Identifikasi Banjir Rob menggunakan Metode Klasifikasi dengan Model Random Forest dan Decision Tree di Pelabuhan Surabaya Tahun 2021-2023

kiki syalasyatun masfufah -; Kartika Dwi Indra Setyaningrum; Endah Rahmawati; Ady Hermanto

doi:10.26740/ifi.v15n1.p21-29

Authors

kiki syalasyatun masfufah - Universitas Negeri Surabaya
Kartika Dwi Indra Setyaningrum Universitas Negeri Surabaya
Endah Rahmawati Universitas Negeri Surabaya
Ady Hermanto BMKG Tanjung Perak

DOI:

https://doi.org/10.26740/ifi.v15n1.p21-29

Keywords:

banjir rob, random forest, decision tree, klasifikasi, hidrometeorologi, Hydrometeorology, Classification, Tidal flooding

Abstract

Abstrak

Banjir rob merupakan salah satu jenis bencana hidrometeorologi yang kerap terjadi di wilayah pesisir, terutama akibat kombinasi antara pasang laut tinggi, fase bulan tertentu, dan curah hujan ekstrem. Penelitian ini bertujuan untuk mengidentifikasi potensi banjir rob di kawasan Pelabuhan Surabaya dengan menggunakan algoritma klasifikasi Random Forest dan Decision Tree. Data yang digunakan meliputi parameter hidrometeorologi seperti fase bulan, pasang surut air laut, dan curah hujan, yang diperoleh dari Stasiun Meteorologi Maritim Tanjung Perak Surabaya. Sebelum dimodelkan, data melalui tahapan pre-processing berupa normalisasi dan pembobotan untuk menyeragamkan skala antar variabel serta menilai tingkat kontribusi masing-masing parameter. Model dikembangkan dengan pembagian data 80% pelatihan dan 20% pengujian. Hasil evaluasi Random Forest menunjukkan akurasi sebesar 99,96% dan Decision Tree sebesar 99,94% dengan tingkat kesalahan yang sangat rendah. Analisis feature importance menunjukkan bahwa fase bulan dan pasang surut merupakan faktor dominan dalam prediksi banjir rob, sedangkan curah hujan memiliki pengaruh minimal. Temuan ini membuktikan bahwa Random Forest merupakan metode yang efektif dan andal untuk klasifikasi banjir rob serta memiliki potensi untuk diimplementasikan dalam sistem peringatan dini. Penelitian ini juga merekomendasikan integrasi data geografis, seperti informasi kerentanan tanah, morfologi wilayah, dan elevasi permukaan untuk meningkatkan akurasi dan generalisasi model di masa mendatang.

Abstract

Tidal flooding is a type of hydrometeorological disaster that often occurs in coastal areas, mainly due to a combination of high tides, certain lunar phases, and extreme rainfall. This study aims to identify the potential for tidal flooding in the Surabaya Port area using Random Forest and Decision Tree classification algorithms. The data used include hydrometeorological parameters such as lunar phases, tides, and rainfall, obtained from the Tanjung Perak Maritime Meteorology Station in Surabaya. Before being modeled, the data went through pre-processing stages such as normalization and weighting to standardize the scale between variables and assess the level of contribution of each parameter. The model was developed by dividing the data into 80% training and 20% testing. The evaluation results of Random Forest showed an accuracy of 99.96% and Decision Tree at 99.94% with a very low error rate. Feature importance analysis showed that lunar phases and tides are the dominant factors in predicting tidal flooding, while rainfall has a minimal influence. These findings prove that Random Forest is an effective and reliable method for tidal flood classification and has the potential to be implemented in early warning systems. This study also recommends the integration of geographic data, such as soil vulnerability information, regional morphology, and surface elevation to improve the accuracy and generalization of future models.

Downloads

Download data is not yet available.

References

Bevacqua, E., Vousdoukas, M. I., Shepherd, T. G., & Vrac, M. (2019). Future changes in extreme storm surges along Europe. Geophysical Research Letters, 46(3), 1344–1352. https://doi.org/10.1029/2018GL081438

Biggs, J., Wright, T. J., Lu, Z., & Parsons, B. (2013). Multi-interferogram method for measuring interseismic deformation: Denali Fault, Alaska. Geophysical Journal International, 194(2), 753–760. https://doi.org/10.1093/gji/ggt132

Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324

Cutler, D. R., Edwards, T. C., Beard, K. H., Cutler, A., Hess, K. T., Gibson, J., & Lawler, J. J. (2007). Random forests for classification in ecology. Ecology, 88(11), 2783–2792. https://doi.org/10.1890/07-0539.1

Guyon, I., & Elisseeff, A. (2003). An introduction to variable and feature selection. Journal of Machine Learning Research, 3, 1157–1182. https://www.jmlr.org/papers/v3/guyon03a.html

Haigh, I. D., Wahl, T., Rohling, E. J., Price, R. M., Pattiaratchi, C. B., Calafat, F. M., & Dangendorf, S. (2025). Timescales for detecting future changes in sea level extremes. Nature Climate Change, 15, 110–118. https://doi.org/10.1038/s41558-024-02090-2

Han, J., Kamber, M., & Pei, J. (2012). Data mining: Concepts and techniques (3rd ed.). Morgan Kaufmann.

Marfai, M. A., & King, L. (2021). Tidal inundation mapping under enhanced land subsidence in Semarang, Central Java Indonesia. Natural Hazards, 105, 259–281. https://doi.org/10.1007/s11069-020-04338-5

Mobley, R., Kiani, M., & Smith, J. (2021). Machine learning approaches for flood susceptibility mapping. Journal of Hydrology, 603, 127042. https://doi.org/10.1016/j.jhydrol.2021.127042

Nicholls, R. J., Hanson, S., Lowe, J. A., Warrick, R. A., Lu, X., & Long, A. J. (2018). Sea-level rise and its possible impacts given a “beyond 4°C world” in the twenty-first century. Philosophical Transactions of the Royal Society A, 369(1934), 161–181. https://doi.org/10.1098/rsta.2010.0291

Phung, D., Van, T., & Kim, S. (2021). Assessment of tidal flooding using harmonic analysis. Ocean Engineering, 235, 109400. https://doi.org/10.1016/j.oceaneng.2021.109400

Pugh, D. T. (1987). Tides, surges and mean sea-level. John Wiley & Sons.

Quinlan, J. R. (1986). Induction of decision trees. Machine Learning, 1(1), 81–106. https://doi.org/10.1007/BF00116251

Setiawan, H., Nugroho, S. P., & Suryadi, F. X. (2018). Analisis banjir rob di wilayah pesisir Indonesia. Jurnal Teknik Hidraulik, 9(2), 85–94.

Shen, Y., Zhang, X., & Wang, Y. (2022). Nonlinear interactions between tides, storm surge, and river discharge. Journal of Hydrology, 610, 127906. https://doi.org/10.1016/j.jhydrol.2022.127906

Vousdoukas, M. I., Mentaschi, L., Feyen, L., & Voukouvalas, E. (2018). Extreme sea levels on the rise along Europe’s coasts. Earth’s Future, 6(5), 1–20. https://doi.org/10.1029/2018EF000816

Wahl, T., Jain, S., Bender, J., Meyers, S. D., & Luther, M. E. (2015). Increasing risk of compound flooding from storm surge and rainfall. Nature Climate Change, 5, 1093–1097. https://doi.org/10.1038/nclimate2736

Ward, R. C., & Robinson, M. (2000). Principles of hydrology (4th ed.). McGraw-Hill.