Penggunaan Metode Machine Learning Random Forest untuk Prediksi Longsor pada Kabupaten Karanganyar
DOI:
https://doi.org/10.32585/modulus.v5i2.4489Keywords:
longsor, Random Forest, ten-folds cross validationAbstract
Tanah longsor adalah salah satu bencana alam yang banyak terjadi di Indonesia terutama Provinsi Jawa Tengah, dengan salah satu daerah yang memiliki kerawanan longsor yang cukup tinggi adalah Kabupaten Karanganyar. Penelitian ini dilakukan untuk menyediakan informasi mengenai kerawanan longsor wilayah Kabupaten Karanganyar dalam suatu bentuk peta yang nantinya dapat dijadikan sebagai sumber tinjauan informasi yang detail dalam upaya mitigasi bencana. Penelitian ini akan memertimbangkan sembilan faktor pengondisi longsor, yaitu jarak terhadap jalan sekunder dan tersier, elevasi, slope, Topographic Wetness Index (TWI), tataguna lahan, litologi, Normalized Difference Vegetation Index (NDVI), dan hujan. Penyusunan peta kerawanan longsor dilakukan menggunakan machine learning dengan metode Random Forest pada pengaturan parameter default dengan bantuan modul Scikit Learn. Validasi model dilakukan menggunakan metode ten-folds cross validation. Hasil prediksi longsor selanjutnya diklasifikasikan men-jadi lima kelas kerawanan longsor menggunakan metode Natural Breaks (Jenk’s) yang performanya akan dievaluasi dengan nilai landslide density. Hasil penelitian ini menunjukkan bahwa metode machine learn-ing Random Forest dapat digunakan untuk memetakan wilayah kerawanan longsor pada Kabupaten Ka-ranganyar. Model yang dihasilkan mampu mengklasifikasikan seluruh wilayah kerawanan longsor dengan nilai AUC mencapai 0,9678, serta menunjukkan hasil klasifikasi yang baik ditandai dengan semakin meningkatnya nilai landslide density pada kelas kerawanan yang semakin tinggi.Downloads
References
Akinci, H. (2022). Assessment of rainfall-induced landslide susceptibility in Artvin, Turkey using machine learning techniques. Journal of African Earth Sciences, 191. https://doi.org/10.1016/j.jafrearsci.2022.104535
Arabameri, A., Saha, S., Roy, J., Chen, W., Blaschke, T., & Bui, D. T. (2020). Landslide susceptibility evaluation and management us-ing different machine learning methods in the Gallicash River Watershed, Iran. Remote Sensing, 12(3). https://doi.org/10.3390/rs12030475
ASTER Global Digital Elevation Model V003 | Earthdata Search. (2013). https://search.earthdata.nasa.gov/search/
Badan Nasional Penanggulangan Bencana. (2023). Data Informasi Bencana Indonesia (DIBI). In Juni 2023. http://dibi.bnpb.go.id/dibi/
Çellek, S. (2020). Effect of the Slope Angle and Its Classication on Landslide. https://doi.org/10.21203/rs.3.rs-61660/v1
Chang, K. T., Merghadi, A., Yunus, A. P., Pham, B. T., & Dou, J. (2019). Evaluating scale ef-fects of topographic variables in landslide susceptibility models using GIS-based ma-chine learning techniques. Scientific Reports, 9(1), 1–21. https://doi.org/10.1038/s41598-019-48773-2
Fitria, I. (2021). Elimination Of Factors In Land-slide Vulnerability Risk Mapping Model Based On Artificial Intelligence System.
Goddard Earth Sciences Data and Information Services Center (GES DISC) by NASA. (2020). https://disc.gsfc.nasa.gov/
Grabowski, D., Laskowicz, I., Małka, A., & Ru-binkiewicz, J. (2022). Geoenvironmental conditioning of landsliding in river valleys of lowland regions and its significance in land-slide susceptibility assessment: A case study in the Lower Vistula Valley, Northern Poland. Geomorphology, 419(October). https://doi.org/10.1016/j.geomorph.2022.108490
Hammad Khaliq, A., Basharat, M., Talha Riaz, M., Tayyib Riaz, M., Wani, S., Al-Ansari, N., Ba Le, L., & Thi Thuy Linh, N. (2022). Spa-tiotemporal landslide susceptibility mapping using machine learning models: A case study from district Hattian Bala, NW Himalaya, Pa-kistan. Ain Shams Engineering Journal. https://doi.org/10.1016/j.asej.2022.101907
He, Q., Shahabi, H., Shirzadi, A., Li, S., Chen, W., Wang, N., Chai, H., Bian, H., Ma, J., Chen, Y., Wang, X., Chapi, K., & Ahmad, B. Bin. (2019). Landslide spatial modelling using novel bivariate statistical based Naïve Bayes, RBF Classifier, and RBF Network machine learning algorithms. Science of the Total En-vironment, 663, 1–15. https://doi.org/10.1016/j.scitotenv.2019.01.329
Li, Y., & Chen, W. (2020). Landslide susceptibil-ity evaluation using hybrid integration of ev-idential belief function and machine learning techniques. Water (Switzerland), 12(1). https://doi.org/10.3390/w12010113
Liao, M., Wen, H., & Yang, L. (2022). Identifying the essential conditioning factors of landslide susceptibility models under different grid resolutions using hybrid machine learning: A case of Wushan and Wuxi counties, China. Catena, 217. https://doi.org/10.1016/j.catena.2022.106428
Marzuki, T. (2021). Pembuatan Script Pemetaan Wilayah Resiko Kerentanan Longsor Ber-basis Sistem Kecerdasan Buatan.
Meinhardt, M., Fink, M., & Tünschel, H. (2015). Landslide susceptibility analysis in central Vietnam based on an incomplete landslide inventory: Comparison of a new method to calculate weighting factors by means of biva-riate statistics. Geomorphology, 234, 80–97. https://doi.org/10.1016/j.geomorph.2014.12.042
Merghadi, A., Yunus, A. P., Dou, J., Whiteley, J., ThaiPham, B., Bui, D. T., Avtar, R., & Abder-rahmane, B. (2020). Machine learning meth-ods for landslide susceptibility studies: A comparative overview of algorithm perfor-mance. Earth-Science Reviews, 207(September 2019), 103225. https://doi.org/10.1016/j.earscirev.2020.103225
MODIS Web - NASA. (2022). https://modis.gsfc.nasa.gov/
Pourghasemi, H. R., & Rahmati, O. (2018). Pre-diction of the landslide susceptibility: Which algorithm, which precision? Catena, 162(May 2017), 177–192. https://doi.org/10.1016/j.catena.2017.11.022
Prawiradisastra Peneliti TLWB-TPSA BPPT, S., & Thamrin No, J. (n.d.). ANALISIS MORFOLOGI DAN GEOLOGI BENCANA TANAH LONGSOR DI DESA LEDOKSARI KABUPATEN KARANGANYAR.
Priyono, K. D., Jumadi, Saputra, A., & Fikriyah, V. N. (2020). Risk analysis of landslide im-pacts on settlements in Karanganyar, Central Java, Indonesia. International Journal of GEOMATE, 19(73), 100–107. https://doi.org/10.21660/2020.73.34128
Shapefile Geologi Seluruh Indonesia - INDONESIA GEOSPASIAL. (2020). https://www.indonesia-geospasial.com/2020/03/download-data-shapefile-shp-geologi-se.html
Sun, D., Gu, Q., Wen, H., Xu, J., Zhang, Y., Shi, S., Xue, M., & Zhou, X. (2022). Assessment of landslide susceptibility along mountain highways based on different machine learn-ing algorithms and mapping units by hybrid factors screening and sample optimization. Gondwana Research. https://doi.org/10.1016/j.gr.2022.07.013
Yang, C., Liu, L. L., Huang, F., Huang, L., & Wang, X. M. (2022). Machine learning-based landslide susceptibility assessment with op-timized ratio of landslide to non-landslide samples. Gondwana Research. https://doi.org/10.1016/j.gr.2022.05.012
Yang, D., Xu, P., Zaman, A., Alomayri, T., Houda, M., Alaskar, A., & Javed, M. F. (2023). Com-pressive strength prediction of concrete blended with carbon nanotubes using gene expression programming and random forest: hyper-tuning and optimization. Journal of Materials Research and Technology, 24, 7198–7218. https://doi.org/10.1016/j.jmrt.2023.04.250
Youssef, A. M., & Pourghasemi, H. R. (2021). Landslide susceptibility mapping using ma-chine learning algorithms and comparison of their performance at Abha Basin, Asir Re-gion, Saudi Arabia. Geoscience Frontiers, 12(2), 639–655. https://doi.org/10.1016/j.gsf.2020.05.010
Zhao, L., Liu, M., Song, Z., Wang, S., Zhao, Z., & Zuo, S. (2022). Regional-scale modeling of rainfall-induced landslides under random rainfall patterns. Environmental Modelling and Software, 155. https://doi.org/10.1016/j.envsoft.2022.105454
Zhou, X., Wen, H., Zhang, Y., Xu, J., & Zhang, W. (2021). Landslide susceptibility mapping us-ing hybrid random forest with GeoDetector and RFE for factor optimization. Geoscience Frontiers, 12(5). https://doi.org/10.1016/j.gsf.2021.101211
Published
Issue
Section
License
Copyright (c) 2023 Rahayu Kusumawati, Raden Harya Dananjaya, Niken Silmi Surjandari
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
