Lu Yuwen, Zhai Guofang

Keywords： Artificial Intelligence (AI); Risk Assessment; Disaster Risk Management; Machine Learning; Neural Network

Abstract：

With the rapid development of urbanization and continuous accumulation of urban elements, the complexity of risks is increasing. Strengthening disaster risk management and improving disaster prevention, mitigation and relief capabilities, can effectively reduce disaster losses and promote the safe and sustainable development of cities. The rapid development of artificial intelligence (AI) has brought new opportunities for disaster risk management. This paper combs the exploration of AI technology in disaster risk management. The key technologies and basic methods of AI technology in disaster risk management are discussed from three stages: pre-disaster prevention and preparation, monitoring and early warning; disaster response during the disaster, emergency treatment; and post-disaster recovery and reconstruction. It suggests that AI should be applied to the construction of urban disaster risk and emergency management in China, to provide inspiration for spatial security pattern planning and the resilient cities construction.

Funds：

• [1] PELLING M. The vulnerability of cities: natural disasters and social resilience[M]. Routledge, 2003.

  [2] HENDERSON L J. Emergency and disaster: pervasive risk and nations[J]. Public organization review: a global journal, 2004(4): 103-119.

  [3] MCCARTHY M P, BEST M J, BETTS R A. Climate change in cities due to global warming and urban effects[J/OL]. Geophysical research letters, 2010, 37(9): L09705[2020-05-21]. https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2010GL042845.

  [4] National Research Council. The Indian Ocean Tsunami Disaster: implications for U.S. and global disaster reduction and preparedness: summary of the June 21, 2005 workshop of the disasters roundtable[R]. Washington, DC: The National Academies Press, 2006.

  [5] ALEXANDER D E. Social media in disaster risk reduction and crisis management[J]. Science & engineering ethics, 2014, 20(3): 717-733.

  [6] McCARTHY J, MINSKY M, ROCHESTER N, et al. A proposal for the Dartmouth summer research project on artificial[R]. 1955.

  [7] MCCARTHY J. What is artificial intelligence?[R]. Computer Science Department, Stanford University, 2007.

  [8] RAY S. Histor y of AI[EB/OL]. (2018-08-11)[2019-06-15]. https://towardsdatascience.com/history-of-ai-484a86fc16ef.

  [9] MELLIT A, KALOGIROU S A. Artificial intelligence techniques for photovoltaic applications: a review[J]. Progress in energy and combustion science, 2008(5): 574-632.

  [10] 斯图尔特·罗素, 彼得·诺维格. 人工智能：一种现代方法（第二版）[M]. 姜哲, 金英江, 张敏, 等, 译. 北京：人民邮电出版社, 2004.

  [11] Artificial intelligence tutorial[EB/OL]. (2019-02-17)[2019-06-12]. https://www.javatpoint.com/artificial-intelligence-tutorial.

  [12] 黄佳. 基于OPENCV 的计算机视觉技术研究[D]. 上海: 华东理工大学, 2013.

  [13] 计算机视觉入门系列（一）综述[EB/OL]. (2020-12-16)[2020-12-27]. https://blog.csdn.net/wangss9566/article/details/54618507.

  [14] 屠李, 赵鹏军, 张超荣, 等. 面向新一代人工智能的城市规划决策系统优化[J]. 城市发展研究, 2019, 26(1): 54-59.

  [15] 张庭伟．复杂性理论及人工智能在规划中的应用[J]. 城市规划学刊, 2017(6): 9-15.

  [16] VAN ECK N J，WALTMAN L．VOS viewer: a computer program for bibliometric mapping[J]. Scientometrics, 2010, 84(2): 523-538.

  [17] 高凯. 文献计量分析软件VOS viewer 的应用研究[J]. 科技情报开发与经济, 2015, 25(12): 95-98.

  [18] ABHIGNA P, JERRITTA S, SRINIVASAN R, et al. Analysis of feed forward and recurrent neural networks in predicting the significant wave height at the Moored Buoys in Bay of Bengal[C] // International Conference on Communication and Signal Processing (ICCSP), 2017: 1856-1860.

  [19] JIA X, WANG R, DAI H, et al. A neural network method for risk assessment and real-time early warning of mountain flood geological disaster[C] // International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), 2017: 540-544.

  [20] WU C L, CHAU K W. A flood forecasting neural network model with genetic algorithm[J]. International journal of environment and pollution, 2006, 28(3/4): 261-273.

  [21] CHOWDHURY F H, NAHIAN R, UDDIN T, et al. Design, control & performance analysis of forecast junction IoT and swarm robotics-based system for natural disaster monitoring[C] // The 8th International Conference on Computing, Communication and Networking Technologies(ICCCNT), 2017: 1-5.

  [22] DANSO-AMOAKO E, SCHOLZ M, KALIMERIS N, et al. Predicting dam failure risk for sustainable flood retention basins: a generic case study for the wider Greater Manchester area[J]. Computers environment & urban systems, 2012, 36(5): 423-433.

  [23] NAGATANI K, AKIYAMA K, YAMAUCHI G, et al. Volcanic ash observation in active volcano areas using teleoperated mobile robotsintroduction to our robotic-volcano-observation project and field experiments[C] // IEEE International Symposium on Safety, Security and Rescue Robotics (SSRR), 2013: 1-6.

  [24] ANINDITA A P, LAKSONO P, NUGRAHA I G B B. Dam water level prediction system utilizing artificial neural network back propagation: case study: Ciliwung Watershed, Katulampa Dam[C] // International Conference on ICT for Smart Society, 2016: 16-21.

  [25] ADNAN R, SAMAD A M, RUSLAN F A. A 3-hours river water level flood prediction model using NNARX with improves modelling strategy[C] // IEEE International Conference on System Engineering & Technology, 2017: 23-27.

  [26] KIA M B, PIRASTEH S, PRADHAN B, et al. An artificial neural network model for flood simulation using GIS: Johor River Basin, Malaysia[J]. Environmental earth sciences, 2012, 67(1): 251-264.

  [27] DUARTE D, NEX F, KERLE N, et al. Satellite image classification of building damages using airborne and satellite image samples in a deep learning approach[C] // ISPRS Annals of Photogrammetry, Remote Sensing & Spatial Information Sciences, 2018, 4(2): 89-96.

  [28] CHEN W, SHIRZADI A, SHAHABI H, et al. A novel hybrid artificial intelligence approach based on the rotation forest ensemble and na?ve Bayes tree classifiers for a landslide susceptibility assessment in Langao County, China[J]. Geomatics, natural hazards and risk, 2017, 8(2): 1955-1977.

  [29] AMIT S N K B, AOKI Y. Disaster detection from aerial image with convolutional neural network[C] // 2017 International Electronics Symposium on Knowledge Creation and Intelligent Computing (IES-KCIC), 2017: 239-245.

  [30] LEE W, KIM S, LEE Y T, et al. Deep neural networks for wild fire detection with unmanned aerial vehicle[C] // IEEE International Conference on Consumer Electronics (ICCE), 2017: 252-253.

  [31] IVI? M. Artificial intelligence and geospatial analysis in disaster management[J]. International archives of the photogrammetry, remote sensing and spatial information sciences, 2019, 42(3): 161-166.

  [32] VETRIVEL A, GERKE M, KERLE N, et al. Disaster damage detection through synergistic use of deep learning and 3D point cloud features derived from very high-resolution oblique aerial images, and multiple-kernellearning[J]. ISPRS journal of photogrammetry and remote sensing, 2018, 140: 45-59.

  [33] DOSHI J, BASU S, PANG G. From satellite imagery to disaster insights[C/OL]. The 32nd Conference on Neural Information Processing Systems. (2018-11-17)[2020-07-19]. https://arxiv.org/pdf/1812.07033.pdf.

  [34] COONER A, SHAO Y, CAMPBELL J. Detection of urban damage using remote sensing and machine learning algorithms: revisiting the 2010 Haiti earthquake[J]. Remote sensing, 2016, 8(10): 868-885.

  [35] NEX F, DUARTE D, STEENBEEK A, et al. Towards real-time building damage mapping with low-cost UAV solutions[J]. Remote sensing, 2019, 11(3): 287-301.

  [36] SYIFA M, KADAVI P R, LEE C W. An artificial intelligence application for post-earthquake damage mapping in Palu, Central Sulawesi, Indonesia[J]. Sensors, 2019, 19(3): 542-560.

  [37] PETROPOULOS G P, VADREVU K P, XANTHOPOULOS G, et al. Acomparison of spectral angle mapper and artificial neural network classifiers combined with Landsat TM imagery analysis for obtaining burnt area mapping[J]. Sensors, 2010, 10(3): 1967-1985.

  [38] GFDRR: Global Facility for Disaster Reduction and Recovery. Machine learning for disaster risk management[R]. Washington, DC, 2018.

  [39] KASSEL S. Predicting building code compliance with machine learning models[EB/OL] (2017-09-21)[2020-05-17]. https://azavea.github.io/buildinginspection-prediction/index.html.

  [40] XIE S M, JEAN N, BURKE M, et al. Transfer learning from deep features for remote sensing and poverty mapping[C] // The 30th AAAI Conference on Artificial Intelligence, 2016: 3929-3935.

  [41] GRAESSER J, CHERIYADAT A, VATSAVAI R, et al. Image based characterization of formal and informal neighborhoods in an urban landscape[J]. IEEE journal of selected topics in applied earth observations and remote sensing, 2012, 5(4): 1164-1176.

  [42] CHOWDHURY S R, IMRAN M, ASGHAR M R, et al. Tweet4act: using incident-specific profiles for classifying crisis-related messages[C] // International Conference on Information Systems for Crisis Response & Management, 2013: 834-839.

  [43] FOHRINGER J, DRANSCH D, KREIBICH H, et al. Social media as an information source for rapid flood inundation mapping[J]. Natural hazards and earth system sciences, 2015, 15: 2725-2738.

  [44] YU F, MONIKA S. Extraction of pluvial flood relevant volunteered geographic information (VGI) by deep learning from user generated texts and photos[J]. International journal of geo-information. 2018, 7(2): 39.

  [45] International Research Institute of Disaster Science. Fujitsu leverages AI tech in joint project to contribute to safe tsunami evacuation in Kawasaki[EB/OL]. (2019-10-24)[2020-07-25]. https://www.fujitsu.com/global/about/resources/news/press-releases/2019/1024-01.html.

  [46] IMRAN M, CASTILLO C, LUCAS J, et al. AIDR: artificial intelligence for disaster response[C] // Proceedings of the 23rd International Conference on World Wide Web (WWW ‘14 Companion). New York: Association forComputing Machinery, 2014: 159-162.