基于人工智能(AI)的地质灾害防控体系建设
|
摘要
近年来,人工智能(AI)技术得到快速发展,并日益融入到经济社会各个领域,成为当代创新发展的新标志,智能防灾减灾将成为未来发展的趋势和研究的热点。在回顾AI发展现状与趋势的基础上,系统梳理出以往地质灾害风险防控的数据依据和传统技术方法,分析了可能采用的潜在AI方法,初步搭建了基于AI的地质灾害风险防控体系建设方案。研究表明,AI技术为地质灾害风险防控提供了新的技术途径,但目前尚无可照搬或可移植的成熟技术或解决方案。智能防灾减灾体系包括早期识别、风险评估、风险防控等3个主要环节,其中最重要的环节是早期识别,传统方法与AI技术融合的关键参数为斜坡失稳概率或泥石流发生概率;根据所依据的数据资料将早期识别方法归纳为图像识别、形变识别、位移识别、内因识别、诱因识别和综合识别等6种方法;提出了从数据层、方法层和应用层3个层次构建基于大数据智能混合优化的地质灾害风险防控平台。认为数据驱动的智能模型与理论驱动的物理模型融合是地质灾害风险防控发展的趋势。
In recent years,artificial intelligence(AI)technology has developed rapidly and is increasingly integrated into various fields of economy and society.It has become a new symbol of contemporary innovation and development.Intelligent disaster prevention and mitigation will become the future development trend and research hotspot.On the basis of reviewing the status and trend of(AI)development,this paper systematically sorts out the data basis and traditional technical methods of previous geological disaster risk prevention and control,analyzes the potential AI methods that may be used,and initially builds a an AI-based geological disaster risk prevention and control system.Research shows that AI technology provides a new technical approach for the prevention and control of geological disaster risks,but there are no mature technologies or solutions that can be copied or portable.The proposed intelligent disaster prevention and mitigation system includes three main parts:early identification,risk assessment,and risk prevention and control.The key point is early identification,while the key parameter for the fusion between traditional methods and AI technology is the probability of slope instability or the probability of derrs flow occurrence;According to the data,the early identification methods are summarized into six methods:image recognition,deformation recognition,displacement recognition,internal factor recognition,incentive identification and comprehensive recognition.This paper proposes a geological disaster risk prevention and control platform based on big data intelligent hybrid optimization from three levels:data layer,method layer and application layer.It is believed that the fusion between data-driven intelligent models and theoretically driven physical models is the trend of geological disaster risk prevention and control development.
In recent years,artificial intelligence(AI)technology has developed rapidly and is increasingly integrated into various fields of economy and society.It has become a new symbol of contemporary innovation and development.Intelligent disaster prevention and mitigation will become the future development trend and research hotspot.On the basis of reviewing the status and trend of(AI)development,this paper systematically sorts out the data basis and traditional technical methods of previous geological disaster risk prevention and control,analyzes the potential AI methods that may be used,and initially builds a an AI-based geological disaster risk prevention and control system.Research shows that AI technology provides a new technical approach for the prevention and control of geological disaster risks,but there are no mature technologies or solutions that can be copied or portable.The proposed intelligent disaster prevention and mitigation system includes three main parts:early identification,risk assessment,and risk prevention and control.The key point is early identification,while the key parameter for the fusion between traditional methods and AI technology is the probability of slope instability or the probability of derrs flow occurrence;According to the data,the early identification methods are summarized into six methods:image recognition,deformation recognition,displacement recognition,internal factor recognition,incentive identification and comprehensive recognition.This paper proposes a geological disaster risk prevention and control platform based on big data intelligent hybrid optimization from three levels:data layer,method layer and application layer.It is believed that the fusion between data-driven intelligent models and theoretically driven physical models is the trend of geological disaster risk prevention and control development.
引文
吴飞,阳春华.人工智能的回顾与展望[J].中国科学基金,2018,42(3):32-44.WU Fei,YANG Chunhua.Artificial intelligence:review and future opportunities[J].Bulletin of National Natural Science Foundation of China,2018,42(3):32-44.
龚健雅.人工智能时代测绘遥感技术的发展机遇与挑战[J].武汉大学学报·信息科学版,2018,43(12):1788-1796.KUI Jianya.Chances and Challenges for Development of Surveying and Remote Sensing in the Age of Artificial Intelligence[J].Geomatics and Information Science of Wuhan University,2018,43(12):1788-1796.
李德仁.脑认知与空间认知---论空间大数据与人工智能的集成[J].武汉大学学报·信息科学版,2018,43(12):1761-1767.LI Deren.Brain Cognition and Spatial Cognition:On Integration of Geo-spatial Big Data and Artificial Intelligence[J].Geomatics and Information Science of Wuhan University,2018,43(12):1761-1767.
腾讯研究院.中国信息通信研究院互联网法律研究中.人工智能.国家人工智能战略行动抓手[M].北京:中国人民大学出版社,2017.Tencent ResearchInstitute.China Academy of Information and Communications Technology.Artificial Intelligence:National Artificial Intelligence Strategic Action Grasp[M].Beijing:China Renmin University Press,2017.
张茂省.地灾调查评估是移民搬迁的关键[J].水文地质工程地质,2011,37(05):143.ZHANGMaosheng.Geological Hazard Investigation and Assessment Is The key To Resettlement[J].Hydrogeology and Engineering Geology,2011,37(05):143.
张茂省,李林,唐亚明,等.基于风险理念的黄土滑坡调查与编图研究[J].工程地质学报,2011,19(1):43-51.ZHANG Maosheng,LI Lin,TANG Yaming,et al.Risk Management based on Landslide Investigation and Mapping in Loessarea[J].Journal of Engineering Geology,2011,19(1):43-51.
张茂省,程秀娟,董英,等.冻结滞水效应及其促滑机理-以甘肃黑方台地区为例[J].地质通报,2013,32(06):852-860.ZHANG Maosheng,CHENG Xiujuan,DONG Ying,et al.The Effect of Frozen Stagnant Water and Its Impact on Slope Stability:A Case Study of Heifangtai,Gansu Province[J].Geological Bulletin Of China,2013,32(06):852-860.
殷跃平,王猛,李滨,等.延安市宝塔区地质灾害详细调查示范[J].西北地质,2007,40(2):29-55.YIN Yaoping,WANG Meng,LI Bin,et al.Detailed Investigation and Demonstration of Geological Disasters in Baota District,Yan'an City[J].Northwestern Geology,2007,40(2):29-55.
殷跃平,吴树仁.滑坡监测预警与应急防治技术研究[M].北京:科学出版社,2012.YIN Yaoping,WU Shuren.Landslide Monitoring Early Warning and Emergency Prevention Technology Research[M].Bijing:Science Press,2012.
张茂省,唐亚明.地质灾害风险调查的方法与实践[J].地质通报,2008a,27(08):1205-1216.ZHANG Maosheng,TANG Yaming.Risk Investigation Method and Practice of Geohazards[J].Geological Bulletin of China,2008,27(08):1205-1216.
张茂省,雷学武,校培喜,等.遥感技术在黄土高原区地质灾害详细调查中的应用[J].西北地质,2007,40(3):92-97.ZHANG Maosheng,LEI Xuewu,JIAO Peixi,et al.Application of Remote Sensing Technology in Detailed Investigation of Geological Hazards in the Loess Plateau[J].Northwestern Geology,2007,40(3):92-97.
张茂省.延安宝塔区滑坡崩塌地质灾害[M].北京:地质出版社,2008.ZHANG Maosheng.Geological Disaster of Landslide Collapse in Baota District,Yan'an[M].Bejing:Geological Press,2008.
刘传正.地质灾害风险识别方法[J].中国地质灾害与防治学报,2018,39(6):3.LIU Chuanzheng.Geological Disaster Risk Identification Method[J].The Chinese Journal of Geological Hazard and Control,2018,29(6):3.
刘传正.崩塌滑坡灾害风险识别方法初步研究[J].工程地质学报,2019,27(1):88-97.LIU Chuanzheng.Preliminary Study on The Identification Method of Collapse and Landslide Disaster Risk[J].Journal of Engineering Geology,2019,27(1):88-97.
张茂省,王尧.基于风险的地质环境承载力评价[J].地质通报,2018,37(2-3):467-475.ZHANG Maosheng,WANG Yao.Research on The Evaluation of The Carrying Capacity of Geological Environment based on Its Risk Level[J].Geological Bulletin of China,2018,37(2-3):467-475.
吴树仁,石菊松.多级旋转黄土滑坡形成机理及失稳模式.吉林大学学报(地球科学版),2012,4 2(3):26-27.WU Shuren,SHI Jusong.Formation Mechanism and Instability Mode of Multi-stage Rotating Loess Landslide[J].Journal of Jilin University:Earth Science Edition,2012,42(3):26-27.
张丽君.法国滑坡灾害风险预防管理政策[J].国土资源情报,2006,13(10):13-18.ZHANG Lijun.French Landslide Disaster Risk Prevention Management Policy[J].Land and Resources Information,2006,13(10):13-18.
陈松灿,高阳.中国机器学习白皮书[M].北京:中国人工智能学会,2015.CHEN Songcan,GAO Yang.Chinese Machine Learning White Paper[M].Beijing:Chinese Association for Artificial Intelligence,2015.
李学龙,龚海刚.大数据系统综述[J].中国科学:信息科学,2015,45(1):1-44.LI Xuelong,GONG Haigang.A survey on big data systems[J].Scientia Sinica Informationis,2015,45(1):1-44.
张珊珊,张茂省,孙萍萍,等.面向黄土地质灾害的优势流研究[J].兰州大学学报(自然科学版),2019,55(2):274-280.ZHANG Shanshan,ZHANG Maosheng,SUN Pingping,et al.Advances and outlooks of preferential flow study in unsaturated soils[J].Journal of Lanzhou University:Natural Sciences,2019,55(2):274-280.
MARKUS REICHSTEIN,Gustau Camps-Valls,Bjorn Stevens,et al.Deep learning and process understanding for data-driven Earth system science[J].Nature,2019,566(7743):195-204.
HINTON G,OSINDERO S,WELLING M,et al.Unsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation[J].Cognitive Science,2006,30(4):725-731.
HUNGR O,FELL R,R,RRPetroleum Geology,2005,22(1-2):0-nagement[J].Crc Press,2005,7(2):117-124.
NADIM F,KVALSTAD T J,GUTTORMSEN T.Quantification of risks associated with seabed instability at Ormen Lange[J].Marine and Petroleum Geology,2005,22(1-2):0-318.
PICARELLI L,URCIUOLI G,RAMONDINI M,et al.Main features of mudslides in tectonised highly fissured clay shales[J].Landslides,2005,2(1):15-30.
GUZZETTI FAUSTO,STARK CONLIN P,SALVATI PA-OLA.Evaluation of Flood and Landslide Risk to The Population of Italy[J].Environmental Management,2005,36(1):15-36.
GANTZ J,REINSEL D.Extracting Value from Chaos[J].IDC Iview,2011:1-12.
龚健雅.人工智能时代测绘遥感技术的发展机遇与挑战[J].武汉大学学报·信息科学版,2018,43(12):1788-1796.KUI Jianya.Chances and Challenges for Development of Surveying and Remote Sensing in the Age of Artificial Intelligence[J].Geomatics and Information Science of Wuhan University,2018,43(12):1788-1796.
李德仁.脑认知与空间认知---论空间大数据与人工智能的集成[J].武汉大学学报·信息科学版,2018,43(12):1761-1767.LI Deren.Brain Cognition and Spatial Cognition:On Integration of Geo-spatial Big Data and Artificial Intelligence[J].Geomatics and Information Science of Wuhan University,2018,43(12):1761-1767.
腾讯研究院.中国信息通信研究院互联网法律研究中.人工智能.国家人工智能战略行动抓手[M].北京:中国人民大学出版社,2017.Tencent ResearchInstitute.China Academy of Information and Communications Technology.Artificial Intelligence:National Artificial Intelligence Strategic Action Grasp[M].Beijing:China Renmin University Press,2017.
张茂省.地灾调查评估是移民搬迁的关键[J].水文地质工程地质,2011,37(05):143.ZHANGMaosheng.Geological Hazard Investigation and Assessment Is The key To Resettlement[J].Hydrogeology and Engineering Geology,2011,37(05):143.
张茂省,李林,唐亚明,等.基于风险理念的黄土滑坡调查与编图研究[J].工程地质学报,2011,19(1):43-51.ZHANG Maosheng,LI Lin,TANG Yaming,et al.Risk Management based on Landslide Investigation and Mapping in Loessarea[J].Journal of Engineering Geology,2011,19(1):43-51.
张茂省,程秀娟,董英,等.冻结滞水效应及其促滑机理-以甘肃黑方台地区为例[J].地质通报,2013,32(06):852-860.ZHANG Maosheng,CHENG Xiujuan,DONG Ying,et al.The Effect of Frozen Stagnant Water and Its Impact on Slope Stability:A Case Study of Heifangtai,Gansu Province[J].Geological Bulletin Of China,2013,32(06):852-860.
殷跃平,王猛,李滨,等.延安市宝塔区地质灾害详细调查示范[J].西北地质,2007,40(2):29-55.YIN Yaoping,WANG Meng,LI Bin,et al.Detailed Investigation and Demonstration of Geological Disasters in Baota District,Yan'an City[J].Northwestern Geology,2007,40(2):29-55.
殷跃平,吴树仁.滑坡监测预警与应急防治技术研究[M].北京:科学出版社,2012.YIN Yaoping,WU Shuren.Landslide Monitoring Early Warning and Emergency Prevention Technology Research[M].Bijing:Science Press,2012.
张茂省,唐亚明.地质灾害风险调查的方法与实践[J].地质通报,2008a,27(08):1205-1216.ZHANG Maosheng,TANG Yaming.Risk Investigation Method and Practice of Geohazards[J].Geological Bulletin of China,2008,27(08):1205-1216.
张茂省,雷学武,校培喜,等.遥感技术在黄土高原区地质灾害详细调查中的应用[J].西北地质,2007,40(3):92-97.ZHANG Maosheng,LEI Xuewu,JIAO Peixi,et al.Application of Remote Sensing Technology in Detailed Investigation of Geological Hazards in the Loess Plateau[J].Northwestern Geology,2007,40(3):92-97.
张茂省.延安宝塔区滑坡崩塌地质灾害[M].北京:地质出版社,2008.ZHANG Maosheng.Geological Disaster of Landslide Collapse in Baota District,Yan'an[M].Bejing:Geological Press,2008.
刘传正.地质灾害风险识别方法[J].中国地质灾害与防治学报,2018,39(6):3.LIU Chuanzheng.Geological Disaster Risk Identification Method[J].The Chinese Journal of Geological Hazard and Control,2018,29(6):3.
刘传正.崩塌滑坡灾害风险识别方法初步研究[J].工程地质学报,2019,27(1):88-97.LIU Chuanzheng.Preliminary Study on The Identification Method of Collapse and Landslide Disaster Risk[J].Journal of Engineering Geology,2019,27(1):88-97.
张茂省,王尧.基于风险的地质环境承载力评价[J].地质通报,2018,37(2-3):467-475.ZHANG Maosheng,WANG Yao.Research on The Evaluation of The Carrying Capacity of Geological Environment based on Its Risk Level[J].Geological Bulletin of China,2018,37(2-3):467-475.
吴树仁,石菊松.多级旋转黄土滑坡形成机理及失稳模式.吉林大学学报(地球科学版),2012,4 2(3):26-27.WU Shuren,SHI Jusong.Formation Mechanism and Instability Mode of Multi-stage Rotating Loess Landslide[J].Journal of Jilin University:Earth Science Edition,2012,42(3):26-27.
张丽君.法国滑坡灾害风险预防管理政策[J].国土资源情报,2006,13(10):13-18.ZHANG Lijun.French Landslide Disaster Risk Prevention Management Policy[J].Land and Resources Information,2006,13(10):13-18.
陈松灿,高阳.中国机器学习白皮书[M].北京:中国人工智能学会,2015.CHEN Songcan,GAO Yang.Chinese Machine Learning White Paper[M].Beijing:Chinese Association for Artificial Intelligence,2015.
李学龙,龚海刚.大数据系统综述[J].中国科学:信息科学,2015,45(1):1-44.LI Xuelong,GONG Haigang.A survey on big data systems[J].Scientia Sinica Informationis,2015,45(1):1-44.
张珊珊,张茂省,孙萍萍,等.面向黄土地质灾害的优势流研究[J].兰州大学学报(自然科学版),2019,55(2):274-280.ZHANG Shanshan,ZHANG Maosheng,SUN Pingping,et al.Advances and outlooks of preferential flow study in unsaturated soils[J].Journal of Lanzhou University:Natural Sciences,2019,55(2):274-280.
MARKUS REICHSTEIN,Gustau Camps-Valls,Bjorn Stevens,et al.Deep learning and process understanding for data-driven Earth system science[J].Nature,2019,566(7743):195-204.
HINTON G,OSINDERO S,WELLING M,et al.Unsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation[J].Cognitive Science,2006,30(4):725-731.
HUNGR O,FELL R,R,RRPetroleum Geology,2005,22(1-2):0-nagement[J].Crc Press,2005,7(2):117-124.
NADIM F,KVALSTAD T J,GUTTORMSEN T.Quantification of risks associated with seabed instability at Ormen Lange[J].Marine and Petroleum Geology,2005,22(1-2):0-318.
PICARELLI L,URCIUOLI G,RAMONDINI M,et al.Main features of mudslides in tectonised highly fissured clay shales[J].Landslides,2005,2(1):15-30.
GUZZETTI FAUSTO,STARK CONLIN P,SALVATI PA-OLA.Evaluation of Flood and Landslide Risk to The Population of Italy[J].Environmental Management,2005,36(1):15-36.
GANTZ J,REINSEL D.Extracting Value from Chaos[J].IDC Iview,2011:1-12.