Hammam Riza, Eko Widi Santoso, Iwan Gunawan Tejakusuma, Firman Prawiradisastra, Prihartanto Prihartanto


Flood disaster is one of predominant disaster event in Indonesia. The frequency and intensity of this disaster tend to increase from year to year as well as the losses caused thereby. To reduce the risks and losses due to flood disasters, innovation in disaster mitigation is needed. Artificial intelligence and machine learning are technological innovations that have been widely applied in various fields of life and can also be used to improve flood disaster mitigation. A literature study conducted in this research shows that the use of artificial intelligence and machine learning has proven to be able, and succeed to fastly and accurately perform flood prediction, flood risk mapping, flood emergency response and, flood damage mapping. ANNs, SVM, SVR, ANFIS, WNN and DTs are popular methods used for flood mitigation in the pre-disaster phase and it is recommended to use a combination or hybrid of these methods. During the flood disaster response phase, the application of artificial intelligence and machine learning are still not much has been done and need to be developed. Examples of the application are the use of big data from social media Twitter and machine learning both supervised learning with Random Forest and unsupervised learning with CNN which have shown good results and have a good prospect to be applied. For the use of artificial intelligence in post-disaster flood phase, are still also rare, because it requires actual data from the field. However, in the future, it will become a promising program for the assessment and application of artificial intelligence in the flood disaster mitigation.

Full Text:



Arinta, R.R. dan E. Andi W.R. 2019. Natural Disaster Application on Big Data and Machine Learning: A Review. Proceeding. The 4th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE) Yogyakarta, Indonesia. 249 – 254.

BNPB. 2020. Data Bencana Indonesia. Badan Nasional Penanggulangan Bencana [terhubung berkala]. https://bnpb.cloud/dibi/ [6 April 2020].

BPPT. 2018. Kongres Teknologi Nasional (KTN) 2018. Badan Pengkajian dan Penerapan Teknologi. [terhubung berkala]. http://ktn.bppt.go.id/ktn2018/ [20 April 2020].

Bui, D.T., K. Khosravi, S. Li, H. Shahabi, M. Panahi, V. P. Singh, K. Chapi, A. Shirzadi, S. Panahi, W. Chen dan B Bin Ahmad. 2018. New Hybrids of ANFIS with Several Optimization Alghorithms for Flood Susceptibility Modeling. Water. 10 (1210): 1-28.

Chang, L., M. Amin, S-N. Yang dan F-J Chang. 2018. Building ANN-Based Regional Multi-Step-Ahead Inundation Forecast Model. Water. 10(1283): 1-18.

ESCAP. 2015. United Nations. Disasters in Asia and the Pacific: 2015 Year in Review. Available online. [terhubung berkala]. https://www.unescap.org/sites/default/files/2015_Year%20in%20Review_final_PDF_1.pdf [15 April 2020].

Darabi, H., B. Choubin., O. Rahmati, A. T. Haghighi, B. Pradhan dan B. Kløve. 2019. Urban Flood Risk Mapping Using the GARP and QUEST Models: A Comparative Study of Machine Learning Techniques. Journal of Hydrology. 569: 142-154.

Fitriyaningsih, I., Y. Basani dan L.M. Ginting. 2018. Web-Based Application Development for Predicting Rainfall, Water Discharge, and Flood Using Machine Learning Method in Deli Serdang, Jurnal Penelitian Komunikasi dan Opini Publik. 22 (2):132-143.

Fujitsu. 2019. Japan: Fujitsu develops AI disaster mitigation technology to predict river flooding with limited data. [terhubung berkala]. https://www.preventionweb.net/ news/ view/67241 [10 April 2020].

Ghaffarian, S., N. Kerle, E. Pasolli dan J.J. Arsanjani. 2019. Post-Disaster Building Database Updating Using Automated Deep Learning: An Integration of Pre-Disaster OpenStreetMap and Multi-Temporal Satellite Data. Remote Sensing. 11 (2427): 1-20.

Kompas. 2018. Penanganan Bencana di Indonesia Masih Jadi Beban APBN. [terhubung berkala]. https://ekonomi. kompas.com/read/2018/10/10/154635126/ penanganan-bencana-di-indonesia-masih-jadi-beban-apbn [12 April 2020].

Mosavi, A., P. Ozturk dan K. Chau. 2018. Flood Prediction Using Machine Learning Models: Literature Review. Water. 10 (1536): 1-40.

Prawiradisastra, F. 2017. Development of Flood Prediction Model Using Adaptive Neuro Fuzzy Inference System (ANFIS) for Ciliwung River. Thesis. IPB University.

Republik Indonesia. 2007. Undang Undang Republik Indonesia Nomor 24 Tahun 2007 tentang Penanggulangan Bencana. [terhubung berkala]. https: //bnpb.go.id/ppid/file/UU_24_2007.pdf [17 April 2020].

Robertson, B.W., M. Johnson, D. Murthy, W.R. Smith dan K. K. Stephens. 2019. Using a Combination of Human Insight and ‘Deep Learning for Real-Time Disaster Communication. Progress in Disaster Science. 2: 1-11.

Sanubari, A.R. 2018. Pemodelan Prediksi Banjir Menggunakan Artificial Neural Network. Skripsi S1. Prodi Sistem Komputer. Fakultas Teknik Elektro. Universitas Telkom.

Moon, S-H., Y-H. Kim, Y.H. Lee, B-R. Moon. 2019. Application of Machine Learning to An Early Warning System for Very Short-Term Heavy Rainfall. Journal of Hydrology 568: 1042-1054.

Shyekhmousa, M., N. Kerle, M. Kuffer dan S. Ghaffarian. 2019. Post-Disaster Recovery Assessment with Machine Learning-Derived Land Cover and Land Use Information. Remote Sensing. 11 (10): 1174.

Soebroto, A.A., I. Cholissodin, R.C. Wihandika, M.T. Frestiyanti dan Z.E. Arif. 2015. Prediksi Tinggi Muka Air (TMA) untuk Deteksi Dini Bencana Banjir Menggunakan SVR-TVIWPSO. Jurnal Teknologi Informasi dan Ilmu Komputer. 2 (2): 79-86.

Wagenaar, D., A. Curran, M. Balbi, A. Bhardwaj, R. Soden, E. Hartato, G.M. Sarica, L. Ruangpan, G. Molinario dan D. Lallemant. 2020. Invited Perspectives: How Machine Learning Will Change Flood Risk and Impact Assessment. Natural Hazard Earth System Sciences. 20: 1149–1161.

Zahra, K., M. Imran dan F.O. Ostermann. 2020. Automatic Identification of Eyewitness Messages on Twitter During Disasters. Information Processing and Management. 57(102107).

DOI: https://doi.org/10.29122/jstmb.v15i1.4145


  • There are currently no refbacks.