برآورد عملکرد محصولات کشاورزی با استفاده از تصاویر سری زمانی سنتینل‌ـ2 (مطالعة موردی: شهرستان زنجان)

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد سنجش ‌از دور و سیستم اطلاعات جغرافیایی، واحد الکترونیکی دانشگاه آزاد اسلامی، تهران

2 استادیار پژوهشگاه هوافضا، وزارت علوم تحقیقات و فنّاوری، تهران

چکیده

اساس برنامه‌ریزی و مدیریت صحیح داشتن آمار و اطلاعات دقیق و به‌هنگام است. یکی از مهم‌ترین آمار و اطلاعات بخش کشاورزی میزان تولید سالیانة هر محصول یا سطح زیرکشت است. یکی از ابزارهایی که در کمترین زمان و با هزینة پایین و دقت مناسب، می‌تواند سطح زیرکشت محصولات را محاسبه کند دانش و فنّاوری سنجش ‌از دور است. در این تحقیق، از دو روش طبقه‌بندی شبکة عصبی مصنوعی و ماشین بردار پشتیبان استفاده‌ شده و سطح زیرکشت محصولات غالب منطقه، شامل هشت کلاس، از تصاویر سری زمانی سنتینل‌ـ2 برآورد شده است. براساس نتایج به‌دست‌آمده، صحت کلی هریک از روش‌های شبکة عصبی مصنوعی و ماشین بردار پشتیبان به‌ترتیب برابر با 97.74 و 97.96%، با ضریب کاپای 0.97 برای برآورد سطح زیرکشت محصولات بوده است. بنابراین، نتایج این دو روش مورد قبول واقع شده است. با توجه به صحت کلی، می‌توان نتیجه گرفت که دو روش طبقه‌بندی نتایج تقریباً یکسانی در منطقه دارد. علاوه‌براین، طبق نتایج صحت کاربر، می‌توان بیان کرد درمورد چهار محصول یونجه، برنج، پیاز و خربزه، عملکرد روش ماشین بردار پشتیبان بهتر از روش شبکة عصبی است و درمورد گندم دیم و آبی، جارو و مرتع، روش شبکة عصبی بهتر از ماشین بردار پشتیبان در منطقه عمل می‌کند.

کلیدواژه‌ها


عنوان مقاله [English]

Estimation of Agricultural Crop Yield Using Sentinel-2 Images (Case Study: Zanjan City)

نویسندگان [English]

  • Seyed Ahmad Mousavi 1
  • milad janalipour 2
  • Nadia Abbaszadeh Tehrani 2
1 M.Sc. Student of Remote Sensing and Geographic Information System, Islamic Azad University, Tehran
2 Assistant Prof. of Aerospace Research Institute, Ministry of Science, Research and technology, Tehran
چکیده [English]

The basis for proper planning and management is to have accurate and timely statistics and information. One of the most important statistics of the agricultural sector is the annual production rate of each crop, which also depends on the area under cultivation of crop and its efficiency. One of the tools that can calculate the area under cultivation in the least time, with low cost and with high accuracy is remote sensing science and technology. In this study, two classification methods including artificial neural networks and support vector machine with different kernels are used and the area under cultivation of major crops in the region consisting of 8 classes is estimated. According to the results, the overall accuracy of the artificial neural networks and support vector machine was 97.74% and 97.96% with a kappa coefficient of 0.97 for both methods, indicating that both methods are good for separation and classification of agricultural lands in the area. Based on the overall accuracy, it can be concluded that the two methods of classification have almost the same results in the region. Also, based on the results of the user's accuracy for the four crops including Alfalfa, Rice, Onion and Melon, the support vector machine method performs better than the neural network method and also for dry and water Wheat, Sorghum, and Pasture, the neural network method out performs the support vector machine in the region.

کلیدواژه‌ها [English]

  • Remote Sensing
  • Classification method
  • Artificial Neural Network
  • Support Vector Machine
  • Sentinel-2
Abbaszadeh, T.N., Beheshtifar, M. & Morabi, M., 2011, Crop Type Mapping in Qazvin by Using Multi-Temporal Satellite Images: Irsc-lissiii Data (In Persian with English Abstract).
Alipour, F., Aghkhani, M., Abasspour-Fard, M. & Sepehr, A., 2016, Demarcation and Estimation of AgriculturalLands Using ETM+ Imagery Data (Case Study: Astan Ghods Razavi Great Farm), Journal of Agricultural Machinery (In Persian with English Abstract).
Arekhi, S., 2014. Comparing accuracy of artificial neural network, Support Vector Machine and maximum likelihood Algorithms for land use classification (Case study: Dashat Abbas arid region Ilam Province). Journal Range management, 2: 30- 43.
Arekhi, S. & Adibnejad, M., 2011, Efficiency Assessment of the of Support Vector Machines for Land Use Classification Using Landsat ETM+ Data (Case Study: Ilam Dam Catchment), Iranian Journal of Range and Desert Research, 18, PP. 420-440 (In Persian with English Abstract).
Bernstein, L.S., Jin, X., Gregor, B. & Adler-Golden, S.M., 2012, Quick Atmospheric Correction Code: Algorithm Description and Recent Upgrades,Optical Engineering, 1719, 11(51).
Dixon,B. & Candade,N., 2008, Multispectral Landuse Classification Using Neural Networks and Support Vectormachines: One or the Other, or Both?, International J.of Remote Sensing, 29(4), PP. 1185-1206.
Dutta, S., Patel, N., Medhavy, T., Srivastava, S., Mishra, N. & Singh, K., 1998, Wheat Crop Classification Using Multidate IRS LISS-I Data, Journal of the Indian Society of Remote Sensing, 26, PP. 7-14.
Foody, G.M., 2000, Mapping Land Cover fromRemotely Sensed Data with a Softened Feedforward Neural Network Classifica-tion, Journal of Intelligent and Robotic Systems, 29, PP. 433-449.
Foody, G.M. & Mathur, A., 2004, A Relative Evaluation of Multiclass Image Classification by Support Vector Machines, IEEE Transactions on Geoscience and Remote Sensing, 42, PP. 1335-1343.
Ghavami, Z., Arefi, H., Bigdeli, B. & Janalipour, M., 2017, Comprehensive Investigation on Non-Parametric Classification Methods in Order to Separate Urban Objects Using the Integration of Very High Spatial Resolution LiDAR and Aerial Data, Engineering Journal Of Geospatial Information Technology, 5(3), PP. 77-97.
Inglada, J., Arias, M., Tardy, B., Hagolle, O., Valero, S., Morin, D., Dedieu, G., Sepulcre, G., Bontemps, S. & Defourny, P., 2015, Assessment of an Operational System for Crop Type MapProduction Using High Temporal and Spatial Resolution Satellite Optical Imagery, Remote Sensing, 7, PP. 12356-12379.
Janalipour, M. & Taleai, M., 2017, Building Change Detection after Earthquake Using Multi-Criteria Decision Analysis Based on Extracted Information from High Spatial Resolution Satellite Images, International Journal of Remote Sensing, 38, PP. 82-99.
Kamkar, B., Dashti Morvili, M. & Kazemi, H., 2019, Detection of Rice and Soybean Grown Fields and their Related Cultivation Area Using Sentinel-2 Satellite Images in Summer Cropping

 
        Patterns to Analyze Temporal Changes in their Cultivation Area (Case Study: Four Watershed Basins of Golestan Province), Journal of Soil and Water Conservation Research, 26, PP. 151-167 (In Persian with English Abstract).
Keshavarz, A. & Ghasemian, H., 2005, A Fast Algorithm for Hyperspectral Image Analysis Using SVM and Spatial Dependency (In Persian with English Abstract), Nashriyyah-I Muhandesi-I Barq Va Muhandesi-I Kampyutar-I Iran (Persian), 3(1), PP. 37-44.
Khodakarami, L. & Soffianian, A., 2012, Application of Multi Temporal Remote Sensing for Precision Farming. JWSS-Isfahan University of Technology, 16, PP. 215-231 (In Persian with English Abstract).
Mokhtari, M. & Najafi, A., 2015, Comparison of Support Vector Machine and Neural Network Classification Methods in Land Use Information Extraction through Landsat TM Data, JWSS-Isfahan University of Technology, 19, PP. 35-45 (In Persian with English Abstract).
Ojaghi, S., Ebadi, H. and Farnood Ahmadi, F., 2015. Using artificial neural network for classification of high resolution remotely sensed images and assessment of its performance compared with statistical methods. American Journal of Engineering, Technology and Society, 2(1): 1-8.
Pileforushha, P., Karimi, M., Taleai, M., Farhadi, B.B. & Sharifi, M.A., 2013, Modeling The Required Area For Agricultural Products Using Multi-Objective Programming Method And GIS (In Persian with English Abstract).
Pontius Jr., R.G. & Millones, M., 2011, Death to Kappa: Birth of Quantity Disagreement and Allocation Disagreement for Accuracy Assessment, International Journal of Remote Sensing, 32, PP. 4407-4429.
Rahimzadegan, M. & Pourgholam, M., 2017, Identification of The Area Under Cultivation of Saffron Using Landsat-8 Temporal Satellite Images (Case Study: Torbat Heydarieh) (In Persian with English Abstract), Journal of Rs And Gis for Natural Resources (Journal of Applied Rs and Gis Techniques in Natural Resource Science), 7(4).
Reby, D., Lek, S., Dimopoulos, I., Joachim, J., Lauga, J. & Aulagnier, S., 1997, Artificial Neural Networks as a Classification Method in the Behavioural Sciences, Behavioural Processes, 40, PP. 35-43.
Riahi, V., Zeaiean Firouzabadi, P., Azizpour, F. & Darouei, P., 2019, Identification and Investigation of the Area under Cultivation in Lenjanat Using Landsat 8 Satellite Images, Scientific Journals Management System, 19, PP. 147-169 (In Persian with English Abstract).
Richards, J.A., 2013, Correcting and Registering Images, Remote Sensing Digital Image Analysis, PP. 27-77.
Samadzadegan, F., Hasani, H. & Schenk, T., 2012, Simultaneous Feature Selection and SVM Parameter Determination inClassification of Hyperspectral Imagery Using ant Colony Optimization. Canadian Journal of Remote Sensing, 38, PP. 139-156.
Sebastian, S., 2002. Multi Perceptreon and back Propagation Learning, 9.641 Lecture4. September, Access: http://doi, 10, 8968.
Shanani, H.S.M. & Zarei, H., 2016, Investigation of Land Use Changes during the Past Two Last Decades (Case Study: Abolabas Basin), Journal of Watershed Management Research, 7(14) (In Persian with English Abstract).
Suykens, J.A. & Vandewalle, J., 1999, Chaos Control Using LeastSquares Support Vector Machines, International journal of circuit theory and applications, 27, PP. 605-615.
Svozil, D., Kvasnicka, V. & Pospichal, J., 1997, Introduction to Multi-Layer Feed-Forward Neural Networks, Chemometrics and intelligent laboratory systems, 39, PP. 43-62.
Szuster, B. W., Chen, Q. and Borger, M., 2011. A comparison of classification techniques to support land cover and land use analysis in tropical coastal zones. Applied Geography, 31: 525-532.
Vapnik, V., 2013, The Nature of Statistical Learning Theory, Springer Science & Business Media.
Watts, D.C., 2001, Land Cover Mapping by Combinations of Multiple Artificial Neural Networks, University of Calgary.
Weston, J. & Watkins, C., 1998, Multi-Class Support Vector Machines, In: Citeseer.
Yousefi, S., Tazeh, M., Mirzaee, S., Moradi, H. R. and Tavangar, Sh., 2011. Comparison of different classification algorithms in satellite imagery to produce land use maps (Case study: Noor city). Journal of Applied RS & GIS Techniques in Natural Resource Science, 2 (2): 15-24.
Yuan, H., 2002, Development and Evaluation of Advanced Classification Systems Using Remotely SensedData for Accurate Land-Use/Land-Cover Mapping, Ph.D. Thesis.
Zhang, X., Sun, R., Zhang, B. & Tong, Q., 2008, Land Cover Classification of the North China Plain Using MODIS_EVI Time Series, ISPRS Journal of Photogrammetry and Remote Sensing, 63, PP. 476-484.