Economic and Environmental Geology (자원환경지질)

The Korean Society of Economic and Environmental Geology (대한자원환경지질학회)
권호 표지
DOI QR코드

DOI QR Code

A Grey Wolf Optimized- Stacked Ensemble Approach for Nitrate Contamination Prediction in Cauvery Delta

  • Kalaivanan K (School of Computer Science Engineering and Information Systems, Vellore Institute of Technology) ;
  • Vellingiri J (School of Computer Science Engineering and Information Systems, Vellore Institute of Technology)
  • Received : 2024.01.08
  • Accepted : 2024.05.24
  • Published : 2024.06.28
Download PDF
⟨ Previous Next ⟩

Abstract

The exponential increase in nitrate pollution of river water poses an immediate threat to public health and the environment. This contamination is primarily due to various human activities, which include the overuse of nitrogenous fertilizers in agriculture and the discharge of nitrate-rich industrial effluents into rivers. As a result, the accurate prediction and identification of contaminated areas has become a crucial and challenging task for researchers. To solve these problems, this work leads to the prediction of nitrate contamination using machine learning approaches. This paper presents a novel approach known as Grey Wolf Optimizer (GWO) based on the Stacked Ensemble approach for predicting nitrate pollution in the Cauvery Delta region of Tamilnadu, India. The proposed method is evaluated using a Cauvery River dataset from the Tamilnadu Pollution Control Board. The proposed method shows excellent performance, achieving an accuracy of 93.31%, a precision of 93%, a sensitivity of 97.53%, a specificity of 94.28%, an F1-score of 95.23%, and an ROC score of 95%. These impressive results underline the demonstration of the proposed method in accurately predicting nitrate pollution in river water and ultimately help to make informed decisions to tackle these critical environmental problems.

Keywords

References

  1. Alizamir, M., Heddam, S., Kim, S. and Mehr, A.D. (2021). On the implementation of a novel data-intelligence model based on extreme learning machine optimized by bat algorithm for estimating daily chlorophyll-a concentration: case studies of river and lake in USA. J. Clean Prod., v.285, 124868. doi: 10.1016/j.jclepro.2020.124868
  2. Al-Tashi, Q., Kadir, S. J. A., Rais, H. M., Mirjalili, S. and Alhussian, H. (2019). Binary optimization using hybrid grey wolf optimization for feature selection. IEEE Access, v.7, p.39496-39508. doi: 10.1109/ACCESS.2019.2906757
  3. Arabgol, R., Sartaj, M. and Asghari, K. (2016). Predicting nitrate concentration and its spatial distribution in groundwater resources using support vector machines (SVMs) model. Environmental Modeling & Assessment, v.21, p.71-82. doi: 10.1007/s10666-015-9468-0
  4. Atangana, R., Tchiotsop, D., Kenne, G. and Chanel, L. (2020). EEG signal classification using LDA and MLP classifier. Health Informat. Int. J., v.9(1), p.14-32. doi: 10.5121/hiij.2020.9102
  5. Azad, A., Karami, H., Farzin, S., Saeedian, A., Kashi, H. and Sayyahi, F. (2018). Prediction of water quality parameters using ANFIS optimized by intelligence algorithms (case study: Gorganrood River). KSCE Journal of Civil Engineering, v.22(7), p.2206-2213 doi: 10.1007/s12205-017-1703-6
  6. Bagherzadeh, F., Mehrani, M.J., Basirifard, M. and Roostaei, J. (2021). Comparative study on total nitrogen prediction in wastewater treatment plant and effect of various feature selection methods on machine learning algorithms performance. Journal of Water Process Engineering, v.41, 102033. doi: 10.1016/j.jwpe.2021.102033
  7. Band, S.S., Janizadeh, S., Pal, S.C., Chowdhuri, I., Siabi, Z., Norouzi, A., ... and Mosavi, A. (2020). Comparative analysis of artificial intelligence models for accurate estimation of groundwater nitrate concentration. Sensors, v.20(20), 5763. doi: 10.3390/s20205763
  8. Bedi, S., Samal, A., Ray, C. and Snow, D. (2020) Comparative evaluation of machine learning models for groundwater quality assessment. Environ Monit Assess, v.192(12), p.1-23. doi: 10.1007/s10661-020-08695-3
  9. Benzer, S. and Benzer, R. (2018). Modelling nitrate prediction of groundwater and surface water using artificial neural networks. Politeknik Dergisi, v.21(2), p.321-325. doi: 10.2339/politeknik.385434
  10. Bhattarai, A., Dhakal, S., Gautam, Y. and Bhattarai, R. (2021). Prediction of nitrate and phosphorus concentrations using machine learning algorithms in watersheds with different landuse. Water, v.13(21), 3096. doi: 10.3390/w13213096
  11. Bis, I. (2012). 10500 Indian standard drinking water-specification, second revision. Bureau of Indian Standards, New Delhi.
  12. Chen, J., Wu, H., Qian, H. and Gao, Y. (2017). 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, v.9(3), p.183-195. doi: 10.1007/s12403-016-0231-9
  13. Dokala, J.K.K., Mohamed, M.R., Kumarasamy, S. and Kurukuri, P. (2022). A new meta-heuristic optimization algorithm based MPPT control technique for PV System under diverse partial shading conditions. doi: 10.21203/rs.3.rs-1531369/v1
  14. Guo, L., Rivero, D., Dorado, J., Rabunal, J.R. and Pazos, A. (2010). Automatic epileptic seizure detection in EEGs based on line length feature and artificial neural networks. Journal of Neuroscience Methods, v.191(1), p.101-109. doi: 10.1016/j.jneumeth.2010.05.020
  15. Ha, N.T., Nguyen, H.Q., Truong, N.C.Q., Le, T.L., Thai, V.N. and Pham, T.L. (2020). Estimation of nitrogen and phosphorus concentrations from water quality surrogates using machine learning in the Tri An Reservoir, Vietnam. Environmental Monitoring and Assessment, v.192, p.1-20. doi: 10.1007/s10661-020-08731-2
  16. He, B., Oki, T., Sun, F., Komori, D., Kanae, S., Wang, Y., ... and Yamazaki, D. (2011). Estimating monthly total nitrogen concentration in streams by using artificial neural network. Journal of Environmental Management, v.92(1), p.172-177. doi: 10.1016/j.jenvman.2010.09.014
  17. Hu, Y., Du, W., Yang, C., Wang, Y., Huang, T., Xu, X. and Li, W. (2023). Source identification and prediction of nitrogen and phosphorus pollution of Lake Taihu by an ensemble machine learning technique. Frontiers of Environmental Science & Engineering, v.17(5), 55. doi: 10.1007/s11783-023-1655-7
  18. Jafari, R., Torabian, A., Ghorbani, M.A., Mirbagheri, S.A. and Hassani, A.H. (2019) Prediction of groundwater quality parameter in the Tabriz plain, Iran using soft computing methods. J. Water Suppl. Res. Technol.- AQUA, v.68(7), p.573-584. doi: 10.2166/aqua.2019.062
  19. Joy, J., Kannan, A., Ram, S. and Rama, S. (2020). Speech emotion recognition using neural network and MLP classifier. IJESC, April-2020.
  20. Keerthan, L., RamyaPriya, R. and Elango, L. (2023). Geogenic and anthropogenic contamination in river water and groundwater of the lower Cauvery Basin, India. Frontiers in Environmental Science, v.11, 278. doi: 10.3389/fenvs.2023.1001052
  21. Knoll, L., Breuer, L. and Bach, M. (2019). Large scale prediction of groundwater nitrate concentrations from spatial data using machine learning. Science of the Total Environment, v.668, p.1317-1327. doi: 10.1016/j.scitotenv.2019.03.045
  22. Kumar, P., Lai, S.H., Mohd, N.S., Kamal, M.R., Afan, H.A., Ahmed, A.N., ... and El-Shafie, A. (2020). Optimised neural network model for river-nitrogen prediction utilizing a new training approach. PLoS One, v.15(9), e0239509. doi: 10.1371/journal.pone.0239509
  23. Latif, S.D., Azmi, M.S.B.N., Ahmed, A.N., Fai, C.M. and El-Shafie, A. (2020). 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, v.15, p.647-652. doi: 10.18280/ijdne.150505
  24. Liang, Y., Zhang, X., Gan, L., Chen, S., Zhao, S., Ding, J., ... and Yang, H. (2024). Mapping specific groundwater nitrate concentrations from spatial data using machine learning: A case study of chongqing, China. Heliyon. doi: 10.1016/j.heliyon.2024.e27867
  25. Lu, H., Yang, L., Fan, Y., Qian, X. and Liu, T. (2022). Novel simulation of aqueous total nitrogen and phosphorus concentrations in Taihu Lake with machine learning. Environmental Research, v.204, 111940. doi: 10.1016/j.envres.2021.111940
  26. Lu, H., Yang, L., Fan, Y., Qian, X. and Liu, T. (2022). Novel simulation of aqueous total nitrogen and phosphorus concentrations in Taihu Lake with machine learning. Environmental Research, v.204, 111940. doi: 10.1016/j.envres.2021.111940
  27. Mehdaoui, I., Boudibi, S., Latif, S.D., Sakaa, B., Chaffai, H. and Hani, A. (2024). Prediction of nitrate concentrations using multiple linear regression and radial basis function neural network in the Cheliff River basin, Algeria. Journal of Applied Water Engineering and Research, v.12(1), p.77-89. doi: 10.1080/23249676.2023.2207838
  28. Mirjalili, S., Mirjalili, S.M. and Lewis, A. (2014). Grey wolf optimizer. J. Advances in Engineering Software. v.69, p.46-61. doi: 10.1016/j.advengsoft.2013.12.007
  29. Myles, A.J., Feudale, R.N., Liu, Y., Woody, N.A. and Brown, S.D. (2004). An introduction to decision tree modeling. Journal of Chemometrics: A Journal of the Chemometrics Society, v.18(6), p.275-285. doi: 10.1002/cem.873
  30. Ottong, Z.J., Puspasari, R.L., Yoon, D. and Kim, K.W. (2022). Predicting As Contamination Risk in Red River Delta using Machine Learning Algorithms. Available at SSRN 3952430. doi: 10.9719/EEG.2022.55.2.127
  31. Pham, Q.B., Mohammadpour, R., Linh, N.T.T., Mohajane, M., Pourjasem, A., Sammen, S.S. and Anh, D.T. (2021). Application of soft computing to predict water quality in wetland. Environ. Sci. Pollut. Res., v.28(1), p.185-200. doi: 10.1007/s11356-020-10344-8
  32. Rahmati, O., Choubin, B., Fathabadi, A., Coulon, F., Soltani, E., Shahabi, H., ... and Bui, D.T. (2019). Predicting uncertainty of machine learning models for modelling nitrate pollution of groundwater using quantile regression and UNEEC methods. Science of the Total Environment, v.688, p.855-866. doi: 10.1016/j.scitotenv.2019.06.320
  33. Raju, P., Rao, V.M. and Rao, B.P. (2018). Grey wolf optimization-based artificial neural network for classification of kidney images. Journal of Circuits, Systems and Computers, v.27(14), 1850231. doi: 10.1142/S0218126618502316
  34. RamyaPriya, R. and Elango, L. (2021). Atmospheric CO2 consumption by rock weathering over a five year period in a large non-perennial tropical river basin of southern India. Environmental Science and Pollution Research, v.28, p.26461-26478. doi: 10.1007/s11356-020-12257-y
  35. Rodriguez-Galiano, V.F., Luque-Espinar, J.A., Chica-Olmo, M. and Mendes, M.P. (2018). Feature selection approaches for predictive modelling of groundwater nitrate pollution: An evaluation of filters, embedded and wrapper methods. Science of the Total Environment, v.624, p.661-672. doi: 10.1016/j.scitotenv.2017.12.152
  36. Sharma, S. and Yadav, N.S. (2023). A Grey Wolf Optimized XGboost-Multilayer Stacking Approach to Detect XSS Attacks. IETE Journal of Research, 1-16. doi: 10.1080/03772063.2023.2264251
  37. Stamenkovic, L.J., Mrazovac Kurilic, S. and Presburger Ulnikovic, V. (2020). Prediction of nitrate concentration in Danube River water by using artificial neural networks. Water Supply, v.20(6), p.2119-2132. doi: 10.2166/ws.2020.104
  38. Sulaiman, R., Azeman, N.H., Bakar, M.H.A., Nazri, N.A.A., Masran, A.S. and Bakar, A.A.A. (2023). Nitrate Classification Based on Optical Absorbance Data Using Machine Learning Algorithms for a Hydroponics System. Applied Spectroscopy, v.77(2), p.210-219. doi: 10.1177/00037028221140924
  39. Tamilmani, A. and Venkatesan, G. (2021). Assessment of trace metals and its pollution load indicators in water and sediments between Upper and Grand Anicuts in the Cauvery. International Journal of Environmental Science and Technology, 1-12. doi: 10.1007/s13762-020-03034-y
  40. Ullah, I., Liu, K., Yamamoto, T., Shafiullah, M. and Jamal, A. (2022). Grey wolf optimizer-based machine learning algorithm to predict electric vehicle charging duration time. Transportation Letters, 1-18. doi: 10.1080/19427867.2022.2111902
  41. Wagh, Vasant Madhav, Dipak Baburao Panaskar, and Aniket Avinash Muley. (2017). Estimation of nitrate concentration in groundwater of Kadava river basin-Nashik district, Maharashtra, India by using artificial neural network model. Modeling Earth Systems And Environment, v.3, p.1-10. doi: 10.1007/s40808-017-0290-3
  42. Wheeler, D.C., Nolan, B.T., Flory, A.R., DellaValle, C.T. and Ward, M.H. (2015). Modeling groundwater nitrate concentrations in private wells in Iowa. Science of the Total Environment, v.536, p.481-488. doi: 10.1016/j.scitotenv.2015.07.080
  43. Yang, B., Zhang, X., Yu, T., Shu, H. and Fang, Z. (2017). Grouped grey wolf optimizer for maximum power point tracking of doubly-fed induction generator-based wind turbine. Energy Conversion and Management, v.133, p.427-443. doi: 10.1016/j.enconman.2016.10.062
  44. Yang, Y., Shang, X., Chen, Z., Mei, K., Wang, Z., Dahlgren, R.A., ... and Ji, X. (2021). A support vector regression model to predict nitrate-nitrogen isotopic composition using hydro-chemical variables. Journal of Environmental Management, v.290, 112674. doi: 10.1016/j.jenvman.2021.112674