MACHINE LEARNING OPTIMIZATION IN THE FLOOD PRONE AREA MAPPING SYSTEM

Zulham Sitorus; Eko Hariyanto; Fahmi Kurniawan

Zulham Sitorus Universitas Pembangunan Panca Budi
Eko Hariyanto Universitas Pembangunan Panca Budi
Fahmi Kurniawan Universitas Pembangunan Panca Budi

Abstract

One of the areas in Batu Bara Regency, Pahlawan Village, Tanjung Tiram District, has an area of 173.79 km² and is located in a lowland area with an altitude of 0.-4.5m which is directly adjacent to the Malacca Strait to the east. Where almost half of the area is affected by sea tides, Hero Village has a tropical climate with two seasons namely the rainy season and the dry season. The people who live in Pahlawan Village, Tanjung Tiram District. There are so many obstacles faced by the people of Pahlawan Village, including the problem of flooding which has an impact on the health and the economy of the community. Lack of counseling and knowledge, as well as public awareness of the occurrence of flooding during high tides, and when the rainy season will increase the water discharge at sea level will rise so that it can cause flooding. Due to the occurrence of floods, and the impact of losses that affect material and non-material, it is very important to map flood-prone areas for regional development planning. Identification of potential floods involves machine learning using the Random Forest method, taking into account the factors that trigger floods. The Random Forest method also provides sensitivity parameters using the Receiver Operating Characteristic (ROC) curve which shows flood-prone areas such as Pahlawan Village, Tanjung Tiram District.

Author Biographies

Zulham Sitorus, Universitas Pembangunan Panca Budi

Computer System

Eko Hariyanto, Universitas Pembangunan Panca Budi

Computer System

Fahmi Kurniawan, Universitas Pembangunan Panca Budi

Computer System

References

Ameliola, S, Nugraha. 2013. Perkembangan Media Informasi dan Teknologi TerhadapAnak dalam Era Globalisasi. Malang : Universitas Brawijaya. http://icssis.files.wordpress.com/2013/09/2013-0229.pdf. Diakses 12 januari 2017.

Amril Mutoi Siregar, 2018 “Penerapan Algoritma K-Means Untuk Pengelompokan Daerah Rawan Bencana di Indonesia” (Information System Journal), 2018.

Arya Febriansyah1 , Alhuda Ramadhan2 , Mokhamad Gustiawan3 , Muhammad Revin R4 , Rahmaniza Maulana5 , Ristu Juli Y6 , Rollando G.E 7 , Ricky Firmansyah, (2020) Penerapan Machine Learning Dalam Mitigasi Banjir Menggunakan Data Mining, Jurnal Nasional Komputasi dan Teknologi Informasi Vol. 3 No. 3, Desember 2020 P-ISSN 2620-8342 E-ISSN 2621-3052.

Ahmed M. Al-Areeq, S. I. Abba, Mohamed A. Yassin, Mohammed Benaafi, Mustafa Ghaleb and Isam H. Aljundi 2022, Computational Machine Learning Approach for Flood Susceptibility Assessment Integrated with Remote Sensing and GIS Techniques from Jeddah, Saudi Arabia, Remote Sens. 2022, 14, 5515. https://doi.org/10.3390/rs14215515.

Hahn, P. (2019). Artificial intelligence and machine learning. Handchirurgie Mikrochirurgie Plastische Chirurgie, 51(1), 62–67. https://doi.org/10.1055/a-0826-4789.

Ligal Sebastian, 2008, Pendekatan Pencegahan Dan Penanggulangan Banjir Flood Prevention and Control Approach, Dinamika TEKNIK SIPIL, Volume 8, Nomor 2, Juli 2008 : 162 – 169.

LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE. 86(11):2278-232.

Niode, F Dennis, Rinde Yaulie, dan Karouw Stanley. 2016. “Geographical Information System (GIS) untuk Mitigasi Bencana Alam Banjir di Kota Manado”. Manado: Universitas Sam Ratuangi. Jurnal Teknik Elektro dan Komputer. Vol.5 No.2 Januari-Maret, ISSN:2301-8402.

Nenden Siti Fatonah, 2021 “Penerapan Deteksi Bencana Banjir Menggunakan Metode Machine Learning”, Jurnal Format Volume 10 Nomor 2 Tahun 2021 :: ISSN : 2089 – 5615 :: E-ISSN : 2722 – 7162.

http://cs231n.github.io/convolutional-networks