نشریه آبیاری و زهکشی ایران

نشریه آبیاری و زهکشی ایران

رویکرد تلفیقی در پایش کیفیت آب رودخانه سیاهرود با بهره‌گیری از روش‌های نوین تحلیل داده

نوع مقاله : مقاله پژوهشی

نویسندگان
1 دانشیار گروه مهندسی آب دانشگاه علوم کشاورزی و منابع طبیعی ساری
2 گروه مهندسی محیط‌زیست، دانشکده مهندسی آب و محیط‌زیست، دانشگاه شهید چمران اهواز، اهواز، ایران.
3 آزمایشگاه زمین‌شناسی، دپارتمان علوم زمین، مدرسه عالی نرمال (ENS)، پاریس، فرانسه.
4 اداره کل حفاظت محیط زیست استان مازندران ، پژوهشکده اکولوژی دریای خزر، ساری ، ایران.
چکیده
شاخص کیفیت آب (WQI) ابزاری مؤثر برای ارزیابی منابع آبی است که با ترکیب پارامترهای مختلف در یک عدد ساده، امکان مقایسه و تصمیم‌گیری را فراهم می‌کند. با این حال، استفاده از وزن‌دهی‌های استاندارد بدون توجه به شرایط محلی ممکن است منجر به نتایج نادرست شود. این پژوهش با هدف بهینه‌سازی محاسبه WQI، از رویکردی تلفیقی شامل تحلیل مؤلفه‌های اصلی (PCA)، تصمیم‌گیری چندمعیاره (MEREC) و مدل‌های هوش مصنوعی بهره برده است. داده‌های ۲۰ ساله (۲۰2۱–۲۰0۱) مربوط به رودخانه سیاهرود در استان مازندران با ۱۱ پارامتر کیفی بررسی شد. کاهش ابعاد داده‌ها با PCA انجام گرفت و شاخص WQI با روش MEREC محاسبه شد. همچنین، پیش‌بینی WQI با دو الگوریتم رگرسیون خطی و جنگل تصادفی، در دو حالت داده‌های واقعی و کاهش‌یافته، انجام شد و با شاخص‌هایی نظیر EVS، MAPE و R² ارزیابی گردید. یافته‌ها نشان دادند کدورت به‌عنوان مؤلفه کلیدی در آلودگی فیزیکی با TSS، BOD و COD همبستگی بالایی دارد. مؤلفه‌های دیگر نمایانگر آلودگی‌های میکروبی، شیمیایی و حرارتی ناشی از فاضلاب و کشاورزی‌اند. میانگین WQI نشان‌دهنده کیفیت نامطلوب آب در بیشتر ایستگاه‌ها بود. مدل رگرسیون خطی عملکرد بهتری نسبت به جنگل تصادفی داشت، هرچند کاهش ابعاد کمی از دقت کاست. روش MEREC نشان داد کلیفرم کل و کدورت بیشترین وزن را دارند، که اهمیت آلودگی میکروبی و ذرات معلق را برجسته می‌سازد. نتایج بر ضرورت پایش مستمر و مدیریت منابع آلودگی تأکید دارند.
کلیدواژه‌ها

عنوان مقاله English

An Integrated Approach to Monitoring Water Quality in the Siahroud River using Modern Data Analysis Methods

نویسندگان English

Mojtaba Khoshravesh 1
Laleh Divband Hafshejani 2
Mostafa Moradzadeh 3
Tahereh Eskandari 4
1 Associate Professor. Department of Water Engineering. Sari Agricultural Sciences and Natural Resources University
2 Department of Environmental Engineering, Faculty of Water and Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran.
3 Laboratoire de Géologie, Département de Géosciences, Ecole Normale Supérieure (ENS), Paris, France.
4 Department of Environment at Mazandaran Province (DOE), Caspian Sea Ecology Research Center (CSERC), Sari, Iran
چکیده English

The Water Quality Index (WQI) is an effective tool for assessing water resources, enabling comparison and decision-making by combining multiple parameters into a single simple numerical value. However, the use of standard weighting schemes without considering local conditions may lead to inaccurate results. This study aims to optimize WQI calculation by adopting an integrated approach involving Principal Component Analysis (PCA), Multi-Criteria Decision Making (MEREC), and artificial intelligence models. Twenty years of data (2001–2021) from the Siahrood River in Mazandaran Province, encompassing 11 water quality parameters, were analyzed. Dimensionality reduction was performed using PCA, and WQI was calculated through the MEREC method. Additionally, WQI prediction was conducted using two algorithms (Linear Regression and Random Forest) under both full and reduced datasets, and evaluated through indicators such as EVS, MAPE, and R². The findings revealed that turbidity, as the key factor in physical pollution, exhibited strong correlations with TSS, BOD, and COD. Other principal components indicated microbial, chemical, and thermal pollution stemming from sources such as wastewater discharge and agricultural activities. The mean WQI values indicated poor water quality in most sampling stations. The Linear Regression model showed superior performance compared to the Random Forest model, although dimensionality reduction slightly reduced predictive accuracy. According to the MEREC method, total coliform (weight: 0.19) and turbidity (weight: 0.15) were identified as the most influential parameters, highlighting the significance of microbial contamination and suspended solids. The results underscore the necessity for continuous monitoring and effective management of pollution sources to improve regional water quality.

کلیدواژه‌ها English

Organic pollution
Principal components
Quality index
Turbidity
Abbas, F., Cai, Z., Shoaib, M., Lqbal, J., Ismail, M., Arifullah, Alrefaei, A. F. and Albeshr, M. F. 2024. Machine learning models for water quality prediction: a comprehensive analysis and uncertainty assessment in Mirpurkhas, Sindh, Pakistan. Water. 16(7): 941.
Adejuwon, E. O., Ogwueleka, T. C., Ogungbemi, E. O., Prabhu, R., Rendon-Nava, A. and Yates, K. 2025. Assessment of surface water quality using chemometric tools: A case study of Jabi Lake, Abuja, Nigeria. Iranian Journal of Science and Technology, Transactions of Civil Engineering, 1-24.
Bahrami, M., Khaksar, E. and Khaksar, E. 2020. Spatial variation assessment of groundwater quality using multivariate statistical analysis (Case Study: Fasa Plain, Iran). Journal of Groundwater Science and Engineering. 8(3): 230-243.
Bhutiani, R., Khanna, D. R., Kulkarni, D. B. and Ruhela, M. 2016. Assessment of Ganga river ecosystem Haridwar, Uttarakhand, India with reference to water quality indices. Applied Water Science. 6: 107-113.
Charkhabi, A. H., Sakizadeh, M. and Rafiee, G. 2005. Seasonal fluctuation in heavy metal pollution in Iran s Siahroud River-a preliminary study (7 pp). Environmental Science and Pollution Research. 12: 264-270.
Dong, D., Guo, Z., Hua, X., Lan, Y., Zhou, J., Ding, X. and Qiao, Q. 2011. Sorption of DDTs on biofilms, suspended particles and river sediments: effects of heavy metals. Environmental Chemistry Letters. 9: 361-367.
Dong, S., Liu, L., Zhang, Y. and Jiang, F. 2019. Occurrence and succession of bacterial community in O3/BAC process of drinking water treatment. International Journal of Environmental Research and Public Health. 16(17): 3112.
Ecology, E. C. V. and Prasad, G. 2024. Interpretation of water quality using principal component analysis–A case study from a tropical Ramsar wetland site adjacent to the Seafood processing facilities. Ecology, Environment & Conservation. 30: 311-305.
Fashagba, T. S., Bessedik, M., ElSayed, N. B., Abdelbaki, C. and Kumar, N. 2024. Evaluating the water quality of the Keddara dam (Algeria) using water quality indices. Water. 16(9): 1291.
Ferreira, W. J., Targa, M. D. S. and Catelani, C. D. S. 2023. Temporal evolution of suspended solids in the management of medium-sized watersheds in the Metropolitan Region of Paraíba Valley. Revista Ambiente & Água. 18: e2945.
Garba, N., Adamu, A. and Audu, I. A. 2022. Assessment of water quality treatment and costing: A case study of Sokoto state water board. International Journal of Research Publication and Reviews. 3(11): 1407-1413.
Gholizadeh, M. H., Melesse, A. M. and Reddi, L. 2016. A comprehensive review on water quality parameters estimation using remote sensing techniques. Sensors. 16(8): 1298.
Jahan, S. and Strezov, V. 2017. Water quality assessment of Australian ports using water quality evaluation indices. PloS One. 12(12): e0189284.
Jover-Smet, M., Martín-Pascual, J. and Trapote, A. 2017. Model of suspended solids removal in the primary sedimentation tanks for the treatment of urban wastewater. Water. 9(6): 448.
Jumbe, A. S. and Nandini, N. 2012. Physicochemical investigation of surface water quality of urban wetlands of Bangalore, India. Asian Journal of Water, Environment and Pollution. 9(1): 59-69.
Karpagam, V. and Christy, S. 2023. Classifying Indian rivers surface water quality using principal component analysis combined with principal component weighted arithmetic index techniques. In 2023 eighth international conference on science technology engineering and mathematics (ICONSTEM). IEEE.
Keshavarz-Ghorabaee, M. 2021. Assessment of distribution center locations using a multi-expert subjective–objective decision-making approach. Scientific Reports. 11(1): 19461.
Liu, W. and Chen, W. 2013. Modeling hydrothermal, suspended solids transport and residence time in a deep reservoir. International Journal of Environmental Science and Technology. 10: 251-260.
Mahbubul, S. M. M., Shakhawat, H. M., Rajaul, K. M., Faisal, U. M., Mahady, H. and Hayat, K. R. 2023. Surface water quality profiling using the water quality index, pollution index and statistical methods: A critical review. Environmental and Sustainability Indicators. 18: 100247.
Nas, S. S. and Nas, E. 2009. Water quality modeling and dissolved oxygen balance in streams: a point source streeter‐phelps application in the case of the harsit stream. Clean–Soil, Air, Water. 37(1): 67-74.
Prasad, D. V. V., Venkataramana, L. Y., Kumar, P. S., Prasannamedha, G., Harshana, S., Srividya, S. J., Harrinei, K. and Indraganti, S. 2022. Analysis and prediction of water quality using deep learning and auto deep learning techniques. Science of the Total Environment. 821: 153311.
Rosenbusch, H., Soldner, F., Evans, A. M. and Zeelenberg, M. 2021. Supervised machine learning methods in psychology: A practical introduction with annotated R code. Social and Personality Psychology Compass. 15(2): e12579.
Şahin Kiy, M. and Arslan, H. 2021. Assessment of groundwater quality for irrigation and drinking using different quality indices and geostatistical methods in Çorum province (Turkey). Irrigation and Drainage. 70(4): 871-886.
Sakson, G. 2023. Analysis of suspended solids emissions from a combined sewage system using the Stormwater Management Model (SWMM). Geology, Geophysics and Environment. 49(4): 389-399.
Shrestha, N. 2021. Factor analysis as a tool for survey analysis. American journal of Applied Mathematics and Statistics. 9(1): 4-11.
Spychała, M. and Nguyen, T. H. 2019. Preliminary study on greywater treatment using nonwoven textile filters. Applied Sciences. 9(15): 3205.
Wakida, F. T., Huato, S. M., Flores, E. G., Colin, T. D. J. P., Gomez, H. E. and Lopez, A. A. 2014. Pollutant association with suspended solids in stormwater in Tijuana, Mexico. International Journal of Environmental Science and Technology. 11: 319-326.
Xu, H., Xu, G., Wen, X., Hu, X. and Wang, Y. 2021. Lockdown effects on total suspended solids concentrations in the Lower Min River (China) during COVID-19 using time-series remote sensing images. International Journal of Applied Earth Observation and Geoinformation. 98: 102301.
Yeom, S., Giacomelli, I., Fredrikson, M. and Jha, S. 2018. Privacy risk in machine learning: Analyzing the connection to overfitting. in 2018 IEEE 31st computer security foundations symposium (CSF). IEEE.
Yu, Y. 2025. Key technologies for purification of suspended solids in turbid surface water under the influence of rainy seasons. Polish Journal of Environmental Studies. 34(2): 1445-1455.