Spatiotemporal Analysis of Deforestation and Comparative Accuracy Assessment of Flood Susceptibility Models based on Machine Learning, MCDA, and GFI using Multispectral Satellite Imagery

Daniel Ari Hutapea, Martin Parluhutan Siburian, Fikry Hadi Pradana, Tuti Adeyani Purba, Rizky Rahmansyah

Abstract


Flood disasters are often triggered by deforestation and land cover changes, highlighting the need for precise spatial flood susceptibility modeling. This study aims to analyze the spatiotemporal dynamics of deforestation (2021–2025) in Langsa and compare the accuracy of three flood hazard prediction models: Multi-Criteria Decision Analysis (MCDA), Geomorphic Flood Index (GFI), and Machine Learning using Random Forest. The study employed a quantitative experimental approach through the cloud-computing architecture of Google Earth Engine (GEE) and offline simulation using QGIS to process multispectral Landsat 9 satellite imagery along with landscape physical data. The results indicate a reduction in vegetation cover area of 1,606.12 hectares (-11.48%), which directly contributed to the expansion of built-up areas and open land. Comparative evaluation demonstrated that the Random Forest algorithm achieved the highest flood modeling accuracy, with an Overall Accuracy of 91.17% and a Kappa Coefficient of 0.87, outperforming MCDA, which was prone to over-prediction bias, and GFI, which exhibited algorithmic blind spots in localized pluvial flood areas. Risk exposure analysis further revealed that 38.5% of current built-up infrastructure areas are located within high flood susceptibility zones due to the loss of ecological infiltration areas. The outputs of this modeling process were successfully integrated into an interactive Decision Support System (DSS) based on a WebGIS dashboard to facilitate spatial disaster mitigation dissemination for policymakers.

Keywords


deforestation, flood susceptibility; google earth engine; machine learning; WebGIS

Full Text:

PDF

References


S. Hajji et al., “Enhancing Flood Prediction Through Remote Sensing, Machine Learning, and Google Earth Engine,” Frontiers in Water, Vol. 7, pp. 1–19, Mar. 2025, DOI: 10.3389/frwa.2025.1514047.

S. D. Arlisa and H. H. Handayani, “Flood Vulnerability Analysis using Random Forest Method in Gresik Regency, Indonesia,” IOP Conf. Ser. Earth Environ. SCI., vol. 1127, No. 1, pp. 1–11, 2023, DOI: 10.1088/1755-1315/1127/1/012023.

C. Cahyaningtyas, E. M. Salfarini, and E. Saputra, “Flood Disaster-Induced Water Inundation Potential Monitoring System in Bengkayang Regency based on Remote Sensing Imagery and Machine Learning,” Jurnal Sisfokom (Sistem Informasi dan Komputer), Vol. 15, No. 02, pp. 260–267, Apr. 2026, DOI: 10.32736/sisfokom.v15i02.2597.

P. Ony Andewi, K. Agus Seputra, K. Yota Ernanda Aryanto, L. Joni Erawati Dewi, and F. Teknik dan Kejuruan, “Integrasi Teknologi Penginderaan Jauh dan Machine Learning pada Web GIS untuk Pemetaan Potensi Banjir,” Jurnal Pendidikan Teknologi dan Kejuruan, vOl. 22, No. 1, pp. 12–23, Jan. 2025, DOI: https://doi.org/10.23887/jptkundiksha.v22i1.87455.

N. Ghea Salsabila, M. Sodik Imanudin, and L. Prima, “Spatial Modeling of Flood-Risk Areas in Palembang City, South Sumatera,” Journal of Wetlands Environment Management (JWEM), Vol. 12, No. 1, pp. 31–43, 2024, DOI: https://dx.doi.org/10.20527/ijwem.v12i1.19953.

J. Jumadi et al., “Utilizing Open Access Spatial Data for Flood Risk Mapping: A Case Study in the Upper Solo Watershed,” Geoplanning, Vol. 11, No. 2, pp. 189–204, 2024, DOI: 10.14710/geoplanning.11.2.189-204.

M. R. P. Putra, Muhirin, Kusrini, R. Ashari, and A. W. Z. Imam, “Flood Prediction using Machine Learning Model Integrated with Geographical Information System,” Khazanah Informatika : Jurnal Ilmu Komputer dan Informatika, Vol. 10, No. 2, pp. 121–126, Mar. 2025, DOI: 10.23917/khif.v10i2.3723.

S. E. Purwati and Y. Pristyanto, “Model Random Forest and Support Vector Machine for Flood Classification in Indonesia,” Sinkron : jurnal dan penelitian teknik informatika, Vol. 8, No. 4, pp. 2261–2268, Oct. 2024, DOI: 10.33395/sinkron.v8i4.13973.

A. D. Hariyanto, A. Yudono, and A. D. Wicaksono, “Comparison of Land Cover Change Prediction Models: A Case Study in Kedungkandang District, Malang City,” Geoplanning, Vol. 11, No. 1, pp. 85–98, 2024, DOI: 10.14710/geoplanning.11.1.85-98.

H. A. Katili, Syartinilia, F. Irmansyah, and Widiatmaka, “Land use Change and Future Prediction in Banggai Islands Regency, Central Sulawesi, Indonesia,” Jurnal Pengelolaan Sumberdaya Alam dan Lingkungan (Journal of Natural Resources and Environmental Management), Vol. 15, No. 5, p. 804, 2025, DOI: 10.29244/jpsl.15.5.804.

K. Aditya, I. Ridwan, and Nurlina, “Flood Risk Modelling based on Machine Learning using Google Earth Engine in Hulu Sungai Utara Regency,” Nature Environment and Pollution Technology, Vol. 24, No. 4, Dec. 2025, DOI: 10.46488/NEPT.2025.v24i04.D1756.

C. A. Lizar, H. Satriawan, and C. Azizah, “Analisis Wilayah Kerentanan Bencana Banjir Berbasis Sistem Informasi Geografis di Kota Lhokseumawe,” Teras Jurnal : Jurnal Teknik Sipil, Vol. 14, No. 1, pp. 53–67, Mar. 2024, DOI: 10.29103/tj.v14i1.1004.

H. S. D. Kospa, H. Haidir, A. S. Natul, and S. A. Hamim, “Pendampingan Penyusunan Peta Kerentanan berbasis WebGIS sebagai Upaya Peningkatan Mitigasi Bencana di Kawasan Pembangunan Pelabuhan Tanjung Carat, Banyuasin II, Sumatera Selatan,” I-Com: Indonesian Community Journal, Vol. 5, No. 2, pp. 635–646, Jun. 2025, DOI: 10.70609/icom.v5i2.6738.

M. Rashid et al., “Integrated Data-Driven Multi-Criteria Analysis and Machine Learning Approaches for Assessment of Flood Susceptibility Mapping,” Water 2026, Vol. 18, No. 7, Apr. 2026, DOI: 10.3390/w18070844.

L. S. Qamarani and M. Riasetiawan, “Klasifikasi Level Banjir menggunakan Random Forest dan Support Vector Machine,” Indonesian Journal of Electronics and Instrumentation Systems (IJEIS, Vol. 14, No. 2, pp. 199–208, 2024, DOI: doi.org/10.22146/ijeis.97043.

V. T. Vu et al., “Predicting Land use Effects on Flood Susceptibility using Machine Learning and Remote Sensing in Coastal Vietnam,” Water Pract. Technol., Vol. 18, No. 6, pp. 1543–1555, Jun. 2023, DOI: https://doi.org/10.2166/wpt.2023.088.

R. F. Abuhanifah, F. Usman, and T. A. Rachmawati, “Pemetaan Risiko Bencana Banjir menggunakan Geomorphic Flood Index di Kecamatan Trenggalek, Kabupaten Trenggalek,” Planning for Urban Region and Environment, Vol. 12, No. 4, pp. 217–228, 2023.

A. Ferdiansyah et al., “Modified Geomorphic Flood Index (GFI) using Land use Parameter and Effective Rainfall Ratio at Cikapundung River,” in E3S Web of Conferences, EDP Sciences, Apr. 2024. DOI: 10.1051/e3sconf/202451301003.

R. Rahmansyah and I. Meiditra, “Network Security System Implementation using Intrusion Prevention System and Honeypot Technology at the Regional Revenue Office (Bapenda) of Padang City,” Internet of Things and Artificial Intelligence Journal, Vol. 5, No. 3, pp. 797–817, Sep. 2025, DOI: 10.31763/iota.v5i3.1013.

A. M. Husein and M. Harahap, “Pendekatan Data Science untuk menemukan Churn Pelanggan pada Sector Perbankan dengan Machine Learning,” Data Sciences Indonesia (DSI), Vol. 1, No. 1, pp. 8–13, Nov. 2021, DOI: 10.47709/dsi.v1i1.1169.




DOI: https://doi.org/10.32520/stmsi.v15i5.6441

Article Metrics

Abstract view : 0 times
PDF - 0 times

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.