ارزیابی کارایی روش‌های شتاب‌دهنده یادگیری ماشین به‌منظور تخمین شاخص کیفی آب رودخانه زاینده‌رود

نوع مقاله : مقاله پژوهشی

نویسندگان

گروه علوم و مهندسی آب، دانشکده کشاورزی، دانشگاه صنعتی اصفهان، اصفهان، ایران

چکیده

باتوجه‌به پدیده تغییر اقلیم، گرمایش کره زمین و کاهش منابع آب، کیفیت آب‌های سطحی به‌عنوان یکی از مهم‌ترین منابع آبی در جهان مورد توجه مهندسین رودخانه قرار دارد. ازآنجاکه پرکاربردترین شاخص سنجش کیفیت آب شاخص WQI است؛ هدف و اهمیت این تحقیق مدل‌سازی شاخص کیفیت آب به کمک دو روش شتاب‌دهنده یادگیری ماشین Gradient Boosting و XGBoost در رودخانه زاینده‌رود انجام‌گرفته است. در این تحقیق ابتدا بر اساس داده‌های کیفیت آب، شاخص کیفیت آب (NSFWQI) محاسبه، و در ادامه به‌منظور مدل‌سازی، از داده‌های ورودی شامل ویژگی‌های کیفی آب ۸ ایستگاه در یک دوره ۳۱ساله و همچنین شاخص کیفیت آب محاسبه شده رودخانه استفاده شد. در این تحقیق برای مدل‌سازی در محیط برنامه‌نویسی پایتون کدنویسی شده، و در مرحله آموزش ۸۰ درصد داده‌ها و در مرحله ارزیابی ۲۰ درصد باقی‌مانده مورد استفاده قرار گرفت. بر اساس نتایج معیارهای ارزیابی ضریب تعیین R2، میانگین قدرمطلق خطا MAE، حداکثر خطا ME، میانگین مربعات خطا MSE، جذر میانگین مربعات خطا RMSE و جذر میانگین مربعات خطای نرمال‌شده NRMSE  مدل بهینه انتخاب شد. نتایج تحقیق نشان داد که در تمام ایستگاه‌ها به جز یک ایستگاه از بین مدل‌های استفاده شده، مدل GB باتوجه‌به معیارهای ارزیابی مدل عملکرد بهتری نسبت به مدل XGBoost برخوردار بوده است. همچنین نتایج نشان داد که برای صرفه‌جویی در زمان و هزینه و همچنین مدیریت بهینه ویژگی‌های کیفیت آب، انتخاب سری شماره ۳ که در آن از سه ویژگی به‌منظور برآورد شاخص کیفیت آب (WQI) استفاده می‌شود، بهترین ترکیب بوده است.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Evaluation the efficiency of machine learning boosting methods for estimating the water quality index of the Zayandeh Rood River

نویسندگان [English]

  • Elham Fazel Najafabadi
  • Mohammad Shayannejad
Department of Water Science and Engineering. College of Agriculture, Isfahan University of Technology, Isfahan, Iran
چکیده [English]

Regarding climate change, global warming, and the reduction of water resources, surface water quality is of great interest to river engineers as surface water is one of the most important water resources in the world. Since the most widely used water quality index is the WQI index, the goal and importance of this research are to model the WQI using two machine learning boosting methods in the Zayandeh Rood River, Gradient Boosting and XGBoost. First, based on water quality data, the water quality index (NSFWQI) was calculated, and then, for modeling, input data including water quality characteristics of 8 stations over 31 years and the calculated WQI were used. In this study, the model was coded in the Google Colab environment, and 80% of the data was used in the training phase and the remaining 20% in the evaluation phase. Based on the results of the evaluation criteria of coefficient of determination (R2), mean absolute error (MAE), maximum error (ME), mean square error (MSE), root mean square error (RMSE), and normalized root mean square error (NRMSE), the optimal model was selected. The results of the study showed that in all stations except one station among the models used, the GB performed better than the XGBoost according to the model evaluation criteria. The results also showed that to save time and cost, and also to optimally manage water quality characteristics, the selection of the number 3 series, in which three characteristics are used to estimate the WQI, was the best combination.

کلیدواژه‌ها [English]

  • Water quality characteristics
  • Zayandeh Rood River
  • Machine learning models
  • GB
  • XGBoost

EXTENDED ABSTRACT

 

Introduction

With the increase in population and the decrease in water resources, the pollution of water resources, especially surface water resources, has received more and more attention. The most widely used water quality index is NSFWQI, which has been used and studied in numerous studies (Mahrouyan et al. 2021, Zamani-Ahmadmahmoodi et al. 2021, Aghaee et al. 2020, Khalife and Khoshnazar 2018). Since several quality parameters affect this index, the estimation and calculation of this index have always faced challenges. With the advancement of metadata science and artificial intelligence, the use of machine learning models can be useful in accurately estimating the water quality index, especially when limited data is available. In research, various machine learning methods have been used to provide an optimal model for estimating the water quality index, including Khoi et al. (2022), Rahaman et al. (2024), Lin et al. (2024), and Palabıyık and Akkan (2024) noted. Considering that the Zayandeh Rood River is vital in the central plateau of Iran, it is important to detect and estimate its water quality index. Also, given the unavailability of some data at some stations, the present study can be a solution to this problem by examining the ability of two algorithms, Gradient Boosting and Extreme Gradient Boosting, in estimating the water quality index (WQI).

Method

This research was conducted on 8 stations of the Zayandeh Rood River. The dataset used in this study included water quality data from 8 stations: Shahrokh Castle, Zayandeh Rood Dam, Zamankhan Bridge, Cham-Aseman Dam, Kaleh Bridge, Diziche, Lanej, and Musian, measured monthly over 31 years (1991 to 2022). These data included (EC), (TDS), (pH), (TH), (Cl-), (Mg2+), (Na+), (Ca2+), (SO42-), and (HCO3-) as target features for estimating the water quality index (WQI). To calculate the water quality index in this study, the NSFWQI index was used, which is one of the first and most widely used indices for the overall assessment of water quality status (Alexakis et al. 2016, Sutadian et al. 2016) and is classified into five classes: very bad, bad, moderate, good, and excellent. In this study, Machine learning models (GB and XGBoost) were used to predict the water quality index (WQI) based on selected features, and coding was done in Google Colab using the Python programming language. The evaluation criteria for presenting the best model were R2, MAE, ME, MSE, RMSE, and NRMSE. Uncertainty analysis and cross-validation analysis were also performed.

Results

Since different water quality variables do not contribute equally to forming WQI values, it is possible to identify several determinant variables that reflect the water quality status without losing key information. In this study, the importance of the variables was identified by the SHAP method. Based on this analysis, the importance of the variables was obtained as follows: EC, TDS, TH, pH, HCO3-, Mg2+, SO42-, Cl-, Na+, and Ca2+. Based on this arrangement, six series were defined, and the aforementioned models were used for these series to estimate the water quality index. The results of this study showed that in 7 stations, the GB model, and in only one station, the XGB model, is recommended for estimating the water quality index. Also, among the defined series, series number 3 has the highest frequency in different stations as the optimal series, and this series can be introduced as the recommended series. In this series, three parameters have been used to estimate the water quality index. Comparison with previous research showed that Ejaz et al. (2024) and Sidek et al. (2024) also introduced the GB model as the best model for estimating water quality index in their research. The commonality of the mentioned research with the present research was the use of anions such as Cl-, cations such as K+, and features such as TDS and pH.

Conclusions

In this study, two augmented machine learning models were used to estimate the NSFWQI water quality index. The findings of this study showed that the GB algorithm performed best at seven stations. The coefficient of determination was in the range of 0.999-0.802, and the RMSE index was in the range of 0.112-0.201. The results of the feature importance analysis showed that the features EC, TDS, TH, and HCO3- were the most important, respectively. The study of different series introduced three key features, EC, TDS, and TH, in predicting the water quality index. Therefore, since the goal of artificial intelligence is to reduce time and cost in studies, by replacing 3 features instead of 10 features, a proper prediction of the Water Quality Index (WQI) can be achieved. The findings of this study will help water managers and policymakers in efficiently calculating water quality indices for rivers and streams. This is achieved by reducing computational time, lowering costs, and monitoring polluted stations. However, it is important to acknowledge several limitations of this study, primarily related to the selection of physicochemical variables and limited sampling locations. The research can be expanded with a larger number of sampling locations and a wider range of physicochemical variables to predict the water quality index of the Zayandeh Rood River.

Author Contributions

“Conceptualization, E.F. and M.Sh.; methodology, E.F.; software, M.Sh.; validation, E.F., M.Sh.; formal analysis, E.F.; investigation, E.F.; resources, E.F.; data curation, E.F.; writing—original draft preparation, E.F.; writing—review and editing, M.Sh.. All authors have read and agreed to the published version of the manuscript.”

Data Availability Statement

Data available on request from the authors

Ethical considerations

The authors avoided data fabrication, falsification, plagiarism, and misconduct.

Conflict of interest

The author declares no conflict of interest.

مراجع

Aghaee, M., Heshmatpoor, A., & Seyedian, S. M. (2020). Investigation of water quality of Chehelchay River using IRWQIsc index.
Akbari Osmavandani, S., Sharafati, A., & Moghaddam, H. K. (2024). Assessing the effectiveness of artificial intelligence models in predicting Zayanderud dam inflow at different time scales. Acta Geophysica, 72(5), 3511-3527.
Alexakis, D. E. (2022). Applying factor analysis and the CCME water quality index for assessing groundwater quality of an Aegean Island (Rhodes, Greece). Geosciences, 12(10), 384.
Alexakis, D., Tsihrintzis, V. A., Tsakiris, G., & Gikas, G. D. (2016). Suitability of water quality indices for application in lakes in the Mediterranean. Water resources management, 30, 1621-1633.
Alizadeh, M., Mirzaei, R., & Kia, S. H. (2017). Determining the spatial trend of water quality indices across Kan and Karaj river basins. Journal of Environmental Health Enginering, 4(3), 256-243.
Al-Mukhtar, M., & Al-Yaseen, F. (2019). Modeling water quality parameters using data-driven models, a case study Abu-Ziriq marsh in south of Iraq. Hydrology, 6(1), 24.
Basha, L., Shyti, B., & Bekteshi, L. (2024). Evaluating the performance of machine learning approaches in predicting Albanian Shkumbini River's waters using water quality index model. Journal of Environmental Engineering and Landscape Management, 32(2), 117-127.
Bentéjac, C., Csörgő, A., & Martínez-Muñoz, G. (2021). A comparative analysis of gradient boosting algorithms. Artificial Intelligence Review, 54, 1937-1967.
Box, G. E., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time series analysis: forecasting and control. John Wiley & Sons.
Breiman, L. (2001). Random forests. Machine learning, 45, 5-32.
Bui, D. T., Khosravi, K., Tiefenbacher, J., Nguyen, H., & Kazakis, N. (2020). Improving prediction of water quality indices using novel hybrid machine-learning algorithms. Science of the Total Environment, 721, 137612.
Chen, K., Chen, H., Zhou, C., Huang, Y., Qi, X., Shen, R., Liu, F., Zuo, M., Zou, X., Wang, J. and Zhang, Y., (2020). Comparative analysis of surface water quality prediction performance and identification of key water parameters using different machine learning models based on big data. Water research, 171, 115454.
Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).
Cheng, G., Wang, M., Chen, Y., & Gao, W. (2020). Source apportionment of water pollutants in the upstream of Yangtze River using APCS–MLR. Environmental Geochemistry and Health, 42, 3795-3810.
de Almeida, G. S., & de Oliveira, I. B. (2018). Application of the index WQI-CCME with data aggregation per monitoring campaign and per section of the river: case study—Joanes River, Brazil. Environmental monitoring and assessment, 190(4), 195.
Dezfooli, D., Mooghari, S.M.H., Ebrahimi, K., & Araghinejad, S. (2017). Water quality classification based on minimum qualitative parameter (Case Study: Karun River). Journal of Natural Environment, 70(3), 583-595. https://sid.ir/paper/195087/en. [In Persian]
DOE (Department of Environment, Islamic Republic of Iran). (2012) Guideline for calculating water quality index in Iran. In Persian, https://www.doe.ir/portal/file/?958505/5-.
Effendi, H., & Wardiatno, Y. (2015). Water quality status of Ciambulawung River, Banten Province, based on pollution index and NSF-WQI. Procedia Environmental Sciences, 24, 228-237.
Ejaz, U., Khan, S. M., Jehangir, S., Ahmad, Z., Abdullah, A., Iqbal, M., Khalid, N., Nazir, A. & Svenning, J. C. (2024). Monitoring the Industrial waste polluted stream-Integrated analytics and machine learning for water quality index assessment. Journal of Cleaner Production, 450, 141877.
Farzana, S. Z., Paudyal, D. R., Chadalavada, S., & Alam, M. J. (2024). Temporal Dynamics and Predictive Modelling of Streamflow and Water Quality Using Advanced Statistical and Ensemble Machine Learning Techniques. Water, 16(15), 2107.
Fonseca, A., Botelho, C., Boaventura, R. A., & Vilar, V. J. (2024). Evaluating the Effects of Parameter Uncertainty on River Water Quality Predictions. Resources, 13(8), 106.
Gao, Y., Wang, S., Zhang, C., Xing, C., Tan, W., Wu, H., Niu, X. and Liu, C. (2023). Assessing the impact of urban form and urbanization process on tropospheric nitrogen dioxide pollution in the Yangtze River Delta, China. Environmental Pollution, 336, 122436.
Gholizadeh, M. H., Melesse, A. M., & Reddi, L. (2016). Water quality assessment and apportionment of pollution sources using APCS-MLR and PMF receptor modeling techniques in three major rivers of South Florida. Science of the Total Environment, 566, 1552-1567.
Goodarzi, M. R., Abedi, M. J., Niknam, A. R. R., & Heydaripour, M. (2022). Groundwater quality status based on a modification of water quality index in an arid area, Iran. Water Supply, 22(7), 6245-6261.
Goodarzi, M. R., Niknam, A. R. R., Rahmati, S. H., & Attar, N. F. (2023a). Assessing land use changes’ effect on river water quality in the Dez Basin using land change modeler. Environmental Monitoring and Assessment, 195(6), 774.
Goodarzi, M. R., Niknam, A. R. R., Rahmati, S. H., & Fatehifar, A. (2023b). Evaluation of the effects of climate change and pollution discharge scenario on the quality of Dez River using the QUAL2Kw model. Environmental Earth Sciences, 82(20), 479.
Gültekin, B., & Sakar, B.E. (2018). Variable importance analysis in default prediction using machine learning techniques. In: Paper Presented at the 7th International Conference on Data Science, Technology and Applications, DATA 2018.
Hamadan, I. R. A. N. (2016). Water quality of Aghlaghan River based on NSFWQI index and zoning it by Geographic Information System (GIS). Journal of Occupational and Environmental Health, 1(1), 68-78.
Hameed, M., Sharqi, S.S., Yaseen, Z.M., Afan, H.A., Hussain, A., & Elshafie, A. (2017). Application of artificial intelligence (AI) techniques in water quality index prediction: a case study in tropical region, Malaysia. Neural Computing and Applications, 28, 893–905.
Horton, R. K. (1965). An index number system for rating water quality. J Water Pollut Control Fed, 37(3), 300-306.
Huang, F., Wang, X., Lou, L., Zhou, Z., & Wu, J. (2010). Spatial variation and source apportionment of water pollution in Qiantang River (China) using statistical techniques. Water research, 44(5), 1562-1572.
Icaga, Y. (2007). Fuzzy evaluation of water quality classification. Ecological Indicators, 7(3), 710-718.
Javid, A., Yaghmaeian, K., Abbasi, E., & Roudbari, A. (2014). An evaluation of water quality from Mojen River, by NSFWQI index. Journal of ecological engineering, 15(4), 1-6.
Kalin, L., & Isik, S. (2010). Prediction of water quality parameters using an artificial neural networks model. In World Environmental and Water Resources Congress 2010: Challenges of Change (pp. 3145-3153).
Kamyab-Talesh, F., Mousavi, S. F., Khaledian, M., Yousefi-Falakdehi, O., & Norouzi-Masir, M. (2019). Prediction of water quality index by support vector machine: a case study in the Sefidrud Basin, Northern Iran. Water Resources, 46, 112-116.
Khalife, S., & Khoshnazar, A. (2018). Evaluation of water quality in Zarrineh-rood River using the standard quality index of Iran's surface water resources. Journal of Water and Wastewater Science and Engineering, 3(1), 22-34.
Khalili, R., Montaseri, H., Motaghi, H., & Jalili, M. B. (2021). Water quality assessment of the Talar River in Mazandaran Province based on a combination of water quality indicators and multivariate modeling. Water and Soil Management and Modelling, 1(4), 30-47.
Khan, M. S. I., Islam, N., Uddin, J., Islam, S., & Nasir, M. K. (2022). Water quality prediction and classification based on principal component regression and gradient boosting classifier approach. Journal of King Saud University-Computer and Information Sciences, 34(8), 4773-4781.
Khoi, D. N., Quan, N. T., Linh, D. Q., Nhi, P. T. T., & Thuy, N. T. D. (2022). Using machine learning models for predicting the water quality index in the La Buong River, Vietnam. Water, 14(10), 1552.
Li, X., Li, P., Wang, D., & Wang, Y. (2014). Assessment of temporal and spatial variations in water quality using multivariate statistical methods: A case study of the Xin’anjiang River, China. Frontiers of environmental science & engineering, 8, 895-904.
Lin, Z., Lim, J. Y., & Oh, J. M. (2024). Innovative interpretable AI-guided water quality evaluation with risk adversarial analysis in river streams considering spatial-temporal effects. Environmental Pollution, 350, 124015.
Luo, H., Nong, X., Xia, H., Liu, H., Zhong, L., Feng, Y., Zhou, W. & Lu, Y. (2024). Integrating Water Quality Index (WQI) and Multivariate Statistics for Regional Surface Water Quality Evaluation: Key Parameter Identification and Human Health Risk Assessment. Water, 16(23), 3412.
Mahrooyan, F., Taghavi, L., Sarai Tabrizi, M., & Babazadeh, H. (2021). Water quality assessment of Qazvin River using NSFWQI Index for water quality classification. Journal of Wetland Ecobiology, 12(1), 99-112.
Malone, B.P., Minasny, B., McBratney, A.B. (2017). Using R for Digital Soil Mapping, vol. 35. Springer.
Matta, G., Nayak, A., Kumar, A., & Kumar, P. (2020). Water quality assessment using NSFWQI, OIP and multivariate techniques of Ganga River system, Uttarakhand, India. Applied Water Science, 10(9), 206.
Niknam, A. R. R., Sabaghzadeh, M., Barzkar, A., & Shishebori, D. (2024). Comparing ARIMA and various deep learning models for long-term water quality index forecasting in Dez River, Iran. Environmental Science and Pollution Research, 1-17.
Ocampo-Duque, W., Ferre-Huguet, N., Domingo, J. L., & Schuhmacher, M. (2006). Assessing water quality in rivers with fuzzy inference systems: A case study. Environment international, 32(6), 733-742.
Oladipo, J. O., Akinwumiju, A. S., Aboyeji, O. S., & Adelodun, A. A. (2021). Comparison between fuzzy logic and water quality index methods: A case of water quality assessment in Ikare community, Southwestern Nigeria. Environmental Challenges, 3, 100038.
Omidi, A., & Shariati, F. (2021). Evaluation of Pasikhan River, north of Iran using water quality index (NSFWQI). Caspian Journal of Environmental Sciences, 19(2), 219-230.
Palabıyık, S., & Akkan, T. (2024). Evaluation of water quality based on artificial intelligence: performance of multilayer perceptron neural networks and multiple linear regression versus water quality indexes. Environment, Development and Sustainability, 1-24.
Panagopoulos, A. (2022). Brine management (saline water & wastewater effluents): Sustainable utilization and resource recovery strategy through Minimal and Zero Liquid Discharge (MLD & ZLD) desalination systems. Chemical Engineering and Processing-Process Intensification, 176, 108944.
Panagopoulos, A., & Giannika, V. (2022). Decarbonized and circular brine management/valorization for water & valuable resource recovery via minimal/zero liquid discharge (MLD/ZLD) strategies. Journal of Environmental Management, 324, 116239.
Panagopoulos, Y., Alexakis, D. E., Skoulikidis, N. T., Laschou, S., Papadopoulos, A., & Dimitriou, E. (2022). Implementing the CCME water quality index for the evaluation of the physicochemical quality of Greek Rivers. Water, 14(17), 2738.
Polikar, R. (2012). Ensemble learning. Ensemble machine learning: Methods and applications, 1-34.
Rahaman, M. H., Sajjad, H., Hussain, S., Masroor, M., & Sharma, A. (2024). Surface water quality prediction in the lower Thoubal river watershed, India: A hyper-tuned machine learning approach and DNN-based sensitivity analysis. Journal of Environmental Chemical Engineering, 12(3), 112915.
Rahman, S., Khan, A. A., Brake, K., & Tobin, A. (2024). Deriving water quality index using site-specific water quality parameter guidelines for real-time water quality stations. Water Quality Research Journal, 59(4), 347-367.
Ramya, S., Srinath, S., & Tuppad, P. (2024). Comprehensive analysis of multiple classifiers for enhanced river water quality monitoring with explainable AI. Case Studies in Chemical and Environmental Engineering, 10, 100822.
Sadeghi, M., Bay, A., Bay, N., Soflaie, N., Mehdinejad, M. H., & Mallah, M. (2015). The survey of Zarin-Gol River water quality in Golestan Province using NSF-WQI and IRWQISC.
Salami, E. S., & Ehteshami, M. (2015). Simulation, evaluation and prediction modeling of river water quality properties (case study: Ireland Rivers). International journal of environmental science and technology, 12, 3235-3242.
Sattari, M. T., Feizi, H., Colak, M. S., Ozturk, A., Ozturk, F., & Apaydin, H. (2021). Surface water quality classification using data mining approaches: Irrigation along the Aladag River. Irrigation and Drainage, 70(5), 1227-1246.
Sidek, L.M., Mohiyaden, H.A., Marufuzzaman, M., Noh, N.S.M., Heddam, S., Ehteram, M., Kisi, O. and Sammen, S.S., (2024). Developing an ensembled machine learning model for predicting water quality index in Johor River Basin. Environmental Sciences Europe, 36(1), 67.
Siham, A., Sara, S., & Abdellah, A. (2021). Feature selection based on machine learning for credit scoring: an evaluation of filter and embedded methods. In: Paper Presented at the 2021 International Conference on Innovations in Intelligent Systems and Applications (INISTA).
Silvert, W. (2000). Fuzzy indices of environmental conditions. Ecological modelling, 130(1-3), 111-119.
Singh, S., Das, A., & Sharma, P. (2024). Predictive modeling of water quality index (WQI) classes in Indian rivers: Insights from the application of multiple Machine Learning (ML) models on a decennial dataset. Stochastic Environmental Research and Risk Assessment, 38(8), 3221-3238.
Singha, S., Pasupuleti, S., Singha, S.S., Singh, R., & Kumar, S. (2021). Prediction of groundwater quality using efficient machine learning technique. Chemosphere, 276, 130265. https://doi.org/10.1016/j.chemosphere.2021.130265.
Soleimanpour, S. M., Mesbah, S. H., & Hedayati, B. (2018). Application of CART decision tree data mining to determine the most effective drinking water quality factors (case study: Kazeroon plain, Fars province).
Sutadian, A. D., Muttil, N., Yilmaz, A. G., & Perera, B. J. C. (2016). Development of river water quality indices—a review. Environmental monitoring and assessment, 188, 1-29.
Tiwari, N.K., Das Gupta, S., Swain, H.S., Jha, D.N., Samanta, S., Manna, R.K., Das, A.K. and Das, B.K. (2022). Water quality assessment in the ecologically stressed lower and estuarine stretches of river Ganga using multivariate statistical tool. Environmental Monitoring and Assessment, 194(7), 469.
Tiwari, D., Kumar, R., Yadav, M., Gupta, G. K., kumar Singh, S., Dhapekar, N. K., ... & Sharma, R. (2025). Holistic analysis of Ganga basin water quality: a statistical approach with WQI, HMCI, HMQI and HRI indices. RSC advances, 15(5), 3290-3316.
Tizro, A. T., Fryar, A. E., Vanaei, A., Kazakis, N., Voudouris, K., & Mohammadi, P. (2021). Estimation of total dissolved solids in Zayandehrood River using intelligent models and PCA. Sustainable Water Resources Management, 7, 1-13.
Tripathi, M., & Singal, S. K. (2019). Use of principal component analysis for parameter selection for development of a novel water quality index: a case study of river Ganga India. Ecological indicators, 96, 430-436.
Uddin, M. G., Nash, S., Rahman, A., & Olbert, A. I. (2022). A comprehensive method for improvement of water quality index (WQI) models for coastal water quality assessment. Water Research, 219, 118532.
Wu, T., Zhang, W., Jiao, X., Guo, W., & Hamoud, Y. A. (2020). Comparison of five Boosting-based models for estimating daily reference evapotranspiration with limited meteorological variables. PLoS One, 15(6), e0235324.
Yadav, A. K., Khan, P., & Sharma, S. K. (2010). Water Quality Index Assessment ofGroundwater in Todaraisingh Tehsil of Rajasthan State, India‐A Greener Approach. Journal of Chemistry, 7, S428-S432.
Yusri, H. I. H., Hassan, S. L. M., Halim, I. S. A., & Abdullah, N. E. (2022, July). Water quality classification using SVM and XGBoost method. In 2022 IEEE 13th Control and System Graduate Research Colloquium (ICSGRC) (pp. 231-236). IEEE.
Zamani-Ahmadmahmoodi, R., Ghaedamini, F., & Najafi, M. (2021). Spatial distribution pattern of water quality of Pireghar river with using water quality index (WQI) and geographic information system (GIS). Journal of Environmental Science and Technology, 23(2), 73-86.
Xu, Y., Li, P., Zhang, M., Xiao, L., Wang, B., Zhang, X., Wang, Y. & Shi, P. (2024). Quantifying seasonal variations in pollution sources with machine learning-enhanced positive matrix factorization. Ecological Indicators, 166, 112543.
Zhao, X., Liu, X., Xing, Y., Wang, L., & Wang, Y. (2022). Evaluation of water quality using a Takagi-Sugeno fuzzy neural network and determination of heavy metal pollution index in a typical site upstream of the Yellow River. Environmental Research, 211, 113058.
تحقیقات آب و خاک ایران
دوره 56، شماره 5
مرداد 1404
صفحه 1355-1378

فایل ها

هم رسانی

ارجاع به این مقاله

آمار