Search

This study proposes a hybrid model based on the combination of Sand Cat Swarm Optimization (SCSO), Echo State Network (ESN), Gated Recurrent Unit (GRU), Least Squares Method (LSM), and Markov Chain (MC) to improve the accuracy of annual runoff prediction. Firstly, conduct correlation analysis on multi-factor data related to runoff to determine the input of the model. Secondly, the SCSO algorithm is used to optimize the parameters of the ESN and GRU models, and the SCSO-ESN and SCSO-GRU models are established. Next, the prediction results of these two models are coupled using LSM to obtain the preliminary prediction results of the SCSO-ESN-GRU model. Finally, the initial prediction results are corrected for errors using MC to get the final prediction results. Choose Changshui Station and Lanxi Station for experiments, and evaluate the predictive performance of the model through five evaluation indicators. The results show that the combined prediction model corrected by the MC achieved the optimal prediction performance at both experimental stations. This study emphasizes that using a combination prediction model based on Markov chain correction can significantly improve the accuracy of annual runoff prediction, providing a reliable basis for predicting annual runoff in complex watersheds. HIGHLIGHTS A new hybrid sand cat swarm optimization-echo state network-gated recurrent unit-Markov chain (SCSO-ESN-GRU-MC) model is proposed for annual runoff prediction.; A new SCSO algorithm is used to optimize the parameters of the prediction model.; Least squares method is used to couple the ESN and GRU models for annual runoff prediction.; MC is used to correct errors in annual runoff prediction results.; The proposed model achieves the best prediction results at both experimental stations.;

Abstract Purpose Hepatocellular carcinoma (HCC) has a poor prognosis, and alpha-fetoprotein (AFP) is widely used to evaluate HCC. However, the proportion of AFP-negative individuals cannot be disregarded. This study aimed to establish a nomogram of risk factors affecting the prognosis of patients with AFP-negative HCC and to evaluate its diagnostic efficiency. Patients and methods Data from patients with AFP-negative initial diagnosis of HCC (ANHC) between 2004 and 2015 were collected from the Surveillance, Epidemiology, and End Results database for model establishment and validation. We randomly divided overall cohort into the training or validation cohort (7:3). Univariate and multivariate Cox regression analysis were used to identify the risk factors. We constructed nomograms with overall survival (OS) and cancer-specific survival (CSS) as clinical endpoint events and constructed survival analysis by using Kaplan-Meier curve. Also, we conducted internal validation with Receiver Operating Characteristic (ROC) analysis and Decision curve analysis (DCA) to validate the clinical value of the model. Results This study included 1811 patients (1409 men; 64.7% were Caucasian; the average age was 64 years; 60.7% were married). In the multivariate analysis, the independent risk factors affecting prognosis were age, ethnicity, year of diagnosis, tumor size, tumor grade, surgery, chemotherapy, and radiotherapy. The nomogram-based model related C-indexes were 0.762 (95% confidence interval (CI): 0.752–0.772) and 0.752 (95% CI: 0.740–0.769) for predicting OS, and 0.785 (95% CI: 0.774–0.795) and 0.779 (95% CI: 0.762–0.795) for predicting CSS. The nomogram model showed that the predicted death was consistent with the actual value. The ROC analysis and DCA showed that the nomogram had good clinical value compared with TNM staging. Conclusion The age(HR:1.012, 95% CI: 1.006–1.018, P-value

Accurate runoff prediction is vital in efficiently managing water resources. In this paper, a hybrid prediction model combining complete ensemble empirical mode decomposition with adaptive noise, variational mode decomposition, CABES, and long short-term memory network (CEEMDAN-VMD-CABES-LSTM) is proposed. Firstly, CEEMDAN is used to decompose the original data, and the high-frequency component is decomposed using VMD. Then, each component is input into the LSTM optimized by CABES for prediction. Finally, the results of individual component predictions are combined and reconstructed to produce the monthly runoff predictions. The hybrid model is employed to predict the monthly runoff at the Xiajiang hydrological station and the Yingluoxia hydrological station. A comprehensive comparison is conducted with other models including back propagation (BP), LSTM, etc. The assessment of each model's prediction performance uses four evaluation indexes. Results reveal that the CEEMDAN-VMD-CABES-LSTM model showcased the highest forecast accuracy among all the models evaluated. Compared with the single LSTM, the root mean square error (RMSE) and mean absolute percentage error (MAPE) of the Xiajiang hydrological station decreased by 71.09 and 65.26%, respectively, and the RMSE and MAPE of the Yingluoxia hydrological station decreased by 65.13 and 40.42%, respectively. The R and NSEC of both sites are near 1. HIGHLIGHTS A novel model (CEEMDAN-VMD-CABES-LSTM) is proposed for monthly runoff prediction.; CEEMDAN-VMD effectively reduces the complexity of the original monthly runoff series.; CABES enhances the generalization ability and prediction performance of the LSTM.; The four evaluation indicators and seven benchmark models are employed to verify the superiority of the developed model.;

This article proposes a multi-head attention flood forecasting model (MHAFFM) that combines a multi-head attention mechanism (MHAM) with multiple linear regression for flood forecasting. Compared to models based on Long Short-Term Memory (LSTM) neural networks, MHAFFM enables precise and stable multi-hour flood forecasting. First, the model utilizes characteristics of full-batch stable input data in multiple linear regression to solve the problem of oscillation in the prediction results of existing models. Second, full-batch information is connected to MHAM to improve the model's ability to process and interpret high-dimensional information. Finally, the model accurately and stably predicts future flood processes through linear layers. The model is applied to Dawen River Basin, and experimental results show that the MHAFFM, compared to three benchmarking models, namely, LSTM, BOA-LSTM (LSTM with Bayesian Optimization Algorithm for Hyperparameter Tuning), and MHAM-LSTM (LSTM model with MHAM in hidden layer), significantly improves the prediction performance under different lead time scenarios while maintaining good stability and interpretability. Taking Nash–Sutcliffe efficiency index as an example, under a lead time of 3 h, the MHAFFM model exhibits improvements of 8.85, 3.71, and 10.29% compared to the three benchmarking models, respectively. This research provides a new approach for flood forecasting. HIGHLIGHTS Proposes a novel multi-head attention flood forecasting model (MHAFFM).; Multi-head attention mechanism strengthens the model's ability to handle high-dimensional data.; Linear layers effectively harness the performance of the multi-head attention mechanism.; MHAFFM significantly enhances the stability of forecasted results.; Even in longer lead time scenarios, the model maintains high accuracy and stability.;

Abstract Aim Patients with chronic liver disease (CLD), especially cirrhosis, are at a high risk of severe illness or death from coronavirus disease‐2019 (COVID‐19) and may have a suboptimal immune response to the severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2) vaccine. This study aimed to evaluate the safety and immunogenicity of the COVID‐19 booster vaccination in patients with CLD. Methods The study protocol was prospectively registered at ClinicalTrials.gov (No. NCT05204602) after approval by the Ethics Committee. Adult participants with CLD were enrolled in this multicenter prospective study. They completed two doses of the inactivated COVID‐19 vaccine and received booster doses at least 6 months later. Adverse reactions were recorded within 14 days after the booster dose. Serum samples of the enrolled patients were collected before and after booster vaccination and tested for SARS‐CoV‐2 receptor‐binding domain (RBD) immunoglobulin G and neutralizing antibodies. The chi‐squared or Fisher's exact test was used to compare categorical data, and the Mann–Whitney U test was used to compare continuous variables. Two‐sided p

Most previous studies on attributing climate change and human activities to streamflow variation focused only on an annual scale, while few attempts were devoted to shorter time scales, such as seasonal or monthly scales. In this study, a multi-scalar framework for attribution analysis was constructed by integrating hydrological modeling into the Budyko-based decomposition method. Then, the multi-scalar framework was employed in the source region of the Yellow River (SRYR) as a case study. Moreover, the quantification results are compared with the simulation of a monthly water balance model (i.e., abcd model). The main results and findings indicate: (1) The mutation point of the annual streamflow is 1991 in the SRYR, and the monthly ABCD hydrological model achieves good performance in streamflow simulation for the prechange period and postchange period; (2) The contribution of climate change to streamflow variation is 65.99%, 37.50%, and 70.86% for annual, dry season, and wet season, respectively, indicating that climate change is the dominant factor controlling streamflow variation for the annual and wet season, while human activities play a major role in streamflow variation for dry season; (3) The contributions of climate change and human activities show obvious dynamic and seasonal characteristics, which are strongly affected by the transition between dry and wet seasons. Generally, the findings of this study provide valuable references for local reasonable water resource planning and management to make timely and appropriate use of the water supply. HIGHLIGHTS A new multi-scalar framework is proposed for attribution of streamflow variation.; The Budyko-based decomposition method is first extended to a monthly scale.; The ABCD model is selected for watershed hydrological modeling.; The quantification of climate and human impacts is verified by the hydrologic simulation approach.;

The long short-term memory network (LSTM) model alleviates the gradient vanishing or exploding problem of the recurrent neural network (RNN) model with gated unit architecture. It has been applied to flood forecasting work. However, flood data have the characteristic of unidirectional sequence transmission, and the gated unit architecture of the LSTM model establishes connections across different time steps which may not capture the physical mechanisms or be easily interpreted for this kind of data. Therefore, this paper investigates whether the gated unit architecture has a positive impact and whether LSTM is still better than RNN in flood forecasting work. We establish LSTM and RNN models, analyze the structural differences and impacts of the two models in transmitting flood data, and compare their performance in flood forecasting work. We also apply hyperparameter optimization and attention mechanism coupling techniques to improve the models, and establish an RNN model for optimizing hyperparameters using BOA (BOA-RNN), an LSTM model for optimizing hyperparameters using BOA (BOA-LSTM), an RNN model with MHAM in the hidden layer (MHAM-RNN), and an LSTM model with MHAM in the hidden layer (MHAM-LSTM) using the Bayesian optimization algorithm (BOA) and the multi-head attention mechanism (MHAM), respectively, to further examine the effects of RNN and LSTM as the underlying models and of cross-time scale bridging for flood forecasting. We use the measured flood process data of LouDe and HuaYuankou stations in the Yellow River basin to evaluate the models. The results show that compared with the LSTM model, under the 1 h forecast period of the LouDe station, the RNN model with the same structure and hyperparameters improves the four performance indicators of the Nash–Sutcliffe efficiency coefficient (NSE), the Kling-Gupta efficiency coefficient (KGE), the mean absolute error (MAE), and the root mean square error (RMSE) by 1.72%, 4.43%, 35.52% and 25.34%, respectively, and the model performance of the HuaYuankou station also improves significantly. In addition, under different situations, the RNN model outperforms the LSTM model in most cases. The experimental results suggest that the simple internal structure of the RNN model is more suitable for flood forecasting work, while the cross-time bridging methods such as gated unit architecture may not match well with the flood propagation process and may have a negative impact on the flood forecasting accuracy. Overall, the paper analyzes the impact of model architecture on flood forecasting from multiple perspectives and provides a reference for subsequent flood forecasting modeling.

In classical severity–duration–frequency (SDF) analysis, the dependence between drought characteristics is not effectively considered. The present study aims to propose the SDF relationships of streamflow drought in the source area of the Yellow River (SAYR) using a copula-based approach. Comparison of multiple time-varying threshold levels and the integration and elimination of drought events were considered. Selection of marginal probability distribution and copula-based joint probability distribution was properly conducted with multiple means. Copula-based joint and conditional probabilities were computed. The findings support carrying out integration and elimination processing on the preliminarily identified streamflow droughts through a run analysis with a time-varying threshold level of the 80% quantile of daily streamflow. The Gaussian copula was selected as the optimal model for constructing bivariate joint probability distribution, with generalized extreme value and log-normal as the suitable marginal probability distributions of streamflow drought duration and severity. The proposed copula-based SDF relationships of streamflow drought events can provide more critical information in addition to univariate frequency analysis, benefitting from the joint and conditional probabilities. The multivariate probabilistic analyses can effectively consider the connection and interaction between drought characteristics, while conditional probability distribution allows analyzing the impact of one drought characteristic on another. The results also indicate a relatively high risk of streamflow drought with short duration and low severity in the region, requiring effective drought-mitigation strategies and measures.

The reservoir flood control operation problem has the characteristics of multiconstraint, high-dimension, nonlinearity, and being difficult to solve. In order to better solve this problem, this paper proposes an improved bald eagle search algorithm (CABES) coupled with ε-constraint method (ε-CABES). In order to test the performance of the CABES algorithm, a typical test function is used to simulate and verify CABES. The results are compared with the bald eagle algorithm and particle swarm optimization algorithm to verify its superiority. In order to further test the rationality and effectiveness of the CABES method, two single reservoirs and a multi-reservoir system are selected for flood control operation, and the ε constraint method and the penalty function method (CF-CABES) are compared, respectively. Results show that peak clipping rates of ε-CABES and CF-CABES are both 60.28% for Shafan Reservoir and 52.03% for Dahuofang Reservoir, respectively. When solving the multi-reservoir joint flood control operation system, only ε-CABES flood control operation is successful, and the peak clipping rate is 51.76%. Therefore, in the single-reservoir flood control operation, the penalty function method and the ε constraint method have similar effects. However, in multi-reservoir operation, the ε constraint method is better than the penalty function method. In summary, the ε-CABES algorithm is more reliable and effective, which provides a new method for solving the joint flood control scheduling problem of large reservoirs.

In the past decade, more than 300 people have died per year on average due to mountain torrents in China. Mountain torrents mostly occur in ungauged small and medium-sized catchments, so it is difficult to maintain high accuracy of flood prediction. In order to solve the problem of the low accuracy of flood simulation in the ungauged areas, this paper studies the influence of different methods on the parameter regionalization of distributed hydrological model parameters in hilly areas of Hunan Province. According to the terrain, landform, soil and land use characteristics of each catchment, we use Shortest Distance, Attribute Similarity, Support Vector Regression, Generative Adversarial Networks, Classification and Regression Tree and Random Forest methods to create parameter regionalization schemes. In total, 426 floods of 25 catchments are selected to calibrate the model parameters, and 136 floods of 8 catchments are used for verification. The results showed that the average values of the Nash–Sutcliffe coefficients of each scheme were 0.58, 0.64, 0.60, 0.66, 0.61 and 0.68, and the worst values were 0.27, 0.31, 0.25, 0.43, 0.35 and 0.59. The random forest model is the most stable solution and significantly outperforms other methods. Using the random forest model to regionalize parameters can improve the accuracy of flood simulation in ungauged areas, which is of great significance for flash flood forecasting and early warning.

With digital information technology based on limited data, disaster simulation review is an important guideline for analyzing disaster mechanisms, planning post-disaster reconstruction, and improving defense capability. Taking the “7.20” flash flood in the Wangzongdian river basin as a research area, a hydrological-hydrodynamic model was established using limited measured data. The results showed that the extreme rainstorm caused flooding in mountainous areas and the collapse of subgrade water damming, and the high-level flood quickly flowed into Wangzongdian Village in a short distance, which was the main cause of this serious disaster. Considering the collapse due to the congestion of the upstream bridge, the simulated flood flow in Wangzongdian Village reached 782 m3/s, which was basically consistent with the post-disaster survey results, with a relative error of only +8%. The modeling strategy proposed in this paper is applicable in the review of sudden heavy rainstorms and flash floods and can provide technical guidance for future flash flood simulation review analysis in other areas.

Due to the influences of climate changes and human activities, extreme climate events have made obvious changes to the hydrological process and the temporal-spatial distribution of water resources over the past several decades [...]

Hubei province is located in the center of China with 56% total area characterized with mountainous area. Thus, flash flood caused by extreme rainfall has become one of the significant obstacles that highly affect the social and economic development of the province. In order to scientifically understand the mechanism of flash flood disasters and provide technological support to the local flood prevention and control work, the IWHR designed and developed a new distributed hydrological model named China-FFMS that can simulate the evolution of natural disasters and make an assessment by setting the flood water sources in line with the flow discharge. The FFMS was further applied to simulate the 8.12 flash flood disaster that occurred in the Liulin county of Hubei province on 12 August (“8.12”) and fed by the data collected from the national flash flood disaster investigation and assessment. The calculated peak flow was 666.22 m3/s with an error of +13% compared with postdisaster investigation data (589 m3/s). The results showed that using a multisourced modelling approach, e.g., mixing spatiotemporal variables and sources, to simulate the flash flood process was able to accurately reproduce the flood process and the consistence of the flow discharge, thereby explaining the underlying reason of the disaster formation and evolution. Regarding the case of the Liulin county, the main factor leading to the disaster was the overlapped peak flow where the Dunne flood peak of three different tributaries from the upper reach met together at the same time. Moreover, the peak flow of the Lianhua river at the downstream of Liulin County also arrived at the same time as the upstream peak, which obstructed the flood progress and increased the damage of the disaster. According to the analysis, several suggestions and recommendations are proposed such as the improvement of the forecast and early warning system of the upstream areas, the optimization of the current flood defense plan, and the enhancement of the residents’ awareness of flash flood disasters.

Accurate rainfall forecasting in watersheds is of indispensable importance for predicting streamflow and flash floods. This paper investigates the accuracy of several forecasting technologies based on Wavelet Packet Decomposition (WPD) in monthly rainfall forecasting. First, WPD decomposes the observed monthly rainfall data into several subcomponents. Then, three data-based models, namely Back-propagation Neural Network (BPNN) model, group method of data handing (GMDH) model, and autoregressive integrated moving average (ARIMA) model, are utilized to complete the prediction of the decomposed monthly rainfall series, respectively. Finally, the ensemble prediction result of the model is formulated by summing the outputs of all submodules. Meanwhile, these six models are employed for benchmark comparison to study the prediction performance of these conjunction methods, which are BPNN, WPD-BPNN, GMDH, WPD-GMDH, ARIMA, and WPD-ARIMA models. The paper takes monthly data from Luoning and Zuoyu stations in Luoyang city of China as the case study. The performance of these conjunction methods is tested by four quantitative indexes. Results show that WPD can efficiently improve the forecasting accuracy and the proposed WPD-BPNN model can achieve better prediction results. It is concluded that the hybrid forecast model is a very efficient tool to improve the accuracy of mid- and long-term rainfall forecasting.

Accurate precipitation prediction can help plan for different water resources management demands and provide an extension of lead-time for the tactical and strategic planning of courses of action. This paper examines the applicability of several forecasting models based on wavelet packet decomposition (WPD) in annual rainfall forecasting, and a novel hybrid precipitation prediction framework (WPD-ELM) is proposed coupling extreme learning machine (ELM) and WPD. The works of this paper can be described as follows: (a) WPD is used to decompose the original precipitation data into several sub-layers; (b) ELM model, autoregressive integrated moving average model (ARIMA), and back-propagation neural network (BPNN) are employed to realize the forecasting computation for the decomposed series; (c) the results are integrated to attain the final prediction. Four evaluation indexes (RMSE, MAE, R, and NSEC) are adopted to assess the performance of the models. The results indicate that the WPD-ELM model outperforms other models used in this paper and WPD can significantly enhance the performance of forecasting models. In conclusion, WPD-ELM can be a promising alternative for annual precipitation forecasting and WPD is an effective data pre-processing technique in producing convincing forecasting models.

Function annotation efforts provide a foundation to our understanding of cellular processes and the functioning of the living cell. This motivates high-throughput computational methods to characterize new protein members of a particular function. Research work has focused on discriminative machine-learning methods, which promise to make efficient, de novo predictions of protein function. Furthermore, available function annotation exists predominantly for individual proteins rather than residues of which only a subset is necessary for the conveyance of a particular function. This limits discriminative approaches to predicting functions for which there is sufficient residue-level annotation, e.g., identification of DNA-binding proteins or where an excellent global representation can be divined. Complete understanding of the various functions of proteins requires discovery and functional annotation at the residue level. Herein, we cast this problem into the setting of multiple-instance learning, which only requires knowledge of the protein’s function yet identifies functionally relevant residues and need not rely on homology. We developed a new multiple-instance leaning algorithm derived from AdaBoost and benchmarked this algorithm against two well-studied protein function prediction tasks: annotating proteins that bind DNA and RNA. This algorithm outperforms certain previous approaches in annotating protein function while identifying functionally relevant residues involved in binding both DNA and RNA, and on one protein-DNA benchmark, it achieves near perfect classification.