Evaluation of PCA and Gamma test techniques on ANN operation for weekly solid waste prediction

Artificial neural networks (ANNs) are suitable for modeling solid waste generation. In the present study, four training functions, including resilient backpropagation (RP), scale conjugate gradient (SCG), one step secant (OSS), and Levenberg–Marquardt (LM) algorithms have been used. The main goal of this research is to develop an ANN model with a simple structure and ample accuracy. In the first step, an appropriate ANN model with 13 input variables is developed using the afore-mentioned algorithms to optimize the network parameters for weekly solid waste prediction in Mashhad, Iran. Subsequently, principal component analysis (PCA) and Gamma test (GT) techniques are used to reduce the number of input variables. Finally, comparison amongst the operation of ANN, PCA-ANN, and GT-ANN models is made. Findings indicated that the PCA-ANN and GT-ANN models have more effective results than the ANN model. These two models decrease the number of input variables from 13 to 7 and 5, respectively.     

Chemometric Analysis of Surface Water Quality Data: Case Study of the Gorganrud River Basin, Iran

Canonical correlation analysis (CCA), principal component analysis (PCA), and principal factor analysis (PFA) have been adopted to provide ease of understanding: interpretation of a large complex data set in the Gorganrud River monitoring networks, evaluation of the temporal and spatial variations of water quality, and finally identification of monitoring stations and parameters which are most important in assessing annual variations of water quality in the river. In accomplishing the research, 11 surface water quality data related to both of physical and chemical parameters have been collected from seven monitoring stations from 1996 to 2002. In general, our results from CCA method indicated strong relationship between physical and chemical parameters in the Gorganrud River. In addition, analyzing data through the PCA and PFA techniques revealed that all monitoring stations are important in explaining the annual variation of data set. From the point of view of the degree of importance of parameters contributing to water quality variations, further investigations by running two scenarios (rotated factor correlation coefficient value equal to 0.95 and 0.90 for the first and second scenarios, respectively) showed that the important parameters in one season may not be important for another season. For example, unlike in summer, water temperature, total suspended solids, total phosphorous, and nitrate parameters were important, electrical conductivity, and turbidity parameters had been realized as important parameters in spring through the first scenario.     

Progress and challenges of helical-shaped geothermal heat exchangers

Environmental Science and Pollution Research - Among various types of renewable energy, geothermal energy is recognized as an effective method for supplying thermal energy. Ground heat exchangers,...     

Development of GP and GEP models to estimate an environmental issue induced by blasting operation

Air overpressure (AOp) is one of the most adverse effects induced by blasting in the surface mines and civil projects. So, proper evaluation and estimation of the AOp is important for minimizing the environmental problems resulting from blasting. The main aim of this study is to estimate AOp produced by blasting operation in Miduk copper mine, Iran, developing two artificial intelligence models, i.e., genetic programming (GP) and gene expression programming (GEP). Then, the accuracy of the GP and GEP models has been compared to multiple linear regression (MLR) and three empirical models. For this purpose, 92 blasting events were investigated, and subsequently, the AOp values were carefully measured. Moreover, in each operation, the values of maximum charge per delay and distance from blast points, as two effective parameters on the AOp, were measured. After predicting by the predictive models, their performance prediction was checked in terms of variance account for (VAF), coefficient of determination (CoD), and root mean square error (RMSE). Finally, it was found that the GEP with VAF of 94.12%, CoD of 0.941, and RMSE of 0.06 is a more precise model than other predictive models for the AOp prediction in the Miduk copper mine, and it can be introduced as a new powerful tool for estimating the AOp resulting from blasting.     

Evaluating the main sources of groundwater pollution in the southern Tehran aquifer using principal component factor analysis

Determining the main sources of pollution (MSP) in groundwater is crucial to improve water quality (WQ) status. Field studies were conducted in this research, where five sampling campaigns were carried out from 36 wells in the southern Tehran aquifer. In all samples, WQ parameters were measured and evaluated regarding the Iranian drinking water standard (IDWS). Finally, by using the principal component factor analysis (PCFA), the probable MSP in the aquifer were determined. The results showed that all ions, total hardness, and total dissolved solids were above the IDWS. To analyze the PCFA results, only the first four of twenty rotated principal factors (RPFs) that conserved a high percentage of the variance of the data (about 90%) were considered. The results of the first PRF revealed that the geological structure was the MSP in the aquifer. Furthermore, the second RPF was mainly affected by nutrients (nitrate and orthophosphate) and microbial parameters (fecal and total coliforms), indicating the importance of agricultural activities and sewage effluents as another MSP in the aquifer. Finally, the remarkable share of heavy metals and pH in formation of the third and fourth RPFs, respectively, reflected the role of industrial activities as a probable MSP of groundwater.     

Uncertainty analysis of developed ANN and ANFIS models in prediction of carbon monoxide daily concentration

This study aims to predict daily carbon monoxide (CO) concentration in the atmosphere of Tehran by means of developed artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) models. Forward selection (FS) and Gamma test (GT) methods are used for selecting input variables and developing hybrid models with ANN and ANFIS. From 12 input candidates, 7 and 9 variables are selected using FS and GT, respectively. Evaluation of developed hybrid models and its comparison with ANN and ANFIS models fed with all input variables shows that both FS and GT techniques reduce not only the output error, but also computational cost due to less inputs. FS–ANN and FS–ANFIS models are selected as the best models considering R², mean absolute error and also developed discrepancy ratio statistics. It is also shown that these two models are superior in predicting pollution episodes. Finally, uncertainty analysis based on Monte-Carlo simulation is carried out for FS–ANN and FS–ANFIS models which shows that FS–ANN model has less uncertainty; i.e. it is the best model which forecasts satisfactorily the trends in daily CO concentration levels.     

Microbial quality and physical–chemical characteristics of thermal springs

Microbial quality and physical–chemical properties of recreational spas were surveyed to investigate the health aspect of the spas’ water. A total of 195 samples were collected from pools and springs of the spas in five sites from Ardebil Province of Iran. The effects of an independent factor defined as ‘condition’ and its component sub-factors (i.e., sampling point, location, and sampling date) on microbial quality and physical–chemical properties of the spas were studied by applying path analysis. The influence of physical–chemical properties on microbial quality was also considered. The percentage of samples exceeding the ISIRI (Swimming pool water microbiological specifications (vol 9412), Institute of Standards and Industrial Research of Iran, Tehran, 2007) limits for Staphylococcus (spp.) was up to 55.8 in the springs and 87.8 in the pools, 58.1 and 99.2 for HPC, 90.7 and 97.8 for total coliform and fecal coliform, and 9.3 and 34.4 for Pseudomonas aeruginosa, respectively. There were significant differences between the pools and springs for both physical–chemical properties and microbial quality. From the path analysis, sampling point was the most effective sub-factor of ‘condition’ on both the physical–chemical properties and microbial quality. Among the physical–chemical properties, water color had the most enhancing or additive influence on microbial pollution, while EC indicated a reducing or subtractive effect.