[논문]고해상도 도시 침수 해석을 위한 딥러닝 기반 초해상화 기술 적용

최현진; 이송희; 우현아; 김민영; 노성진

doi:10.3741/jkwra.2023.56.10.641

고해상도 도시 침수 해석을 위한 딥러닝 기반 초해상화 기술 적용
Applying deep learning based super-resolution technique for high-resolution urban flood analysis 원문보기

Journal of Korea Water Resources Association = 한국수자원학회논문집, v.56 no.10, 2023년, pp.641 - 653

최현진 (금오공과대학교 토목공학과) , 이송희 (금오공과대학교 토목공학과) , 우현아 (금오공과대학교 토목공학과) , 김민영 (금오공과대학교 토목공학과) , 노성진 (금오공과대학교 토목공학과)

초록
AI-Helper

기후변화와 도시화의 영향으로 인해 자연재해의 발생빈도와 규모가 증가하고 있다. 특히 도시 침수는 발생 시간이 짧고 막대한 인명 및 경제적 손실을 초래할 수 있기 때문에 신속하고 정확도 높은 예측 정보 생산이 중요하다. 하지만, 기존 물리과정 및 인공지능 기반 기법은 고해상도 침수 해석을 위해 많은 전산 자원이나 데이터가 요구되는 한계가 있다. 본 연구에서는 딥러닝 기반 초해상화(Super-Resolution) 기법을 통한 고해상도 도시 침수 해석 방법을 제안하고 적용성을 평가한다. 제안된 방법은 고해상도 물리 모형의 결과로 훈련된 초해상화 딥러닝 모형을 이용하여 저해상도 침수 해석 이미지를 고해상도로 변환한다. 미국 포틀랜드 도심지의 두 가지 침수 사례에 대해 적용, 4 m 공간해상도 물리 모의 결과를 1 m 급 고해상도 침수 해석 정보로 초해상화 하였으며, 초해상화 이미지와 고해상도 원본 간 높은 구조적 유사성이 확인되었다. 성능 지표로 평가한 결과, 전체 검증 대상 이미지에 대한 평균 PSNR 22.77 dB, SSIM 0.77로 우수하여, 초해상화 기법의 도시 침수 해석 적용성이 검증되었다. 제안된 방법은 적은 양의 침수 시나리오만으로도 효율적인 딥러닝 모형 훈련이 가능하고, 물리 모형의 정보를 최대한 활용할 수 있기 때문에, 고해상도 도시 침수 정보 생산에 효과적으로 사용될 수 있을 것으로 기대된다.

Abstract ▼ AI-Helper

As climate change and urbanization are causing unprecedented natural disasters in urban areas, it is crucial to have urban flood predictions with high fidelity and accuracy. However, conventional physically- and deep learning-based urban flood modeling methods have limitations that require a lot of computer resources or data for high-resolution flooding analysis. In this study, we propose and implement a method for improving the spatial resolution of urban flood analysis using a deep learning based super-resolution technique. The proposed approach converts low-resolution flood maps by physically based modeling into the high-resolution using a super-resolution deep learning model trained by high-resolution modeling data. When applied to two cases of retrospective flood analysis at part of City of Portland, Oregon, U.S., the results of the 4-m resolution physical simulation were successfully converted into 1-m resolution flood maps through super-resolution. High structural similarity between the super-solution image and the high-resolution original was found. The results show promising image quality loss within an acceptable limit of 22.80 dB (PSNR) and 0.73 (SSIM). The proposed super-resolution method can provide efficient model training with a limited number of flood scenarios, significantly reducing data acquisition efforts and computational costs.

주제어

표/그림 (12)

그림 Fig. 1. Framework of the proposed super-resolution urban flood analysis method
그림 Fig. 2. Super-resolution results using EDSR and DIV2K dataset
그림 Fig. 3. SRResNet and EDSR residual network (Galar et al., 2020)
그림 Fig. 4. Input data of physically-based model H12. (a) Digital surface moel (1-m resolution), (b) Land cover (1-m resolution)
그림 Fig. 5. Concept of image down sampling by bicubic interpolation and super resolution. (a) Original high resolution urban flood modeling result, (b) 4X down sampled input image, (c) Super resolution result
그림 Fig. 6. Training loss function of the super-resolution urban flood model network
그림 Fig. 7. Variation of PSNR and SSIM in training and validation periods. (a) PSNR curves, (b) SSIM curves
그림 Fig. 8. High-resolution(1-m resolution) flooding modeling results of maximum water depth in downtown Portland, U.S. simulated by physically-based model H12. The white square box indicates the location of the super-resolution image in Figure 9 among the 60 verification images
그림 Fig. 9. Results of super-resolution urban flood analysis (right panel) at 7 locations (a to g) compared with low resolution (middle panel) and original high resolution (left panel). The location of each images can be found in Fig. 8
그림 Fig. 10. Bar graphs of a super-resolution results of urban flooding images for 7 locations. (a) PSNR, (b) SSIM
그림 Fig. 11. Box graphs of super-resolution results for 95-hour historical precipitation and 100-year 6-hour precipitation for 60 verification images respectively. (a) PSNR, (b) SSIM
표 Table 1. Average PSNR and SSIM of 95-hour historical precipitation and 100-year frequency 6-hour precipitation for 60 verification images respectively

참고문헌 (30)

Ballard, T., and Erinjippurath, G. (2020). "FireSRnet: Geoscience-driven super-resolution of future fire risk from climate？change." arXiv Preprint, arXiv:2011.12353.
Ballard, T., and Erinjippurath, G. (2022). "Contrastive learning for？climate model bias correction and super-resolution." arXiv？Preprint, arXiv:2211.07555.
Bashir, S.M.A., Wang, Y., Khan, M., and Niu, Y. (2021). "A comprehensive review of deep learning-based single image super-resolution." PeerJ Computer Science, Vol. 7, e621.

상세보기
Caballero, J., Ledig, C., Aitken, A., Acosta, A., Totz, J., Wang, Z.,？and Shi, W. (2017). "Real-time video super-resolution with？spatio-temporal networks and motion compensation." Proceedings of the IEEE Conference on Computer Vision and？Pattern Recognition, Honolulu, HI, U.S., pp. 4778-4787.
Cheng, J., Kuang, Q., Shen, C., Liu, J., Tan, X., and Liu, W. (2020).？"ResLap: Generating high-resolution climate prediction through？image super-resolution." IEEE Access, Vol. 8, pp. 39623-39634.

상세보기
Cooley, A., and Chang, H. (2017). "Precipitation intensity trend？detection using hourly and daily observations in Portland,？Oregon." Climate, Vol. 5, No. 1, 10.

상세보기
Dai, T., Cai, J., Zhang, Y., Xia, S.-T., and Zhang, L. (2019). "Second-order attention network for single image super-resolution."？Proceedings of the IEEE/CVF Conference on Computer Vision？and Pattern Recognition, Long Beach, USA, pp. 1106511074.
Dong, C., Loy, C.C., He, K., and Tang, X. (2014). "Learning a deep？convolutional network for image super-resolution." Computer？Vision - ECCV 2014: 13th European Conference, Zurich, Switzerland, pp. 184-199.
Galar, M., Sesma, R., Ayala, C., Albizua, L., and Aranda, C. (2020).？"Super-resolution of Sentinel-2 images using convolutional？neural networks and real ground truth data." Remote Sensing,？MDPI, Vol. 12, No. 18, 2941.

상세보기
Guidolin, M., Chen, A.S., Ghimire, B., Keedwell, E.C., Djordjevic,？S., and Savic, D.A. (2016). "A weighted cellular automata 2D？inundation model for rapid flood analysis." Environmental？Modelling & Software, Vol. 84, pp. 378-394.

상세보기
Guo, Z., Leitao, J.P., Simoes, N.E., and Moosavi, V. (2021). "Data-driven flood emulation: Speeding up urban flood predictions？by deep convolutional neural networks." Journal of Flood Risk？Management, Vol. 14, No. 1, e12684.

상세보기
He, J., Zhang, L., Xiao, T., Wang, H., and Luo, H. (2023). "Deep？learning enables super-resolution hydrodynamic flooding process？modeling under spatiotemporally varying rainstorms." Water？Research, Vol. 239, 120057.
Hwang, S.-G., and Lee, J.-H. (2023). "Super-resolution technique of？underwater image based on lightweight convolutional neural？network for marine accident cause analysis." Journal of？Korean Institute of Intelligent Systems, Vol. 33, No. 2, pp.？127-132.

상세보기
Jia, Y., Ge, Y., Chen, Y., Li, S., Heuvelink, G.B.M., and Ling, F.？(2019). "Super-resolution land cover mapping based on the？convolutional neural network." Remote Sensing, MDPI, Vol.？11, No. 15, 1815.

상세보기
Kim, J., Lee, J.K., and Lee, K.M. (2016). "Deeply-recursive convolutional network for image super-resolution." Proceedings of？the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, U.S., pp. 1637-1645.
Kwon, O.-S. (2023). "Vehicle detection algorithm using super resolution based on deep residual dense block for remote sensing？images." Journal of Broadcast Engineering, Vol. 28, No. 1,？pp. 124-131.
Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta,？A., Aitken, A., Tejani, A., Totz, J., Wang, Z., and Shi, W. (2017).？"Photo-realistic single image super-resolution using a generative adversarial network." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu,？HI, U.S., pp. 4681-4690.
Lee, S., Nakagawa, H., Kawaike, K., and Zhang, H. (2016). "Urban？inundation simulation considering road network and building？configurations." Journal of Flood Risk Management, Vol. 9,？No. 3, pp. 224-233.
Lim, B., Son, S., Kim, H., Nah, S., and Lee, K.M. (2017). "Enhanced？deep residual networks for single image super-resolution." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, U.S., pp. 136-144.
Lombana, L., and Martinez-Grana, A. (2022). "A flood mapping？method for land use management in small-size water bodies:？Validation of spectral indexes and a machine learning technique." Agronomy, MDPI, Vol. 12, No. 6, 1280.
Mei, Y., Fan, Y., Zhou, Y., Huang, L., Huang, T.S., and Shi, H.？(2020). "Image super-resolution with cross-scale non-local？attention and exhaustive self-exemplars mining." Proceedings？of the IEEE/CVF Conference on Computer Vision and Pattern？Recognition, Seattle, WA, U.S., pp. 5690-5699.
Moreno-Rodenas, A.M., Bellos, V., Langeveld, J.G., and Clemens,？F.H.L.R. (2018). "A dynamic emulator for physically based flow？simulators under varying rainfall and parametric conditions."？Water Research, Vol. 142, pp. 512-527.

상세보기
Noh, S.J., Lee, J.-H., Lee, S., and Seo, D.-J. (2019). "Retrospective？dynamic inundation mapping of hurricane harvey flooding in？the Houston Metropolitan Area using high-resolution modeling？and high-performance computing." Water, Vol. 11, No. 3, 597.
Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D.J., and Norouzi,？M. (2021). "Image super-resolution via iterative refinement."？IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45, No. 4, pp. 4713-4726.
Sara, U., Akter, M., and Uddin, M.S. (2019). "Image quality assessment through FSIM, SSIM, MSE and PSNR - A comparative？study." Journal of Computer and Communications, Vol. 7, No.？3, pp. 8-18.
Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2016). "Inception-v4, Inception-ResNet and the impact of residual connections on learning." Proceedings of the AAAI Conference on？Artificial Intelligence, Phoenix, AZ, U.S., Vol. 31, No. 1, pp.？4278-4284.
Wang, X., Yi, J., Guo, J., Song, Y., Lyu, J., Xu, J., Yan, W., Zhao, J.,？Cai, Q., and Min, H. (2022). "A review of image super-resolution？approaches based on deep learning and applications in remote？sensing." Remote Sensing, MDPI, Vol. 14, No. 21, 5423.
Wang, Y., Chen, A.S., Fu, G., Djordjevic, S., Zhang, C., and Savic,？D.A. (2018). "An integrated framework for high-resolution？urban flood modelling considering multiple information sources？and urban features." Environmental Modelling & Software,？Vol. 107, pp. 85-95.

상세보기
Wang, Z., Bovik, A., Sheikh, H., and Simoncelli, E. (2004). "Image？quality assessment: From error visibility to structural similarity." IEEE Transactions on Image Processing, Vol. 13, No.？4, pp. 600-612.

상세보기
Zha, L., Yang, Y., Lai, Z., Zhang, Z., and Wen, J. (2021). "A lightweight dense connected approach with attention on single？image super-resolution." Electronics, MDPI, Vol. 10, No. 11,？1234.

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증