با همکاری انجمن‏‌ بیماری شناسی گیاهی ایران

نوع مقاله : حشره شناسی کشاورزی

نویسندگان

1 دانش‌آموخته کارشناسی ارشد حشره شناسی، دانشکده کشاورزی، دانشگاه شاهرود، شاهرود

2 استادیار گروه گیاه پزشکی سازمان پژوهش‌های علمی و صنعتی ایران، تهران

چکیده

پژوهش حاضر با هدف پیش‌بینی تراکم کنه تارتن دولکه‌ای با روش‌های زمین‌آمار و شبکه‌ی عصبی مصنوعی در مرزعه خیار استان خوزستان شهرستان رامهرمز انجام شد. بدین منظور مختصات طول و عرض ۱۰۰ نقطه با فاصله ۱۰متر، در سطح مزرعه مشخص و به عنوان ورودی‌های هر دو روش تعریف شد. خروجی هر روش نیز تعداد این آفت در آن نقاط بود. در بخش زمین‌آمار از روش کریجینگ معمولی و در بخش شبکه عصبی مصنوعی، ساختار پرسپترون سه لایه با الگوریتم پس انتشار خطا، مورد ارزیابی قرار گرفت. مقایسه نتایج زمین‌آمار و شبکه عصبی مصنوعی بیانگر توانایی بالای شبکه عصبی در مقایسه با روش زمین‌آمار بود، به طوری که به ترتیب شبکه عصبی مصنوعی و زمین آمار با ضریب تبیین 0.891 ، 0.601 و مجموع مربعات باقیمانده 0.14، 0.071 نسبت به زمین­آمار خطای کمتری داشت. در مجموع می­توان چنین نتیجه گرفت که روش شبکه عصبی مصنوعی با تلفیق دو عامل طول و عرض جغرافیایی، قادر به پیش­بینی تراکم آفت با دقت مناسب بود.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Evaluation of the Geostatistical and Artificial Neural Network Methods to estimate the Spatial Distribution of Tetranychus urticae (Acari: Tetranychidae) in Ramhormoz Cucumber fields

نویسندگان [English]

  • A. R. SHABANINEJAD 1
  • B. TAFAGHODINIA 2

چکیده [English]

In this study, the geostatistical and artificial neural network methods were used to estimate the spatial distribution of Tetranychus urticae in Ramhormoz Cucumber fields. For this purpose, latitude and longitude of 100 points with 10 meters distance of each point were defined as inputs and output of each method was number of these pests on those points. Ordinary kriging, and perceptron with propagation algorithm were evaluated in geostatistical and artificial neural network method, respectively. In neural network a hidden layer and three-layer were considered as input. Results of the aforementioned two methods showed that artificial neural network capability is more than kriging method. So that, the artificial neural network predicts distribution of this pest with 0.891 coefficient of determination and 0.14 residual sums of squares. While in the geostatistical methods coefficient of determination and residual sums of squares were 0.601 and 0.071, respectively. So it can be concluded that the Artificial Neural Network approach with combining latitude and longitude can forecast pest density with sufficient accuracy.

کلیدواژه‌ها [English]

  • Artificial Neural Network
  • Kriging
  • Tetranychus urticae
  • Variogram
ANONYMOUS, 2011. Agricultural statistics, Department of Planning and Economy, The office of Statistics and Information Technology, Tehran.
AZADEH, A., S. F. GHADERI and S. SOHRABKHANI, 2006. Forecasting electrical consumption by integration of Neural Network, time series and ANOVA. Applied Mathematics and Computation, 186: 1753-1761.
DE ALVES, M. C., F. M. DA SILVA, J. C. MORAES, E. A. POZZA, M. S. DE OlIVIRA, J. C. S. SOUZA and L. S. ALVES, 2011. Geostatistical analysis of the spatial variation of the berry borer and leaf miner in a coffee agroecosystem. Precision Agriculture, 12:18–31.
GOEL, P. K., S. O. PRASHER, R. M. PATEL, J. A. LANDRY, R. B. BBONNELL and A. A. VIAU, 2003. Classification of hyperspectral data by decision trees and artificial neural networks to identify weed stress and nitrogen status of corn. Computers and Electronics in Agriculture, 39: 67–93.
GOOVAETS, P. 1997. Geostatictics for Natural Resources Evaluation. 512pp. Oxford University presses. Londen.
GORMAN, K., F. HEWITT, L. DENHOLM and G. J. DEVINE, 2001. New developments in insecticide resistance in the glasshouse whitefly (Trialeurodes vaporariorum) and the two-spotted spider mite (Tetranychus urticae) in the UK. Pest Management Science, 58: 123-130.
GRESSIE, N. 1993. Statistics for spatial data. 430PP. John Wiley and Sons, New York.
GUTIERREZ, P. A., F. LOPEZ-GRANADOS, J. M. PENA-BARRAGAN, M. JURADIO-EXPOSITO, M. T. GOMEZ-CASERO and C. HERVAS-MARTINEZ, 2008. Mapping sunflower yield as affected by Ridolfia segetum patches and elevation by applying evolutionary product unit neural networks to remote sensed data. Computers and electronics in agriculture, 60: 122-132.
HABASHI, H., M. HOSSEINI, J. MOHAMMADI and R. RAHMANI, 2007. Geostatistic applied in forest soil studing process. Journal of Agricultural Science and natural Resources, 14: 1-10 (in Persian with English summary).
HASSANI-PAK, A. A. 2007. Geostatistics. 314pp. University of Tehran Press. Tehran, Iran. (In Persian).
HEYKIN, S. 1999. Neural Networks A Comprehensive Foundation, Second Edition. 14-29.
IRMAK, A., J. W. JONES, W. D. BATCHELOR, S. IRMAK, K. J. BOOTE and J. PAZ, 2006. Artificial neural network model as a data analysis tool in precision farming. Transactions of the American Society of Agricultural and Biological Engineers, 49: 2027-2037.
ISMAN, M. 1999. Pestcides based on plant essential oils. Pesticide Outlook, 5: 68 – 72.
JOURNEL, A. G. and C. J. HUIJBREGTS, 1978. Mining Geostatistics. 599pp. Academic press. USA.
KATHRINE, A. R. 2001. Geostatistic using SAS software. Own analyticinc. 360 PP.  Oxford University Press. Londen.
KAUL, M., R. L. HILL and C. WALTHALL, 2005. Artificial neural networks for corn and soybean yield prediction. Agriculture system,85: 1-18.
KRIGE, D. G. and E. J. MAGRI, 1982. Studies of the effects of outliers and data transformation on variogram estimates for a base metal and a gold ore body. Mathematical Geology, 14: 557­567.
LATIFIAN, M. and E. SOLEYMANNEJADIAN, 2009. Study of the Lesser moth Batrachedra amydraula (Lep.: Batrachedridae) distribution based on geostatistical models in Khuzestan province. Journal of Entomological Research- Iran,1: 43-55 (in Persian with English summary).
LEE, D. S., C. O. JOEN, J. M. PARK and K. S. CHANG, 2002. Hybrid neural network modeling of a full-scale industrial wastewater treatment plant. Biotechnology and Bioengineering, 78: 670–682.
LIEBHOLD, A. M., X. ZHANG, M. E. HOHN, J. S., ELKINTON, M. TICEHURST, C. L. BENZON and R. W. CAMPBELL, 1991. Geostatistical analysis of Gypsy moth (Lepidoptera: Lymantridae) egg mass population. Environmental Entomology, 20: 1407­1417.
MAKARIAN, H., M. H. RASHED, M. BANNAYAN and M. NASSIRI, 2007. Soil seed bank and seedling populations of Hordeum murinum and Cardaria draba in saffron fields. Agriculture Ecosystems and Environment, 120: 307- 312.
NARIO, L. S., J. OLIVER-VEREL, E. E. STASHENKO, 2010. Repellent activity of essential oils:A review. Bioresource Technology, 101: 372-378.
RIBES-DASI, M., J. AIMACELLAS, J. SIO, R. TORIA,
S. PLANAS and J. AVILLA, 2005. The use of Geostatistics and GIS to optimize pest control practices in precision farming systems. Information and Technology for Sustainable Fruit and Vegetable Production, 10: 583-590.
SCIARRETTA, A., P. TREMATERRA and J. BAUMGARTNER, 2001. Geostatistical analysis of Cydia funebrana (Lepidoptera: Tortricidae) pheromone trap catches at two spatial scales. American Entomologist 47: 174-184.
SHABANI NEJAD, A. R. and B. TAFAGHODINIA, 2017. Evaluation of the Ability of LVQ4 Artificial Neural Network Model to Predict the Spatial Distribution Pattern of Tuta absoluta in the tomato field in Ramhormoz. Journal of Entomolological Society of Iran, 36: 195-204 (in Persian with English summary).
SHABANI NEJAD, A. R., B. TAFAGHODINIA and N. ZANDI SOHANI, 2017. Hybrid neural network With genetic algorithms for predicting distribution pattern of Tetranychus urticae (Acari.: Tetranychidae) in cucumbers field of Ramhormoz. Persian Journal of Acarology, 6: 53-62.
SHAFIEENASAB, B., J. SHAKARAMI, A. MOHISENI, and H. JAFARI, 2015. Geostatistical characteristics of the spatial distribution of the infestation pods by the pod borer, Heliothis viriplaca Huf. (Lep.: Noctuidae) in rain-fed chickpea (Cicer arietinumL.) fields in Delfan (Lorestan province). Plant Pests Research, 5: 49-59 (in Persian with English summary).
STORY, M. and R. G. CONGALTON, 1994. Accuracy assessment: A user’s perspective:L.K. Fenestermaleer. Remote sensing thematic assessment. American society for photogrammetry and remote sensing, 10: 257­259.
TORRECILLA, J. S., L. OTERO and P. D. SANZ, 2004. A neural network approach for thermal/pressure food processing. Food Engineer, 62: 89-95.
VAKIL-BAGHMISHEH, M. T. and N. PAVEŠIC, 2003. A Fast simplified fuzzy ARTMAP network. Neural Processing Letters, 17: 273-301.
VAKIL-BAGHMISHEH, M. T. and N. PAVEŠIC, 2003. Premature clustering phenomenon and new training algorithms for LVQ. Pattern recognition, 36: 1901-1921.
WANG, Y. M. and T. M. S. ELHAG, 2007. A comparison of neural network, evidential reasoning and multiple regression analysis in modeling bridge risks. Expert Systems with Applications, 32: 336-348.
WRIGHT, R. J., T. A. DEVRIES, L. J. YOUNG, K. J. JARVI and R. C. SEYMOUT, 2002. Geostatistical analysis of small­scale distribution of European corn borer (Lepidoptera:  Crambidae) larvae and damage in whorl stage corn. Environmental Entomology, 31: 160­167.
YOUNG, P., K. JA-MYUNG, L. BUOM-YOUNG, YEONG-JIN. and K. YOOSHIN, 2000. Use of an Artificial Neural Network to Predict Population Dynamics of the Forest–Pest Pine Needle Gall Midge (Diptera: Cecidomyiida). Environmental Entomology, 29:1208-1215.
YUXIN, M., D. J. MULLA and C. R. PIERRE, 2006. Identifying important factors influencing corn yield and grain quality variability using artificial neural networks. Precision Agriculture, 7: 117–135.
ZHANG, W. J., X. Q. ZHONG and G. H. LIU, 2008. Recognizing spatial distribution patterns of grassland insects: neural network approaches. Stochastic Environmental. Research and Risk Assessment, 22:207–216.
ZHANG, Y. F. and J. Y. H. FUH, 1998. A neural network approach for early cost estimation of packaging products. Computers & Industrial Engineering, 34: 433-50.
ZHAO, J., F. Q. ZHENG, Y. J. WANG, B. H. YE, M. H. Y. ZHAOXIN and L. U. HAO, 2011. Geostatistical Analysis of Spatial Patterns of Bemisia tabaci (Homoptera: Aleyrodidae) Adults in Tobacco Field. 6th IEEE Conference on Industrial Electronics and Applications. 2394 – 2398.