Harnessing machine learning tools for water quality assessment in the Kebili shallow aquifers,Southwestern Tunisia

An integrated method that implements multivariate statistical analysis and ML methods to evaluate groundwater quality of the shallow aquifers of the Djerid and Kebili district,Southern Tunisia,was adopted.An evaluation of their suitability for irrigation and/or drinking purposes is necessary.A comprehensive hydrochemical assessment of 52 samples with entropy weighted water quality index(EWQI)was also proposed.Eleven water parameters were calculated to ascertain the potential use of those resources in irrigation and drinking.Multivariate analysis showed two main components with Dim1(variance=62.3%)and Dim.2(variance=22%),due to the bicarbonate,dissolution,and evaporation and the intrusion of drainage water.The evaluation of water quality has been carried out using EWQI model.The calculated EWQI for the Djerid and Kebili waters(i.e.,52 samples)varied between 7.5 and 152.62,indicating a range of 145.12.A mean of 79.12 was lower than the median(88.47).From the calculation of EWQI,only 14 samples are not suitable for irrigation because of their poor to extremely poor quality(26.92%).The bivariate plot showed high correlation for EWQI~TH(r=0.93),EWQI~SAR(r=0.87),indicating that water quality depended on those parameters.Diff erent ML algorithms were successfully applied for the water quality classifi cation.Our results indicated high prediction accuracy(SVM>LDA>ANN>kNN)and perfect classifi cation for kNN,LDA and Naive Bayes.For the purposes of developing the prediction models,the dataset was divided into two groups:training(80%)and testing(20%).To evaluate the models’performance,RMSE,MSE,MAE and R^(2) metrics were used.kNN(R^(2)=0.9359,MAE=6.49,MSE=79.00)and LDA(accuracy=97.56%;kappa=96.21%)achieved high accuracy.Moreover,linear regression indicated high correlation for both training(R^(2)=0.9727)and testing data(0.9890).This well confi rmed the validity of LDA algorithm in predicting water quality.Cross validation showed a high accuracy(92.31%),high sensitivity(89.47%)and high specifi city(95%).These fi ndings are fundamentally important for an integrated water resource management in a larger context of sustainable development of the Kebili district.

Water resource forecasting with machine learning and deep learning:A scientometric analysis

Water prediction plays a crucial role in modern-day water resource management,encompassing both logical hydro-patterns and demand forecasts.To gain insights into its current focus,status,and emerging themes,this study analyzed 876 articles published between 2015 and 2022,retrieved from the Web of Science database.Leveraging CiteSpace visualization software,bibliometric techniques,and literature review methodologies,the investigation identified essential literature related to water prediction using machine learning and deep learning approaches.Through a comprehensive analysis,the study identified significant countries,institutions,authors,journals,and keywords in this field.By exploring this data,the research mapped out prevailing trends and cutting-edge areas,providing valuable insights for researchers and practitioners involved in water prediction through machine learning and deep learning.The study aims to guide future inquiries by highlighting key research domains and emerging areas of interest.

Machine learning aided design of perovskite oxide materials for photocatalytic water splitting

Suffering from the inefficient traditional trial-and-error methods and the huge searching space filled by millions of candidates, discovering new perovskite visible photocatalysts with higher hydrogen production rate(RH_(2)) still remains a challenge in the field of photocatalytic water splitting(PWS). Herein, we established structural-property models targeted to RH_(2) and the proper bandgap(Eg) via machine learning(ML) technology to accelerate the discovery of efficient perovskite photocatalysts for PWS. The Pearson correlation coefficients(R) of leave-one-out cross validation(LOOCV) were adopted to compare the performances of different algorithms including gradient boosting regression(GBR), support vector regression(SVR), backpropagation artificial neural network(BPANN), and random forest(RF). It was found that the BPANN model showed the highest R values from LOOCV and testing data of 0.9897 and 0.9740 for RH_(2),while the GBR model had the best values of 0.9290 and 0.9207 for Eg. Furtherly, 14 potential PWS perovskite candidates were screened out from 30,000 ABO3-type perovskite structures under the criteria of structural stability, Eg, conduction band energy, valence band energy and RH_(2). The average RH_(2) of these14 perovskites is 6.4% higher than the highest value in the training data set. Moreover, the online web servers were developed to share our prediction models, which could be accessible in http://materialsdata-mining.com/ocpmdm/material_api/ahfga3d9puqlknig(E_g prediction) and http://materials-datamining.com/ocpmdm/material_api/i0 ucuyn3 wsd14940(RH_(2) prediction).

3D Finite Element Simulation of Tunnel Boring Machine Construction Processes in Deep Water Conveyance Tunnel

Applying stiffness migration method,a 3D finite element mechanical model is established to simulate the excavation and advance processes.By using 3D nonlinear finite element method,the tunnel boring machine(TBM) excavation process is dynamically simulated to analyze the stress and strain field status of surrounding rock and segment.The maximum tensile stress of segment ring caused by tunnel construction mainly lies in arch bottom and presents zonal distribution.The stress increases slightly and limitedly in the course of excavation.The maximum and minimum displacements of segment,manifesting as zonal distribution,distribute in arch bottom and vault respectively.The displacements slightly increase with the advance of TBM and gradually tend to stability.

Support Vector Machines(SVM)-Markov Chain Prediction Model of Mining Water Inflow

This study was conducted to establish a Support Vector Machines(SVM)-Markov Chain prediction model for prediction of mining water inflow. According to the raw data sequence, the Support Vector Machines(SVM) model was built, and then revised by means of a Markov state change probability matrix. Through dividing the state and analyzing absolute errors and relative errors and other indexes of the measured value and the fitted value of SVM, the prediction results were improved. Finally,the model was used to calculate relative errors. Through predicting and analyzing mining water inflow, the prediction results of the model were satisfactory. The results of this study enlarge the application scope of the Support Vector Machines(SVM) prediction model and provide a new method for scientific forecasting water inflow in coal mining.

Application of least squares vector machines in modelling water vapor and carbon dioxide fluxes over a cropland

Least squares support vector machines (LS-SVMs), a nonlinear kemel based machine was introduced to investigate the prospects of application of this approach in modelling water vapor and carbon dioxide fluxes above a summer maize field using the dataset obtained in the North China Plain with eddy covariance technique. The performances of the LS-SVMs were compared to the corresponding models obtained with radial basis function (RBF) neural networks. The results indicated the trained LS-SVMs with a radial basis function kernel had satisfactory performance in modelling surface fluxes; its excellent approximation and generalization property shed new light on the study on complex processes in ecosystem.

Analysis of Ammonia Nitrogen Content in Water Based on Weighted Least Squares Support Vector Machine (WLSSVM) Algorithm

Determination of ammonia nitrogen content in water is the basic item of the environmental water pollution, and is the key index to evaluate the water quality. This article designs a water quality monitoring system based on the on-line automatic ammonia nitrogen monitoring system, and establishes a forecasting model based on the weighted least squares support vector machine algorithm. The weighted least squares support vector machine algorithm increases the weight parameter setting, improves the speed and accuracy of prediction learning, and improves the robustness. In this article, a comparison between neural network model and weighted least square support vector machine model is made, which shows that the weighted least squares support vector machine model has better prediction accuracy.

Analysis of Water Pollution Causes and Control Countermeasures in Liaohe Estuary via Support Vector Machine Particle Swarm Optimization under Deep Learning

This study explores the loss or degradation of the ecosystem and its service function in the Liaohe estuary coastal zone due to the deterioration ofwater quality.Aprediction systembased on support vectormachine(SVM)-particle swarm optimization(PSO)(SVM-PSO)algorithm is proposed under the background of deep learning.SVM-PSO algorithm is employed to analyze the pollution status of the Liaohe estuary,so is the difference in water pollution of different sea consuming types.Based on the analysis results for causes of pollution,the control countermeasures of water pollution in Liaohe estuary are put forward.The results suggest that the water pollution index prediction model based on SVM-PSO algorithm shows the maximum error of 2.41%,the average error of 1.24%in predicting the samples,the root mean square error(RMSE)of 5.36×10^(−4),and the square of correlation coefficient of 0.91.Therefore,the prediction system in this study is feasible.At present,the water pollution status of Liaohe estuary is of moderate and severe levels of eutrophication,and the water pollution status basically remains at the level of mild pollution.The general trend is fromphosphorus moderate restricted eutrophication to phosphorus restricted potential eutrophication.To sumup,the SVM-PSO algorithm shows good sewage prediction ability,which can be applied and promoted in water pollution control and has reliable reference significance.

Combination of effective color information and machine learning for rapid prediction of soil water content

Soil water content(SWC)is one of the critical indicators in various fields such as geotechnical engineering and agriculture.To avoid the time-consuming,destructive,and laborious drawbacks of conventional SWC measurements,the image-based SWC prediction is considered based on recent advances in quantitative soil color analysis.In this study,a promising method based on the Gaussian-fitting gray histogram is proposed for extracting characteristic parameters by analyzing soil images,aiming to alleviate the interference of complex surface conditions with color information extraction.In addition,an identity matrix consisting of 32 characteristic parameters from eight color spaces is constituted to describe the multi-dimensional information of the soil images.Meanwhile,a subset of 10 parameters is identified through three variable analytical methods.Then,four machine learning models for SWC prediction based on partial least squares regression(PLSR),random forest(RF),support vector machines regression(SVMR),and Gaussian process regression(GPR),are established using 32 and 10 characteristic parameters,and their performance is compared.The results show that the characteristic parameters obtained by Gaussian-fitting can effectively reduce the interference from soil surface conditions.The RGB,CIEXYZ,and CIELCH color spaces and lightness parameters,as the inputs,are more suitable for the SWC prediction models.Furthermore,it is found that 10 parameters could also serve as optimal and generalizable predictors without considerably reducing prediction accuracy,and the GPR model has the best prediction performance(R^(2)≥0.95,RMSE≤2.01%,RPD≥4.95,and RPIQ≥6.37).The proposed image-based SWC predictive models combined with effective color information and machine learning can achieve a transient and highly precise SWC prediction,providing valuable insights for mapping soil moisture fields.

Treatment of Textile Industrial Wastewater from Water Jet Loom Machine

The objective of this research was to investigate the optimum condition for treatment of textile industrial wastewater from water jet loom machine by chemical coagulation and electrocoagulation methods. The variables of chemical coagulation method were type and amount of chemicals, pH and stirring rate. For electrocoagulation method, the variables were electrode materials, electric potential and contact time. It was found that the optimum condition of chemical coagulation method was 10% （w/w） of aqueous solution of aluminum sulphate 80 mL and 0.01% （w/w） of aqueous solution of coagulant aids, cationic polymer 32 mL per 4 L of wastewater at oH 8. The mixture solution was rapidly stirred with 120 rpm for 1 min and then slowly stirred with 20 rpm for 20 rain. The removal efficiency of turbidity, COD and oil content were 88.88%, 85.20% and 77.72%, respectively. For electrocoagulation method, the optimum condition was using aluminum electrode with 35 V and 150 min of contact time. The removal efficiency of turbidity, COD and oil content were 98.86%, 91.63% and 89.84%, respectively. It can be concluded from this study that the textile industrial wastewater treatment from water jet loom machine with electrocoagulation method is more efficient than that with chemical coagulation method.

Aviation-oriented Micromachining Technology—Micro-ECM in Pure Water

This article proposes a precise and ecofriendly micromachining technology for aerospace application called electrochemical machining in pure water （PW-ECM）. On the basis of the principles of water dissociation, a series of test setups and tests are devised and performed under different conditions. These tests explain the need for technological conditions realizing PW-ECM, and further explore the technological principles. The results from the tests demonstrate a successful removal of electrolytic slime by means of ultrasonic vibration of the workpiece. To ensure the stability and reliability of PW-ECM process, a new combined machining method of PW-ECM assisted with ultrasonic vibration （PW-ECM/USV） is devised. Trilateral and square cavities and holes as well as a group of English alphabets are worked out on a stainless steel plate. It is confirmed that PW-ECM will be probably an efficient new aviation precision machining method.

Runoff Modeling in Ungauged Catchments Using Machine Learning Algorithm-Based Model Parameters Regionalization Methodology

Model parameters estimation is a pivotal issue for runoff modeling in ungauged catchments.The nonlinear relationship between model parameters and catchment descriptors is a major obstacle for parameter regionalization,which is the most widely used approach.Runoff modeling was studied in 38 catchments located in the Yellow–Huai–Hai River Basin(YHHRB).The values of the Nash–Sutcliffe efficiency coefficient(NSE),coefficient of determination(R2),and percent bias(PBIAS)indicated the acceptable performance of the soil and water assessment tool(SWAT)model in the YHHRB.Nine descriptors belonging to the categories of climate,soil,vegetation,and topography were used to express the catchment characteristics related to the hydrological processes.The quantitative relationships between the parameters of the SWAT model and the catchment descriptors were analyzed by six regression-based models,including linear regression(LR)equations,support vector regression(SVR),random forest(RF),k-nearest neighbor(kNN),decision tree(DT),and radial basis function(RBF).Each of the 38 catchments was assumed to be an ungauged catchment in turn.Then,the parameters in each target catchment were estimated by the constructed regression models based on the remaining 37 donor catchments.Furthermore,the similaritybased regionalization scheme was used for comparison with the regression-based approach.The results indicated that the runoff with the highest accuracy was modeled by the SVR-based scheme in ungauged catchments.Compared with the traditional LR-based approach,the accuracy of the runoff modeling in ungauged catchments was improved by the machine learning algorithms because of the outstanding capability to deal with nonlinear relationships.The performances of different approaches were similar in humid regions,while the advantages of the machine learning techniques were more evident in arid regions.When the study area contained nested catchments,the best result was calculated with the similarity-based parameter regionalization scheme because of the high catchment density and short spatial distance.The new findings could improve flood forecasting and water resources planning in regions that lack observed data.

智能传感技术在水肥一体系统中的应用研究

以进一步提升水肥一体机系统的作业效率为目标,选取智能传感的监测技术,针对整机的监测控制与信号处理展开应用设计研究。考虑水肥一体机过程作业肥液融合的均匀性及系统各模块之间的协同性功能实现,结合微分补偿的传感数据算法处理方法,进行智能传感的水肥一体机架构布局,并匹配可执行的软件控制程序及硬件实施结构,进行实地传感应用监测与灌施控制作业试验。结果表明:水肥一体机系统的数据监测准确率可达95.25%,系统故障率相对降低3.79%,监测数据准确及时,能够确保系统各环节指令得到有效的调整与反馈,进而保证灌施土壤的含水稳定率相对提升7.87%,对于作物的稳定生长与产量提升有重要的参考价值。

主路式水肥一体机施肥系统的设计与试验

针对现阶段水肥一体化设备存在施肥不均、自动化程度不高及滞后性严重的问题,根据现代化农业节水省肥和减少环境污染的灌溉要求,设计了一款可实现自动混肥、施肥、节水灌溉的主路式水肥一体化施肥机。根据液肥的EC和pH值调节过程的特点,开发了以SIEMENS S7-1200为核心的液肥控制系统硬件,并结合MatLab设计了以模糊PID为控制器的液肥EC和pH值控制系统。为验证施肥机在实际应用中的精确性和鲁棒性,设计了施肥系统动态调节性能试验,结果表明:在施肥阶段,模糊PID控制系统具有较短的稳态时间和较小的超调量,相比于PID控制系统,对EC和pH值进行调节的稳态时间分别减少了37.7%和52.1%,稳态超调量分别降低了1.2%和2.2%,可实现对混肥溶液进行迅速有效的调节,满足现代农业实际生产需要。

基于数值分析法的水肥一体机设计研究

以进一步提升水肥一体机的智能性、数字性作业为目标,针对整机的灌施精准性要求展开设计。充分考虑水肥一体机的运用特点和结构组成,结合水肥的参数融合关系,建立用于水肥一体机准确控制作业的状态方程模型,设计以数值分析处理函数为核心的软件控制模块,搭建同步动作实施的硬件执行平台。展开多作物的灌施作业试验,结果表明:基于数值分析方法的水肥一体机系统架构设计合理,数值分析算法融入有效,整机试验的数值计算准确率可达98.00%以上;水肥混合均匀有度,整体管路灌施顺畅,灌施指令准确率可达99.00%以上,整机灌施效率较高,充分验证了数值分析方法应用的正确性与优越性,可以促进类似农机装备与高等数学多维度融合。

Water structures and anisotropic dynamics at Pt(211)/water interface revealed by machine learning molecular dynamics

Water molecules at solid–liquid interfaces play a pivotal role in governing interfacial phenomena that underpin electrochemical and catalytic processes.The organization and behavior of these interfacial water molecules can significantly influence the solvation of ions,the adsorption of reactants,and the kinetics of electrochemical reactions.The stepped structure of Pt surfaces can alter the properties of the interfacial water,thereby modulating the interfacial environment and the resulting surface reactivity.Revealing the in situ details of water structures at these stepped Pt/water interfaces is crucial for understanding the fundamental mechanisms that drive diverse applications in energy conversion and material science.In this work,we have developed a machine learning potential for the Pt(211)/water interface and performed machine learning molecular dynamics simulations.Our findings reveal distinct types of chemisorbed and physisorbed water molecules within the adsorbed layer.Importantly,we identified three unique water pairs that were not observed in the basal plane/water interfaces,which may serve as key precursors for water dissociation.These interfacial water structures contribute to the anisotropic dynamics of the adsorbed water layer.Our study provides molecular-level insights into the anisotropic nature of water behavior at stepped Pt/water interfaces,which can influence the reorientation and distribution of intermediates,molecules,and ions—crucial aspects for understanding electrochemical and catalytic processes.

Water quality prediction based on sparse dataset using enhanced machine learning

Water quality in surface bodies remains a pressing issue worldwide.While some regions have rich water quality data,less attention is given to areas that lack sufficient data.Therefore,it is crucial to explore novel ways of managing source-oriented surface water pollution in scenarios with infrequent data collection such as weekly or monthly.Here we showed sparse-dataset-based prediction of water pollution using machine learning.We investigated the efficacy of a traditional Recurrent Neural Network alongside three Long Short-Term Memory(LSTM)models,integrated with the Load Estimator(LOADEST).The research was conducted at a river-lake confluence,an area with intricate hydrological patterns.We found that the Self-Attentive LSTM(SA-LSTM)model outperformed the other three machine learning models in predicting water quality,achieving Nash-Sutcliffe Efficiency(NSE)scores of 0.71 for COD_(Mn)and 0.57 for NH_(3)N when utilizing LOADEST-augmented water quality data(referred to as the SA-LSTMLOADEST model).The SA-LSTM-LOADEST model improved upon the standalone SA-LSTM model by reducing the Root Mean Square Error(RMSE)by 24.6%for COD_(Mn)and 21.3%for NH_(3)N.Furthermore,the model maintained its predictive accuracy when data collection intervals were extended from weekly to monthly.Additionally,the SA-LSTM-LOADEST model demonstrated the capability to forecast pollution loads up to ten days in advance.This study shows promise for improving water quality modeling in regions with limited monitoring capabilities.

In situ experimental study on TBM excavation with high-pressure water-jet-assisted rock breaking

China’s first high-pressure hydraulically coupled rock-breaking tunnel boring machine(TBM) was designed to overcome the rock breaking problems of TBM in super-hard rock geology, where high-pressure water jet system is configured, including high-flow pump sets, high-pressure rotary joint and high-pressure water jet injection device. In order to investigate the rock breaking performance of high-pressure water-jet-assisted TBM, in situ excavation tests were carried out at the Wan’anxi Water Diversion Project in Longyan, Fujian Province, China, under different water jet pressure and rotational speed. The rock-breaking performance of TBM was analyzed including penetration, cutterhead load, advance rate and field penetration index. The test results show that the adoption of high-pressure water-jet-assisted rock breaking technology can improve the boreability of rock mass, where the TBM penetration increases by 64% under the water jet pressure of 270 MPa. In addition, with the increase of the water jet pressure, the TBM penetration increases and the field penetration index decreases. The auxiliary rock-breaking effect of high-pressure water jet decreases with the increase of cutterhead rotational speed. In the case of the in situ tunneling test parameters of this study, the advance rate is the maximum when the pressure of the high-pressure water jet is 270 MPa and the cutterhead rotational speed is 6 r/min. The technical superiority of high-pressure water-jet-assisted rock breaking technology is highlighted and it provides guidance for the excavation parameter selection of high-pressure hydraulically coupled rock-breaking TBM.

Bulk metallic glass rings prepared by a modified water quenching method

Bulk metallic glass rings have the potential applications as annular gasket and active solder in special fields. The bulk metallic glass ring of ZГ41.2Ti13.8Cu12.5Ni10.0Be22.5 with the outer diameter, the inner diameter, and the thickness of 38, 36, and 5 mm, respectively, was prepared by using a special shaped quartz tube water quenching method. The mechanical properties along the whole cross section were investigated by a nanoindentation method, and no evident variation of the Young＇s modulus and hardness was found, further indicating the single amorphous structure. Amorphous ring and tube-shape parts with different dimensions can be produced by this method.

Application of SVM in Analyzing the Headstream of Gushing Water in Coal Mine

To recognize the presence of the headstream of gushing water in coal mines, the SVM (Support Vector Ma- chine) was proposed to analyze the gushing water based on hydrogeochemical methods. First, the SVM model for head- stream analysis was trained on the water sample of available headstreams, and then we used this to predict the unknown samples, which were validated in practice by comparing the predicted results with the actual results. The experimental results show that the SVM is a feasible method to differentiate between two headstreams and the H-SVMs (Hierachical SVMs) is a preferable way to deal with the problem of multi-headstreams. Compared with other methods, the SVM is based on a strict mathematical theory with a simple structure and good generalization properties. As well, the support vector W in the decision function can describe the weights of the recognition factors of water samples, which is very important for the analysis of headstreams of gushing water in coal mines.