Classification of the Agricultural Crops Using Landsat-8 NDVI Parameters by Support Vector Machine

Abstract

Along with the data obtained from the developing remote sensing technologies, the use of machine learning techniques is widely employed in classification at a more effective and precise level. In this study, support vector machines (SVM) technique, one of the machine learning approaches, was utilized with the help of data obtained from satellite image, and it was aimed to classify agricultural products. Moreover, lentil and wheat products were employed for object detection, and Landsat-8 satellite was preferred as satellite imagery. In order to determine the plant indexes in the image, Landsat-8 image of the development period of agricultural products dated May 6, 2018 was used and 98 sample points were taken with the help of GPS on the pilot area. After that, the position of these points were transferred to Landsat-8 satellite image employing the QGIS program and NDVI values were calculated from these points, which corresponds to Landsat-8 NDVI image pixels. The obtained NDVI values were then utilized in the SVM as inputs. As a result, the accuracy of the overall system for crop classification on the pilot area was computed as 83.3%.

Keywords

• Remote Sensing
• SVM
• Landsat-8
• NDVI
• Crop Classification

References

1. [1] Q. Weng, "Introduction to Remote Sensing Systems, Data, Applications."Remote Perception of Natural Resources July 2013, pp 3-20
2. [2] T. Kavzoğlu, and İ. Çölkesen, "Remote Sensing Technologies and Applications." Sustainable Land Management Workshop In Turkey, 26-27 May 2011.
3. [3] Huang, J., Blanz, V., & Heisele, B. (2002, August). Face recognition using component-based SVM classification and morphable models. In International Workshop on Support Vector Machines (pp. 334-341). Springer, Berlin, Heidelberg.
4. [4] Kobayashi, N., Tani, H., Wang, X., & Sonobe, R. (2020). Crop classification using spectral indices derived from Sentinel-2A imagery. Journal of Information and Telecommunication, 4(1), 67-90.
5. [5] Htitiou, A., Boudhar, A., Lebrini, Y., Hadria, R., Lionboui, H., & Benabdelouahab, T. (2020). A comparative analysis of different phenological information retrieved from Sentinel-2 time series images to improve crop classification: A machine learning approach. Geocarto International, (just-accepted), 1-20.
6. [6] Acar, E., & ÖZERDEM, M. S. (2020). On a yearly basis prediction of soil water content utilizing sar data: a machine learning and feature selection approach. Turkish Journal of Electrical Engineering & Computer Sciences, 28(4), 2316-2330.
7. [7] Chakhar, A., Ortega-Terol, D., Hernández-López, D., Ballesteros, R., Ortega, J. F., & Moreno, M. A. (2020). Assessing the Accuracy of Multiple Classification Algorithms for Crop Classification Using Landsat-8 and Sentinel-2 Data. Remote Sensing, 12(11), 1735.
8. [8] Nasa U.S. Geological Survey. Landsat Data Continuity Mission ,February 2013, pp.1-17.

9. [9] A. Gönenç, " Comparison of NDVI and RVI Vegetation Indices Using Satellite Images. " 2019 Master Thesis, D.Ü, Institute of Science, Diyarbakır, 22-56
10. [10] N. Kobayashi, T.Tani, X. Wang, R. Sonobe, "Product classification using spectral indices derived from Sentinel-2A images, " 2019.
11. [11] Gonenc, A., OZERDEM, M. S., & Emrullah, A. C. A. R. (2019, July). Comparison of NDVI and RVI Vegetation Indices Using Satellite Images. In 2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics) (pp. 1-4). IEEE.
12. [12] P. Kumar, D.K. Gupta, V.N. Mishra, R. Prasad, "Comparison of spectral angle matching algorithms for crop classification using support vector machine, artificial neural network, and LISS IV data." International Journal of Remote Sensing 2015.