Daily flow prediction of the Huayuankou hydrometeorological station based on the coupled CEEMDAN-SE-BiLSTM model.

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.

Improvement and evaluation of hydrodynamic conditions in plain regional drainage systems by artificial lakes: a case study of Xinxiang Economic Development Zone, China.

With the development of the city, people pay more attention to the ecological construction of the city. The objective of this work was to study the effect of artificial lakes on hydrodynamic conditions in urban drainage systems. With Arcgis and the advantage of SWMM in analyzing the impact of the rainfall process on urban runoff, the urban flooding model of "pipe network + river network + artificial lake" was established in the study area. Two scenarios were set up with and without the presence of artificial lakes, and comparative analyses were conducted under the different intensities of rainfall (0.5a, 1a, 2a, 5a, 10a, 20a). The results show that under certain rainfall conditions, the presence of the artificial lake increases the peak flow and rate of upstream streams and decreases the flow and rate of downstream streams in the regional drainage system. The duration of the peak flow rate in the upstream channel increases, and the flow rate curve becomes flat during the confluence; the flow rate in the downstream section decreases, and the magnitude of the peak flow rate change decreases, and a more obvious horizontal section appears. The time of peak occurrence in the downstream river is earlier. The hydrodynamic impact on the downstream channel is more significant. The improvement of hydrodynamic conditions of the drainage system by the artificial lake helps to optimize the layout of low impact development (LID) measures in the study area and also guides ecological construction in other cities.

A new rainfall prediction model based on ICEEMDAN-WSD-BiLSTM and ESN.

Precipitation, as an important indicator describing the evolution of the regional climate system, plays an important role in understanding the spatial and temporal distribution characteristics of regional precipitation. Scientific and accurate prediction of regional precipitation is helpful to provide theoretical basis for relevant departments to guide flood and drought control. To address the uncertainty and nonlinear characteristics of precipitation series, this paper uses the established improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN)-wavelet signal denoising (WSD)-bi-directional long short-term memory (BiLSTM), and echo state network (ESN) models to predict precipitation of four cities in southern Anhui Province. The BiLSTM is used to predict the high-frequency components and the ESN to predict the low-frequency components, thus avoiding the influence between the two neural network predictions. The results show that the ICEEMDAN-WSD-BiLSTM and ESN models are more accurate. The average relative error reached 2.64% and the NSE (Nash-Sutcliffe efficiency coefficient) was 0.91, which was significantly better than the other four models. The model reveals the temporal change pattern and evolution characteristics of future precipitation, guides flood prevention and mitigation, and has certain theoretical significance and application value for promoting regional sustainable development.

Monthly precipitation prediction in Luoyang city based on EEMD-LSTM-ARIMA model.

At present, the method of using coupled models to model different frequency subseries of precipitation series separately for prediction is still lacking in the research of precipitation prediction, thus in this paper, a coupled model based on Ensemble Empirical Mode Decomposition (EEMD), Long Short-Term Memory neural network (LSTM) and Autoregressive Integrated Moving Average (ARIMA) is proposed for month-by-month precipitation prediction. The monthly historical precipitation data of Luoyang City from 1973 to 2021 were used to build the model, and the modal components of different frequencies obtained by EEMD decomposition were divided into high-frequency series part and low-frequency series part using the Permutation Entropy (PE) algorithm, the LSTM model is used to predict the high-frequency sequence part, while the ARIMA model is used to predict the low-frequency sequence part. Monthly precipitation forecasts are obtained by superimposing the results of the two models. Finally, the predictive performance is evaluated using several assessment metrics. The indicators show that the model predictive performance outperforms the EMD-LSTM (Empirical Mode Decomposition), EEMD-LSTM, EEMD-ARIMA combined models and the single models, and the model has high confidence in the prediction results of future precipitation.

Runoff prediction of lower Yellow River based on CEEMDAN-LSSVM-GM(1,1) model.

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.

Superhydrophobic-Superhydrophilic Hybrid Surface with Highly Ordered Tip-Capped Nanopore Arrays for Surface-Enhanced Raman Scattering Spectroscopy.

The designed superhydrophobic-superhydrophilic hybrid surface (SSHS) with highly ordered tip-capped nanopore arrays can be used as an intelligent and fast platform to realize different analyte solutions with different concentrations to be detected at the same time by surface-enhanced Raman spectroscopy. This surface is fabricated in a large area by a facile and low-cost method of programmed multistep anodization of aluminum and pore widening process followed by selective chemical modification. The highly ordered tip-capped nanopore arrays can induce the highly sensitive and reproducible Raman signal, whose enhanced factor for rhodamine 6G (R6G) at 1358 cm-1 is 4.46 × 106. The superhydrophobic-superhydrophilic hybrid property can realize the homogeneous distribution of the concentrated analyte in a droplet at the fixed place, which can avoid the diffusion-limit problem and further enhance the Raman signal. Surface-enhanced Raman spectroscopy of dried droplets with different concentrations of R6G or thiram is tested on SSHS, which show good reproducibility. The detection limits of R6G and thiram on SSHS are 10-10 and 10-7 M in 50 µL droplets, respectively. Due to the industrial compatibility of the fabrication technique, this smart surface has the potential to evolve into a general platform to develop various advanced chemical and biological sensors.

A Bioinspired, Highly Transparent Surface with Dry-Style Antifogging, Antifrosting, Antifouling, and Moisture Self-Cleaning Properties.

Transparent coatings with antireflection, antifogging, antifrosting, antifouling, and moisture self-cleaning properties can dramatically improve the efficiency and convenience of optical elements and thus are highly desirable for practical applications. Here, it is demonstrated that a bionic nanocone surface (BNS) fabricated by a facile, low-cost process consisting of template-assisted prepolymer curing followed by surface modification can possess the multiple functions listed above. The polymer coating firmly adheres to a glass substrate due to bonding agents. After SiO2 nanoparticle deposition and low-surface-energy fluorosilane modification, the coating shows low microdroplet adhesion. As a result, the as-prepared BNS exhibits a high transmittance when exposed to fog and good clarity even when the temperature decreases to -20 °C in a humid environment. Dipping the BNS into exemplified graphite powder has almost no influence on the transparency, and the BNS can realize self-cleaning of moisture when the surface is covered with a thick layer of man-made contaminants.

Fabrication of Self-Ordered Alumina Films with Large Interpore Distance by Janus Anodization in Citric Acid.

Self-organized porous anodic alumina (PAA) formed by electrochemical anodization have become a fundamental tool to develop various functional nanomaterials. However, it is still a great challenge to break the interpore distance (Dint) limit (500 nm) by using current anodization technologies of mild anodization (MA) and hard anodization (HA). Here, we reported a new anodization mode named "Janus anodization" (JA) to controllably fabricate self-ordered PAA with large Dint at high voltage of 350-400 V. JA naturally occurs as anodizing Al foils in citric acid solution, which possessing both the characteristics of MA and HA. The process can be divided into two stages: I, slow pore nucleation stage similar to MA; II, unequilibrium self-organization process similar to HA. The as-prepared films had the highest modulus (7.0 GPa) and hardness (127.2 GPa) values compared with the alumina obtained by MA and HA. The optical studies showed that the black films have low reflectance (<10 %) in the wavelength range of 250-1500 nm and photoluminescence property. Dint can be tuned between 645-884 nm by controlling citric acid concentration or anodization voltage. JA is a potential technology to efficiently and controllably fabricate microstructured or hybrid micro- and nanostructured materials with novel properties.