Performance of machine learning methods in predicting water quality index based on irregular data set: application on Illizi region (Algerian southeast)

AbstractGroundwater quality appraisal is one of the most crucial tasks to ensure safe drinking water sources. Concurrently, a water quality index (WQI) requires some water quality parameters. Conventionally, WQI computation consumes time and is often found with various errors during subindex calculation. To this end, 8 artificial intelligence algorithms, e.g., multilinear regression (MLR), random forest (RF), M5P tree (M5P), random subspace (RSS), additive regression (AR), artificial neural network (ANN), support vector regression (SVR), and locally weighted linear regression (LWLR), were employed to generate WQI prediction in Illizi region, southeast Algeria. Using the best subset regression, 12 different input combinations were developed and the strategy of work was based on two scenarios. The first scenario aims to reduce the time consumption in WQI computation, where all parameters were used as inputs. The second scenario intends to show the water quality variation in the critical cases when the necessary analyses are unavailable, whereas all inputs were reduced based on sensitivity analysis. The models were appraised using several statistical metrics including correlation coefficient (R), mean absolute error (MAE), root mean square error (RMSE), relative absolute error (RAE), and root relative square error (RRSE). The results reveal that TDS and TH are the key drivers influencing WQI in the study area. The comparison of performance evaluation metric shows that the MLR model has the higher accuracy compared to other models in the first scenario in terms of 1, 1.4572*10–08, 2.1418*10–08, 1.2573*10–10%, and 3.1708*10–08% for R, MAE, RMSE, RAE, and RRSE, respectively. The second scenario was executed with less error rate by using the RF model with 0.9984, 1.9942, 3.2488, 4.693, and 5.9642 for R, MAE, RMSE, RAE, and RRSE, respectively. The outcomes of this paper would be of interest to water planners in terms of WQI for improving sustainable management plans of groundwater resources.

Download Full-text

GIS-based Spatio-Temporal and Geostatistical Analysis of Groundwater Parameters of Lahore Region Pakistan and their Source Characterization

10.21203/rs.3.rs-431857/v1 ◽

2021 ◽

Author(s):

Sadia Ismail ◽

M Farooq Ahmed

Keyword(s):

Water Quality ◽

Groundwater Quality ◽

Water Quality Index ◽

Physicochemical Parameters ◽

Quality Index ◽

Large Data ◽

Quality Parameters ◽

Source Characterization ◽

Data Set ◽

Spatio Temporal

Abstract Assessment of groundwater quality is critical, especially in the areas where it is continuously deteriorating due to unplanned industrial growth. This study utilizes GIS-based spatio-temporal and geostatistics tools to characterize the groundwater quality parameters of Lahore region. For this purpose, a large data set of the groundwater quality parameters (for a period of 2005–2016) was obtained from the deep unconfined aquifers. GIS-based water quality index (WQI) and entropy water quality index (EWQI) models were prepared using 15 water quality parameters pH (power of hydrogen), TDS (Total dissolve solids), EC (Electrical conductivity), TH (Total hardness), Ca2+ (Calcium), Mg2+ (Magnesium), Na+ (Sodium), K+ (Potassium), Cl− (Chloride), As (Arsenic), F (Fluoride), Fe (Iron), HCO3− (Bicarbonate), NO3− (Nitrate), and SO42− (Sulfate). The data analysis exhibits that 12% of the groundwater samples fell within the category of poor quality that helped to identify the permanent epicenters of deteriorating water quality index in the study area. As per the entropy theory, Fe, NO3−, K, F, SO42− and As, are the major physicochemical parameters those influence groundwater quality. The spatio-temporal analysis of the large data set revealed an extreme behavior in pH values along the Hudiara drain, and overall high arsenic concentration levels in most of the study area. The geochemical analysis shows that the groundwater chemistry is strongly influence by subsurface soil water interaction. The research highlights the significance of using GIS-based spatio-temporal and geostatistical tools to analyze the large data sets of physicochemical parameters at regional level for the detailed source characterization studies.

Download Full-text

Exploring Artificial Intelligence Techniques for Groundwater Quality Assessment

Water ◽

10.3390/w13091172 ◽

2021 ◽

Vol 13 (9) ◽

pp. 1172

Author(s):

Purushottam Agrawal ◽

Alok Sinha ◽

Satish Kumar ◽

Ankit Agarwal ◽

Ashes Banerjee ◽

...

Keyword(s):

Artificial Intelligence ◽

Water Quality ◽

Water Quality Index ◽

Quality Index ◽

Traditional Approach ◽

Human Life ◽

Large Data ◽

Quality Parameters ◽

Support Vector ◽

Artificial Intelligence Techniques

Freshwater quality and quantity are some of the fundamental requirements for sustaining human life and civilization. The Water Quality Index is the most extensively used parameter for determining water quality worldwide. However, the traditional approach for the calculation of the WQI is often complex and time consuming since it requires handling large data sets and involves the calculation of several subindices. We investigated the performance of artificial intelligence techniques, including particle swarm optimization (PSO), a naive Bayes classifier (NBC), and a support vector machine (SVM), for predicting the water quality index. We used an SVM and NBC for prediction, in conjunction with PSO for optimization. To validate the obtained results, groundwater water quality parameters and their corresponding water quality indices were found for water collected from the Pindrawan tank area in Chhattisgarh, India. Our results show that PSO–NBC provided a 92.8% prediction accuracy of the WQI indices, whereas the PSO–SVM accuracy was 77.60%. The study’s outcomes further suggest that ensemble machine learning (ML) algorithms can be used to estimate and predict the Water Quality Index with significant accuracy. Thus, the proposed framework can be directly used for the prediction of the WQI using the measured field parameters while saving significant time and effort.

Download Full-text

Evaluation of Ground Water Quality For AL Shuwayja area –Wasit Provence Using GIS Technique

Wasit Journal of Engineering Sciences ◽

10.31185/ejuow.vol1.iss2.8 ◽

2017 ◽

Vol 1 (2) ◽

pp. 1-11

Author(s):

Ali Nasser Hilo

Keyword(s):

Water Quality ◽

Drinking Water ◽

Ground Water ◽

Water Quality Index ◽

Quality Index ◽

Poor Quality ◽

Quality Parameters ◽

Ground Water Quality ◽

Water Index ◽

The City

The low level of water in rivers in Iraq leads to poor water quality, on that basis; we need to assess Iraq's water resources for uses of irrigation and drinking water. This study present a model accounts for ground water quality by using a water quality index (WQI) for the region defined between the city of Kut and the city of Badra in Wasit province. this study relies on a system of wells set up along the path through the Badra –Kut and around it up to 78 wells. The study showed poor quality of ground water in the region of study and it is unsuitability for irrigation and drinking water, as well as provided a solution to the water accumulated in the Shuwayja to reduce the bad effect on groundwater by using a system of branch and collection canals then pumping at the effluent of Al Shuwayja in seasons of rainy season ..Water quality index calculated depend on the basis of various physic-chemical parameters as PH, Ec , TDS, TSS, Nacl , SO4 ,Na , and Mg. The resultant and analytical are present with use of Arch GIS program – geostastical analysis for the water index and water quality parameters

Download Full-text

A study on ground water quality of industrial area at Gajraula (U.P.), India

Journal of Applied and Natural Science ◽

10.31018/jans.v1i2.70 ◽

2009 ◽

Vol 1 (2) ◽

pp. 275-279 ◽

Cited By ~ 3

Author(s):

D. S. Malik ◽

Pawan Kumar ◽

Umesh Bharti

Keyword(s):

Water Quality ◽

Ground Water ◽

Water Samples ◽

Water Quality Index ◽

Quality Index ◽

Analytical Techniques ◽

Industrial Area ◽

Quality Standard ◽

Quality Parameters ◽

Marginal Values

The present study aims to identify the ground water contamination problem in villages located in the close vicinity of Gajraula industrial area at Gajraula (U.P.), India. Ground water samples were collected from different villages at the depth of 40 and 120 feet from earth’s surface layer. Analytical techniques as described in the standard methods for examination of water and waste water were adopted for physico-chemical analysis of ground water samples and the results compared with the standards given by WHO and BIS guidelines for drinking water. Water quality index was calculated for quality standard of ground water for drinking purposes. The present investigation revealed that the water quality is moderately degraded due to high range of seven water quality parameters such as Temperature (18.33-32.36 0C), conductivity (925.45-1399.59 μmho/cm), TDS (610.80-923.73 mgL-1), Alkalinity (260.17- 339.83 mgL-1), Ca-Hardness (129.68-181.17 mgL-1), Mg-Hardness (94.07-113.50 mgLÉ1) and COD (13.99-25.62 mgL-1). The water quality index (WQI) also indicated the all the water quality rating comes under the standard marginal values (45-64) i.e. water quality is frequently threatened or impaired and conditions usually depart from natural or desirable levels.

Download Full-text

Forecasting Water Quality Index in Groundwater Using Artificial Neural Network

Energies ◽

10.3390/en14185875 ◽

2021 ◽

Vol 14 (18) ◽

pp. 5875

Author(s):

Monika Kulisz ◽

Justyna Kujawska ◽

Bartosz Przysucha ◽

Wojciech Cel

Keyword(s):

Neural Network ◽

Water Quality ◽

Artificial Neural Network ◽

Water Quality Index ◽

Quality Index ◽

Network Models ◽

Multiple Regression Model ◽

Neural Network Models ◽

Artificial Neural ◽

Artificial Neural Network Ann

Groundwater quality monitoring in the vicinity of drilling sites is crucial for the protection of water resources. Selected physicochemical parameters of waters were marked in the study. The water was collected from 19 wells located close to a shale gas extraction site. The water quality index was determined from the obtained parameters. A secondary objective of the study was to test the capacity of the artificial neural network (ANN) methods to model the water quality index in groundwater. The number of ANN input parameters was optimized and limited to seven, which was derived using a multiple regression model. Subsequently, using the stepwise regression method, models with ever fewer variables were tested. The best parameters were obtained for a network with five input neurons (electrical conductivity, pH as well as calcium, magnesium and sodium ions), in addition to five neurons in the hidden layer. The results showed that the use of the parameters is a convenient approach to modeling water quality index with satisfactory and appropriate accuracy. Artificial neural network methods exhibited the capacity to predict water quality index at the desirable level of accuracy (RMSE = 0.651258, R = 0.9992 and R2 = 0.9984). Neural network models can thus be used to directly predict the quality of groundwater, particularly in industrial areas. This proposed method, using advanced artificial intelligence, can aid in water treatment and management. The novelty of these studies is the use of the ANN network to forecast WQI groundwater in an area in eastern Poland that was not previously studied—in Lublin.

Download Full-text

Evaluation of Water Quality of Hemren Lake

Diyala Journal of Engineering Sciences ◽

10.24237/djes.2013.06205 ◽

2013 ◽

Vol 6 (2) ◽

pp. 57-76

Author(s):

SAAD SH. SAMMEN

Keyword(s):

Water Quality ◽

Water Quality Index ◽

Quality Index ◽

Quality Parameters ◽

Lake Ecosystem ◽

Index Method ◽

Weighted Arithmetic ◽

Canadian Council ◽

Calcium Magnesium

In this study Water Quality Index (WQI) was applied in Hemren Lake, Diyala province, Iraq using ten water quality parameters (pH, Electrical Conductivity, Hardness, Total Dissolve Soluble, Sodium, Calcium, Magnesium, Potassium, Chloride, Phosphate) from 2008 to 2010 to evaluate the suitability of Hemren Lake ecosystem for drinking and irrigation uses. The Weighted Arithmetic Index method (WAM) and the Canadian Council of Ministers of the Environment Water Quality Index methodology (The CWQI 1.0 model) were used to calculate the water quality index (W.Q.I). The results indicated that drinking water quality of Hemren Lake is good and marginal for the study period according to (WAM) and (CCME) respectively, while the irrigation water quality is good and according to (WAM) and (CCME). It is suggested that monitoring of the lake is necessary for proper management. Application of the WQI is also suggested as a very helpful tool that enables the public and decision makers to evaluate water quality of lakes in Iraq.

Download Full-text

Assessment of groundwater quality around municipal solid waste landfill by using Water Quality Index for groundwater resources and multivariate statistical technique: a case study of the landfill site, Qaem Shahr City, Iran

Environmental Geochemistry and Health ◽

10.1007/s10653-019-00417-0 ◽

2019 ◽

Vol 42 (5) ◽

pp. 1305-1319 ◽

Cited By ~ 3

Author(s):

Hossein Najafi Saleh ◽

Sima Valipoor ◽

Asma Zarei ◽

Mahmood Yousefi ◽

Farzaneh Baghal Asghari ◽

...

Keyword(s):

Water Quality ◽

Municipal Solid Waste ◽

Groundwater Quality ◽

Water Quality Index ◽

Quality Index ◽

Groundwater Resources ◽

Statistical Technique ◽

Multivariate Statistical ◽

Waste Landfill

Download Full-text

Evaluation of Water Quality of the Titas River Using NSF Water Quality Index

Journal of Scientific Research ◽

10.3329/jsr.v3i1.6170 ◽

2010 ◽

Vol 3 (1) ◽

pp. 151 ◽

Cited By ~ 2

Author(s):

S. Islam ◽

T. Rasul ◽

J. Bin Alam ◽

M. A. Haque

Keyword(s):

Water Quality ◽

Water Quality Index ◽

Quality Index ◽

Laboratory Tests ◽

Oxygen Demand ◽

Quality Parameters ◽

Huge Amount ◽

Water Quality Status ◽

Quality Status

The Titas River, a trans-boundary river of Bangladesh flows almost the entire Brahmanbaria district, consumes a huge amount of sewage, agricultural discharges and runoff, waste produced from human excreta, discharges of two oil mills and contaminants from other minor sources. A study is conducted to find the water quality status of the river during the period from July 2008 to June 2009 and by using National Sanitation Foundation (NSF) water quality index, the probable use of this water is predicted. This work consists of laboratory tests for the evaluation of some water quality parameters of the Titas and to identify its probable use in various purposes. The results of the laboratory tests and NSF water quality index suggest that the water can be used for recreation, pisciculture and irrigation purposes but requires treatment before using for drinking.Keywords: Water pollution; Faecal coliform; Dissolved oxygen (DO); Biochemical oxygen demand (BOD).© 2011 JSR Publications. ISSN: 2070-0237 (Print); 2070-0245 (Online). All rights reserved.doi:10.3329/jsr.v3i1.6170 J. Sci. Res. 3 (1), 151-159 (2011)

Download Full-text