Main Article Content

Abstract

Lack of river and watershed management will cause problems and disasters. One of it is the flood that can cause physical, social and economic loss. So countermeasures or flood anticipation are needed by using the Early Warning System (EWS) to provide early information if a flood is going to occur. This study uses five input indicators: temperature, humidity, water discharge, water surface altitude and rainfall data that will produce output in the form of notifications and alarms for the Early Warning System (EWS). Then the input and output data configuration will be processed using a Backpropagation Neural Network. Data used is data recorded in real-time on the research object for two weeks with the composition of training and testing data with a percentage of 80% and 20%. The best backpropagation neural network model used has the input of 5 neurons layer architecture, 15 neurons as the hidden layer and three neurons as the output layer. The flood prediction result uses the Backpropagation Neural Network method, has an RMSE score performance of 2.16e-21 and a percentage success testing system of 91.33%. It shows that the model has an excellent accuracy level.

Article Details

How to Cite
Ani Dwi Ratnasari, Hasin, K., Subagio Soim, Setiawan, B. T., & Afif Zuhri Arfianto. (2022). Flood Detection Using Backpropagation Neural Network Method. Indonesian Journal of Engineering Research, 3(1), 1-10. https://doi.org/10.11594/ijer.v3i1.40

References

[1] Abas, MI, Syukur , A. and Soeleman , MA (2017) ' Prediction Time Sequence Amount Airport Passengers Using Neural Network Algorithm Based on Genetic Algorithm', Jurnal Technology Information , 13(January 2017), pp. 101– 114.
[2] Ary , M. (2017) ' Application Prediction Flooding with Spade' Algorithm , Indonesian Journal on Computer and Information Technology, 2(1), pp. 11–16. Espressif (2019) 'ESP32 Series Datasheet',
[3] Espressif Systems, pp. 1–61. Available at: www.espressif.com.
[4] Fadhilah , RN and Ginardi , RVH (2017) ' Pricing Using the Back Propagation Method in the CariKos E-Commerce Application Web- Based ', ITS Engineering Journal , 6(2). doi : 10.12962/j23373539.v6i2.23978.
[5] Al Fikri , I. (2016) ' Application Navigation Based on Device Moving Using the Wikitude Platform for Study Case ITS' Environment , ITS Engineering Journal , 5(1), pp. 48–51. doi : 10.12962/j23373539.v5i1.14511.
[6] Fitriadini , A. et al. (2020) ' Application of Backpropagation Neural Network in Stock Price Prediction ', Student National Seminar Knowledge Computers and their Applications (SENAMIKA), p. 561.
[7] Hokya , S. (2013) ' Python Programming Handbook ', Books , 84, pp. 487–492. Available at: http://ir.obihiro.ac.jp/dspace/handle/10322/3933 .
[8] Ike, Y. and L. (2018) ' Application Prediction of Rainfall, Water Discharge, and Flood Web-based with Machine Learning in Deli Serdang', Journal of Communication Research and Public Opinion, 22(2), pp. 150–160.
[9] Joni, W. (2019) ' Do'a and Iqro' E - Learning System in Enhancing the Learning Process in Kindergarten Amal Ikhlas', Journal Student Application Technology Computers and Information, 1(3), pp. 154–159. Available at: http://www.ejournal.pelitaindonesia.ac.id/JMApTeKsi/index.php/JOM/articl e/view/526.
[10] Junaidi and Prabowo, YD (2018) Project System control Electronic Arduino based, CV Anugrah Utama Raharja. Available at: https://docplayer.info/109709787-Project-sistem-kendali-elektronik-based-arduino-dr-junaidi-s-si-m-sc-yuliyan-dwi-prabowo.html. Ministry of Health (2016) ' Already Are we ready to face Flood ?' Mauliana , P. (2016) ' Prediction Citarum River Flood With Fuzzy Logic Results of Particle Swarm Optimization Algorithm , Informatics, AMIK BSI Bandung, 3(9), pp. 269–276. Available at: file:///C:/Users/Septian/Downloads/citarum teteh /CITARUM RIVER FLOOD PREDICTION WITH FUZZY LOGIC RESULTS OF PARTICLE SWARM OPTIMIZATION ALGORITHM.pdf.
[11] Rafiuddin Syam, ST, M.Eng , P. (2013) Basics of Sensor Engineering. Available at: http://anies.staff.gunadarma.ac.id/Downloads/files/73301/Ref_2_Rafiuddin +Syam_Dasar_teknik+sensor.pdf.
[12] Republic of Indonesia (2004) Law of the Republic of Indonesia No. 7 of 2004 concerning Source Water Power. Jakarta: State Secretariat .
[13] Republic of Indonesia (2012) Regulation Government Republic of Indonesia Number 37 of 2012 concerning Watershed Management , State Secretariat . Available at: https://dspace.ups.edu.ec/bitstream/123456789/5224/1/UPS-QT03885.pdf.
[14] Sari, YN (2016) Network Nerves Backpropagation clone to predict attack area . Semarang: Semarang State University.
[15] Shah, C. (2020) 'MySQL', A Hands-On Introduction to Data Science, pp. 187–206. doi : 10.1017/9781108560412.008.
[16] Soebroto , AA et al. (2015) ' Prediction of Water Level (TMA) for Early Detection of Disasters Flood Using SVR-TVIWPSO', Journal Technology Information and Science Computer , 2(2), p. 79. doi : 10.25126/jtiik.201522126.
[17] Subhan Panji Cipta (2016) ' Application Evolving Neural Network Algorithm for Rainfall Prediction ' , Jurnal Technology Lambung University Information Mangkurat (JTIULM), 1(1), pp. 1–8. doi : 10.20527/ jtiulm.v 1i1.2.
[18] Sulistyo Ida; Adipraja , Philip Faster Eka, DAW (2020) ' Tsukamoto Fuzzy Inference System Modeling for Prediction Incident Floods in Malang City', Jurnal Technology Information and Science Computer , 7(Vol 7, No 1: February 2020), pp. 189–196. doi : 10.25126/jtiik.202071898.
[19] Syahbeni , M. et al. (2018) ' Design Get up Rainfall Detector _ Using the Tipping Bucket Rain Sensor and Arduino Uno', Agrotechnics , 1(2), pp. 51–62. doi : 10.32530/ agtk.v 1i2.22.
[20] Villela , lucia maria aversa (2013) ' Cause Floods ', Journal of Chemical Information and Modeling, 53(9), pp. 1689–1699. Water Flow Sensor: YF-S201 Datasheet (2015).
[21] Widiawaty , MA and Dede, M. (2018) ' Modeling Spatial Dangers And Vulnerabilities Disaster Flood In the Eastern Region of the District Cirebon', Journal of Dialogue Countermeasures BNPB Disaster , 9(2), pp. 142–153