Comparing microbial water quality in an intermittent and continuous piped water supply

Supplying piped water intermittently is a common practice throughout the world that increases the risk of microbial contamination through multiple mechanisms. Converting an intermittent supply to a continuous supply has the potential to improve the quality of water delivered to consumers. To understand the effects of this upgrade on water quality, we tested samples from reservoirs, consumer taps, and drinking water provided by households (e.g. from storage containers) from an intermittent and continuous supply in Hubli–Dharwad, India, over one year. Water samples were tested for total coliform, Escherichia coli, turbidity, free chlorine, and combined chlorine. While water quality was similar at service reservoirs supplying the continuous and intermittent sections of the network, indicator bacteria were detected more frequently and at higher concentrations in samples from taps supplied intermittently compared to those supplied continuously (p < 0.01). Detection of E. coli was rare in continuous supply, with 0.7% of tap samples positive compared to 31.7% of intermittent water supply tap samples positive for E. coli. In samples from both continuously and intermittently supplied taps, higher concentrations of total coliform were measured after rainfall events. While source water quality declined slightly during the rainy season, only tap water from intermittent supply had significantly more indicator bacteria throughout the rainy season compared to the dry season. Drinking water samples provided by households in both continuous and intermittent supplies had higher concentrations of indicator bacteria than samples collected directly from taps. Most households with continuous supply continued to store water for drinking, resulting in re-contamination, which may reduce the benefits to water quality of converting to continuous supply.     

Slope stability prediction using ensemble learning techniques: A case study in Yunyang County,Chongqing, China

Slope stability prediction plays a significant role in landslide disaster prevention and mitigation. This study develops an ensemble learning-based method to predict the slope stability by introducing the random forest (RF) and extreme gradient boosting (XGBoost). As an illustration, the proposed approach is applied to the stability prediction of 786 landslide cases in Yunyang County, Chongqing, China. For comparison, the predictive performance of RF, XGBoost, support vector machine (SVM), and logistic regression (LR) is systematically investigated based on the well-established confusion matrix, which contains the known indices of recall rate, precision, and accuracy. Furthermore, the feature importance of the 12 influencing variables is also explored. Results show that the accuracy of the XGBoost and RF for both the training and testing data is superior to that of SVM and LR, revealing the superiority of the ensemble learning models (i.e. XGBoost and RF) in the slope stability prediction of Yunyang County. Among the 12 influencing factors, the profile shape is the most important one. The proposed ensemble learning-based method offers a promising way to rationally capture the slope status. It can be extended to the prediction of slope stability of other landslide-prone areas of interest.     

Vulnerability of hand-dug wells in the core area of Akure,Nigeria

Hand-dug wells (HDWs) are a major source of water supply in developing nations. This is consequent upon the failure of government to provide safe water to the people. This paper looks at the vulnerability of HDWs in the core area of Akure, Nigeria. The study area is made up of 11 residential quarters with 1149 buildings; 10% of buildings and five wells in each quarter were randomly selected for the study. Data were collected using structured questionnaires and laboratory examinations. Water quality assessment showed that most parameters fall within WHO permissible limits for drinking water. However, microbial examinations indicated that drinking water quality was compromised in two residential quarters as there was evidence of coliform and e-coli. The study also identified other possible sources of water contamination in the study area. This paper recommends regular treatment of wells and the adoption of pipe-borne water supply systems in the city and other similar cities in developing countries.     

基于LS-SVM的粉煤灰混凝土强度预测模型

提出一种基于最小二乘支持向量机(LS-SVM)的粉煤灰混凝土强度智能预测模型,并给出了相应的步骤和算法。通过该模型分析了水胶比、水泥用量、粉煤灰替代率及砂率等因素对粉煤灰混凝土强度的影响。在此基础上,对不同配比所浇注的混凝土强度进行预测,有助于准确认识混凝土强度随配比参数的变化规律。与多元线性回归、神经网络及标准SVM模型比较,该模型的优点为:(1)采用了结构风险最小化准则,在最小化样本误差的同时减小模型泛化误差的上界,提高了模型小样本泛化能力;(2)将迭代学习算法转换为求解线性方程组,使得整个模型仅有一个全局最优点,解决局部最小问题;(3)用等式约束代替标准SVM算法中的不等式约束,将求解二次规划问题转化为直接求解线性矩阵方程,有效提高建模速度。用该模型对混凝土的强度预测实例表明,其建模速度比标准SVM高近1个数量级,预测误差仅为SVM方法的20%、BP神经网络方法的10%左右。     

PSO-SVM与BP神经网络组合预测供水系统余氯的方法

针对余氯量在供水系统内非线性变化的特性,建立了PSO-SVM与BP神经网络组合模型对管网末端余氯进行预测分析。该模型通过粒子群优化算法(PSO),对SVM的特性参数进行优化;采用BP神经网络对模型进行残差修正。通过对单一的BP模型和SVM模型、组合模型的预测精度进行分析。结果表明:组合模型预测比BP和SVM单一预测均方误差分别降低了62.30%、75.29%,平均相对误差降低了55.03%、54.27%。综上所述,该模型具有强大的非线性拟合能力,预测精度高,运行稳定性强,对供水企业控制余氯的投加量和设置二次加氯点有一定的指导作用。     

Real-time prediction of rock mass classification based on TBM operation big data and stacking technique of ensemble learning

Real-time prediction of the rock mass class in front of the tunnel face is essential for the adaptive adjustment of tunnel boring machines(TBMs).During the TBM tunnelling process,a large number of operation data are generated,reflecting the interaction between the TBM system and surrounding rock,and these data can be used to evaluate the rock mass quality.This study proposed a stacking ensemble classifier for the real-time prediction of the rock mass classification using TBM operation data.Based on the Songhua River water conveyance project,a total of 7538 TBM tunnelling cycles and the corresponding rock mass classes are obtained after data preprocessing.Then,through the tree-based feature selection method,10 key TBM operation parameters are selected,and the mean values of the 10 selected features in the stable phase after removing outliers are calculated as the inputs of classifiers.The preprocessed data are randomly divided into the training set(90%)and test set(10%)using simple random sampling.Besides stacking ensemble classifier,seven individual classifiers are established as the comparison.These classifiers include support vector machine(SVM),k-nearest neighbors(KNN),random forest(RF),gradient boosting decision tree(GBDT),decision tree(DT),logistic regression(LR)and multilayer perceptron(MLP),where the hyper-parameters of each classifier are optimised using the grid search method.The prediction results show that the stacking ensemble classifier has a better performance than individual classifiers,and it shows a more powerful learning and generalisation ability for small and imbalanced samples.Additionally,a relative balance training set is obtained by the synthetic minority oversampling technique(SMOTE),and the influence of sample imbalance on the prediction performance is discussed.     

基于边坡位移监测数据的进化支持向量机预测模型研究

支持向量机方法是基于统计学习理论和结构风险最小化原则的学习方法,在回归预测方面具有良好外推能力,并且适合小样本的统计学习问题。建立支持向量机预测模型,对边坡位移进行预测计算,将预测值和实测值对比分析,验证了支持向量机预测模型较强的外推能力和预测计算的有效性。通过对边坡位移初始时序位移数据进行灰色理论的累加生成和累减生成处理,形成新的时间序列数据,在此基础上,计算出预测值,并与基于初始时间序列的支持向量机预测结果对比分析,基于新生成的时间序列数据进行预测计算结果精度明显提高。基于边坡位移监测数据构建训练样本数据集,研究了训练样本数据集的选取对预测结果的影响。对支持向量机预测模型的关键参数进行敏感度分析,并采用进化算法–微粒群算法对支持向量机模型参数加以优化,提高了预测精度。     

Environmental experts in the motor industry

Hazardous wastes are posing the greatest threat to the environment than ever before. Indiscriminate transfer of technology from the Developed Nations for the production of highly hazardous chemicals can lead to a frequent contamination of the environment with the hazardous wastes. The situation appears to be very serious in many of the Third World Nations, where basic problems of water supply and sanitation still need a solution. Contamination of the ground and surface waters with hazardous materials is likely to increase in the developing countries, owing to lack of suitable monitoring techniques. Location of the industries producing hazardous chemicals in the crowded cities has to be prevented to obviate recurrence of serious catastrophes in future. The situation appears to be equally alarming in the developed countries, where ground and surface waters are at a greater risk of contamination with the hazardous wastes. Co disposal of solid chemical wastes with the municipal solid wastes will result in a greater contamination of the ground and surface waters, with longer lasting environmental effects. Hazardous gaseous spills can have serious environmental effects, particularly if the spills contain radioactive contaminants. The intensity of a hazardous gaseous spill can be greatly enhanced under abnormal meteorological conditions.     

演化追踪法优化相空间的SVM供水量预测模型

相空间重构的支持向量机预测模型应用十分广泛,在城市供水量预测方面也占据着重要地位,传统的预测模型趋向于将重构的相空间整体带入,这样可能存在引入无效相点从而影响预测精度的问题,基于此将演化追踪法引入相空间重构的预测模型对有效相点进行筛选,优化预测模型的训练样本,达到提高预测精度目的。利用MATLAB编程软件将演化追踪法用于城市供水量的预测,预测结果的平均绝对误差由0.52%降低到了0.29%,证明了演化追踪法的可利用性与有效性。     

Prediction of elastic modulus of normal and high strength concrete by support vector machine

Elastic modulus is an important property of concrete and is used to calculate deformation of structures. Support vector machine (SVM) is firmly based on learning theory and uses regression technique by introducing accuracy insensitive loss function. This paper investigates the use of SVM to predict elastic modulus of normal and high strength concrete. The elastic modulus predicted by SVM was compared with the experimental data and those from other prediction models. SVM demonstrated good performance and proven to be better than other models.     

Classification of clustered microseismic events in a coal mine using machine learning

Discrimination of seismicity distributed in different areas is essential for reliable seismic risk assessment in mines. Although machine learning has been widely applied in seismic data processing, feasibility and reliability of applying this technique to classify spatially clustered seismic events in underground mines are yet to be investigated. In this research, two groups of seismic events with a minimum local magnitude (M_L) of −3 were observed in an underground coal mine. They were respectively located around a dyke and the longwall face. Additionally, two types of undesired signals were also recorded. Four machine learning methods, i.e. random forest (RF), support vector machine (SVM), deep convolutional neural network (DCNN), and residual neural network (ResNN), were used for classifying these signals. The results obtained based on a primary dataset showed that these seismic events could be classified with at least 91% accuracy. The DCNN using seismogram images as the inputs reached the best performance with more than 94% accuracy. As mining is a dynamic progress which could change the characteristics of seismic signals, the temporal variance in the prediction performance of DCNN was also investigated to assess the reliability of this classifier during mining. A cascaded workflow consisting of database update, model training, signal prediction, and results review was established. By progressively calibrating the DCNN model, it achieved up to 99% prediction accuracy. The results demonstrated that machine learning is a reliable tool for the automatic discrimination of spatially clustered seismicity in underground mining.     

The quest for safe drinking water: an example from Guinea-Bissau (West Africa)

While humans require water for life, one-sixth of our species lives without access to safe water. In Africa, the situation is particularly acute because of global warming, the progression of the Sahara desert, civil unrest and poor governance, population growth, migration and poverty. In rural areas, the lack of adequate safe water and sanitary infrastructures leaves millions with doubtful water quality, increasing the harshness of daily life. In this paper, a pilot study was conducted during the wet season on Bolama Island (Guinea-Bissau, West Africa), a UNESCO Man and the Biosphere Reserve. Twenty-eight shallow wells, supplying water to most of the population, were sampled for microbiological, physical and chemical water quality characteristics. A ten-parameter water quality index (WQI) adapted to tropical conditions was applied to compare the different wells. About 79% of the wells showed moderate to heavy fecal contamination. From the surveyed parameters, it was found that chemical contamination was less important, although all samples were acidic, with the pH averaging 5.12+/-0.08. The WQI was 43+/-4% (0%-worst; 100%-best quality), showing that the water from the majority of wells was polluted but should be suitable for domestic use after appropriate treatment. At the onset of the wet season, diarrhea represented 11.5% of all medical cases, 92.5% of which were children aged <15. This paper suggests inexpensive steps to reduce the fecal contamination and control the pH in order to increase the potability of the well water and, concomitantly, to raise the living standards of the population in one of the poorest countries of the world.     

Prediction of contamination potential of groundwater arsenic in Cambodia, Laos, and Thailand using artificial neural network

The arsenic (As) contamination of groundwater has increasingly been recognized as a major global issue of concern. As groundwater resources are one of most important freshwater sources for water supplies in Southeast Asian countries, it is important to investigate the spatial distribution of As contamination and evaluate the health risk of As for these countries. The detection of As contamination in groundwater resources, however, can create a substantial labor and cost burden for Southeast Asian countries. Therefore, modeling approaches for As concentration using conventional on-site measurement data can be an alternative to quantify the As contamination. The objective of this study is to evaluate the predictive performance of four different models; specifically, multiple linear regression (MLR), principal component regression (PCR), artificial neural network (ANN), and the combination of principal components and an artificial neural network (PC-ANN) in the prediction of As concentration, and to provide assessment tools for Southeast Asian countries including Cambodia, Laos, and Thailand. The modeling results show that the prediction accuracy of PC-ANN (Nash-Sutcliffe model efficiency coefficients: 0.98 (traning step) and 0.71 (validation step)) is superior among the four different models. This finding can be explained by the fact that the PC-ANN not only solves the problem of collinearity of input variables, but also reflects the presence of high variability in observed As concentrations. We expect that the model developed in this work can be used to predict As concentrations using conventional water quality data obtained from on-site measurements, and can further provide reliable and predictive information for public health management policies.     

Runoff-related agricultural impact in relation to macroinvertebrate communities of the Lourens River, South Africa

A field study at the Lourens River, South Africa, was undertaken during the pesticide application period between November 2001 and January 2002 in order to investigate the potential relation of agricultural pollution to the aquatic macroinvertebrate fauna. The upper regions of the Lourens River were free of contamination (LR1), whereas subsequent stretches flowing through a 400-ha orchard area (LR2) received transient insecticide peaks. Continuously operating suspended-particle samplers as well as flood samplers operating during runoff events were used to measure pesticide contamination. In addition, various physicochemical and morphological parameters were examined. A survey of the macroinvertebrate communities associated with the rocky substrates was carried out every three weeks. Community indices were calculated using the South African Scoring System (SASS 5) for bioassessment of water quality in rivers. The two sites differed in pesticide pollution as well as in average turbidity levels (LR1 5.5 mg/L; LR2 64.3 mg/L), but were similar in bottom substrate composition and most other abiotic factors. At the downstream site (LR2), pesticide values of 0.05 microg/L azinphos-methyl in water as well as 49 microg/kg azinphos-methyl, 94 microg/kg chlorpyrifos and 122 microg/kg total endosulfan in suspended particles were found during runoff conditions. The macroinvertebrate communities of the two sampling sites were similar in terms of number of total individuals, but differed significantly (ANOVA) in average number of taxa (LR1 11.7, LR2 8.9). Seven out of 17 investigated taxa occurred in significantly reduced numbers or were even absent at the downstream site LR2. The community characteristics determined by SASS 5 showed a significantly less sensitive community structure at the downstream site (TS 41; ASPT 4.6), indicating continuously lower water quality compared to site LR1 (TS 80; ASPT 6.9). It is concluded that the Lourens River macroinvertebrate communities are affected by agricultural pollution, with pesticides and increased turbidity as the most important stressors.     

Multiclass stand-alone and ensemble machine learning algorithms utilised to classify soils based on their physico-chemical characteristics

This study has provided an approach to classify soil using machine learning. Multiclass elements of stand-alone machine learning algorithms (i.e. logistic regression (LR) and artificial neural network (ANN)), decision tree ensembles (i.e. decision forest (DF) and decision jungle (DJ)), and meta-ensemble models (i.e. stacking ensemble (SE) and voting ensemble (VE)) were used to classify soils based on their intrinsic physico-chemical properties. Also, the multiclass prediction was carried out across multiple cross-validation (CV) methods, i.e. train validation split (TVS), k-fold cross-validation (KFCV), and Monte Carlo cross-validation (MCCV). Results indicated that the soils' clay fraction (CF) had the most influence on the multiclass prediction of natural soils' plasticity while specific surface and carbonate content (CC) possessed the least within the nature of the dataset used in this study. Stand-alone machine learning models (LR and ANN) produced relatively less accurate predictive performance (accuracy of 0.45, average precision of 0.5, and average recall of 0.44) compared to tree-based models (accuracy of 0.68, average precision of 0.71, and recall rate of 0.68), while the meta-ensembles (SE and VE) outperformed (accuracy of 0.75, average precision of 0.74, and average recall rate of 0.72) all the models utilised for multiclass classification. Sensitivity analysis of the meta-ensembles proved their capacities to discriminate between soil classes across the methods of CV considered. Machine learning training and validation using MCCV and KFCV methods enabled better prediction while also ensuring that the dataset was not overfitted by the machine learning models. Further confirmation of this phenomenon was depicted by the continuous rise of the cumulative lift curve (LC) of the best performing models when using the MCCV technique. Overall, this study demonstrated that soil's physico-chemical properties do have a direct influence on plastic behaviour and, therefore, can be relied upon to classify soils.     

Modeling of bentonite/sepiolite plastic concrete compressive strength using artificial neural network and support vector machine

Plastic concrete is an engineering material, which is commonly used for construction of cut-off walls to prevent water seepage under the dam. This paper aims to explore two machine learning algorithms including artificial neural network (ANN) and support vector machine (SVM) to predict the compressive strength of bentonite/sepiolite plastic concretes. For this purpose, two unique sets of 72 data for compressive strength of bentonite and sepiolite plastic concrete samples (totally 144 data) were prepared by conducting an experimental study. The results confirm the ability of ANN and SVM models in prediction processes. Also, Sensitivity analysis of the best obtained model indicated that cement and silty clay have the maximum and minimum influences on the compressive strength, respectively. In addition, investigation of the effect of measurement error of input variables showed that change in the sand content (amount) and curing time will have the maximum and minimum effects on the output mean absolute percent error (MAPE) of model, respectively. Finally, the influence of different variables on the plastic concrete compressive strength values was evaluated by conducting parametric studies.     

建筑与小区二次供水设施运维情况调研与分析

为了了解目前国内典型城市二次供水设施现状以及运维管理存在的问题,对国内18个代表性城市随机抽取的建筑及小区进行实地调研,对发放的调查问卷数据进行统计学分析,在调查的175个二次供水点中,供水设备采用变频泵+低位水箱的占调查总数的53.37%,水箱材质以304不锈钢为主的占调查总数的71.34%。调研结果分析表明,各市需合理选择二次供水设施及其材质,加强督促供水单位对二次供水贮水设施定期清洗消毒,安装水质在线监测设备,对水质即时变化制定应急措施,加强对二次供水点的巡检管理,合理选用巡检模式,保证水质安全。     

重庆小城镇居民用水状况研究

对重庆小城镇(市)———永川、黔江居民生活用水状况调查研究表明:2004年两座城市居民实际人均用水量与居民的家庭收入具有一定的相关性,但总体而言仍低于现行规范值。居民对现有的自来水水质满意程度不一,26.21%的居民对现在的自来水水质非常不满意或不满意,74.6%的居民都希望供水的卫生状况得到改善,27.27%的居民希望有直饮水供应,并且被调查的居民中已有56.68%的家庭将桶装水作为饮用水。85%以上的家庭愿意为自来水质改善和污水处理支付费用。     

Futurism in Planning for Developing Countries

Futurism, coupled with long-range planning, is an extremely significant intellectual development, stretching out into lead-times of up to 100 years. For over a century, Marxists have been intellectually engaged with futurism, and slowly the West—especially France under “indicative planning”—is attempting to apply this approach. However, developing countries take much longer (than was originally thought) to “modernize” with traditional psychosocial barriers to the process. “Modern” men with hard-to-come-by qualities are needed for “modem” society. This raises serious questions about the effectiveness of applied futurism in developing countries, at least for the present.     

Escherichia coli O157:H7 in drinking water from private water supplies in the Netherlands

The microbiological quality of drinking water from 144 private water supplies in the Netherlands was tested and additionally the occurrence of Escherichia coli O157 was examined. Faecal indicators were enumerated by using standard membrane filtration methods. The presence of E. coli O157 was determined using a specific enrichment method. Eleven percent of the samples contained faecal indicators whereas E. coli O157:H7 was isolated from 2.7% of the samples that otherwise met the drinking water standards. The E. coli O157 positive water supplies were located on camp-sites in agricultural areas with large grazer densities. Pulsed field gel electrophoresis (PFGE) analysis suggested that cattle might have been the cause of contamination. Our results indicate that compliance with microbiological quality standards obtained in routine monitoring does not always guarantee the absence of pathogens. The presence of pathogens such as E. coli O157 may suggest possible health consequences; however, a risk assessment process should be performed as the monitoring of both faecal indicator parameters and pathogens do not predict the effect of microbial contamination of drinking water on a population.