse source pollution control. HIGHLIGHT A two-dimensional hydrodynamic model was developed using MIKE software and validated by field test data to determine the two-dimensional model parameters, including flow rate, flow velocity, eddy viscosity coefficient, boundary conditions, roughness, etc.;

In order to improve the accuracy of hydrological models for runoff prediction and to solve the problem of disappearing time series data break or data fluctuation due to the extension of time series, monthly runoff data from 1996 to 2015 at the Cuntan hydrological station in the upper reaches of the Yangtze River are used as the basis to develop the annual runoff prediction. Prediction of the five Intrinsic Mode Function (IMF) components and one residual from the Ensemble Empirical Mode Decomposition (EEMD) decomposition used different models of Auto-Regressive Integrated Moving Average Model (ARIMA). Except for the small errors in the first two components, the rest of the ARIMA models are highly fitted. For prediction of runoff in 2014 and 2015 based on EEMD-ARIMA model, the relative errors are 6.26% and −1.17%. Compared with the single ARIMA model and Back Propagation (BP) model, the prediction effect is better, and the prediction method is simple and clear. It is shown that the combined EEMD-ARIMA model is an efficient and useful method for the prediction of annual runoff volume. HIGHLIGHTS The study used 240 months of runoff data from Cuntan hydrological station in the upper reaches of the Yangtze River.; An annual runoff prediction model based on EEMD-ARIMA hybrid method is proposed.; The EEMD-ARIMA model outperforms the EMD-ARIMA, BP, and LSTM models.;

The prediction of river runoff is crucial for flood forecasting, agricultural irrigation and hydroelectric power generation. A coupled runoff prediction model based on the Gravitational Search Algorithm (GSA) and the Seasonal Autoregressive Integrated Moving Average (SARIMA) model is proposed to address the non-linear and seasonal features of runoff data. The GSA has a significant local optimisation capability, while the SARIMA model allows for real-time adjustment of the model using historical data and is suitable for analysing time series with seasonal variations. Consequently, the GSA-SARIMA model was developed and applied to the runoff prediction of the Xianyang section of the Wei River. The results suggest that the GSA-SARIMA model achieves a linear correlation coefficient of 0.9351, a Nash efficiency coefficient of 0.91, a mean relative error of 6.57 and a root mean square error of 0.21. All of the evaluation indicators of this model outperform the other models developed, and its application to actual runoff prediction is feasible, which creates a new path for runoff prediction. HIGHLIGHTS The Mann-Kendall trend test is applied to ascertain the separation point between the training and prediction datasets. It avoids too little data in the test set, while effectively improving the generalisation of the model.; The SARIMA model is an improvement on the ARIMA model and allows for convenient real-time adjustment of the model.; The GSA algorithm is applicable to parameter search optimization of the model and has great global search capability.;

Abstract Background Recognition of viral invasion by innate antiviral immune system triggers activation of the type I interferon (IFN-I) and proinflammatory signaling pathways. Subsequently, IFN-I induction regulates expression of a group of genes known as IFN-I-stimulated genes (ISGs) to block viral infection. The tripartite motif containing 22 (TRIM22) is an ISG with strong antiviral functions. Results Here we have shown that the TRIM22 has been strongly upregulated both transcriptionally and translationally upon Zika virus (ZIKV) infection. ZIKV infection is associated with a wide range of clinical manifestations in human from mild to severe symptoms including abnormal fetal brain development. We found that the antiviral function of TRIM22 plays a crucial role in counterattacking ZIKV infection. Overexpression of TRIM22 protein inhibited ZIKV growth whereas deletion of TRIM22 in host cells increased ZIKV infectivity. Mechanistically, TRIM22, as a functional E3 ubiquitin ligase, promoted the ubiquitination and degradation of ZIKV nonstructural protein 1 (NS1) and nonstructural protein 3 (NS3). Further studies showed that the SPRY domain and Ring domain of TRIM22 played important roles in protein interaction and degradation, respectively. In addition, we found that TRIM22 also inhibited other flaviviruses infection including dengue virus (DENV) and yellow fever virus (YFV). Conclusion Thus, TRIM22 is an ISG with important role in host defense against flaviviruses through binding and degradation of the NS1 and NS3 proteins.

Groundwater resources play an important role in life, but the lack of effective management of groundwater resources has led to a regional decline in groundwater levels. How to curb the over-exploitation of groundwater and realize the sustainable use of groundwater resources has become an important issue for ecological environmental protection. Therefore, accurate prediction of groundwater depth is an important foundation for the rational use of groundwater resources. Based on the significant advantages of empirical model decomposition (EMD) in dealing with non-smooth and nonlinear data and the long-term memory function of long and short-term memory (LSTM) network, a coupled EMD-LSTM-based groundwater prediction model is constructed and apply to groundwater depth prediction of three professional observation wells. The results show that the maximum relative error of the prediction results of the EMD-LSTM model for the three professional observation wells is 5.00% and the minimum is 0.07%. The prediction passing rate is 100% and the prediction accuracy of the coupled model for groundwater depth is higher than that of the single LSTM model and back-propagation (BP) model. In conclusion, the model has high prediction accuracy and provides an effective method for the prediction of groundwater depth. HIGHLIGHTS Empirical mode decomposition (EMD) is a relatively novel data preprocessing method that can effectively reduce the non-smoothness of time series.; LSTM is considered to be superior in terms of learning rate and generalization ability.; The EMD-LSTM coupled model has better nonlinear and complex process learning ability in groundwater forecasting.;

This paper presents numerical simulations regarding the transport characteristics of soil salt. It has been recognized in recent years that the growth and output of crops in the irrigation area of the lower reaches of the Yellow River are affected by the decreased fertility of soil as a result of the transport of soil salt, due to the long-term farming, fertilization of farmland which contains a high proportion of sands. Accordingly, numerical simulations by Hydrus are carried out, in which, based on the similarity principle, two-dimensional convection-diffusion partial-differential governing equations of unsteady flow in saturated-unsaturated porous media are applied to depict the motion parameters’ spatial variability of soil water in the irrigation area. And the van Genuchten equation is adopted to express the relationship between volumetric water content and soil hydraulic conductivity and negative soil water pressure. The irrigation basin of the People’s Victory Canal, which is downstream of the Yellow River, is investigated in detail as an example. The findings revealed that soil salt in the irrigation region is transferred by water diffusion, with irrigation and fertilization being the primary causes of downward migration and salt accumulation. It benefits the soil in irrigation areas and protects groundwater.

The wetting deformation of coarse-grained materials can seriously affect the safety of earth and rock dams during initial water storage. The wetting model formulas are expressed in various forms and have complex parameters. Only a small amount of test data is fitted by mathematical statistics, and the universality of the obtained wetting model is unknown. Duncan-Chang E-B constitutive model cannot accurately reflect the wetting deformation characteristics of coarse-grained materials. Through the double-line wetting test of coarse-grained materials, the wetting model proposed by predecessors was verified and analyzed. Based on the indoor wetting test data, the parameters of each wetting model were fitted to analyze the accuracy of each wetting model in describing the wetting deformation characteristics. According to the P-Z model in the elastic-plastic theory and the wetting model formula, the P-Z wetting model is established, and the BP artificial neural network is introduced to establish the artificial neural network wetting deformation prediction model based on the P-Z model. The results show that the relationship between wetting axial strain and wetting stress level is best expressed by the exponential function. The relationship between wetting volumetric strain and wetting stress level is best described by Cheng’s linear function. The relative errors between the predicted and experimental values of the proposed neural network prediction model are all within 6%. The relationship between wetting axial strain and wetting stress level is exponential function, and the relationship between wetting volumetric strain and wetting stress level is linear function. The P-Z wetting model proposed in this research can better reflect the wetting deformation characteristics of coarse-grained materials under complex stress paths. The artificial neural network prediction model based on P-Z wetting model is more reliable and accurate, which can meet the prediction requirements of actual engineering for wetting deformation of coarse-grained materials.

IntroductionPulmonary fibrosis is a consequential complication of microbial infections, which has notably been observed in SARS-CoV-2 infections in recent times. Macrophage polarization, specifically the M2-type, is a significant mechanism that induces pulmonary fibrosis, and its role in the development of Post- COVID-19 Pulmonary Fibrosis is worth investigating. While pathological examination is the gold standard for studying pulmonary fibrosis, manual review is subject to limitations. In light of this, we have constructed a novel method that utilizes artificial intelligence techniques to analyze fibro-pathological images. This method involves image registration, cropping, fibrosis degree classification, cell counting and calibration, and it has been utilized to analyze microscopic images of COVID-19 lung tissue.MethodsOur approach combines the Transformer network with ResNet for fibrosis degree classification, leading to a significant improvement over the use of ResNet or Transformer individually. Furthermore, we employ semi-supervised learning which utilize both labeled and unlabeled data to enhance the ability of the classification network in analyzing complex samples. To facilitate cell counting, we applied the Trimap method to localize target cells. To further improve the accuracy of the counting results, we utilized an effective area calibration method that better reflects the positive density of target cells.ResultsThe image analysis method developed in this paper allows for standardization, precision, and staging of pulmonary fibrosis. Analysis of microscopic images of COVID-19 lung tissue revealed a significant number of macrophage aggregates, among which the number of M2-type macrophages was proportional to the degree of fibrosis.DiscussionThe image analysis method provids a more standardized approach and more accurate data for correlation studies on the degree of pulmonary fibrosis. This advancement can assist in the treatment and prevention of pulmonary fibrosis. And M2-type macrophage polarization is a critical mechanism that affects pulmonary fibrosis, and its specific molecular mechanism warrants further exploration.

The analysis of annual precipitation evolution characteristics is of great value and significance for revealing the spatial and temporal variation patterns of regional precipitation, water resources development and utilization, short-term climate, drought, flood disaster prediction, etc. The Mann-Kendall (MK) mutation test, cumulative distance level method, and Morlet wavelet analysis were used to analyze the precipitation evolution in Anhui Province from 1961 to 2020. The results showed that the average annual temperature and precipitation in Anhui Province showed a significant increasing trend during 1961–2020, with warming and humidification. 1994 was the year of abrupt climate change in Anhui Province, and the temperature after the abrupt change was 2.10 times that before the abrupt change. El Niño-Southern Oscillation (ENSO) has a synchronized resonance cycle with droughts and floods in Anhui Province at 5.8 a. The annual scale of ENSO events is an important theoretical support for regional drought and flood warnings. The chance of drought and flooding in Anhui Province is greater than 50% in the year of ENSO event or two years after the event, and the year of ENSO event or the year after is prone to drought and flooding, so we should strengthen the flood and drought warning, disaster prevention and mitigation. HIGHLIGHTS Changes in precipitation characteristics and changes in droughts and floods were analyzed from the provincial scale.; Anhui Province tends to be warm and humid after the sudden change of temperature.; The frequency of droughts and floods increases after sudden changes in temperature.; Droughts and floods are one of the most frequent and serious meteorological disasters in Anhui Province.;

The simulation of precipitation changes can provide references for the prediction and prevention of flood disasters, and has guiding significance for the comprehensive utilization of regional water resources. Precipitation forecasting is difficult due to the randomness and uncertainty of precipitation events. CEEMD can effectively overcome modal aliasing and white noise interference. The WTD process has obvious denoising effects on the original signal. GRU can effectively solve long-term memory and reflection. Based on the advantages of problems such as gradients in propagation, a CEEMD-WTD-GRU precipitation prediction coupling model is constructed. The second decomposition of CEEMD-WTD-GRU can more effectively extract complex time series information. The time series forecasting provided a new method, which effectively improved the accuracy of the forecast and applied it to the forecast of monthly precipitation in Shanghai. The research results show that the average absolute error of the CEEMD-WTD-GRU model is 3.86, the average relative error is 3.30%, and the Nash efficiency coefficient is 0.99. The prediction accuracy is better than the CEEMD-WTD-GRU model without noise reduction, the CEEMD-LSTM model and GRU model, which shows that it has strong nonlinear and complex process learning ability in hydrological factor simulation, and can be used for regional precipitation prediction. HIGHLIGHTS Complementary ensemble empirical modal decomposition (CEEMD) is a relatively novel data preprocessing method that can effectively reduce the non-smoothness of time series.; Wavelet threshold noise (WTD) reduction is an excellent noise reduction technology that can effectively reduce the noise in the signal.; Gated Recurrent Unit (GRU) as a prediction model is more adept at handling long time series.;

Rainfall prediction is a very important guideline for water resources management as well as ecological protection, and its changes are the result of multiple factors with obvious uncertainties and nonlinearities. Based on the advantages of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) non-smooth signal decomposition, the Particle Swarm Optimization (PSO) can be used to optimize the input weights and thresholds of the Extreme Learning Machine (ELM), which can effectively improve the prediction effect and accuracy of ELM, and a rainfall prediction model based on CEEMDAN-PSO-ELM is constructed. The model is applied to the monthly rainfall prediction of Zhongwei City, and the results show that the CEEMDAN-PSO-ELM coupled model has a high prediction accuracy, the mean absolute error (MAE) is 1.29, relative percentage error (RPE) is 0.45, root mean square error (RMSE) is 1.43 and the Nash efficiency coefficient (NSE) is 0.93. It has obvious advantages in hydrological simulation prediction when compared and analyzed with the deep Long-Short Term Memory (LSTM), PSO-ELM coupled model and ELM model. HIGHLIGHTS CEEMDAN is a novel data preprocessing method, which can effectively reduce the nonsmoothness of time series.; ELM has advantages in learning rate and generalization ability. PSO can optimize the input weight and threshold of ELM and effectively improve the prediction accuracy of elm.; CEEMDAN-PSO-ELM coupling model has good nonlinear and complex process learning ability in hydrological simulation.;

Precipitation forecasting is an important guide to the prevention and control of regional droughts and floods, the rational use of water resources and the ecological protection. The precipitation process is extremely complex and is influenced by the intersection of many variables, with significant randomness, uncertainty and non-linearity. Based on the advantages that complementary ensemble empirical modal decomposition (CEEMD) can effectively overcome modal aliasing, white noise interference, and the ability of long short-term memory (LSTM) networks to handle problems such as gradient disappearance. A CEEMD–LSTM coupled long-term and short-term memory network model was developed and adopted for monthly precipitation prediction of Zhengzhou City. The performance shows that the CEEMD–LSTM model has a mean absolute error of 0.056, a root mean square error of 0.153, a mean relative error of 2.73% and a Nash efficiency coefficient of 0.95, which is better than the CEEMD–Back Propagation (BP) neural network model, the LSTM model and the BP model in terms of prediction accuracies. This demonstrates its powerful nonlinear and complex process learning capability in hydrological factor simulation for regional precipitation prediction. HIGHLIGHTS Complementary ensemble empirical modal decomposition (CEEMD) is a relatively novel data preprocessing method that can effectively reduce the non-smoothness of time series.; Long short-term memory network (LSTM) as a prediction model is more adept at handling long time series.; The CEEMD–LSTM coupled has better nonlinear and complex process learning ability in hydrological factor simulation.;

Scientific and accurate prediction of river runoff is important for river flood control and sustainable use of water resources. This study evaluates the ability of a Nonlinear Auto Regressive model (NAR) in predicting runoff volume. Using the Cuntan Hydrological Station in the upper reaches of the Yangtze River as the research object, the model was established based on the runoff characteristics from 1951 to 2020 and tested by NAR. To improve the prediction efficiency, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) preprocessing technique is used to decompose the data. The results show that the coupled CEEMDAN-NAR model has better predictive ability than the single model, with a coupled model deterministic coefficient (DC) of 0.93 and a prediction accuracy of Class A. HIGHLIGHTS Proposed a runoff prediction model using CEEMDAN-NAR hybrid approach.; Decomposition of runoff data using CEEMDAN preprocessing techniques to improve model prediction accuracy.; Using models to predict runoff in the upper Yangtze River from 2005 to 2020 and verifying their accuracy; The CEEMDAN-NAR model provides better predictions than the GRU, NAR and EEMD-NAR prediction models.;

The different shapes of bridge piers across rivers have a great influence on the river water movement, and the study of the influence of pier morphology changes on the water movement characteristics is of great value for bridge design and river flooding. The hydrodynamic model can effectively simulate and predict the changes of river flow patterns, which can provide scientific data support for river management. This paper constructs a hydrodynamic model based on MIKE21 and applies it to the numerical simulation of river hydrodynamics in the lower reaches of the Yellow River, taking elliptical piers as an example, and simulates the effect of the change of pier morphology on the flow velocity, water level and flow field of the river. The results show that the effect of elliptical pier morphology on the flow characteristics of the river channel is significant; under the same flow rate, the congestion value of the pier at the maximum axis ratio is 1.65 times the minimum axis ratio, and the larger the axis ratio, the more serious the congestion; the difference in flow velocity at the maximum axis ratio can reach 2.33 times the minimum axis ratio. HIGHLIGHTS This paper uses MIKE21 numerical simulation to analyze and study the changes in river congestion and flow patterns caused by bridge construction, and to provide more practical simulation data for the construction of cross-river bridges.; The Nash efficiency coefficient of 0.94 is highly accurate in the model validation and evaluation.;

The study of the temporal and spatial evolution of precipitation is of great importance for the efficient use of water resources. This paper examines the long series of precipitation in Henan province from 1959-2018. Innovative Trend Analysis (ITA) method and Mann-Kendall (MK) test were used to analyze the characteristics of precipitation trend changes. Mann-Kendall (MK) mutation test and the sliding T method were used to study the jump features of precipitation. Wavelet analysis of the cyclical characteristics of precipitation. The results show that the spatial distribution of precipitation in Henan Province is uneven, with a gradual increase from north to south. The precipitation of northern, central and southern regions showed a downward trend, while that of western regions showed an upward trend. Both the northern and southern regions experienced jump features in precipitation around 1975 and 2008, while the western region experienced jump features around 1962 and 1980, and the central region experienced jump features around 1980; There are 3.5 different scales of “abundance and depletion” in the northern, western and southern regions, with a first principal cycle of 28a, and 5.5 different scales of “abundance and depletion” in the central region, with a first principal cycle of 17a.

It is of great value to reveal the self-purification capacity of surface-sourced nutrients in the watershed and its change pattern, which is important to enrich the study of self-purification capacity of rivers and provide scientific basis for river water environment management. Based on the SWAT model and different self-purification capacity expression indicators, the self-purification capacity of non-point source pollutant nutrients and its change pattern in each river section of the Yiluo River basin from 2018 to 2021 were analyzed, and the physical significance of each indicator, its influence factor and its use range were systematically discussed. The results show that the self-purification of TN and TP in the Yiluo River exceeds 50% of the self-purification of the whole water system, but the self-purification rate is smaller than that of the Yiluo and Luo Rivers; the self-purification of TN and TP is the largest during the abundant water period and the smallest during the dry water period. The self-purification capacity expressed by the indicators of self-purification amount RL and area self-purification amount RA increases with the increase of hydrological variables such as flow (including water depth and velocity), river morphological parameters such as river width and length, and pollutant load; The self-cleaning ability expressed by the self-cleaning coefficient Kx/Kt, self-cleaning length SL, self-cleaning rate Re and load weight self-cleaning rate RLw is opposite; The self-purification rate Vf of the river only increases with the increase of water temperature. From the perspective of differences in application, the two indicators of self-purification speed Vf and area self-purification amount RA should be used for spatial comparison; The other six indicators should be used for the comparison of the same river at different times, of which the self-purification length SL can be used to reflect the influence of hydrological conditions on the self-purification process because of its sensitivity to changes in hydrological conditions.

The shape of bridge piers across rivers is one of the significant factors that affect the backwater in the river. The study on the influence of bridge pier shapes on the flow patterns of the river is valuable to the design of the bridge and river flooding. Based on the MIKE21 Flow Model hydrodynamic model, dynamic numerical simulations were conducted to investigate the effect of different shapes of bridge piers on water flow. The result shows that rectangular, circular and elliptical piers have a water blocking effect on the river. The flow patterns changed in local areas near the piers. Under the same flow rate, the backwater of the rectangular pier was the largest, followed by the circular piers, and the elliptical pier was the smallest. The value of backwater volume caused by the rectangular pier was 1.95 times the elliptical pier. The elliptical bridge piers basically do not change the overall flow patterns of the river, and have little effect on the river regime. This work provides a reference for the layout of river bridge piers. Highlights The MIKE21 FM module is used to analyze the numerical simulation of different pier shapes under different working conditions, as well as the backwater conditions and speed changes.; The MIKE21 numerical model can simulate complex terrain well. The relative error of the model in the calibration process is less than 1%, and the Nash efficiency coefficient is 0.97.;

Precipitation is an important component in the climate system and plays a key role in water resources protection, drought and flood prevention. Innovation Trend Analysis (ITA) method, R/S method, maximum entropy spectrum analysis and wavelet analysis were used to study the evolution characteristics of the Yellow River Delta annual precipitation from 1954 to 2014. The results suggest that the precipitation series changed significantly and showed an overall downward trend, and may show an upward trend in the future, which is relatively strong. There are three-time scales of annual precipitation variation: 20-32a, 8-18a, and 3-6a. The quasi-27 year was the main oscillation period of the average annual precipitation in the Yellow River Delta, the secondary major period was 13 years, and the small-scale oscillation period was 5 years. Precipitation changed suddenly in 1980 and 2003. In contrast, there was no significant mutation point in 2002-2014.

Reservoir dams have varying degrees of damage and hidden dangers under long-term and complex operating conditions, engineering problems mainly focus on the gradual decrease of seepage stability and guarantee rate of deformation and stability of dam foundation. However, due to the complexity of the dam foundation structure and the surrounding environment, the performance degradation of the dam foundation caused by the aging of the impervious structure lacks a systematic study of the process and its mechanism, In particular, the determination of relevant seepage parameters is complicated, moreover the simulation accuracy of its inversion model is not enough to meet the needs of long-term stability evaluation of the dam foundation. In order to study the seepage stability of the dam foundation of the reservoir during operation, a three-dimensional finite element model of complex geological bodies is combined with artificial neural network to establish a model of inversion of seepage field in the dam foundation, According to the 22 groups of predicted grouting schemes, five groups of representative grouting schemes were selected and the seepage characteristics of the same location were analyzed. The conclusions as below: (1) the inversion predicted that when the permeability coefficient was in the range of 3.0 × 10−6 cm/s to 5.0 × 10−6 cm/s, the change range was small, and the curtain's anti-seepage effect was more obvious. (2) The analysis of the dam base surface and the bottom of the grouting area shows that the difference between the water head and seepage gradient of the dam base surface and the bottom of the grouting area under the GZ7 and GZ3 schemes vary significantly with the grouting effect. Among them, especially in the GZ3 scheme, the key parts of the dam foundation surface F2 ~ F4: the seepage gradient value gradually increases, and all reach the maximum value in the GZ3 scheme; For G6 ~ G15 at the bottom of the grouting area, the water head value under the GZ3 scheme is gradually smaller than the three grouting schemes of GZ11, GD3 and GD7, as the water head value gradually decreases, the anti-seepage effect becomes more and more obvious. The above results show that the inversion prediction range is in good agreement with the actual law, when the permeability coefficient is within the predicted range, the anti-seepage effect is optimal. (3) The difference of the water head and seepage gradient difference between the dam foundation and the grouting area near the curtain changes significantly with the grouting effect. Characteristics of seepage field in key parts of the dam foundation under the six curtain grouting coefficients, the water head value F1-F2 decreased by 75%, F3-F13 decreased by 28%, the seepage gradient value F1-F2 decreased by 88%, and F3-F13 decreased by 29%, namely the grouting effect of the dam foundation and the grouting area gradually weakens as the distance between the characteristic part and the curtain increases. The research in this paper can provide a theoretical reference for the analysis and evaluation of dam seepage conditions.

In order to study the strength and development rate of the chemical erosion of the stilling pool base slab and analyze the influence of chemical erosion on the strength and durability of the stilling pool base slab, it established a reverse constitutive model of the chemical erosion of concrete of the stilling pool base slab. The model calculation results show that the results of the model calculation and prototype tests are in good agreement. Conclusion: 1) Most easily soluble mineral components in the concrete of the stilling pool base slab are cement hydration products, such as cement (Ca(OH)2). Compared with the active calcium ion content in the infiltration liquid, the higher the active calcium ion content in the exudate, the stronger the reaction between water seepage and concrete, and the higher the pH value of the exudate; 2) Under given leakage conditions, the greater the amount of material exchange between the stilling pool base slab and the water, the more severe the chemical erosion of the concrete; 3)The intensity of chemical erosion has a good correlation with the degree of damage to the surface of the concrete, that is, when the surface damage is relatively serious, the chemical erosion process is fast, otherwise it is slow.

By simulating and estimating non-point source pollution in Luoyang, the sources and spatial distribution of nitrogen pollution sources in this region were revealed, which provided a decision-making basis for further promoting non-point source pollution control and governance. Based on the SWAT model and different scenarios, the non-point nitrogen pollution sources in Luoyang from 2009 to 2018 were quantitatively identified, and the reasons for their changes under different pollution sources and different land uses were analyzed. The results show: From the analysis of different pollution source types, the main sources of non-point source pollution total nitrogen (TN) are nitrogen fertilizer application, atmospheric deposition and soil nitrogen reservoirs, and the pollution brought by livestock and poultry breeding and rural life is relatively low; From the analysis of different land use types, the entry coefficient of each non-point source TN pollution in Luoyang region is ranked as follows: atmospheric deposition (18.1%) > nitrogen fertilizer application (14.7%) > rural life (12.5%) > livestock manure (2.9%) > soil nitrogen pool (0.2%); Different pollution sources have different critical control periods, the key period for controlling natural sources (soil nitrogen pools and atmospheric deposition) is the rainy season, while the focus for controlling anthropogenic sources (rural living, livestock and poultry farming and fertilizer application) is the period of pollution cast emissions. In terms of time, the key period for controlling natural sources (soil nitrogen pool and atmospheric deposition) is the rainy season, while the key period for controlling anthropogenic sources (rural life, livestock and poultry breeding and application of chemical fertilizers) is the period of pollution input and emission; The key pollution sources of different land uses are also different. The key pollution sources of non-point source pollution of garden land and human settlements are nitrogen fertilizer application and domestic sewage, while the three major pollution sources of paddy field and dry land are nitrogen fertilizer application, atmospheric deposition and soil nitrogen pool.

In recent years, ecological water replenishment has become the main means to improve the water environment of the reservoir. Considering the complexity of the water characteristics of the reservoir, it is very necessary to simulate the impact of water replenishment on the water environment. Based on the two-dimensional water environment mathematical model theory, the water environment model of Baiguishan Reservoir was constructed by Mike21. Under the conditions of 6 different ecological water replenishment scenarios, the evolution characteristics and improvement of the water environment of the reservoir were analyzed. Finally, the cloud model was used to comprehensively evaluate the results and compare them. Come up with the best ecological water replenishment plan. The results show that the strong convective diffusion phenomenon caused by the large flow of water replenishment makes the water quality show a cascade distribution, and the water quality improvement rate can reach up to 40.01%. Optimal; the water body with large flow replenishment has better fluidity and reoxygenation ability, which improves the self-purification ability of the water body. The comparison with the actual replenishment effect shows that the effect of large flow and short duration is better under the same replenishment amount. The quantitative analysis results of pollutants under different scenarios can provide a scientific basis for the construction of the South-to-North Water Diversion Project and the ecological restoration of the reservoir.

The eco-environmental vulnerability is an important indicator of the development in wetland. However, the vulnerability is influenced by various interacting factors. The interaction among these factors is fuzzy and stochastic, making it difficult to describe the evaluation results accurately and quantitatively. To overcome the difficulty, this study takes the Yellow River Delta wetland as object, and makes an accurate vulnerability evaluation. Through investigations, the author establishes a four-layer evaluation indicator system, including a target layer, a criterion layer, an indicator layer and an element layer. The cloud model theory is introduced to describe qualitative indicators. Meanwhile, two cloud models are constructed, respectively, the comment layer and the membership of the element layer. In addition, the indicator weight is solved by the queuing theory. In this way, the state of each indicator is quantified in an accurate manner. The results show that the comprehensive evaluation of the eco-environmental vulnerability in the study area is C (0.697, 0.083, 0.017) and the corresponding eco-environmental vulnerability falls to the “strong vulnerability” level. The results, compared with the catastrophe progression method, are valid. The research results provide technical support for the comprehensive evaluation of eco-environmental vulnerability in wetland.

According to the problems in dynamic stability analysis for slopes of earth and rockfill dam, the P-Z constitutive model, which is a kind of the multi-mechanism plastic model based on generalized plasticity, is introduced in the paper. Strength reduction factors of P-Z model are derived and verified, and based on them a new kind of method of dam slopes dynamic stability is put forward. For the method, the dynamic stability of dam slopes is judged by dynamic displacement time history and post-earthquake permanent displacement. The results show that local instability of dam slopes and variation features of dynamic response are obtained by the method, which is more reasonable.