پیش‌بینی میزان سرب خاک با استفاده از خصوصیات زودیافت براساس مدل شبکه عصبی مصنوعی

نوع مقاله: مقاله اصلی

نویسندگان

1 کارشناسی ارشد، گروه علوم خاک، دانشکده کشاورزی، دانشگاه فردوسی، مشهد، ایران

2 دانشیار، گروه علوم خاک، دانشکده کشاورزی، دانشگاه فردوسی ، مشهد، ایران

3 دانشجوی دکتری، گروه علوم خاک، دانشکده کشاورزی، دانشگاه فردوسی مشهد، مشهد، ایران

4 استاد گروه علوم خاک، دانشکده کشاورزی، دانشگاه فردوسی مشهد،مشهد، ایران

5 استاد، گروه علوم خاک، دانشکده کشاورزی، دانشگاه فردوسی مشهد، مشهد، ایران

چکیده

افزایش تولید آلاینده‌ها از جمله فلزات سنگین یکی از مشکلات جدی و در حال گسترش جامعه بشری است. آلودگی به فلزات سنگین نه‌تنها بر خصوصیات فیزیکی و شیمیایی خاک تأثیرگذار است، بلکه برای سلامتی انسان از طریق ورود به چرخه غذایی و نفوذ به آب‌های زیرزمینی خطرناک است. مطالعه حاضر با هدف پیش‌بینی میزان سرب خاک به‌عنوان یکی از مهم‌ترین فلزات سنگین با استفاده از خصوصیات زود­یافت خاک به کمک مدل شبکه عصبی مصنوعی انجام شد. بدین منظور 63 نمونه از عمق صفر تا 30 سانتی‌متر خاک‌های مختلف واقع در حاشیه رودخانه کشف‌رود در شمال شهرستان مشهد برداشته شد. پارامترهای pH، هدایت الکتریکی، فراوانی نسبی ذرات، کربن آلی و سرب خاک اندازه‌گیری شدند. مدل شبکه عصبی مصنوعی نوع پرسپترون چندلایه برای پیش‌بینی غلظت سرب خاک مورداستفاده قرار گرفت. ارزیابی مدل با استفاده از پارامترهای آماری مانند ضریب تبیین (R2)، میانگین خطای مطلق (MAE) و همچنین مجذور میانگین مربعات خطا (RMSE) انجام شد. نتایج نشان داد که کارایی مدل شبکه عصبی مصنوعی مناسب است و می‌تواند به‌عنوان روشی دقیق جهت جایگزین شدن با روش پرهزینه و زمان‌بر اندازه‌گیری مستقیم آزمایشگاهی این فلز سنگین در خاک مورداستفاده قرار گیرد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Predicting Lead Concentration of Soil using Readily Available Properties Based on Artificial Neural Network Model

نویسندگان [English]

  • Saman Haji Namaki 1
  • Hojjat Emami 2
  • Ahmad Bazoobandi 3
  • Amir Fatovat 4
  • GholamHossein Haghnia 5
1 M.Sc., Soil Science Department, Faculty of Agriculture, Ferdowsi University, Mashhad, Iran
2 Associate Prof., Department of Soil Sciences, Faculty of Agriculture, Ferdowsi University, Mashhad, Iran
3 Ph.D. Scholar., Soil Science Department, Faculty of Agriculture, Ferdowsi University, Mashhad, Iran
4 Prof., Department of Soil Sciences, Faculty of Agriculture, Ferdowsi University, Mashhad, Iran
5 Prof., Department of Soil Sciences, Faculty of Agriculture, Ferdowsi University, Mashhad, Iran
چکیده [English]

Increased generation of pollutants such as heavy metals is one of the serious and developing environmental issues threatening human society. Heavy metal pollution not only affects the physical and chemical properties of the soil but also it is dangerous to human health through entering into the food chain and finding its way into the groundwater. The present study was conducted to predict soil lead concentration, as one of the most important heavy metals, using readily available soil properties based on artificial neural network model. For this purpose, 63 soil samples were collected from 60-cm depth of the land surrounding Kashafrud River located in Mashhad City. Measured parameters included pH, electrical conductivity, particle size distribution, organic carbon, and Pb content in soil. The multilayer perceptron (MLP) as an artificial neural network model was used to predict the Pb concentration in soil. The performance of this model was assessed by the coefficient of determination (R2), mean absolute error (MAE), and also root mean square error (RMSE). The results showed that artificial neural network model is a suitable method to determine Pb concentration in soil rather than the direct laboratory measurement, which is an expensive and time-consuming method.

کلیدواژه‌ها [English]

  • Lead
  • Artificial Neural Network
  • Heavy metal
  • Kashafrud

Altfelder S., Duijnisveld W. H. M., Streck T., Meyenburg G. and Utermann J. (2007). Quantifying the influence of uncertainty and variability on groundwater risk assessment for trace elements. Vandose Zone J., 6, 668-678.

 

Amini M., Abbaspour K. C., Khademi H., Fathianpour N., Afyuni M. and Schulin R. (2005). Neural network models to predict cation exchange capacity in arid regions of Iran. Euro. J. Soil Sci., 56, 551–559.

 

Anagu I., Ingwersen J., Utermann U. and Streck T. (2009). Estimation of heavy metal sorption in German soils artificial neural networks. Geoderm., 152, 104–112.

 

Bar N., Biswas M. N. and Das, S. K. (2010). Prediction of pressure drop using artificial neural network for gas non-Newtonian liquid flow through piping. Ind. Eng. Chem. Res., 49, 19, 9423-9429 

 

Barančíková G., Madams M. and Rybàr O. (2004). Crop contamination by selected trace elements. J. Soil Sedim., 4, 37-42.

 

Bazoobandi A., Saberi I., Ghorbani H. and Emamgholizadeh S. (2015). Prediction of soil Cd and pb using neural network. 5th Int. conference on novel finding in bioscience and agriculture, Tehran [In Persian].

 

Bila S., Harkouss Y., Ibrahim M., Rousset J., Goya E., Baillargeat D., Verdeyme M., Aubourg M. and Guillon P. (1999). An accurate wavelet neural-network-based model for electromagnetic optimization of microwave circuits. Int. J. RF. Microwave Comput.- aided Eng., 93, 297–306.

 

Bou-Kheir R., Greve M. H., Abdallah C. and Dalgaard T. (2010). Spatial soil zinc content distribution from terrain parameters: A GIS-based decision-tree model in Lebanon. Environ. Pollut., 158, 520-528.

 

Bouten W. and Schaap M. G.  (1996). Modelling water retention curves of sandy soils using neural networks. Water Res., 32, 3033- 3040.

 

Das B., Ganguly N., Bar N., and Das S.K. (2015). Holdup prediction in inverse fluidization using non-Newtonian pseudoplastic liquids: Empirical correlation and ANN modeling. Powder Technol. 273, 83–90.

 

Deligani F., Khazemi G., Parvinnia M. and Khakshor M. (2009). Enrichment and distribution of heavy metals in soils of South Pars Special Economic Zone in Assaluyeh. 5th Int. Conference on Civil Engineering, University of Shiraz [In Persian].

 

Devabhaktuni V., Yagoub M., Fang Y., Xu J. and Zhang Q. (2001). Neural networks for microwave modeling: model development issues and nonlinear modeling techniques, Int. J. RF. Microwave Comput.-aided Eng.., 11, 4–21.

 

Ghorbani H., Kashi H., Hafezi Moghadas N. and Emamgholizadeh S. (2015). Estimation of soil cation exchange capacity using multiple regression, artificial neural networks, and adaptive neuro-fuzzy inference system models in Golestan Province, Iran. Commun. Soil Sci. Plant Anal., 46, 763-780.

 

Hunter A., Kennedy L., Henry J. and Ferguson I. (2000). Application of neural networks and sensitivity analysis to improve prediction of trauma survival. Comput. Meth. Prog. Bio., 62, 11- 19.

 

Ingwersen J. (2001). The environmental fate of cadmium in the soils of the waste water irrigation area of Braunschweig: measurement, modeling and assessment. PhD thesis, Technische, Universität Braunschweig, Germany.

 

Ingwersen J. and Streck T. (2006). Modeling the environmental fate of cadmium in a large  wastewater irrigation area. J. Environ. Qual., 35, 1702- 1714.

 

Kabata-Pendias A. (2010). Trace elements in soils and plants. CRC press. 

 

Kasraeian A., Karimian N., and Ghafouri V. (2014). Evaluation of spatial distribution of soil cadmium and cadmium hot points in a part of an arable lands in west of Shiraz in Fars Province by kriging method. Water Wastewater, 4, 44-50. 

 

Kimura M. and Nakano R. (2000). Dynamical systems produced by recurrent neural networks. Sys. Comput. Japan., 31, 818–28.

 

Köleli N., Eker S. and Cakmak I. (2004). Effect of zinc fertilization on cadmium toxicity in durum and bread wheat grown in zincdeficient soil. Environ. Pollut., 131, 453459.

 

Lindsay W. L. and Norvell W. A. (1978). Development of a DTPA soil test for zinc, iron, manganese, and copper. Soil Sci. Soci. Am. J., 42, 421-428.

 

Menhaj M. (2009). Fundamental of artificial neural networks. Amirkabir Press [In Persian].

 

Mirzaee R., Ghorbani H. and Hafezimoghghaddam N. (2015). The distribution pattern of heavy metals in the surface soils of Golestan Province. Res.Soil (Soil Sci. Water), 1, 93-103 [In Persian].

 

Mitra T., Singha B., Bar N. and Das S. K. (2014). Removal of Pb (II) ions from aqueous solution using water hyacinth root by fixedbed column and ANN modeling. J. Hazard. Mat., 273, 94-103.

 

Richards L. A. (1954). Diagnosis and improvement of saline and alkali soils. Soil Sci., 78, 154.

 

Sarmadian F., Taghizadeh R. A. and Akbarzadeh E. (2009). Comparison of neuro-fuzzy neural network and multiple regression analysis to predict soil properties (Case Study: Golestan). J. Soil Water Res., 41, 211-220 [In Persian].

 

Schipper L. A., Williamson J. C., Kettles H. A. and Speir T. W. (1996). Impact of landapplied tertiary-treated effluent on soil biochemical properties. J. Environ. Qual., 25, 1073-1077.

 

Shuang H., RenDuo Z., JiaYing Z. and Rong P. (2009). Effects of pH and soil texture on the adsorption and transport of Cd in soils. J. Sci. China Ser. E-Tech Sci., 52(11), 32933299.

 

Singha B., Bar N. and Das S. K. (2015). The use of artificial neural network (ANN) for modeling of Pb(II) adsorption in batch process. J. Molecul. Liquids, 211, 228-232.

 

Streck T. and Richter J. (1997). Heavy metal displacement in a sandy soil at the field scale: I Measurements and parameterization of sorption. J. Environ. Qual., 26, 49–56.

 

Walkley A. and 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 Sci., 37, 29-38.

 

Wosten J. H. M., Pachepsky Y. A. and Rawls W. J. (2001). Pedotransfer functions: bridging the gap between available basic soil data and missing soil hydraulic characteristics. J. Hydro., 251, 123–150.