مدل سازی ارتباط کیفیت آب های سطحی و سنجه های سیمای سرزمین با استفاده از سیستم استنتاج عصبی-فازی (مطالعه موردی: استان مازندران)

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانش‌آموخته کارشناسی ارشد محیط زیست، دانشکده منابع طبیعی، دانشگاه تربیت مدرس، نور، مازندران

2 دانشیار گروه محیط زیست، دانشکده منابع طبیعی، دانشگاه تربیت مدرس، نور، مازندران

3 دانشیار گروه محیط زیست، دانشکده شیلات و محیط زیست، دانشگاه علوم کشاورزی و منابع طبیعی گرگان

4 استادیار گروه محیط زیست، دانشکده منابع طبیعی، دانشگاه تربیت مدرس، نور، مازندران

چکیده

تغییرات کیفیت آب، رویکرد مناسبی برای پایش آلودگی‌های غیر نقطه‌ای است. در مطالعه حاضر، اطلاعات کیفیت آب 81 ایستگاه آبسنجی واقع بر رودخانه‌های استان مازندران در خلال سال‌های 1391 و 1392 مورد بررسی قرار گرفت. مرز زیر حوضه‌های بالادست ایستگاه‌ها ترسیم شد و سنجه‌های سیمای سرزمین در دو سطح کلاس و سیما برای زیر حوضه‌های موجود استخراج شدند. از تحلیل مولفه‌های اصلی برای تعیین پارامترهای کیفیت آب و از رگرسیون خطی پیشرو به‌منظور تعیین سنجه‌های بهینه در توصیف تغییرات هر کدام از پارامترها استفاده شد. پنج مؤلفه اول قادر به توصیف 61/96 درصد از تغییرات کیفیت آب رودخانه‌های استان مازندران بودند. برای مدل‌سازی ارتباط میان سنجه‌های سیمای سرزمین و پارامترهای کیفیت آب از شبکه عصبی-فازی تطبیقی و رگرسیون چند متغیره خطی استفاده شد. نتایج حاکی از بود رگرسیون چند متغیره خطی توانسته است پارامترهای SAR، TDS، pH، NO3 و PO43- را با ضریب تبیین 81/0، 56/0، 73/0، 44/0 و 63/0 در مرحله آزمون پیش‌بینی نماید. این در حالی است که ضریب تبیین شبکه عصبی-فازی به‌ترتیب برابر با 82/0، 79/0، 82/0، 31/0 و 36/0 بوده است. بنابراین، شبکه عصبی-فازی در اغلب موارد کارایی بالاتری داشته و این امر ارتباط غیر خطی میان پارامترهای کیفیت آب و سنجه‌های سیمای سرزمین را نشان می‌دهد. از آنجا که کاربری‌ها و پوشش سرزمین مختلف در حوضه دارای تأثیر زیادی بر کیفیت آب خروجی، آلاینده‌های در دسترس و بار مواد محلول در رودخانه‌ها هستند، استفاده از روش این پژوهش می‌تواند به‌عنوان ابزاری تکمیلی در برنامه‌ریزی منطقه‌ای و ارزیابی اثرات محیط زیستی در برنامه‌های توسعه مطرح شود.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Modeling Relationships between Surface Water Quality and Landscape Metrics Using the Adaptive Neuro-Fuzzy Inference System, A Case Study in Mazandaran Province

نویسندگان [English]

  • mohsen Mirzayi 1
  • Alireza Riyahi Bakhtiyari 2
  • Abdolrasool Salman Mahini 3
  • Mehdi Gholamali Fard 4
1 MSc Graduate Student of Environment, Faculty of Natural Resources, Tarbiat Modares University, Noor, Mazandaran
2 Assoc. Prof. of Environment, Faculty of Natural Resources, Tarbiat Modares University, Noor, Mazandaran
3 Assoc. Prof. of Environment, Faculty of Fisheries and Environment, Gorgan University of Natural Resources and Agriculture, Gorgan
4 Assist. Prof. of Environment, Faculty of Natural Resources, Tarbiat Modares University, Noor, Mazandaran
چکیده [English]

 Landscape indices can be used as an approach for predicting water quality changes to monitor non-point source pollution. In the present study, the data collected over the period from 2012 to 2013 from 81 water quality stations along the rivers flowing in Mazandaran Province were analyzed. Upstream boundries were drawn and landscape metrics were extracted for each of the sub-watersheds at class and landscape levels. Principal component analysis was used to single out the relevant water quality parameters and forward linear regression was employed to determine the optimal metrics for the description of each parameter. The first five components were able to describe 96.61% of the variation in water quality in Mazandaran Province. Adaptive Neuro-fuzzy Inference System (ANFIS) and multiple linear regression were used to model the relationship between landscape metrics and water quality parameters. The results indicate that multiple regression was able to predict SAR, TDS, pH, NO3, and PO43 in the test step, with R2 values equal to 0.81, 0.56, 0.73, 0.44. and 0.63, respectively. The corresponding R2 value of ANFIS in the test step were 0.82, 0.79, 0.82, 0.31, and 0.36, respectively. Clearly, ANFIS exhibited a better performance in each case than did the linear regression model. This indicates a nonlinear relationship between the water quality parameters and landscape metrics. Since different land cover/uses have considerable impacts on both the outflow water quality and the available and dissolved pollutants in rivers, the method can be reasonably used for regional planning and environmental impact assessment in development projects in the region.

1. Bahar, M. M., Hiroo, O., and Masumi, Y. (2008). “Relationship between river water quality and land use in a small river basin running through the urbanizing area of central Japan.” J. Limnology, 9(1), 19-26.
 2. Crim, J. F., Schoonover, J. E., and Lockaby, B. G. (2012). “Assessment of fecal coliform and escherichia coli across a land cover gradient in west georgia streams.” J. Water Quality, Exposure and Health, 4(3), 143-158.
3. Delpla, I., Jung, A. V., Baures, E., Clement, M., and Thomas, O. (2009). “Impacts of climate change on surface water quality in relation to drinking water production.” J. Environment International, 35(8), 1225-1233.
4. Abbaspour, K. C., Yang, J., Maximov, I., Siber, R., Bogner, K., Mieleitner, J., Zobrist, J., and Srinivasan, R. (2007). “Modelling hydrology and water quality in the pre-alpine/alpine Thur watershed using SWAT.” J. Hydrology, 333(2), 413-430.
5. Turner, R. E., and Rabalais, N. N. (2003). “Linking landscape and water quality in the Mississippi river basin for 200 years.” J. BioScience, 53(6), 563-572.
6. Lek, S., Guiresse, M., and Giraudel, J. L. (1999). “Predicting stream nitrogen concentration from watershed features using neural networks.” J. Water Research, 33(16), 3469-3478.
7. Jarvis, N. (2007). “A review of non‐equilibrium water flow and solute transport in soil macropores: Principles, controlling factors and consequences for water quality.” European Journal of Soil Science, 58(3), 523-546.
8. Sonneveld, M. P. W., Schoorl, J. M., and Eldkamp, A. V. (2006). “Mapping hydrological pathways of phosphorus transfer in apparently homogeneous landscapes using a high-resolution DEM.” J. Geoderma, 133(1), 32-42.
9. Nakane, K., and Haidary, A. (2009). “Sensitivity analysis of stream water quality and land coverlinkage  models  using  monte  carlo  method.”  J. Environmental Research and Public Health, 4(1),121-130.
10. Lee, S. W., Hwang, S. J., Lee, S. B., Hwang, H. S., and Sung, H. C. (2009). “Landscape ecological approach to the relationships of land use patterns in watersheds to water quality characteristics.” J. Landscape and Urban Planning, 92(2), 80-89.
11. Tong, S. T., and Chen, W. (2002). “Modeling the relationship between land use and surface water quality.” J. Environmental Management, 66(4), 377-393.
12. Maier, H. R., and Dandy, G. C. (2000). “Neural networks for the prediction and forecasting of water resources variables: A review of modelling issues and applications.” J. Environmental Modelling and Software, 15(1), 101-124.
13. Ahearn, D., S., Sheibley, R., W., Dahlgren, R. A., Anderson, M., Johnson, J., and Tate, K. W. (2005). “Land use and land cover influence on water quality in the last free-flowing river draining the western Sierra Nevada, California.” J. Hydrology, 313(3), 234-247.
14. King, R. S., Matthew, E., Baker, D. F., Whigham, D. E., Weller, T. E., Jordan, P. F., and Martin K. (2005). “Spatial considerations for linking watershed land cover to ecological indicators in streams.” J. Ecological Applications, 15 (1), 137-153.
15. Haidary, A., Amiri, B. J., Adamowski, J., Fohrer, N., and Nakane, K. (2013). “Assessing the impacts of four land use types on the water quality of wetlands in Japan.” Water Resources Management, 27(7), 2217-2229.
16. Alberti, M., Booth, D., Hill, K., Coburn, B., Avolio, C., Coe, S., and Spirandelli, D. (2007). “Theimpact of urban patterns on aquatic ecosystems: An empiricalanalysis on Pugetlowland sub-basins.” J. Landscape Urban Plan, 80 (4), 345-361.
17. Salajegeh, A., Khorasani, N., Hamidifar, M., and Salajegeh, S. (2010). “Landcover change and this impacts on water quality.” J. Environmental Studies, 37 (58), 81-86. (In Persian)
18. Nemati, M., Ebrahimi, A., Mirghafari, N., and Safyanian, A. (2007). “Effects of land use on nitrate and phosphate river water.” 4th Conference of Engineering Sciences and Watershed Management, Faculty of Natural Resources, Theran University, Karaj. (In Persian)
19. Wu, M. Y., Xue, L., Jin, W. B., Xiong, Q. X., Ai, T.C., and Li, B.L. (2012). “Modeling the linkage between landscape metrics and water quality indices of hydrological units in Sihu basin, Hubei Province, China.” J. An Allometric Model.Procedia Environmental Sciences, 13(1), 2131-2145.
20. Shiels, D. R. (2010). “Implementing landscape indices to predict stream water quality in an agricultural setting: An assessment of the lake and river enhancement (LARE) protocol in the mississinewa river watershed, East-Central Indiana.” J. Ecological Indicators, 10(6), 1102-1110.
21. Shu, C., and Ouarda, T. (2008). “Regional flood frequency analysis at ungauged sites using the adaptive neuro-fuzzy inference system.” J. Hydrology, 349(1), 31-43.
22. Noori, R., Karbassi, A. R., Moghaddamnia, A., Han, D., Zokaei-Ashtiani, M.H., Farokhnia, A., and Gousheh, M.G. (2011). “Assessment of input variables determination on the SVM model performance using PCA, Gamma test, and forward selection techniques for monthly stream flow prediction.” J. Hydrology, 401 (3),
177-189.
23. McGarigal, K., and Marks, B. J. (1995). Spatial pattern analysis program for quantifying landscape structure, Gen. Tech. Rep. PNW-GTR-351. US Department of Agriculture, Forest Service, Pacific Northwest Research Station.
24. Lausch, A., and Herzog, F. (2002). “Applicability of landscape metrics for the monitoring of landscape change: issues of scale, resolution and interpretability.” Ecological Indicators, 2(1), 3-15.
25. Wagner, J. M., and Shimshak, D. G. (2007). “Stepwise selection of variables in data envelopment analysis: Procedures and managerial perspectives.” J. Operational Research, 180(1), 57-67.
26. Gholamalifard, M., Zare Maivan, H., Joorabian Shooshtari, S., and Mirzaei, M. (2012). “Monitoring land cover changes of forests and coastal areas of northern Iran (1988-2010): A remote sensing approach.” J. Persian Gulf, 3(10), 47-56.
27. Mirkatuli, J., and Kanani, M. (2010). “Assessment of ecological capability of urban development by MCDM and GIS (Case study: Sari, Mazandaran Province).” J. Human Geography Researchs, 43(77), 75-88.(In Persian)
28. Talebi Amiri, Sh., Azari Dehkordi, F., Sadeghi, H., and Soofbaf, R. (2009). “Study on landscape degradation in Neka watershed using landscape metrics.” J. Environmental  Sciences, 6(3), 133-144. (In Persian)
29. Salman Mahini, A., Fazli, H., Daryanabard, R., Kamyab, H., Fendereski, F., Davar, L., Azarm Del, L., Mehri A., and Kheyrabadi, V. (2011). Zoning and degree of ecologically sensitive coastal areas, Department of Environment, Tehran, Page 231. (In Persian)
30. Ouyang, Y. (2005). “Evaluation of river water quality monitoring stations by principal component analysis.” J. Water Research, 39(12), 2621-2635.
31. Riitters, K. H., O'neill, R.V., Hunsaker, C. T., Wickham, J. D., Yankee, D. H., Timmins, S. P., Jones. K. B., and Jackson, B.L. (1995). “A factor analysis of landscape pattern and structure metrics.” J. Landscape Ecology, 10 (1),  23-39.
32. Noori, R., Sabahi, M., Karbassi, A., Baghvand, A., and Taati Zadeh, H. (2010). “Multivariate statistical analysis of surface water quality based on correlations and variations in the data set.” J. Desalination, 260(1), 129-136.
33. Alavi, N., Nozari, V., Mazloumzadeh, S., and Nezamabadi-pour, H. (2010). “Irrigation water quality evaluation using adaptive network-based fuzzy inference system.” J. Paddy and Water Environment, 8(3), 259-266.
34. Ocampo-Duque W., Ferre´H. N., Domingo, J. L., and Schuhmacher, M. (2006). “Assessing  water  quality  in  rivers with fuzzy inference systems: A case study.” J. Environ. Int., 32,733-742.
35. Wilcox, L. V. (1955). Classification and use of irrigation waters, U.S. Dept. Agric. Circ., 969, 19 p.
36. Tran, C. P., Bode, R. W., Smith, A. J., and Kleppel, G. S. (2010). “Land-use proximity as a basis for assessing stream water quality in New York State (USA).” J. Ecological Indicators, 10(3), 727-733.
37. Amiri, B. J., and Nakane, K. (2008a). “Modeling the linkage between river water quality and landscape metrics in the chugoku district of japan.” Water Resour Manage, 23(5), 931-956.
38. Wickham, J. D., O'Neill, R. V., Riitters, K. H., Wade, T. G., and Jones, K. B. (1997). “Sensitivity of selected landscape pattern metrics to land-cover misclassification and differences in land-cover composition.” J. Photogrammetric Engineering and Remote Sensing, 63(4), 397-401.
39. Herold, M., Couclelis, H., and Clarke, K. C. (2005). “The role of spatial metrics in the analysis and modeling of urban land use change.” J. Computers, Environment and Urban Systems, 29(4), 369-399.
40. Li, X., Jongman, R. H., Hu, Y., Bu, R., Harms, B., Bregt, A. K., and He, H. S. (2005). “Relationship between landscape structure metrics and wetland nutrient retention function: A case study of Liaohe Delta, China.” J. Ecological Indicators, 5(4), 339-349.
41. Han, H. G., Chen, Q. l., and Qiao, J. F. (2011). “An efficient self-organizing RBF neural network for water quality prediction.” J. Neural Networks, 24(7), 717-725.
42. Moosavi, V., Vafakhah, M., Shirmohammadi, B., and Behnia, N. (2013). “A wavelet-anfis hybrid model for groundwater level forecasting for different prediction periods.” Water Resources Management, 27 (2), 1-21.
43. Moreno, M. D., Mander, Ü., Comín, F. A., Pedrocchi, C., and Uuemaa, E. (2008). “Relationships between landscape pattern, wetland characteristics, and water quality in agricultural catchments.” J. Environmental Quality, 37(6), 2170-2180.