Artificial neural network modeling of dissolved oxygen in the Heihe River, Northwestern China

Identification and quantification of dissolved oxygen (DO) profiles of river is one of the primary concerns for water resources managers. In this research, an artificial neural network (ANN) was developed to simulate the DO concentrations in the Heihe River, Northwestern China. A three-layer back-propagation ANN was used with the Bayesian regularization training algorithm. The input variables of the neural network were pH, electrical conductivity, chloride (Cl^?), calcium (Ca²⁺), total alkalinity, total hardness, nitrate nitrogen (NO₃-N), and ammonical nitrogen (NH₄-N). The ANN structure with 14 hidden neurons obtained the best selection. By making comparison between the results of the ANN model and the measured data on the basis of correlation coefficient (r) and root mean square error (RMSE), a good model-fitting DO values indicated the effectiveness of neural network model. It is found that the coefficient of correlation (r) values for the training, validation, and test sets were 0.9654, 0.9841, and 0.9680, respectively, and the respective values of RMSE for the training, validation, and test sets were 0.4272, 0.3667, and 0.4570, respectively. Sensitivity analysis was used to determine the influence of input variables on the dependent variable. The most effective inputs were determined as pH, NO₃-N, NH₄-N, and Ca²⁺. Cl^? was found to be least effective variables on the proposed model. The identified ANN model can be used to simulate the water quality parameters.     

基于小波分析优化PM 2.5浓度预测模型

采用多元线性回归方法(MLR)和BP神经网络方法(BPNN),按1 h、3 h、6 h、12 h、24 h、48 h预测时长对贵港市2015—2018年PM_2.5浓度建模并检验对比模型准确率。结果表明,基于MLR与BPNN都能对PM_2.5浓度作预测,预测效果随着预测时长的增加而下降,MLR、BPNN模型预测结果平均绝对误差(MAE)分别为4.01μg/m³~15.48μg/m³、3.89μg/m³~15.63μg/m³。采用小波分析方法对污染物数据优化并再次建模,结果表明,小波-多元线性回归(W-MLR)模型与小波-神经网络(W-BPNN)模型均得到优化,3 h~24 h预测时长优化效果尤为显著,W-MLR、W-BPNN模型预测结果分别使MAE降低1.6%~13.5%、0.8%~9.8%,且后者预测效果优于前者。     

Hybrid Neural Networks and Boosted Regression Tree Models for Predicting Roadside Particulate Matter

This paper examines the application of artificial neural network (ANN) and boosted regression tree (BRT) methods in air quality modelling. The methods were applied to developing air quality models for predicting roadside particle mass concentration (PM₁₀, PM_2.5) and particle number counts (PNC) based on air pollution, traffic and meteorological data from Marylebone Road in London. Elastic net, Lasso and principal components analysis were used as feature selection methods for the ANN models to reduce the number of predictor variables and improve their generalisation. The performance of the ANN with feature selection (ANN hybrid) and the BRT models was evaluated and compared using statistical performance metrics. The performance parameters include root mean square error (RMSE), fraction of prediction within a factor of two of the observation (FAC2), mean bias (MB), mean gross error (MGE), the coefficient of correlation (R) and coefficient of efficiency (CoE) values. The input variables selected by the elastic net produced the best performing ANN models. The ANN hybrid produced models performed only slightly better than the BRT models. The R values of the ANN elastic net and BRT models were 0.96 and 0.95 for PM₁₀, 0.96 and 0.96 for PM_2.5 and 0.89 and 0.87 for PNC, respectively. Their corresponding CoE values were 0.72 and 0.70 for PM₁₀, 0.74 and 0.76 for PM_2.5 and 0.81 and 0.71 for PNC respectively. About 80–99% of all the model predictions are within a factor of two of the observed particle concentrations. The BRT models offer more advantages regarding model interpretation and permit feature selection. Therefore, the study recommends the use of BRT over ANN where the model interpretation is a priority.     

Monitoring sediment oxygen demand for assessment of dissolved oxygen distribution in river

Sediment oxygen demand (SOD) has become an integral part of modeling dissolved oxygen (DO) within surface water bodies. Because very few data on SOD are available, it is common for modeler to take SOD values from literature for use within DO models. SOD is such an important parameter in modeling DO that this approach may lead to erroneous results. This paper reported on developing an approach for monitoring sediment oxygen demand conducted with undisturbed sediment core samples, where the measured results were incorporated into a water quality model for simulating and assessing dissolved oxygen distribution in the Xindian River of northern Taiwan. The measured results indicate that a higher freshwater discharge results in a lower SOD. Throughout a 1-year observation in 2004, the measured SOD ranged from 0.367 to 1.246 g/m(2)/day at the temperature of 20°C. The mean values of the measured SOD at each station were adopted in a vertical two-dimensional water quality model to simulate the DO distribution along the Xindian River. The simulating results accurately depict the field-measured DO distribution during the low and high flow conditions. Model sensitivity analyses were also conducted with increasing and decreasing SOD values for the low and high flow conditions and revealed that SOD had a significant impact on the DO distribution along the Xindian River. The present work combined with field measurements and numerical simulation should assist in river water quality management.     

Artificial neural network analysis for reliability prediction of regional runoff utilization

Many factors in the reliability analysis of planning the regional rainwater utilization tank capacity need to be considered. Based on the historical daily rainfall data, the following four analyzing procedures will be conducted: the regional daily rainfall frequency, the amount of runoff, the water continuity, and the reliability. Thereafter, the suggested designed storage capacity can be obtained according to the conditions with the demand and supply reliability. By using the output data, two different types of artificial neural network models are used to build up small area rainfall–runoff supply systems for the simulation of reliability and the prediction model. They are also used for the testing of stability and learning speed assessment. Based on the result of this research, the radial basis function neural network (RBFNN) model, using the Gaussian function that has a similar trend as the nature as basic function, has better stability than using the back-propagation neural network (BPNN) model. Despite the fact that RBFNN was more reliable than BPNN, it still made a conservative estimate for the actual monitoring data. The error rate of RBFNN was still higher than the correction of BPNN 4-3-1-1. This should have significant benefit in the future application of the instantaneous prediction or the development of related intelligent instantaneous control equipment.     

Monitoring diel dissolved oxygen dynamics through integrating wavelet denoising and temporal neural networks

Diel dissolved oxygen (DO) time series measured continuously using proximal sensors in situ for a temperate lake were denoised using discrete wavelet transform (DWT) with the orthogonal wavelet families of coiflet, daubechies, and symmlet with order of 10. Diel DO time series denoised were modeled using nine temporal artificial neural networks (ANNs) as a function of water level, water temperature, electrical conductivity, pH, day of year, and hour. Our results showed that time-lag recurrent network (TLRN) using denoised data emulated diel DO dynamics better than the best-performing TLRN using the original data, time-delay neural network (TDNN), and recurrent network (RNN). Daubechies basis dealt with diel DO data slightly better than the other bases given its coefficient of determination (r ²?=?87.1 %), while symmlet performed slightly better than the other bases in terms of root mean square error (RMSE?=?1.2 ppm) and mean absolute error (MAE?=?0.9 ppm).     

Water Quality Prediction of Water Sources Based on Meteorological Factors using the CA-NARX Approach

With the increasingly serious problem of surface water environmental safety, it is of great significance to study the changing trend of reservoir water quality, and it is necessary to establish a water quality prediction and early warning system for the management and maintenance of water resources. Aiming at the problem of water quality prediction in reservoirs, a CA-NARX algorithm is designed, which combines the improved dynamic clustering algorithm with the idea of machine learning and the forward dynamic regression neural network. The improved dynamic clustering algorithm is used to classify the eutrophication degree of waterbodies according to the total phosphorus and total nitrogen content. Considering four meteorological factors, air temperature, water temperature, water surface evaporation, and rainfall, synthetically for each water quality condition, the total phosphorus and total nitrogen in the waterbody are forecasted by an improved forward NARX dynamic regression neural network. Based on this, the CA-NARX prediction algorithm can realize short period water quality prediction. Compared with the traditional support vector regression machine model, improved GA-BP neural network, and exponential smoothing method, the CA-NARX model has the least prediction error.

     

合肥市生活垃圾产量多模型预测与分析

针对合肥市生活垃圾产量现状,通过建立时间序列(ARIMA)、多元线性回归(MLR)、灰色系统GM(1,1)和反向传播神经网络(BPNN)模型对历史数据进行验证比较分析。结果表明,ARIMA(0,1,2)模型的MAPE、MAE、RMSE、NRMSE分别为1.879%、2.240、2.781、0.021,其精度最高、效果最好,为合肥市生活垃圾产量的最佳预测模型。用该模型预测合肥市2021—2025年的城市生活垃圾产量,结果显示生活垃圾产生量为218.89万t～290.71万t。     

Precipitable water modelling using artificial neural network in Çukurova region

Precipitable water (PW) is an important atmospheric variable for climate system calculation. Local monthly mean PW values were measured by daily radiosonde observations for the time period from 1990 to 2006. Artificial neural network (ANN) method was applied for modeling and prediction of mean precipitable water data in Çukurova region, south of Turkey. We applied Levenberg–Marquardt (LM) learning algorithm and logistic sigmoid transfer function in the network. In order to train our neural network we used data of Adana station, which are assumed to give a general idea about the precipitable water of Çukurova region. Thus, meteorological and geographical data (altitude, temperature, pressure, and humidity) were used in the input layer of the network for Çukurova region. Precipitable water was the output. Correlation coefficient (R²) between the predicted and measured values for monthly mean daily sum with LM method values was found to be 94.00% (training), 91.84% (testing), respectively. The findings revealed that the ANN-based prediction technique for estimating PW values is as effective as meteorological radiosonde observations. In addition, the results suggest that ANN method values be used so as to predict the precipitable water.     

Generalized regression neural network (GRNN)-based approach for colored dissolved organic matter (CDOM) retrieval: case study of Connecticut River at Middle Haddam Station,USA

The prediction of colored dissolved organic matter (CDOM) using artificial neural network approaches has received little attention in the past few decades. In this study, colored dissolved organic matter (CDOM) was modeled using generalized regression neural network (GRNN) and multiple linear regression (MLR) models as a function of Water temperature (TE), pH, specific conductance (SC), and turbidity (TU). Evaluation of the prediction accuracy of the models is based on the root mean square error (RMSE), mean absolute error (MAE), coefficient of correlation (CC), and Willmott’s index of agreement (d). The results indicated that GRNN can be applied successfully for prediction of colored dissolved organic matter (CDOM).     

Modeling hourly dissolved oxygen concentration (DO) using two different adaptive neuro-fuzzy inference systems (ANFIS): a comparative study

This article presents a comparison of two adaptive neuro-fuzzy inference systems (ANFIS)-based neuro-fuzzy models applied for modeling dissolved oxygen (DO) concentration. The two models are developed using experimental data collected from the bottom (USGS station no: 420615121533601) and top (USGS station no: 420615121533600) stations at Klamath River at site KRS12a nr Rock Quarry, Oregon, USA. The input variables used for the ANFIS models are water pH, temperature, specific conductance, and sensor depth. Two ANFIS-based neuro-fuzzy systems are presented. The two neuro-fuzzy systems are: (1) grid partition-based fuzzy inference system, named ANFIS_GRID, and (2) subtractive-clustering-based fuzzy inference system, named ANFIS_SUB. In both models, 60 % of the data set was randomly assigned to the training set, 20 % to the validation set, and 20 % to the test set. The ANFIS results are compared with multiple linear regression models. The system proposed in this paper shows a novelty approach with regard to the usage of ANFIS models for DO concentration modeling.     

Monitoring and validating spatio-temporal dynamics of biogeochemical properties in Mersin Bay (Turkey) using Landsat ETM+

The objective of this study was to devise and validate simple models for estimating spatio-temporal dynamics of seven optically (in)active biogeochemical properties in Mersin Bay using Landsat 7 Enhanced Thematic Mapper Plus (ETM+) data and GIS. Spatio-temporal dynamics of Secchi depth (S (depth)), dissolved oxygen (DO), nitrite nitrogen (NO(2)-N), nitrate nitrogen (NO?-N), silicate (SiO?), 5-day biological oxygen demand (BOD5), and chlorophyll-a (Chl-a) were estimated using best-fit multiple linear regression (MLR) models as a function of Landsat 7 ETM+ and ground data in 2007 and 2008, latitude, longitude, and day of year. Validation of the MLR models against Landsat and ground data in 2005 led to r values ranging from 0.39 for NO?-N (P?=?0.008) to 0.79 for S (depth) (P?相似文献   

Forest cover change and fragmentation using Landsat data in Maçka State Forest Enterprise in Turkey

In this study, Grey model (GM) and artificial neural network (ANN) were employed to predict suspended solids (SSeff) and chemical oxygen demand (CODeff) in the effluent from a wastewater treatment plant in industrial park of Taiwan. When constructing model or predicting, the influent quality or online monitoring parameters were adopted as the input variables. ANN was also adopted for comparison. The results indicated that the minimum MAPEs of 16.13 and 9.85% for SSeff and CODeff could be achieved using GMs when online monitoring parameters were taken as the input variables. Although a good fitness could be achieved using ANN, they required a large quantity of data. Contrarily, GM only required a small amount of data (at least four data) and the prediction results were even better than those of ANN. Therefore, GM could be applied successfully in predicting effluent when the information was not sufficient. The results also indicated that these simple online monitoring parameters could be applied on prediction of effluent quality well.     

基于遥感影像的木兰溪水质参数反演

水质监测对水环境评价及污染预防至关重要,但地面监测成本高、监测面积有限等,难以满足实时、大范围监测的要求。为了更好地解决该问题,基于遥感影像的空中监测技术越来越得到研究人员的青睐。以木兰溪为研究区,利用和地面监测数据同步的Landsat-8卫星遥感影像数据,对木兰溪的典型水质参数总磷、总氮、溶解氧、高锰酸盐指数的反演问题进行研究。首先,根据Landsat-8的水体敏感波段,分别选取总磷、总氮、溶解氧、高锰酸盐指数的反演特征波段组合为(b1-b2)/(b2+b3),(b1-b2)/(b3-b4),b2/(b1+b4),b1/b2;其次,利用反演特征波段组合分别构建总磷、总氮、溶解氧、高锰酸盐指数浓度的SVR(Support Vector Regression)反演模型,通过IPSO算法对SVR模型的参数进行优选;然后,将IPSO-SVR反演模型和统计回归反演模型、广义回归神经网络(GRNN)反演模型在验证集上进行评估,以平均绝对误差和均方根误差作为评价指标进行对比分析,结果表明IPSO-SVR反演模型的平均绝对误差和均方根误差最小,说明IPSO-SVR反演模型具有较高的精度和较好的实用性...     

Prediction of the effluent from a domestic wastewater treatment plant of CASP using gray model and neural network

When a domestic wastewater treatment plant (DWWTP) is put into operation, variations of the wastewater quantity and quality must be predicted using mathematical models to assist in operating the wastewater treatment plant such that the treated effluent will be controlled and meet discharge standards. In this study, three types of gray model (GM) including GM (1, N), GM (1, 1), and rolling GM (1, 1) were used to predict the effluent biochemical oxygen demand (BOD), chemical oxygen demand (COD), and suspended solids (SS) from the DWWTP of conventional activated sludge process. The predicted results were compared with those obtained using backpropagation neural network (BPNN). The simulation results indicated that the minimum mean absolute percentage errors of 43.79%, 16.21%, and 30.11% for BOD, COD, and SS could be achieved. The fitness was higher when using BPNN for prediction of BOD (34.77%), but it required a large quantity of data for constructing model. Contrarily, GM only required a small amount of data (at least four data) and the prediction results were analogous to those of BPNN, even lower than that of BPNN when predicting COD (16.21%) and SS (30.11%). According to the prediction, results suggested that GM could predict the domestic effluent variation when its effluent data were insufficient.     

Use of a GIS-based hybrid artificial neural network to prioritize the order of pipe replacement in a water distribution network

A methodology based on the integration of a seismic-based artificial neural network (ANN) model and a geographic information system (GIS) to assess water leakage and to prioritize pipeline replacement is developed in this work. Qualified pipeline break-event data derived from the Taiwan Water Corporation Pipeline Leakage Repair Management System were analyzed. “Pipe diameter,” “pipe material,” and “the number of magnitude-3^?+? earthquakes” were employed as the input factors of ANN, while “the number of monthly breaks” was used for the prediction output. This study is the first attempt to manipulate earthquake data in the break-event ANN prediction model. Spatial distribution of the pipeline break-event data was analyzed and visualized by GIS. Through this, the users can swiftly figure out the hotspots of the leakage areas. A northeastern township in Taiwan, frequently affected by earthquakes, is chosen as the case study. Compared to the traditional processes for determining the priorities of pipeline replacement, the methodology developed is more effective and efficient. Likewise, the methodology can overcome the difficulty of prioritizing pipeline replacement even in situations where the break-event records are unavailable.     

WEPP and ANN models for simulating soil loss and runoff in a semi-arid Mediterranean region

This paper presents the use of both the Water Erosion Prediction Project (WEPP) and the artificial neural network (ANN) for the prediction of runoff and soil loss in the central highland mountainous of the Palestinian territories. Analyses show that the soil erosion is highly dependent on both the rainfall depth and the rainfall event duration rather than on the rainfall intensity as mostly mentioned in the literature. The results obtained from the WEPP model for the soil loss and runoff disagree with the field data. The WEPP underestimates both the runoff and soil loss. Analyses conducted with the ANN agree well with the observation. In addition, the global network models developed using the data of all the land use type show a relatively unbiased estimation for both runoff and soil loss. The study showed that the ANN model could be used as a management tool for predicting runoff and soil loss.     

Soil water content forecasting by ANN and SVM hybrid architecture

Soil water content prediction is essential to the development of advanced agriculture information systems. Because soil water content series are inherently noise and non-stationary, it is difficult to get an accurate forecasting result. Considering the problems, in this paper, a novel hybrid learning architecture is proposed according to divide-and-conquer principle, the forecasting accuracy is improved. This novel hierarchical architecture is composed of ANN (Kohonen neural network) and SVM (support vector machine). The Kohonen network is used as a classifier, which partitions the whole input space into several distinct feature regions. Then, the best SVM predictor combined with an appropriate kernel function can be achieved for correspondence regions. The experimental results based on the hybrid model exhibit good agreement with actual soil water content measurements and outperform ANN and SVM single-stage models.     

基于集合经验模态分解和支持向量机的溶解氧预测

应用集合经验模态分解(EEMD)和支持向量机(SVM)相结合的方法,建立一种天然水体溶解氧浓度预测模型。首先,利用EEMD方法将溶解氧时序分解成不同频段的分量,以降低序列的非平稳性;然后,根据各序列分量的自身特征建立合适的SVM预测模型,此过程通过相关分析确定各分量输入量;最后,将各子分量预测值合成得到最终的预测结果。使用该模型对嘉陵江北温泉段的溶解氧浓度进行预测,结果表明,与传统单一的SVM和BP神经网络模型相比,该模型能有效提高预测精密度,具有良好的应用前景。     

Water Quality Assessment of an Untreated Effluent Impacted Urban Stream: The Bharalu Tributary of the Brahmaputra River, India

Guwahati, the lone city on the bank of the entire midstream of the Brahmaputra River, is facing acute civic problem due to severe depletion of water quality of its natural water bodies. This work is an attempt towards water quality assessment of a relatively small tributary of the Brahmaputra called the Bharalu River flowing through the city that has been transformed today into a city drainage channel. By analyzing the key physical, chemical and biological parameters for samples drawn from different locations, an assessment of the dissolved load and pollution levels at different segments in the river was made. Locations where the contaminants exceeded the permissible limits during different seasons were identified by examining spatial and temporal variations. A GIS developed for the watershed with four layers of data was used for evaluating the influence of catchment land use characteristics. BOD, DO and total phosphorus were found to be the sensitive parameters that adversely affected the water quality of Bharalu. Relationship among different parameters revealed that the causes and sources of water quality degradation in the study area were due to catchments input, anthropogenic activities and poor waste management. Elevated levels of total phosphorus, BOD and depleted DO level in the downstream were used to develop an ANN model by taking total phosphorus and BOD as inputs and dissolved oxygen as output, which indicated that an ANN based predictive tool can be utilized for monitoring water quality in the future.