نوع مقاله : مقالات پژوهشی
نویسنده
استادیار مهندسى بهداشت محیط، دپارتمان مهندسی بهداشت محیط، دانشکده علوم پزشکی فردوس، دانشگاه علوم پزشکى بیرجند، بیرجند، ایران.
چکیده
زمینه و هدف: نیترات همواره به عنوان یک شاخص کیفیت آب آشامیدنی و یک موضوع اساسی در سلامت انسان مورد توجه بوده است. توسعه مدل‌های پیشرفته برای مدیریت کیفیت آب، تصمیم‌گیرندگان را تشویق کرده است که فناوری‌های هوش مصنوعی را در برنامه‌ریزی کیفیت آب لحاظ نمایند. این مطالعه، قصد دارد تا با استفاده از مدل‌های AdaBoost (تقویت تطبیقی) بعنوان یکی از مدل های نوظهور در حیطه مدیریت کیفیت آب به پیش بینی غلظت نیترات در آب زیرزمینی با استفاده از هدایت الکتریکی، pH بپردازد.
مواد و روشها: در این مطالعه ابتدا تحلیل همبستگی پیرسون انجام شد سپس با تعیین متغیر های ورودی مدل چندین مدل AdaBoost با هاپپر پارامترهای مختلف ساخته شد. سپس تحلیل حساسیت و وابستگی متغیر های ورودی مدل در پیش بینی نیترات ارزیابی شدند.
یافته ها: نتایج مدل AdaBoostنشان داد که مقادیر ضریب R2 برای داده آموزش 0/915 و برای داده های تست 0/924 بودند. مقادیر MSE، RMSE، MAE، MAPE برای داده های آموزش به ترتیب 1/02، 1/01، 0/823 و 7/3درصد بدست آمد. این معیار ها برای داده های تست به ترتیب0/228، 0/477، 0/375 و3/2 درصد بودند. تحلیل حساسیت مدل، متغیر pH به عنوان مهمترین متغیر تاثیر گذار در پیش بینی نیترات معرفی کرد.
نتیجه گیرى: تحلیل مدل نشان داد که روش پیشنهادی در پیش بینی غلظت نیترات عملکرد بالایی دارد. این روش پتانسیل ویژه برای پیاده‌سازی به عنوان یک سامانه هوشمند برای پیش‌بینی پارامترهای کیفیت آب را دارد.
کلیدواژه‌ها
عنوان مقاله [English]
Prediction of groundwater nitrate variations using AdaBoost approach
نویسنده [English]
- Mansour Baziar
Assistant Professor, Department of Environmental Health Engineering, Ferdows Faculty of Medical Sciences, Birjand University of Medical Sciences, Birjand, Iran.
چکیده [English]
Background and Purpose: Nitrates have long been considered indicative of drinking water quality and a critical concern for human health. The evolution of advanced models for water quality management has spurred decision-makers to incorporate artificial intelligence technologies into water quality planning. This study aims to employ the AdaBoost model, one of the cutting-edge models in water quality management, to predict nitrate concentrations in groundwater using pH and EC (Electrical Conductivity) as input variables.
Materials and Methods: Initially, the study analyzed the Pearson correlation matrix and subsequently determined the input variables for multiple AdaBoost models with varying hyperparameters. A sensitivity and dependence analysis of the model's input variables was conducted to assess their impact on nitrate prediction.
Results: The results obtained from the AdaBoost model reveal R-squared (R2) values of 0.915 for the training dataset and 0.924 for the test dataset. Additionally, the Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) scores for the training dataset were recorded as 1.02, 1.01, 0.823, and 7.3%, respectively. For the test dataset, these metrics were observed in the order of 0.228, 0.477, 0.375, and 3.2%. The model's sensitivity analysis identified the pH variable as the most influential factor in nitrate prediction.
Conclusion: The model analysis demonstrates that the proposed method performs well in predicting nitrate concentrations. This approach holds significant potential for implementation as an intelligent system for forecasting water quality parameters.
کلیدواژه‌ها [English]
- AdaBoost
- groundwater
- Nitrate
- sensitivity analysis
- water quality
2. Chen J, Wu H, Qian H, Gao Y. Assessing nitrate and fluoride contaminants in drinking water and their health risk of rural residents living in a semiarid region of Northwest China. Exposure and Health. 2017;9:183-95.
3. Nakagawa K, Amano H, Takao Y, Hosono T, Berndtsson R. On the use of coprostanol to identify source of nitrate pollution in groundwater. Journal of Hydrology. 2017;550:663-8.
4. Li Z, Yang Q, Xie C, Lu X. Source identification and health risks of nitrate contamination in shallow groundwater: a case study in Subei Lake basin. Environmental Science and Pollution Research. 2023;30(5):13660-70.
5. Pouye A, Cissé Faye S, Diédhiou M, Gaye CB, Taylor RG. Nitrate contamination of urban groundwater and heavy rainfall: Observations from Dakar, Senegal. Vadose Zone Journal. 2023:e20239.
6. Iqbal J, Su C, Wang M, Abbas H, Baloch MYJ, Ghani J, et al. Groundwater fluoride and nitrate contamination and associated human health risk assessment in South Punjab, Pakistan. Environmental Science and Pollution Research. 2023;30(22):61606-25.
7. El Bilali A, Taleb A, Brouziyne Y. Groundwater quality forecasting using machine learning algorithms for irrigation purposes. Agricultural Water Management. 2021;245:106625.
8. Tung TM, Yaseen ZM. A survey on river water quality modelling using artificial intelligence models: 2000–2020. Journal of Hydrology. 2020;585:124670.
9. Lu H, Ma X. Hybrid decision tree-based machine learning models for short-term water quality prediction. Chemosphere. 2020;249:126169.
10. Castrillo M, García ÁL. Estimation of high frequency nutrient concentrations from water quality surrogates using machine learning methods. Water Research. 2020;172:115490.
11. Meyers G, Kapelan Z, Keedwell E. Short-term forecasting of turbidity in trunk main networks. Water research. 2017;124:67-76.
12. Bilali AE, Taleb A, Mazigh N, Mokhliss M. Prediction of chemical water quality used for drinking purposes based on artificial neural networks. Moroccan Journal of Chemistry. 2020;8(3):8-3 (2020) 665-672.
13. Fijani E, Barzegar R, Deo R, Tziritis E, Skordas K. Design and implementation of a hybrid model based on two-layer decomposition method coupled with extreme learning machines to support real-time environmental monitoring of water quality parameters. Science of the total environment. 2019;648:839-53.
14. Wagh VM, Panaskar DB, Muley AA, Mukate SV, Lolage YP, Aamalawar ML. Prediction of groundwater suitability for irrigation using artificial neural network model: a case study of Nanded tehsil, Maharashtra, India. Modeling Earth Systems and Environment. 2016;2:1-10.
15. Ahmed SH, Abed MF. Evaluating Groundwater Quality for Sustainable Drinking and Irrigation Purposes and Assessing Nitrate Risks on Human Health in Rural Areas. 2020.
16. Hosseinzadeh A, Zhou JL, Altaee A, Baziar M, Li X. Modeling water flux in osmotic membrane bioreactor by adaptive network-based fuzzy inference system and artificial neural network. Bioresource technology. 2020;310:123391.
17. Zhu X, Wang X, Ok YS. The application of machine learning methods for prediction of metal sorption onto biochars. Journal of hazardous materials. 2019;378:120727.
18. Sajedi-Hosseini F, Malekian A, Choubin B, Rahmati O, Cipullo S, Coulon F, et al. A novel machine learning-based approach for the risk assessment of nitrate groundwater contamination. Science of the total environment. 2018;644:954-62.
19. Knoll L, Breuer L, Bach M. Large scale prediction of groundwater nitrate concentrations from spatial data using machine learning. Science of the total environment. 2019;668:1317-27.
20. Benaroussi O, Djellal M. Mapping groundwater vulnerability to nitrate contamination using machine learning techniques 2022.
21. Latif SD, Azmi M, Ahmed AN, Fai CM, El-Shafie A. Application of artificial neural network for forecasting nitrate concentration as a water quality parameter: a case study of Feitsui Reservoir, Taiwan. Int J Des Nat Ecodynamics. 2020;15:647-52.
22. Ubah J, Orakwe L, Ogbu K, Awu J, Ahaneku I, Chukwuma E. Forecasting water quality parameters using artificial neural network for irrigation purposes. Scientific Reports. 2021;11(1):24438.
)