Land cover change detection using random forest algorithm on multitemporal satellite imagery
Keywords:
Change Detection, Land Cover, Multitemporal, Random Forest Algorithm, SatelliteAbstract
Changes in land cover contribute significantly to alterations in temperature and the environment. Human activity is the primary driver of these land cover changes. Detecting land cover change is essential to determine the magnitude of the shifts occurring on the land surface. In practice, detection can be conducted through direct observation or by utilizing remote sensing. Remote sensing produces multitemporal imagery as a primary data source. This multitemporal imagery can be processed and analyzed using various methods to identify the changes that have occurred in land cover. With technological advancements, implementing machine learning for this task can help optimize resources for land cover change detection. Machine learning models built with the Random Forest algorithm yield accurate detection within the target areas. The Random Forest algorithm is an appropriate choice due to its capability to process complex and imbalanced data using decision tree methods. The model in this study achieved an accuracy of 0.9641, or 96.41%, with model evaluation performed using a confusion matrix. Land cover change detection using machine learning produces results with high accuracy. Consequently, policies regarding land cover change can be formulated by considering climate change mitigation and efforts to preserve the environment for the well-being of all living things
References
J. TOWNSHEND and C. JUSTICE, “Information extraction from remotely sensed data.,” Int. J. Remote Sens., vol. 2, no. 4, pp. 313–329, Oct. 1981, doi: 10.1080/01431168108948367.
[2] P. Wibisono, N. Miladan, and R. P. Utomo, “Hubungan Perubahan Kerapatan Vegetasi dan Bangunan terhadap Suhu Permukaan Lahan: Studi Kasus di Aglomerasi Perkotaan Surakarta,” Desa-Kota, vol. 5, no. 1, p. 148, 2023, doi: 10.20961/desa-kota.v5i1.63639.148-162.
[3] S. A. Al Mukmin, A. P. Wijaya, and A. Sukmono, “Analisis Pengaruh Perubahan Tutupan Lahan Terhadap Distribusi Suhu Permukaan dan Keterkaitannya Dengan Fenomena Urban Heat Island,” J. Geod. Undip, vol. 5, no. 1, pp. 224–233, 2016, [Online]. Available: https://doi.org/10.14710/jgundip.2016.10594%0Ahttps://ejournal3.undip.ac.id/index.php/geodesi/article/view/10594
[4] G. Biau and E. Scornet, “A random forest guided tour,” TEST, vol. 25, no. 2, pp. 197–227, 2016, doi: 10.1007/s11749-016-0481-7.
[5] W. Wardhana, J. Sartohadi, L. Rahayu, and A. Kurniawan, “Analisis Transisi Lahan di Kabupaten Gunungkidul dengan Citra Penginderaan Jauh Multi Temporal,” J. Ilmu Kehutan., vol. 6, no. 2, p. 89, 2015, doi: 10.22146/jik.5737.
[6] S. Huang, L. Tang, J. P. Hupy, Y. Wang, and G. Shao, “A commentary review on the use of normalized difference vegetation index (NDVI) in the era of popular remote sensing,” J. For. Res., vol. 32, no. 1, pp. 1–6, 2021, doi: 10.1007/s11676-020-01155-1.
[7] K. P. Widiatmika, “No 主観的健康感を中心とした在宅高齢者における 健康関連指標に関する共分散構造分析Title,” Etika Jurnalisme Pada Koran Kuning Sebuah Stud. Mengenai Koran Lampu Hijau, vol. 16, no. 2, pp. 39–55, 2015.
[8] N. R. Hasna, A. Setiawan, and H. A. Parhusip, “Penentuan Lokasi Lumbung Pangan Berdasarkan Gravity Location Models dengan Koordinat UTM di Provinsi Maluku Utara,” J. Sains dan Edukasi Sains, vol. 1, no. 2, pp. 7–16, 2018, doi: 10.24246/juses.v1i2p7-16.
[9] E. Sediyono, “The use of google maps and universal transverse mercator (UTM) coordinate in land measurement of region in different zone,” J. Theor. Appl. Inf. Technol., vol. 96, pp. 8071–8080, Dec. 2018.
[10] S. Li, L. Xu, Y. Jing, H. Yin, X. Li, and X. Guan, “High-quality vegetation index product generation: A review of NDVI time series reconstruction techniques,” Int. J. Appl. Earth Obs. Geoinf., vol. 105, p. 102640, 2021, doi: 10.1016/j.jag.2021.102640.
[11] A. Huete, K. Didan, T. Miura, E. P. Rodriguez, X. Gao, and L. G. Ferreira, “Overview of the radiometric and biophysical performance of the MODIS vegetation indices,” Remote Sens. Environ., vol. 83, no. 1, pp. 195–213, 2002, doi: https://doi.org/10.1016/S0034-4257(02)00096-2.
[12] F. Baret, G. Guyot, and D. J. Major, “TSAVI: A Vegetation Index Which Minimizes Soil Brightness Effects On LAI And APAR Estimation,” in 12th Canadian Symposium on Remote Sensing Geoscience and Remote Sensing Symposium, 1989, pp. 1355–1358. doi: 10.1109/IGARSS.1989.576128.
[13] H. A. Salman, A. Kalakech, and A. Steiti, “Random Forest Algorithm Overview,” Babylonian J. Mach. Learn., vol. 2024, pp. 69–79, 2024, doi: 10.58496/bjml/2024/007.
[14] E. Helmud, E. Helmud, F. Fitriyani, and P. Romadiana, “Classification Comparison Performance of Supervised Machine Learning Random Forest and Decision Tree Algorithms Using Confusion Matrix,” J. Sisfokom (Sistem Inf. dan Komputer), vol. 13, no. 1, pp. 92–97, 2024, doi: 10.32736/sisfokom.v13i1.1985.
[15] D. K. Barupal and O. Fiehn, “Generating the blood exposome database using a comprehensive text mining and database fusion approach,” Environ. Health Perspect., vol. 127, no. 9, pp. 2825–2830, 2019, doi: 10.1289/EHP4713.
[16] T. B. Kshetri, “Volume II Geomatics for Sustainable Development NDVI, NDBI AND NDWI CALCULATION USING LANDSAT 7 AND 8,” GeoWorld, vol. Volume II, no. May, 2018, [Online]. Available: https://www.researchgate.net/publication/327971920
[17] C. He, P. Shi, D. Xie, and Y. Zhao, “Improving the normalized difference built-up index to map urban built-up areas using a semiautomatic segmentation approach,” Remote Sens. Lett., vol. 1, no. 4, pp. 213–221, Dec. 2010, doi: 10.1080/01431161.2010.481681.
[18] Y. Zha, J. Gao, and S. Ni, “Use of normalized difference built-up index in automatically mapping urban areas from TM imagery,” Int. J. Remote Sens., vol. 24, no. 3, pp. 583–594, Jan. 2003, doi: 10.1080/01431160304987.
[19] B. Gao, “NDWI—A normalized difference water index for remote sensing of vegetation liquid water from space,” Remote Sens. Environ., vol. 58, no. 3, pp. 257–266, 1996, doi: https://doi.org/10.1016/S0034-4257(96)00067-3.
[20] H. Xu, “Extraction of urban built-up land features from landsat imagery using a thematic-oriented index combination technique,” Photogramm. Eng. Remote Sensing, vol. 73, no. 12, pp. 1381–1391, 2007, doi: 10.14358/PERS.73.12.1381.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Machine Intelligence for Societal Advancement
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
