کاربرد الگوریتم ژنتیک در برآورد توزیع مکانی پ‌هاش خاک با ترکیب زمین‌آمار و برنامه‌ریزی بیان ژن

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشگاه شهید مدنی آذربایجان

2 دانشگاه شهید مدنی اذربایجان

چکیده

آگاهی در مورد توزیع مکانی ویژگی­های خاک نقش مهمی در سیستم رشد و عملکرد محصول در بخش کشاورزی دارد. در این راستا جهت افزایش دقت در توزیع مکانی pHخاک، الگوریتم ژنتیک در ترکیب برآوردهای رگرسیون خطی، برنامه­ریزی بیان ژن (GEP) و زمین­آمار (درون­یابی کریجینگ) در مناطقی از استان آذربایجان­شرقی (شهرستان­های بناب، عجب­شیر و مراغه) مورد استفاده قرار گرفت. مدل نیم­تغییرنمایخطی در درون­یابی کریجینگ دارای کمترین مقدار خطااست. برنامه­ریزی بیان ژن و رگرسیون خطی به­ترتیب در برآورد توزیع مکانیpHخاک، کمترین و بیشترین مقدارخطا را دارند،میزان کاهشمیانگین مربع خطا، خطای جذر میانگین مربعات، خطای جذر میانگین مربعات نسبیاز رگرسیون خطی به زمین­آمار بهترتیب 67/47،58/27 و 47/26 درصد و میزان کاهششاخص پراکندگی و میانگین درصد خطای مطلق تعدیل شده از رگرسیون خطی به برنامه­ریزی بیان ژن به­ترتیب 8/23 و 03/37 درصد است.روش ترکیبیبا استفاده از الگوریتم ژنتیک نسبت به سه نوع مدل­سازی، خطای برآورد توزیع مکانی pHخاک را کاهش می­دهد­،به­عنوان نمونه میزان کاهشمیانگین مربع خطا، خطای جذر میانگین مربعات، خطای جذر میانگین مربعات نسبیاز مدلبرنامه­ریزی بیان ژن به روش ترکیبی به­ترتیب برابر با 33/23،76/11­ و 10 درصد است. برآوردهای pHبا روش ترکیبی در محدوده قلیایی می­باشد که با مقادیر اندازه­گیری شدههم­خوانی دارد. کمینه و بیشینه مقدار قدر مطلق اختلاف بین مقادیر اندازه­­­گیری و تخمینی در نقاط مورد­بررسی به­ترتیب در بناب(09/0) و عجب­شیر (25/0)می­باشد.معیار میانگین درصد خطای مطلق در روش ترکیبی در محدوده قابل­قبول از نظر عملکرد است و این مسئله کارایی روش مورد­استفاده را در برآورد توزیع مکانی پ­هاشخاک نشان می­دهد.

کلیدواژه‌ها


عنوان مقاله [English]

Genetic Algorithm Application for Soil pHSpatial Distribution Estimation with Geostatistics and Gene Expression ProgrammingCombination

نویسندگان [English]

  • Reza Ahadi 2
  • Fatemeh Seyyed Milani 1
1
2 Azarbaijan Shahid Madani University
چکیده [English]

Awareness about spatial distribution of soil properties plays an important role in the system of crop growth and yield in the agricultural field. In this regard, genetic algorithm was used to increase the accuracy in spatial distribution of soil pHwhich combines the estimates of linear regression, gene expression programming (GEP) and geostatistics (kriging interpolation) with data related to some parts of East Azerbaijan province (Bonab,Maragheh and Ajabshir). The linear model of kriging interpolation had the minimum error. Gene expression programming and linear regression had the lowest and highest error for soil pH spatial distribution estimation, respectively, for example the mean square error, root mean square error, relative root mean square errordecreasing from linear regression to geostatistics was 47.67%,27.58%, 26.47% and scatter index and adopted mean absolute percentage error decreasing from linear regression to GEP was 23.8% and 37.03%, respectively. The use of genetic algorithm in combination method reduced the error of spatial distribution compared to the tree types of models, for example mean square error, root mean square error, relative root mean square errordecreasing from GEP to combination method was 23.33%, 11.76%,10%, respectively. The estimates of soil pH with combination method are in the alkaline range, which is consistent with the obtained data.  The minimum and maximum value of the absolute difference between measured and estimated data were at point in Bonab (0.09) and Ajabshir(0.25), respectively. The mean absolute percentage error of combination method was in acceptable range and this shows the efficiency of combination method for soil pH spatial distribution estimation.

کلیدواژه‌ها [English]

  • Spatial distribution
  • Genetic algorithm
  • Gene expression programming
  • Geostatstic
Adhikari R., and Agrawal R.K. 2014. Performance evaluation of weights selection schemes for linear combination of multiple forecasts. Artificial Intelligence Review, 42(4):529-48.

Afzali A., Varvani J., and Jafania R. 2018. Application of Geostatistical analysis for prediction of Spatial Variations in Soil Texture (Case study: Farahan Plain, Markazi province). Sarzamin, 15(58):1-16 .(In Persian)

Ahmadi F.F., and Layegh N.F. 2015. Integration of artificial neural network and geographical information system for intelligent assessment of land suitability for the cultivation of a selected crop. Neural Computing and Applications, 26(6):1311-20.

Arbab M., Pahlavanravi A., Piri Sahragard H., and Amiri M. 2018. Accuracy Assessment of Geo-Statistics and Artificial Neural Networks Methods to Estimate Threshold Wind Velocity: A Case of Jazinak Region, Sistan Plain. Quarterly Journal of Environmental Erosion Research, 31(3):87-105. (In Persian)

Bayat Varkeshi M.,and Fasihi R. 2018. Comparison of Numerical Model, Neural intelligent and geostatistical in Estimating Groundwater Table. Journal of Geographical Sciences, 18(48):165-182. (In Persian)

Belkhiri L., Tiri A., and Mouni L. 2020. Spatial distribution of the groundwater quality using kriging and Co-kriging interpolations. Groundwater for Sustainable Development, 11:100473.
Calzolari C., Ungaro F., and Vacca A. 2021. Effectiveness of a soil mapping geomatic approach to predict the spatial distribution of soil types and their properties. Catena,196:104818.
Chen W., Xu H., Chen Z., and Jiang M. 2021. A novel method for time series prediction based on error decomposition and nonlinear combination of forecasters. Neurocomputing, 426:85-103.
Dahiya I.S., Richter J., and Malik R.S. 1984. Soil spatial variability: a review, International Journal of Tropical Agricultural, 11:1-102.

Dehghani R., and Noorali A.2016. Comparison of geo-statistical methods and artificial neural network in estimating groundwater level (Case Study: Nourabad Plain,Lorestan). Journal of Environmental Science and Technology, 18(1):31-43. (In Persian)

Del Carmen Bas M., Ortiz J., Ballesteros L., and Martorell S. 2017. Forecasting 7BE concentrations in surface air using time series analysis. Atmospheric Environment, 155:154-61.

Ebadi Y., Javdan J., and Rezaei Moghaddam M.H.2019.Estimating accuracy of Artificial Neural Networks (ANN) and Geo Statistical Methods in interpolating Groundwater Levels Case study: Shabestar-Sufian Plain.Scintific-Research Quarterly of Geographical Data,28(110):133-145. (In Persian)

Eleyedath A., Kar S.S., and Swamy A.K. 2021. Modelling of expansion ratio and half-life of foamed bitumen using gene expression programming. International Journal of Pavement Engineering,22(3):369-81.
Foroughifar H., Jafarzadah A.A., Torabi Gelsefidi H., Aliasgharzadah N., Toomanian N., and Davatgar N. 2010. Spatial variations of surface soil pH physical and chemical properties on different landforms of Tabriz plain.Journal of Soil and Water Science, 21(3):1-21.(In Persian)

Gia Pham T., Kappas M., Van Huynh C., and Nguyen L. 2019. Application of ordinary kriging and regression kriging method for soil properties mapping in hilly region of Central Vietnam. ISPRS International Journal of Geo-Information,8(3):147.

Habibi M.H., Nadiri A.A, Asghari Moghaddam A., and Naderi K. 2016. Combination of geostatistical and artificial intelligence methods for predicting spatiotemporal water level in the Hadishahr plain. Iran-Watershed Management Science & Engineering, 10(32):27-33. (In Persian)
Hashemi M., Gholamalizadeh A., Bameri A., Sarani F., and Hejaziziadeh A. 2016. Survey and zoning of soil پ هاشysical and chemical properties using geostatistical methods in GIS (Case Study: Miankangi Region in Sistan). Journal of Water and Soil,30(2):443-458 .(In Persian)

John K., Afu S.M., Isong I.A., Aki E.E., Kebonye N.M., Ayito E.O., Chapman P.A., Eyong M.O., and Penížek V. 2021. Mapping soil properties with soil-environmental covariates using geostatistics and multivariate statistics. International Journal of Environmental Science and Technology, 4:1-6.

Karamouz M., and Kerachian R. 2003. Water Quality Planning and Management. Amirkabir University of Technology.

Luan F., Si H.Z., Liu H.T., Wen Y.Y., and Zhang X.Y. 2008.Prediction of atmospheric degradation data for POPs by gene expression programming. SAR and QSAR in Environmental Research, 19(5-6):465-79.

Maghami Y., Ghazavi R., Vali A.A., and Sharafi S.2011. Evaluation of spatial interpolation methods for water quality zoning using GIS Case study, Abadeh Township. Geography and Environmental Planning Journal,42(2):171-182. (In Persian)
Mirzaee S., Asadzadeh F., and Zolphaghari A.A.2017. Suitable geostatistical methods and incorporation of them with pedotransfer functions for mapping cation exchange capacity. Applied Soil Research Journal. 4(2): 1-13. (In Persian)

Nadiri A., Naderi K., Asghari Moghaddam A.,and Habibi M.H.2017. Spatiotemporal Predicting of Groundwater Level using Artificial Intelligence Models and Geostatistics Model (Case Study: Duzduzan Plain). Journal of Geography and Planning, 20(58):218-301. (In Persian)

Nadiri A., SHakor S., Asghari Moghaddam A., and Vadie M. 2014.Investigation of Groundwater Nitrate Pollution with Different Interpolation Methods (Case Study: East Azarbayjan, Bilverdy Plain).HydroGemorphology, 1(1):75-92. (In Persian)

Pahlavan-Rad M.R., and Akbarimoghaddam A. 2018. Spatial variability of soil texture fractions and phin a flood plain (case study from eastern Iran). Catena,160:275-81.
Shabani H., Delavar M.A., Safari Y., and Alamdari P. 2020. Spatial Variability of Some Soil Characteristics in Lands of Zanjan University. Applied Soil Research Journal.7(4): 164-178.

Shi W., Liu Y., Kong W., and Shen Q. 2015. Tea classification by near infrared spectroscopy with projection discriminant analysis and gene expression programming. Analytical Letters, 48(18):2833-42.

Shit P.K., Bhunia G.S., and Maiti R. 2016. Spatial analysis of soil properties using GIS based geostatistics models. Modeling Earth Systems and Environment, 2(2):1-6.
Zamani Ahmad Mahmoodi R., Akhondali A.M., Zarei H., and Radmanesh F. 2014. Estimation of the groundwate level by using a combined optimized method with Genetic Algorithms in Ramhormoz plain. Journal of Irrigation and Water Engineering, 4(15):26-38.(In Persian)
ZaynoddinM., Bonakdari H., Azari A., Ebtehaj I., Gharabaghi B., and Riahi Madavar H. 2018. Novel hybrid linear stochastic with non-linear extreme learning machine methods for forecasting monthly rainfall a tropical climate. Journal Environmental and Management, 222:190-206.
Zhang Y., and Hartemink AE. 2021. Quantifying short-range variation of soil texture and total carbon of a 330-ha farm. Catena, 201:105200.