Classification of Rice Growth Phases with an Object-Based Approach using Sentinel-2 Imagery
Abstract
Monitoring of rice crops in Indonesia is supported by the local government at the sub-district level. This practice requires a lot of funds and is considered less efficient. Another option is to utilize remote sensing data using Sentinel-2 free satellite imagery to monitor rice growth spatio-temporally and over a wider area. Sentinel-2 is designed to support agricultural monitoring. To monitor the growth phase of rice can be done with a pixel-based classification, but this approach has limitations due to the appearance of salt and pepper that affect the classification results and accuracy. The object-based image analysis approach can overcome this phenomenon and better mimic human perception of objects. This study aims to identify the growth phases of rice in Sentinel-2 imagery using an object-based classification approach, and to monitor the spatio-temporal distribution of rice growth phases. Sentinel-2 imagery with 10 acquisitions in May – August 2021 was analyzed using an object-based approach and the growth phases of rice were classified using the SVM approach. The results show that the growth phase of rice can be identified and classified properly without the salt and pepper phenomenon with an object-based approach from Sentinel-2 multi-temporal imagery. The accuracy of the SVM classification model is good with an average accuracy of 81.60. The object-based SVM classification can map the distribution of rice growth phases consistently and continuously from Sentinel-2 multi-temporal images.
Downloads
References
Blaschke T, Hay GJ, Kelly M, Lang S, Hofmann P, Addink E, Queiroz FR, Freek VDM, Harald VDW, Frieke VC, Tiede D. 2014. Geographic object-based image analysis-towards a new paradigm. ISPRS J Photogram. 87: 180–191.
Blaschke T. 2010. Object based image analysis for remote sensing. ISPRS J Photogramm Remote Sens. 65(1): 2–16.
Boori, M.S., Choudhary, K., Kupriyanov, A.V. 2020. Crop growth monitoring through sentinel and landsat data based ndvi time-series. Comput. Opt. 44 (3): 409–419.
Cai Y, Lin H, Zhang M. 2019. Mapping paddy rice by the object-based random forest method using time series Sentinel-1/Sentinel-2 data. Adv. Space Res. 64: 2233–2244
Congedo L. (2021). Semi-Automatic Classification Plugin Documentation Release 7.9.7.1. Sep 07. 2022. https://buildmedia.readthedocs.org/media/pdf/semiautomaticclassificationmanual/latest/semiautomaticclassificationmanual.pdf (accessed on 29 February 2023).
Huang H, Lanc Y, Yanga A, Zhangd Y, Wene S, Deng J. 2020. Deep learning versus object- based image analysis (OBIA) in weed mapping of UAV imagery. International Journal of Remote Sensing. 41(9) : 3446–3479.
Luo KS, Li RD, Chang BR. 2013. Survey method of large scale land cover based on object classification technology. Journal of University of Chinese Academy of Science. 6(30): 770-777
Kim M, Madden M, Warner T. 2008. Estimation of optimal image object size for the segmentation of forest stands with multispectral IKONOS imagery. In Object-Based Image Analysis; Springer: Berlin/Heidelberg, Germany. pp. 291–307
Laliberte AS, Rango A, Havstad KM, Paris JF, Beck RF, Mcneely R, Gonzalez AL. 2004. Object-oriented image analysis for mapping shrub encroachment from 1937 to 2003 in southern New Mexico. Remote Sens. Environ. 93: 198–210.
Lao RJ, Aguilar MA, Ladisa C, Aguilar FJ, Nemmaoui A. 2022. Multiresolution segmentation for extracting plastic greenhouse from Deimos-2 imagery. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 5(2): 251-259
Mariana N. 2022. Identifikasi umur tanaman padi dengan teknik Support Vector Machine di Bojongpicung Cianjur [skripsi]. Bogor: Institut Pertanian Bogor.
Nirtanto IC, Prasetyo Y, Sasmito B. 2022. Analisis pemodelan fase tumbuh padi menggunakan citra Synthetic Aperture Radar C-Band Sentinel-1. Jurnal Geodesi UNDIP. 11(2):1-10
Nurfaizah D. 2020. Analisis pola termal citra Landsat 8 dan drone thermal pada fase tumbuh padi sawah di Kecamatan Bojongpicung, Kabupaten Cianjur [skripsi]. Bogor: Institut Pertanian Bogor
Phiri D, Morgenrotha J, Xua C, Hermosillab T. 2018. Effects of pre-processing methods on Landsat OLI-8 land cover classification using OBIA and random forests classifier. Int J Appl Earth Obs Geoinformation. 73 : 170–178.
Ramazayandi R. 2021. Citra Sentinel-2 untuk identifikasi fase tumbuh tanaman padi dengan klasifikasi [skripsi]. Bogor: Institut Pertanian Bogor.
Raniah N. 2022. Citra Sentinel-2 untuk klasifikasi umur tanaman padi dengan pendekatan Gaussian Mixture Model [skripsi]. Bogor: Institut Pertanian Bogor.
Rumora L, Miler M, Medak D. 2020. Impact of Various Atmospheric Corrections on Sentinel- 2 Land Cover Classification Accuracy Using Machine Learning Classifiers. ISPRS Int. J. Geo-Inf. 9(277): 1-23.
Wijayanti RS. 2018. Citra Sentinel-2 untuk identifikasi fase tumbuh padi dengan analisis pola reflektan di Kabupaten Cianjur [skripsi]. Bogor : Institut Pertanian Bogor
Yang K, Zhang H, Wang F, Lai R. 2022. Extraction of broad-leaved tree crown based on UAV visible images and OBIA-RF model: A case study for chinese olive trees. Remote Sens. 14 (2469) : 1-23.
Zheng L. 2015. Parameter optimization in multi-scale segmentation of high resolution remotely sensed image and its application in object-oriented classification. Proceedings of the 2015 International Conference on Environmental Engineering and Remote Sensing. 84-90
Copyright (c) 2023 Jurnal Ilmu Tanah dan Lingkungan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Department of Soil Science and Land Resources Departemen Ilmu Tanah dan Sumberdaya Lahan, Faculty of Agriculture Fakultas Pertanian, IPB University
