نشریه محیط زیست طبیعی

برآورد میزان غلظت کادمیوم خاک با استفاده از مدل‌های ANN و ANFIS

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانش آموختۀ کارشناسی ارشد خاکشناسی، گروه آب و خاک، دانشکدۀ کشاورزی، دانشگاه صنعتی شاهرود

2 دانشیار گروه آب و خاک، دانشکدۀ کشاورزی، دانشگاه صنعتی شاهرود

چکیده

بررسی سطوح آلودگی خاک به فلزات سنگین مانند میزان کادمیوم خاک برای سلامتی انسان و مدیریت محیط‌زیست انسان مهم و ضروری است. با توجه به این­که اندازه­گیری مستقیم کادمیوم خاک زمان‌بر و هزینه­بر  است، در این پژوهش، از دو روش هوشمند مصنوعی شامل مدل شبکۀ عصبی مصنوعی (ANN) و شبکۀ عصبی فازی تطبیقی (ANFIS) برای تخمین میزان کادمیوم خاک به‌عنوان یکی از خطرناک‌ترین فلزات سنگین استفاده شد. برای برآورد میزان غلظت کادمیوم خاک از عناصر زود یافت خاک مانند درصد سیلت، شن، کربن آلی، pH، EC، T.N و P به‌عنوان پارامترهای ورودی به مدل استفاده شد و از طریق دو مدل ANN و ANFIS ارتباط میان پارامترهای مذکور و میزان غلظت کادمیوم برقرار گردید. برای آموزش و صحت سنجی مدل­های مذکور از 250 نمونه خاک که از خاک‌های استان گیلان گرفته شد، استفاده شد. ارزیابی مدل­ها با استفاده از پارامترهای آماری مانند ضریب تبیین (R2)، میانگین خطای مطلق (MAE)، مجــذور میــانگین مربعــات خطــا (RMSE) انجام شد. نتایج به‌دست‌آمده نشان داد مدل شبکۀ عصبی مصنوعی با ضریب تبیین (R2) 83/0 و همچنین مجذور میانگین مربعات خطا (RMSE) 01/1 و میانگین خطای مطلق (MAE) برابر 54/0 روش مناسب‌تری نسبت به شبکۀ عصبی فازی تطبیقی است. همچنین نتایج آنالیز حساسیت پارامترهای ورودی به مدل­ها نشان داد درصد کربن آلی و EC خاک به ترتیب بیشترین و کمترین تأثیرگذاری را بر میزان کادمیوم دارند. مدل پیشنهادی می‌تواند برای برآورد میزان غلظت کادمیوم خاک در سایر نقاط در محدودۀ موردمطالعه که اندازه­گیری غلظت کادمیوم خاک انجام نشده است و همچنین برای سایر مناطق  با داشتن شرایط مشابه مورد استفاده قرار گیرد.

کلیدواژه‌ها

عنوان مقاله [English]

Prediction of cadmium concentration of soil using ANN and ANFIS models

نویسندگان [English]

  • q q 1
  • q q 2
  • q q 2
  • q q 1

1 q

2 q

چکیده [English]

Evaluation of soil contamination by heavy metals such as cadmium in soils is essential for human health and also for environment management. As direct measurement of soil cadmium is time-consuming and costly, in this study, the two methods of artificial intelligence, artificial neural network (ANN) and adaptive fuzzy neural network (ANFIS) used to estimate the amount of cadmium in soil as one of the dangerous heavy metals. For estimating of cadmium, soil readily available properties such as clay and sand percentage, organic carbon, EC, T.N and P used as input parameters and the relationship between these parameters and the concentration of cadmium established by ANN and ANFIS models. For training and testing the models, 250 soil samples collected from soils of Guilan province. For assessment of artificial intelligence models the statistical criteria such as the coefficient of determination (R2), mean absolute error (MAE), root mean square error (RMSE) used. The results showed that ANN model with R2 = 0.83 and RMSE= 1.01, and MAE= 0.54 is superior to ANFIS model. Also the results of the sensitivity analysis on the input variables to the model showed that organic carbon and EC have the most and the least effect on the amount of Cd. The proposed model could be used to estimate the amount of cadmium in other parts of the studied area which the concentration of cadmium has not been measured, as well as for other areas with similar conditions.

کلیدواژه‌ها [English]

  • Cadmium
  • Heavy metal
  • artificially intelligent models
  • Guilan province
Akbarzadeh, A., Mehrjardi, R.T., Rouhipour, H., Gorji, M., Rahimi, H.G., 2009. Estimating of soil erosion covered with rolled erosion control systems using rainfall simulator (neuro-fuzzy and artificial neural network approaches). Journal of Applied Science Research, 5: 505–14.
Amini, M., Afyuni, M., Fathianpourb, N., Khademi, H., Fluchler, H., 2005. Continuous soil pollution mapping using fuzzy logic and spatial interpolation. Geoderma, 124, 223–233
Azamathulla, H. M., Chang, C.K., Ghani, A.A., Ariffin, J., Zakaria, N.A., Abu Hasan, Z. 2009. An ANFIS-based approach for predicting the bed load for moderately sized rivers, Journal of Hydrology and Environmental Reearch, 3 35-44.
Bila, S., Harkouss, Y., Ibrahim, M., Rousset, J., Goya, E., Baillargeat, D., Verdeyme, M., Aubourg, M., Guillon, P., 1999. An accurate wavelet neural-network-based model for electromagnetic optimization of microwave circuits. International Journal of RF and Microwave Computer-Aided Engineering, 93: 297–306.
Barančíková G, Madaras M and Rybár O, 2004.Crop contamination by selected trace elements. Soils and Sediments, 4: 37-42.
Behrens, T., Förster, H., Scholten, T., Steinrüken, U., Spies, E., Goldschmitt, M., 2005. Digital soil mapping using artificial neural networks Journal of Plant Nutrition and Soil Science, 168, 21-33.
Bouyoucos, G.J. 1962. Hydrometer method improved for making particle size analysis of soils..Agronomy Journal, 56: 464-465.
Covelo, E.F., Andrade, M.L., Vega, F.A., 2004. Heavy metal adsorpation by humic umbrisols:selectivity sequences and competitive sorption kinetics, Journal of Colloid and Interface Science, 280(1): 1-8
Coelho, M.C., Farias, T.L., Rouphail, N.M., 2005. Impact of speed control traffic signals on pollutant emissions. Transportation Research Part D, 10, p. 323–340.
Devabhaktuni, V., Yagoub, M., Fang, Y., Xu, J., Zhang, Q., 2001. Neural networks for microwave modeling: model development issues and nonlinear modeling techniques, International Journal of RF and Microwave Computer-Aided Engineering, 11:4–21
Erfanmanesh, M., Afyuni. 2000. Environmental pollution: Water, Soil, Air, Fourth Edition, Arkan Publish (In Farsi)
Fausett, L.V., 1994. Fundamentals of Neural Networks: Architectures, Algorithms, and Applications. Prentice Hall, Englewood Cliff, N.J. Gurney, K., 1997. An Introduction to Neural Networks. UCL press,
London Hayati, M., Rashdi, A. M., Rezaee, A., 2011. Prediction of grain size of nanocrystalline nickel coatings using adaptive neuro-fuzzy inference system, Solid State Sciences, 13, 163-167.
Hunter, A., Kennedy, L., Henry, J., Ferguson, R.I., 2000. Application of neural networks and sensitivity analysis to improve prediction of traumasurvival Computer Methods and Programs in Biomedicine. 62,11-19.
Hecht-Nielsen, R., 1990. Neuro computing. Addison-Wesley, Reading, Mass. Anagu, I., Ingwersen, J., Utermann, U., Streck, T., 2009. Estimation of heavy metal sorption in German soils using artificial neural networks Geoderma. 152. 104–112
Jang, J.S.R., 1993. ANFIS: adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man and Cybernetics, 23: 665–685.
Liu X., Wu J., and Xu, J., 2010a. Characterizing the risk assessment of heavy metals and sampling uncertainty analysis in paddy field by geostatistics and GIS Environmental Pollution, 141: 257-264.
Liu, M.L., Liu, X.N., Li, M., Fang, M.H., Chi, W.X., 2010b. Neural-network model for estimating leaf chlorophyll concentration in rice under stress from heavy metals using four spectral indices. Biosystems Engineering 106,223–233
Kammeno, O., 2000. River flow modeling using artificial neural networks. ASCE Journal of Hydrology Engineering, 9 (1): 60–63.
Kimura, M., Nakano, R., 2000. Dynamical systems produced by recurrent neural networks. Systems and Computers in Japan; 31:818–28.
Khoshnevisan, B., Rafiee, S.H., Omid, M., Mousazadeh, H,. 2014. Development of an intelligent system based on ANFIS for predicting wheat grain yield on the basis of energy inputs, Information Processing in Agriculture.10:1016.
Koekkoek, E.J.W., Booltink, H. 1999. Neural network models to predict soil water retention. European Journal of Soil Science. 50: 489-495.
Mirmahmudi, M., 2013. Environmental principles, printing, publishing the University Jihad Mashhad (In Farsi) Menhaj, M., 2009. Fundamental of Artificial neural networks. Amirkabir Press. (In Farsi)
Mico´, C., Recatala´, Peris, M., Sa´nchez, J., 2006. Assessing heavy metal sources in agricultural soils of an European Mediterranean area by multivariate analysis.Chemosphere. 65:863–872.
Morshed, J., Kaluarachchi J.J. (1998) Parameter estimation using artificial neural network and genetic algorithm for free-product migration and recovery. Water Resource Resesrch. 34 (5), 1101-1113.
Olsen, S.R., Sommers, L.E., 1982. Phosphorous. Pp. 423-424. In: Methods of soil analisis (2nded) part2. Soil Science Society of America, Madison, WI.
Page, A. L., Miller, R. H., Keeney, D. R., 1982. Methods of soil analysis. Part 2. Chemical and microbiological properties. American Society of Agronomy. In Soil Science Society of America (Vol. 1159)
Raheli Namin, B., Salman, A., Mahiny., H., Moradi, R., 2012. Quantification of Underground Water Quality Parameters Using Land Use/Cover (Ghareh-Su Watershed, Golestan Province). Journal of Natural Environment, 65(1): 67-82.
Rezaei, M., Majdi, A., Monjezi, M., 2012. An intelligent approach to predict unconfined compressive strength of rock surrounding access tunnels in longwall coal mining. Neural Computing Application 24(1):233–241.
Rodriguez, L., Rinco´ N, J., Asencio I., Rodrı´guez-Castellanos, L. 2007. Capabilityof selected crop plants for shoot mercury accumulation from pollutedsoils: phytoremediation perspectives. International Journal of Phytoremediation 9, 1–13.
Rump, P, H. H., Krist, H., 1988. Laboratory manual for the examination of water, wastewater and soil. VCH, New York , U.S.A. Safa, M., Samarasinghe, S., 2011. Determination and modelling of energy consumption in wheat production using neural networks, A case study in Canterbury province, New Zealand. Energy, 390; 36:5140-7.
Sarmadian, F., Taghizadeh, R. A., Akbarzadeh, E., 2009. Comparison of neuro-fuzzy neural network and multiple regression analysis to predict. Soil Properties Case Study: Golestan. Journal of Soil and Water Research, 41, 211-220(In Farsi)
Schaap, M.G., Leij, F.J. 1998. Using neural networks to predict soil water retention and soil hydraulic conductivity Soil and Tillage Research, 47: 37–42.
Schaap, M.G., Bouten, W., 1996. Modelling water retention curves of sandy soils using neural networks. Water Resource Research, 32 (10), 3033-3040.
Schilcher, H., 1983. Contamination of natural products with pesticides and heavy metals Amsterdam: Elsevier Science Publishers; 417-423.
Shuang, H., Ren Duo, Z., Jia Ying, Z., Rong, P., 2009. Effects of pH and soil texture on the adsorption and transport of Cd in soils, Journal of Science China Technological Sciences, 52(11): 3293-3299.
Tay, J. H., Zhang, X., 2000. A fast predicting neural fuzzy model for high-rate anaerobic wastewater treatment systems, Water Research. 34 (11), 2849–2860.
Tomasella, J., Hodnett, M. G., Rossato, L., 2000. Pedotransfer functions for the estimation of soil water retention in Brazilian soils, Soil Science Society of America Journal, 49, 1100-1105.
Tudoreanu, L., Phillips, C.J.C., 2004. Modeling cadmium uptake and accumulation in plants Agronomy 84: 121-157.
Walkly, A., Black, I.A., 1934. An examination of the degtjareff method for determining soil organic matter and a proposed modification of the chromic acid titration method. Soil Science 37: 29-38.
Wasiol, C.S., Motavalli, P., Kitchen, N.R., Otter, D.K., 1998. Soil phosphorous spatial distribution in pastures receiving poultry litter application. Agronomy abstracts. American Society of Agronomy.
Madison, W.I. Wosten, J. H. M., Pachepsky, Y.A., Rawls, W.J .2001. Pedo transfer functions: bridging the gap between available basic soil data and missing soil hydraulic characteristics. Journal of Hydrology. 251, 123–150.
Yang, F. G., Cao, S. Y., Liu, X. N., Yang, K.J., 2011. Design of groundwater level monitoring network with ordinary kriging Journal of Hydrodynamic, 20(3): 339-346.
نشریه محیط زیست طبیعی
دوره 70، شماره 3
آذر 1396
صفحه 509-523