Estimation of the train wheat under cultivation area using Sentinel-2 satellite images (Case study: Sojasroud region, Khodabandeh city, Zanjan province)

Wheat is one of the strategic agricultural products in Iran and the world. Having statistics data and information about the area under cultivation of this crop and estimating the amount of its production in one crop year can help the planners of agriculture and industry parts in order to manage the production and consumption of the mentioned product as effectively as possible. One of the tools that can calculate the area under wheat cultivation in the shortest time and with low cost and appropriate accuracy is the remote sensing system. In this study, the area under cultivation of rain wheat crop in Sojasroud village of Khodabandeh city of Zanjan province was estimated using multi-time satellite images of Sentinel-2 measuring satellite and its results were compared with the agricultural cadastral map of 2017-2018. Supervised classification and two methods of support vector machine and maximum likelihood were used to extract information and by comparing the two methods, the most appropriate method was selected and suggested. The error matrix was used to evaluate the accuracy of the classification. The overall accuracy of the support vector machine method was 89% with a capa coefficient of 0.80 and in the maximum llikelihood method it was 88% with a capa coefficient of 0.79. The evaluation results showed that the support sector machine classification method has a higher accuracy than the maximum likelithood, so to extract the area under cultivation in the study area, the support vector Machine classification method is proposed. Comparison of the results of the area under cultivation with the statistics of Jihad Keshavarzi showed a deviation of 18% and the amount of wheat crop using the area under cultivation obtained by classification method was compared with the statistics of the Rural Cooperative Organization which showed a deviation of 17%. The results showed that the classification of the support vector machine is an acceptable and appropriate method for identifying and separating wheat from other agricultural crops.