Pencitraan Banjir Rob Zona Medan Utara Menggunakan Regresi Logistik dan Artificial Neural Network Serta Global Information System

Authors

  • Farino Pyanto Program Studi Teknik Sipil Universitas Al Azhar

DOI:

https://doi.org/10.35965/eco.v23i1.2441

Keywords:

Banjir Rob, Regresi Logistik, Artificial Neural Network, GIS

Abstract

Perlunya memetakan zona terancam banjir rob berdasarkan faktor-faktor penyebab banjir rob di wilayah Medan Utara sebagai dasar bagi stakeholder dalam rangka penanganan banjir rob. Indikator kerawanan terhadap banjir rob mencakup curah hujan, drainage density, land use, jarak ke sungai, jenis tanah, elevasi, kemiringan, aspek, jarak ke muara. Analisis data menggunakan GIS dan regresi logistik serta ANN. Lokasi penelitian adalah kecamatan Belawan, Marelan dan Labuhan. Hasil analisis yang didapat, yaitu faktor curah hujan, drainage density, elevasi, jarak ke muara, aspek berpengaruh terhadap kerawanan banjir rob. Sedangkan indikator land use, jenis tanah, jarak ke sungai, kemiringan tidak berpengaruh terhadap kerawanan banjir rob. Hasil analisis menunjukkan peringkat indikator yang mempengaruhi terhadap kerawanan banjir rob dari pertama sampai sembilan adalah jarak ke muara, elevasi, aspek, jarak ke sungai, jenis tanah, land use, kemiringan, curah hujan dan drainage density. Sampel 209 dengan 9 dan 7 faktor didapat ketepatan model penelitian sebesar 86,1%. Hasil penelitian dengan rumus MAPE menunjukkan akurasi data train percobaan 1 sebesar 64,5662% dan data tes percobaan 1 sebesar 75,7515%. Sementara data train percobaan 2 sebesar 70,5429% dan data tes percobaan 2 sebesar 78,5544%.

The need to map tidal flood threat zones based on the factors that cause tidal floods in the North Medan area as a basis for stakeholders in the context of tidal flood management. Indicators of vulnerability to tidal flooding include rainfall, drainage density, land use, distance to the river, soil type, elevation, slope, aspect, distance to the estuary. The purpose of this study was to map the level of vulnerability to tidal floods in the northern coastal area of Medan and identify the factors that influence tidal flooding. Data analysis using GIS and logistic regression and ANN. The research locations are Belawan, Marelan and Labuhan districts. The results of the analysis obtained, namely the factors of rainfall, drainage density, elevation, distance to the estuary, aspects that influence tidal flood vulnerability. While the indicators of land use, soil type, distance to the river, slope have no effect on tidal flood hazard. The results of the analysis show that the ranking of indicators that affect the tidal flood vulnerability from first to nine is distance to the estuary, elevation, aspect, distance to the river, soil type, land use, slope, rainfall and drainage density. Sample 209 with 9 and 7 factors obtained the accuracy of the research model of 86.1%. The results of the study using the MAPE formula showed that the accuracy of the first trial train data was 64.5662% and the first experimental test data was 75.7515%. While the data for trial 2 was 70.5429% and the data for trial 2 was 78.5544%.

Downloads

Download data is not yet available.

References

Arekhi, Masters. (2011). Modeling spatial pattern of deforestation using GIS and logistic regression: A case study of northern Ilam forests, Ilam province, Iran. African Journal of Biotechnology, 10(72), 16236–16249.

Asfaw, T. N., Tyan, L., Glukhov, A. V, & Bondarenko, V. E. (2020). A compartmentalized mathematical model of mouse atrial myocytes. American Journal of Physiology-Heart and Circulatory Physiology, 318(3), H485–H507

Bernie, Mohammad. 2020. Imbauan BMKG dan Cerita Warga Pesisir Jakarta Hadapi Banjir Rob. https://tirto.id/imbauan-bmkg-cerita-warga-pesisir-jakarta-hadapi-banjir-rob-erPY. (Diakses tanggal 15-01-2020).

Chandra, Aldi. 2020. BMKG Prediksikan Banjir Rob, Warga Diharap Waspada. http://www.economiczone.id/read/413/bmkg-prediksikan-banjir-rob-warga-diharap-waspada. (Diakses tanggal 10-01-2020).

Chang, K. (2016). Geographic Information System. International Encyclopedia of Geography: People, the Earth, Environment and Technology: People, the Earth, Environment and Technology, 1–9.

Darmawan, K., & Suprayogi, A. (2017). Analisis Tingkat Kerawanan Banjir di Kabupaten Sampang menggunakan Metode Overlay dengan Scoring Berbasis Sistem Informasi Geografis. Jurnal Geodesi Undip, 6 (1), 31–40.

Hendayana, R. (2013). Penerapan Metode Regresi Logistik dalam Menganalisis Adopsi Teknologi Pertanian. Informatika Pertanian. 22(1), 1–9.

Falah, F., Rahmati, O., Rostami, M., Ahmadisharaf, E., Daliakopoulos, I. N., & Pourghasemi, H. R. (2019). Artificial neural networks for flood susceptibility mapping in data-scarce urban areas. In Spatial modeling in GIS and R for Earth and Environmental Sciences (. 323–336).

Frederick, H., & Hariadi, H. (2016). Pemetaan Banjir Rob Terhadap Pasang Tertinggi di Wilayah Pesisir Kecamatan Medan Belawan, Sumatera Utara. Journal of Oceanography, 5 (3), 334–339.

Khambali, I., & ST, M. (2017). Manajemen Penanggulangan Bencana. Yogyakarta : Penerbit Andi.

Kurniawan, L. (2014). Kajian Banjir Rob di Kota Semarang (Kasus Dadapsari). Jurnal ALAMI: Jurnal Air, Lahan, Lingkungan, dan Mitigasi Bencana, 8 (2).

Mardiatno, D. (2018). Potensi Sumberdaya Pesisir Kabupaten Jepara. Yogyakarta : UGM PRESS.

Marfai, M. A., & King, L. (2008). Potential vulnerability implications of coastal inundation due to sea level rise for the coastal zone of Semarang city, Indonesia. Environmental Geology, 54(6), 1235–1245.

Montgomery, Douglas C. & Runger, George C. (2014). Applied Statistics and Probability for Engineers. New York : John Wiley & Sons.

Muhari, Abdul. (2021). Banjir Rob Merendam 15.000 Rumah Warga Medan. Badan Nasional Penanggulangan Bencana (https://www.bnpb.go.id/berita/banjib-rob-merendam-15-000-rumah-warga-medan)

Nugraha, A. L., Santosa, P. B., & Aditya, T. (2015). Dissemination of tidal flood risk map using online map in semarang. Procedia Environmental Sciences, 23, 64–71.

Nurdin, R. (2015). Komunikasi dalam Penanggulangan Bencana. Jurnal Simbolika: Research and Learning in Communication Study, 1 (1).

Prawira, M. P., & Pamungkas, A. (2014). Mitigasi Kawasan Rawan Banjir Rob di Kawasan Pantai Utara Surabaya. Jurnal Teknik ITS, 3 (2), C160–C165.

Sanubari, A. R., Kusuma, P. D., Setianingsih, C. (2018). Pemodelan Prediksi Banjir Menggunakan Artificial Neural Network. e-Proceeding of Engineering, 4(3), 6276-6282

Saputra, N. A. (2019). Pemetaan Zona Rawan Banjir Rob di Wilayah Medan Utara dengan AHP dan GIS. Tesis di Universitas Sumatera Utara

Sari, Kartika Indah & Tanjung, Darlina. (2022). Pemetaan Daerah Rawan Bencana Kecamatan Belawan dengan Aplikasi Sistem Informasi Geografis. Journal of Civil Engineering, Building and Transportation, 6 (1), 85-91.

Triana, Y. T., & Hidayah, Z. (2020). Kajian Potensi Daerah Rawan Banjir Rob Dan Adaptasi Masyarakat Di Wilayah Pesisir Utara Surabaya. Juvenil: Jurnal Ilmiah Kelautan Dan Perikanan, 1 (1), 141–150.

Downloads

Published

2023-04-30