Analisis Metode Klasifikasi Pemetaan Tutupan Lahan (Land Cover) di Area Kota Bandung Menggunakan Algoritma Random Forest Pada Google Earth Engine

Hajiar Yuliana; Zahra Cahya Hanifa Rizqiana

doi:10.55893/epsilon.v22i2.119

Hajiar Yuliana
Zahra Cahya Hanifa Rizqiana

DOI: https://doi.org/10.55893/epsilon.v22i2.119

Keywords: Random Forest, Google Earth Engine, Sentinel-2, Land Cover

Abstract

This research aims to map land cover in Bandung City using the Random Forest (RF) algorithm implemented on the Google Earth Engine (GEE) cloud-based platform. Sentinel-2 satellite image data was used to analyze four main classes of land cover, namely residential land, green land, water, and open land. The classification process involved initial data processing, model training using sample data, and accuracy evaluation through confusion matrix and cross-validation. The results showed that the RF algorithm had an overall accuracy of 89%, with the highest accuracy in the residential land class (92%) and the lowest in the water class (80%). Cross-validation showed stable performance with an average accuracy of 88.5%, precision 0.91, recall 0.88, and F1-score 0.89. Confusion matrix analysis identified misclassification in certain classes due to spectral overlap, especially between green land and open area. This research proves that the RF algorithm in GEE is an efficient and accurate method for land cover classification, while supporting spatial planning and environmental management. Further developments could include the use of higher resolution data, advanced learning algorithms and time-based analysis to understand the dynamics of land cover change.

References

T. N. Phan, V. Kuch, and L. W. Lehnert, “Land Cover Classification Using Google Earth Engine and Random Forest Classifier—The Role of Image Composition,” Remote Sens., vol. 12, no. 15, p. 2411, 2020, doi: 10.3390/rs12152411.
[2] M. Mahdavifard, S. K. AHANGAR, B. Feizizadeh, K. V. Kamran, and S. Karimzadeh, “Spatio-Temporal Monitoring of Qeshm Mangrove Forests Through Machine Learning Classification of SAR and Optical Images on Google Earth Engine,” Int. J. Eng. Geosci., vol. 8, no. 3, pp. 239–250, 2023, doi: 10.26833/ijeg.1118542.
[3] V. Eisavi, S. Homayouni, A. M. Yazdi, and A. Alimohammadi, “Land Cover Mapping Based on Random Forest Classification of Multitemporal Spectral and Thermal Images,” Environ. Monit. Assess., vol. 187, no. 5, 2015, doi: 10.1007/s10661-015-4489-3.
[4] A. A. Kuntoro, A. W. Putro, M. S. B. Kusuma, and S. Natasaputra, “The Effect of Land Use Change to Maximum and Minimum Discharge in Cikapundung River Basin,” 2017, doi: 10.1063/1.5011621.
[5] N. Ponganan, T. Horanont, K. Artlert, and P. Nuallaong, “Land Cover Classification using Google Earth Engine’s Object-oriented and Machine Learning Classifier,” 2021 2nd Int. Conf. Big Data Anal. Pract. IBDAP 2021, pp. 33–37, 2021, doi: 10.1109/IBDAP52511.2021.9552099.
[6] A. Tassi, D. Gigante, G. Modica, L. Di Martino, and M. Vizzari, “Pixel-vs. Object-based landsat 8 data classification in google earth engine using random forest: The case study of maiella national park,” Remote Sens., vol. 13, no. 12, 2021, doi: 10.3390/rs13122299.
[7] S. Amini, M. Saber, H. Rabiei-Dastjerdi, and S. Homayouni, “Urban Land Use and Land Cover Change Analysis Using Random Forest Classification of Landsat Time Series,” Remote Sens., vol. 14, no. 11, pp. 1–23, 2022, doi: 10.3390/rs14112654.
[8] S. Xie, L. Liu, X. Zhang, J. Yang, X. Chen, and Y. Gao, “Automatic land-cover mapping using landsat time-series data based on google earth engine,” Remote Sens., vol. 11, no. 24, 2019, doi: 10.3390/rs11243023.
[9] J. Sun and S. Ongsomwang, “Optimal parameters of random forest for land cover classification with suitable data type and dataset on Google Earth Engine,” Front. Earth Sci., vol. 11, no. October, pp. 1–17, 2023, doi: 10.3389/feart.2023.1188093.
[10] V. F. Rodriguez-Galiano, B. Ghimire, J. Rogan, M. Chica-Olmo, and J. P. Rigol-Sanchez, “An assessment of the effectiveness of a random forest classifier for land-cover classification,” ISPRS J. Photogramm. Remote Sens., vol. 67, no. 1, pp. 93–104, 2012, doi: 10.1016/j.isprsjprs.2011.11.002.
[11] A. Jamali, “Land Use Land Cover Mapping Using Advanced Machine Learning Classifiers,” Ekológia (Bratislava), vol. 40, no. 3, pp. 286–300, 2021, doi: 10.2478/eko-2021-0031.
[12] C. Pelletier, S. Valero, J. Inglada, N. Champion, C. M. Sicre, and G. Dedieu, “Effect of Training Class Label Noise on Classification Performances for Land Cover Mapping With Satellite Image Time Series,” Remote Sens., vol. 9, no. 2, p. 173, 2017, doi: 10.3390/rs9020173.