Development of a Flood Damage Prediction System Using GIS and AI

doi:10.15683/kosdi.2025.3.31.273

All Issue

2025 Vol.21, Issue 1 Preview Page Next Page

Original Article

Development of a Flood Damage Prediction System Using GIS and AI GIS 및 AI를 이용한 침수 피해 예측 시스템 개발: 조성호¹ㆍ김성재²*
Sungho Cho¹, Sung Jae Kim²*; ¹Director, Data Fusion Department, Sundosoft, Seoul, Republic of Korea
²Director, Research Institute, SmartGEO, Daegu, Republic of Korea

31 March 2025. pp. 273-282

PDF

Abstract

Purpose: Recent advances in GIS and AI technologies are opening up new possibilities to overcome the limitations of disaster management systems. The purpose of this study is to develop a prediction system for flooded areas using AI and GIS technologies. Method: Real-time data collection uses various APIs, and AI model linkage adopts the message queue method. The display speed test was performed through index creation and n field settings, and the system was developed based on Eclipse 4.18.0, JAVA 1.8.0_031, MAVEN, Apache Tomcat 9.0, PostgreSQL 13.16, and GeoServer. Result: Real-time weather data was collected and integrated into a GIS database. The system was linked with an AI model for flood damage prediction. Performance tests were conducted to analyze the visualization speed of large-scale real-time data, and the GIS system was developed considering the characteristics of both urban and river areas. Conclusion: This study designed and implemented a system capable of predicting flood damage in real time and visualizing the results efficiently. The system supports effective decision-making for flood response personnel by providing timely and accurate information.

Keywords

Flood Damage Prediction

Real-Time Data Collection

AI Model Linkage

GIS System Development

연구목적: 최근 지리정보시스템 및 인공지능 기술의 발전은 재난 관리 시스템의 한계를 극복할 수 있는 새로운 가능성을 열어주고 있다. AI는 대규모 데이터를 학습하여 패턴을 분석하고 미래를 예측하는 데 탁월하며, GIS는 공간 데이터를 기반으로 재난 상황을 시각화하여 직관적이고 효과적인 의사결정을 지원할 수 있다. 이러한 기술들을 이용하여 침수 지역에 대한 예측 시스템을 개발하고자 한다. 연구방법: 침수 피해 예측을 위하여 실시간 자료수집은 다양한 API를 통하여 자료를 수집하였으며 기존 침수 피해지 예측 관련 LSTM 모델과의 연계는 메시지 큐 방식을 채택하였다. 인덱스 생성 및 n 필드 설정을 통하여 표출 속도 테스트를 수행하였으며 시스템 개발은 Eclipse 4.18.0, JAVA 1.8.0_031, MAVEN, 서버 환경은 Apache Tomcat 9.0 데이터베이스는 PostgreSQL 13.16 버전을 사용하였으며 GIS 엔진으로는 GeoServer를 기반으로 개발하였다. 연구결과: 실시간 기상 자료수집하고 이를 GIS DB로 구축하였으며 침수 피해 예측 AI 모델과의 연계를 수행하였다. 대량의 실시간 데이터의 표출 속도 테스트 분석 및 도시와 하천 지역 특성을 고려하여 GIS 시스템을 개발하였다. 결론: 본 연구에서는 침수 피해를 실시간으로 예측하고, 효율적으로 표출할 수 있는 시스템을 설계 및 구현을 통하여 침수 관련 담당자들의 업무에 있어 효율적인 의사결정 정보를 지원할 수 있게 하였다.

키워드

침수 피해 예측

실시간 데이터 수집

AI모델 연계

GIS 시스템 개발

References

Arabameri, A., Saha, S., Chen, W., Roy, J., Pradhan, B., Bui, D.T. (2020). "Flash flood susceptibility modeling using functional tree and hybrid ensemble techniques." Journal of Hydrology, Vol. 587, pp. 1-15. 10.1016/j.jhydrol.2020.125007
Choi, N.J, Kim, S.J, Yoon, Y.H, Beak, J.S. (2023). "MicroService architecture space reservation web service using message queue." Proceedings of KSCI Conference 2023, Vol. 31, No. 2, pp. 273-274.
Hochreiter, S., Schmidhuber, J. (1997). "LSTM can solve hard long time lag problems." NIPS'96: Proceedings of the 10th International Conference on Neural Information Processing Systems, pp. 473-479.
Jung, S.H., Lee, D.E., Lee, K.S. (2018). "Prediction of river water level using deep-learningopen library." Journal of the Korean Society of Hazard Mitigation, Vol. 18, No. 1, pp. 1-11. 10.9798/KOSHAM.2018.18.1.1
Kang, H.S, Lee, H.S, Moon, H.J, Cho, J.W. (2023). "Development of RAINSYS(Real-time Alert for INundation SYStem) to Support Inundation Situation Management." Journal of the Korea Academia-Industrial Cooperation Society, Vol. 24, No. 11 pp. 461-469. 10.5762/KAIS.2023.24.11.461
Kim, D.H., Cho, M.K., Yun, H.S., Lee, S.Y. (2024). "Analysis of building flood damage using HEC-RAS2D and GIS." Journal of the Society of Disaster Information, Vol. 20, No. 4, pp. 749-760.
Kim, J.H., Kang, M.S., Kim, S.H. (2019). "Comparing the performance of artificial neural networks and long short-term memory networks for rainfall-runoff analysis." Proceedings of the Korea Water Resources Association Conference, KWRA, pp. 320-320.
Kim, P.D., Kim, K.S., Moon, Y.M. (2020). "A study on the improvement of the disaster prevention and control system for underpasses by analytic hierarchy process." Journal of the Society of Disaster Information, Vol. 16, No. 4, pp. 734-746.
Lee, C.Y., Park, G.J., Kim, T., Lee, H.S. (2019). "A study of the situation based disaster response model from the damage of storm and flood field manual." Journal of the Society of Disaster Information, Vol. 15, No. 4, pp. 617-625.
Lee, J.H. (2021). A Study on Development of Real-time Urban Flood Forecasting System Using Deep Learning and Radar-based Very Short-term Rainfall Prediction. Ph.D. Dissertation, University of Seoul.
Li, G., Zhao, H.D., Liu, C.S., Wang, J.F., Yang, F. (2022). "City flood disaster scenario simulation based on 1D-2D coupled rain-flood model." Water, Vol. 14, 3548. 10.3390/w14213548
Liang, C., Li, H., Lei, M., Du, Q. (2018). "Dongting Lake water level forecast and its relationship with the three gorges dam based on a long short-term memory network." Water, Vol. 10, No. 10, 1389. 10.3390/w10101389
National Disaster Management Research Institute (2021). "Development of Real-time Flood Prediction Technology based on Deep Learning. Korea.
Tran, Q.K., Song, S.K. (2017). "Water level forecasting based on deep learning: A use case of Trinity River-Texas-The United States." Journal of KIISE, Vol. 44, No. 6, pp. 607-612. 10.5626/JOK.2017.44.6.607
Xie, S., Wu, W., Mooser, S., Wang, Q.J., Nathan, R., Huang, Y. (2021). "Artificial neural network based hybrid modeling approach for flood inundation modeling." Journal of Hydrology, Vol. 592, pp. 1-14. 10.1016/j.jhydrol.2020.125605
Yuk, J.H. (2018). Construction and Application of Inundation Analysis System Considering Inland and River Flood. Master Thesis, University of Seoul.

Information

Publisher :The Korean Society of Disaster Information
Publisher(Ko) :한국재난정보학회
Journal Title :Journal of the Society of Disaster Information
Journal Title(Ko) :한국재난정보학회논문집
Volume : 21
No :1
Pages :273-282
DOI :https://doi.org/10.15683/kosdi.2025.3.31.273

[1] Arabameri, A., Saha, S., Chen, W., Roy, J., Pradhan, B., Bui, D.T. (2020). "Flash flood susceptibility modeling using functional tree and hybrid ensemble techniques." Journal of Hydrology, Vol. 587, pp. 1-15. 10.1016/j.jhydrol.2020.125007

[2] Choi, N.J, Kim, S.J, Yoon, Y.H, Beak, J.S. (2023). "MicroService architecture space reservation web service using message queue." Proceedings of KSCI Conference 2023, Vol. 31, No. 2, pp. 273-274.

[3] Hochreiter, S., Schmidhuber, J. (1997). "LSTM can solve hard long time lag problems." NIPS'96: Proceedings of the 10th International Conference on Neural Information Processing Systems, pp. 473-479.

[4] Jung, S.H., Lee, D.E., Lee, K.S. (2018). "Prediction of river water level using deep-learningopen library." Journal of the Korean Society of Hazard Mitigation, Vol. 18, No. 1, pp. 1-11. 10.9798/KOSHAM.2018.18.1.1

[5] Kang, H.S, Lee, H.S, Moon, H.J, Cho, J.W. (2023). "Development of RAINSYS(Real-time Alert for INundation SYStem) to Support Inundation Situation Management." Journal of the Korea Academia-Industrial Cooperation Society, Vol. 24, No. 11 pp. 461-469. 10.5762/KAIS.2023.24.11.461

[6] Kim, D.H., Cho, M.K., Yun, H.S., Lee, S.Y. (2024). "Analysis of building flood damage using HEC-RAS2D and GIS." Journal of the Society of Disaster Information, Vol. 20, No. 4, pp. 749-760.

[7] Kim, J.H., Kang, M.S., Kim, S.H. (2019). "Comparing the performance of artificial neural networks and long short-term memory networks for rainfall-runoff analysis." Proceedings of the Korea Water Resources Association Conference, KWRA, pp. 320-320.

[8] Kim, P.D., Kim, K.S., Moon, Y.M. (2020). "A study on the improvement of the disaster prevention and control system for underpasses by analytic hierarchy process." Journal of the Society of Disaster Information, Vol. 16, No. 4, pp. 734-746.

[9] Lee, C.Y., Park, G.J., Kim, T., Lee, H.S. (2019). "A study of the situation based disaster response model from the damage of storm and flood field manual." Journal of the Society of Disaster Information, Vol. 15, No. 4, pp. 617-625.

[10] Lee, J.H. (2021). A Study on Development of Real-time Urban Flood Forecasting System Using Deep Learning and Radar-based Very Short-term Rainfall Prediction. Ph.D. Dissertation, University of Seoul.

[11] Li, G., Zhao, H.D., Liu, C.S., Wang, J.F., Yang, F. (2022). "City flood disaster scenario simulation based on 1D-2D coupled rain-flood model." Water, Vol. 14, 3548. 10.3390/w14213548

[12] Liang, C., Li, H., Lei, M., Du, Q. (2018). "Dongting Lake water level forecast and its relationship with the three gorges dam based on a long short-term memory network." Water, Vol. 10, No. 10, 1389. 10.3390/w10101389

[13] National Disaster Management Research Institute (2021). "Development of Real-time Flood Prediction Technology based on Deep Learning. Korea.

[14] Tran, Q.K., Song, S.K. (2017). "Water level forecasting based on deep learning: A use case of Trinity River-Texas-The United States." Journal of KIISE, Vol. 44, No. 6, pp. 607-612. 10.5626/JOK.2017.44.6.607

[15] Xie, S., Wu, W., Mooser, S., Wang, Q.J., Nathan, R., Huang, Y. (2021). "Artificial neural network based hybrid modeling approach for flood inundation modeling." Journal of Hydrology, Vol. 592, pp. 1-14. 10.1016/j.jhydrol.2020.125605

[16] Yuk, J.H. (2018). Construction and Application of Inundation Analysis System Considering Inland and River Flood. Master Thesis, University of Seoul.

Journal of the Society of Disaster Information ISSN:1976-2208(Print) 2671-5287(Online) 한국재난정보학회논문집

All Issue