WO2021174971A1 - 一种水环境风险预测预警方法 - Google Patents
一种水环境风险预测预警方法 Download PDFInfo
- Publication number
- WO2021174971A1 WO2021174971A1 PCT/CN2020/140224 CN2020140224W WO2021174971A1 WO 2021174971 A1 WO2021174971 A1 WO 2021174971A1 CN 2020140224 W CN2020140224 W CN 2020140224W WO 2021174971 A1 WO2021174971 A1 WO 2021174971A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- pollution
- early warning
- risk prediction
- risk
- value
- Prior art date
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000007613 environmental effect Effects 0.000 claims abstract description 33
- 238000012544 monitoring process Methods 0.000 claims abstract description 10
- 238000011156 evaluation Methods 0.000 claims abstract description 8
- 238000011160 research Methods 0.000 claims abstract description 7
- 238000003912 environmental pollution Methods 0.000 claims abstract description 5
- 239000003344 environmental pollutant Substances 0.000 claims description 42
- 231100000719 pollutant Toxicity 0.000 claims description 42
- 238000005516 engineering process Methods 0.000 claims description 17
- 238000012502 risk assessment Methods 0.000 claims description 13
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 238000003066 decision tree Methods 0.000 claims description 8
- 238000013136 deep learning model Methods 0.000 claims description 8
- 238000007637 random forest analysis Methods 0.000 claims description 8
- 238000012706 support-vector machine Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 5
- 230000010354 integration Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000007812 deficiency Effects 0.000 abstract 1
- 230000002708 enhancing effect Effects 0.000 abstract 1
- 238000003911 water pollution Methods 0.000 description 3
- 238000005094 computer simulation Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000013058 risk prediction model Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003891 environmental analysis Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000007711 solidification Methods 0.000 description 1
- 230000008023 solidification Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F1/00—Treatment of water, waste water, or sewage
- C02F1/008—Control or steering systems not provided for elsewhere in subclass C02F
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24143—Distances to neighbourhood prototypes, e.g. restricted Coulomb energy networks [RCEN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/001—Upstream control, i.e. monitoring for predictive control
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/005—Processes using a programmable logic controller [PLC]
- C02F2209/008—Processes using a programmable logic controller [PLC] comprising telecommunication features, e.g. modems or antennas
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/12—Alarms for ensuring the safety of persons responsive to undesired emission of substances, e.g. pollution alarms
Definitions
- the invention belongs to the technical field of water environment management, and specifically relates to a water environment risk prediction and early warning method.
- the water environment risk prediction method is a key technology for the early warning and emergency response of sudden water pollution in the river basin.
- the technical requirements for emergency management of water environmental accidents have become higher and higher.
- the accident process can be quickly simulated and emergency response can be carried out.
- the use of advanced information technologies such as network, computer simulation and database management systems to establish a water pollution accident impact prediction and early warning technology system is a hot topic of current research.
- the advantage of this model calculation is that it can not only numerically simulate and analyze the physical and chemical conditions of the water environment, but also combine computer simulation technology to visually display the accident simulation process, and provide the urgently needed decision-making basis for the management and decision-making level to respond quickly.
- the purpose of the present invention is to provide a water environment risk prediction and early warning method suitable for river basins.
- a water environment risk prediction and early warning method including the following steps:
- Pollution sources that require environmental risk prediction and early warning are classified into different risk prediction and early warning levels according to their basic pollution index parameters; different pollution sources are predicted according to their risk prediction and early warning levels corresponding to the risk prediction and early warning cycle;
- V V1*w1+V2*w2+V3*w3+V3*w4+V5*w5
- V1, V2, V3, V4, and V5 are the values of historical pollution emissions, pollutant types, pollutant characteristics, pollutant discharge points, and pollution event impact range respectively;
- the value of historical pollution discharge is the ratio of the historical pollution discharge of this pollution source to the average value of historical pollution discharge across the country; the value of the pollutant type is assigned to different pollutant types. The more severe the damage of the pollutant type, the corresponding The higher the pollutant type value; the higher the pollutant characteristics are values assigned to different concentrations, the higher the hazard, the higher the corresponding pollutant characteristic value, the more pollutant emission points, the higher the corresponding pollutant emission point distribution value; the pollution incident The value of the impact range is assigned to different impact ranges. The greater the impact on the ecological environment, the higher the impact range of the corresponding pollution event;
- the pollution source is classified into the corresponding risk prediction and warning level.
- the evaluation method of the fuzzy comprehensive risk prediction and early warning model includes establishing the membership function according to the hierarchical structure relationship among the target layer, the system layer, the criterion layer, and the index layer, and calculating the membership degree of each pollution element to the risk prediction and early warning level ; According to the relationship between the levels of the pollution element system, the structural model is established, and the fuzzy relationship matrix is established through the relative membership function; the final risk prediction and early warning result is determined according to the principle of maximum membership.
- the risk prediction and early warning method further includes adopting a sampling evaluation method to assess pollution sources in a river basin:
- the overall pollution event risk value of the watershed is calculated, and the average value of the pollution event risk value of each pollution source sample is taken as the pollution event risk value of the watershed pollution source.
- the present invention has the following advantages:
- the present invention realizes the prediction of the pollution risk of the river basin, overcomes the problem of low efficiency of the existing single-point risk prediction and processing, and makes up for the vacancy of the existing pollution risk prediction and early warning of the river basin;
- the present invention screens the pollution sources that need risk prediction and early warning, and predicts the pollution sources that need risk prediction and early warning according to different risk prediction and early warning levels and with different risk prediction and early warning cycles, which overcomes the existing pollution risks.
- the forecasting and early warning method is single, dealing with the problem of solidification, while supervising the safety of a large number of pollution sources, while reducing the complexity of pollution source risk forecasting and early warning;
- the present invention trains and generates multiple pollution risk prediction models, selects several prediction models with the best performance for fuzzy risk prediction, and combines the advantages of multiple risk prediction models to improve the accuracy of risk prediction.
- the pollution discharge information module is used to predict the discharge information of all pollution sources in the basin based on the water environment model
- the primary screening module is used to screen the pollution sources in the basin based on the pollution discharge information, and select the pollution sources that require environmental risk prediction and early warning;
- the classification module is used to classify pollution sources that require environmental risk prediction and early warning into different risk prediction and early warning levels according to their basic pollution index parameters; different pollution sources are predicted according to the risk prediction and early warning cycle corresponding to their risk prediction and early warning levels;
- the element pollution element determination module is used to preliminarily determine element pollution elements for environmental pollution risk assessment from environmental monitoring department data, the National Meteorological Information Center, and literature research;
- the secondary screening module is used to screen the preliminarily determined element pollution elements to obtain the main element pollution elements that affect the pollution event;
- the training module is used to collect historical pollution event data. Based on the main elements of pollution, it can classify naive Bayes, random forest, KNN nearest neighbor classification, support vector machine, decision tree, and high-resolution remote sensing based on convolutional neural network.
- the deep learning model of image recognition technology is trained to generate multiple environmental risk prediction and early warning models;
- Evaluation module used to evaluate the environmental risk prediction and early warning generated by deep learning model training based on naive Bayes, random forest, KNN nearest neighbor classification, support vector machine, decision tree, and high-resolution remote sensing image recognition technology based on convolutional neural network Model performance, select several risk prediction and early warning models with the best performance to form a fuzzy comprehensive risk prediction and early warning model;
- the prediction module is used to collect the value of the main element pollution element corresponding to the pollution source that requires risk prediction and early warning through the application of high-precision remote sensing environmental monitoring technology and sensor network technology integration, and input the value of the main element pollution element into the fuzzy synthesis formed by the joint Risk prediction and early warning model to predict the risk value of pollution incidents of pollution sources.
- the specific water environment risk prediction and early warning method includes the following steps:
- Pollution sources that require environmental risk prediction and early warning are classified into different risk prediction and early warning levels according to their basic pollution index parameters; different pollution sources are predicted according to their risk prediction and early warning levels corresponding to the risk prediction and early warning cycle;
- the different risk prediction and early warning levels are specifically as follows:
- V V1*w1+V2*w2+V3*w3+V3*w4+V5*w5
- V1, V2, V3, V4, and V5 are the values of historical pollution emissions, pollutant types, pollutant characteristics, pollutant discharge points, and pollution event impact range respectively;
- the value of historical pollution discharge is the ratio of the historical pollution discharge of this pollution source to the average value of historical pollution discharge across the country; the value of the pollutant type is assigned to different pollutant types. The more severe the damage of the pollutant type, the corresponding The higher the pollutant type value; the higher the pollutant characteristics are values assigned to different concentrations, the higher the hazard, the higher the corresponding pollutant characteristic value, the more pollutant emission points, the higher the corresponding pollutant emission point distribution value; the pollution incident The value of the impact range is assigned to different impact ranges. The greater the impact on the ecological environment, the higher the impact range of the corresponding pollution event;
- the pollution source is classified into the corresponding risk prediction and warning level.
- the evaluation method of the fuzzy comprehensive risk prediction and early warning model includes establishing the membership function according to the hierarchical structure relationship among the target layer, the system layer, the criterion layer, and the index layer, and calculating the membership degree of each pollution element to the risk prediction and early warning level ; According to the relationship between the levels of the pollution element system, the structural model is established, and the fuzzy relationship matrix is established through the relative membership function; the final risk prediction and early warning result is determined according to the principle of maximum membership.
- the risk prediction and early warning method further includes adopting a sampling evaluation method to assess pollution sources in a river basin:
- the overall pollution event risk value of the watershed is calculated, and the average value of the pollution event risk value of each pollution source sample is taken as the pollution event risk value of the watershed pollution source.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Emergency Management (AREA)
- Probability & Statistics with Applications (AREA)
- Organic Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Water Supply & Treatment (AREA)
Abstract
一种水环境风险预测预警方法,基于水环境模型预测流域内所有污染源的排污信息;选出需要进行环境风险预测预警的污染源;划分为不同的风险预测预警等级;从环境监测部门资料及文献调研中初步确定环境污染风险评价的要素污染要素;获得影响污染事件的主要要素污染要素;生成多个环境风险预测预警模型;选择性能最好的几个风险预测预警模型联合形成模糊综合风险预测预警模型;将主要要素污染要素的值输入联合形成的模糊综合风险预测预警模型,预测污染源污染事件的风险值。该方法实现了流域污染风险的预测,弥补了现有的流域污染风险预测和预警的空缺;提高了流域污染风险预测的污染预测覆盖率,提升了风险预测的准确率。
Description
本发明属于水环境管理技术领域,具体涉及一种水环境风险预测预警方法。
水环境风险预测方法是流域突发水污染预警应急的关键技术。近几年来,随着环境管理定量化、系统化、信息化的发展,对水环境事故应急管理的技术要求越来越高。尤其是在发生水环境污染事故时能快速模拟事故过程,并能进行紧急响应。利用网络、计算机仿真和数据库管理系统等先进的信息技术,建立水污染事故影响预测预警技术体系是当前研究的热点问题。这种模型计算的优点是既能数值模拟分析水环境的物理化学条件,又能结合计算机仿真技术,直观展示事故模拟过程,为管理决策层进行紧急响应快速提供所急需的决策依据。
目前有关水污染事故影响预测预警的技术研究及应用,一般针对确定污染源监测点开发定制,缺乏对整个流域环境分析预测的通用性和普适性。
本发明的目的是,提供一种适用于流域的水环境风险预测预警方法。
具体技术方案为:
一种水环境风险预测预警方法,包括以下步骤:
(1)基于水环境模型预测流域内所有污染源的排污信息;
(2)基于所述排污信息对流域内的污染源进行筛选,选出需要进行环境风险预测预警的污染源;
(3)对需要进行环境风险预测预警的污染源根据其基本污染指标参数划分为不同的风险预测预警等级;不同的污染源根据其风险预测预警等级对应的风险预测预警周期进行预测;
(4)从环境监测部门资料及文献调研中初步确定环境污染风险评价的要素污染要素;
(5)对初步确定的要素污染要素进行筛选,获得影响污染事件的主要要素污染要素;
(6)采集历史污染事件数据,基于确定的主要要素污染要素分别对朴素贝叶斯、随机森林、KNN最近邻分类、支持向量机、决策树和基于卷积神经网络的高分辨率遥感图像识别技术的深度学习模型进行训练,生成多个环境风险预测预警模型;
(7)评估朴素贝叶斯、随机森林、KNN最近邻分类、支持向量机、决策树和基于卷积神经网络的高分辨率遥感图像识别技术的深度学习模型训练生成的环境风险预测预警模型的性能,选择性能最好的几个风险预测预警模型联合形成模糊综合风险预测预警模型;
(8)通过高精度遥感环境监测技术和传感网技术相互集成应用采集需要进行风险预测预警污染源所对应的主要要素污染要素的值,将主要要素污染要素的值输入联合形成的模糊综合风险预测预警模型,预测污染源污染事件的风险值。
其中,所述根据其基本污染指标参数划分为不同的风险预测预警等级具体为:
设置历史污染排放量、污染物种类、污染物特性、污染物排放点、污染事件影响范围的权重依次为w1、w2、w3、w4、w5,其中,w1+w2+w3+w4+w5=1;污染源对应的污染事件风险评估值为:
V=V1*w1+V2*w2+V3*w3+V3*w4+V5*w5
其中,V1、V2、V3、V4、V5分别为历史污染排放量、污染物种类、污染物特性、污染物排放点、污染事件影响范围的值;
历史污染排放量的值为该污染源历史污染排放量与全国范围内历史污染排放量平均值的比值;污染物种类的值为分别赋予不同污染物种类的值,污染物种类危害越陡,相应的污染物种类值越高;污染物特性为赋予不同浓度的值,危害越高,相应的污染物特性值越高,污染物排放点越多,相应的污染物排放点分布值越高;污染事件影响范围的值为分别赋予不同影响范围的值,对生态环境的影响越大,相应的污染事件影响范围值越高;
基于计算出的风险评估值,将污染源划分到相应的风险预测预警等级,风险评估值越高,风险预测预警等级越高。
所述的模糊综合风险预测预警模型的评价法,包括根据目标层、系统层、准则层、指标层间层次结构关系,建立隶属度函数,并计算出各污染要素对于风险预测预警等级的隶属度;根据污染要素体系各层级关系,建立结构模型,通过相对隶属度函数建立模糊关系矩阵;根据最大隶属度的原则确定最终风险预测预警结果。
进一步的,所述风险预测预警方法还包括,采用抽样评价方法进行流域污染源评估:
计算各污染源污染事件预警级别所对应污染源数占流域污染源总数的比例,设置抽样的样本总数,根据抽样样本总数及各污染事件预警级别的比例,计算各污染事件预警级别所对应的抽样样本数;
随机在各污染事件预警级别的污染源中抽取相应数量的污染源;
在不需要进行环境风险预测预警的污染源中进行抽取,直到抽取的污染源数量达到抽样的样本总数;
根据抽样的污染源样本,计算流域的整体污染事件风险值,将各污染源样本的污染事件风险值的平均值作为流域性污染源的污染事件风险值。
本发明的优点主要有:
与现有技术相比,本发明具有如下优点:
(1)本发明实现了流域污染风险的预测,克服了现有的单点风险预测处理效率低的问题,弥补了现有的流域污染风险预测和预警的空缺;
(2)由于逐个污染源的单点预测处理复杂,因此现有的流域污染风险预测预警覆盖低,对于大量的污染源并没有实现有效的监管,本发明同时对流域内的所有污染源进行监管,提高了流域污染风险预测的污染预测覆盖率;
(3)本发明对需要进行风险预测预警的污染源进行筛选,并对需要进行风险预测预警的污染源根据不同的风险预测预警等级、以不同的风险预测预警周期进行预测,克服了现有的污染风险预测预警方法单一,处理固化的问题,在对大量污染源进行安全监管的同时,降低污染源风险预测预警的复杂度;
(4)本发明训练生成多个污染风险预测模型,并选择性能最好的几个预测模型进行模糊风险预测,结合多个风险预测模型的优点,提升了风险预测的准确率。
以下结合具体实施例,对本发明作进一步说明,但本发明的保护范围并不仅限于此。
构建流域性环境风险预测预警系统,包括:
排污信息模块,用于基于水环境模型预测流域内所有污染源的排污信息;
初级筛选模块,用于基于所述排污信息对流域内的污染源进行筛选,选出需要进行环境风险预测预警的污染源;
等级划分模块,用于对需要进行环境风险预测预警的污染源根据其基本污染指标参数划分为不同的风险预测预警等级;不同的污染源根据其风险预测预警等级对应的风险预测预警周期进行预测;
要素污染要素确定模块,用于从环境监测部门资料、国家气象信息中心及文献调研中初步确定环境污染风险评价的要素污染要素;
次级筛选模块,用于对初步确定的要素污染要素进行筛选,获得影响污染事件的主要要素污染要素;
训练模块,用于采集历史污染事件数据,基于确定的主要要素污染要素分别对朴素贝叶斯、随机森林、KNN最近邻分类、支持向量机、决策树和基于卷积神经网络的高分辨率遥感图像识别技术的深度学习模型进行训练,生成多个环境风险预测预警模型;
评估模块,用于评估朴素贝叶斯、随机森林、KNN最近邻分类、支持向量机、决策树和基于卷积神经网络的高分辨率遥感图像识别技术的深度学习模型训练生成的环境风险预测预警模型的性能,选择性能最好的几个风险预测预警模型联合形成模糊综合风险预测预警模型;
预测模块,用于通过高精度遥感环境监测技术和传感网技术相互集成应用采集需要进行风险预测预警污染源所对应的主要要素污染要素的值,将主要要素污染要素的值输入联合形成的模糊综合风险预测预警模型,预测污染源污染事件的风险值。
实施例1
具体的水环境风险预测预警方法,包括以下步骤:
(1)基于水环境模型预测流域内所有污染源的排污信息;
(2)基于所述排污信息对流域内的污染源进行筛选,选出需要进行环境风险预测预警的污染源;
(3)对需要进行环境风险预测预警的污染源根据其基本污染指标参数划分为不同的风险预测预警等级;不同的污染源根据其风险预测预警等级对应的风险预测预警周期进行预测;
所述根据其基本污染指标参数划分为不同的风险预测预警等级具体为:
设置历史污染排放量、污染物种类、污染物特性、污染物排放点、污染事件影响范围的权重依次为w1、w2、w3、w4、w5,其中,w1+w2+w3+w4+w5=1;污染源对应的污染事件风险评估值为:
V=V1*w1+V2*w2+V3*w3+V3*w4+V5*w5
其中,V1、V2、V3、V4、V5分别为历史污染排放量、污染物种类、污染物特性、污染物排放点、污染事件影响范围的值;
历史污染排放量的值为该污染源历史污染排放量与全国范围内历史污染排放量平均值的比值;污染物种类的值为分别赋予不同污染物种类的值,污染物种类危害越陡,相应的污染物种类值越高;污染物特性为赋予不同浓度的值,危害越高,相应的污染物特性值越高,污染物排放点越多,相应的污染物排放点分布值越高;污染事件影响范围的值为分别赋予不同影响范围的值,对生态环境的影响越大,相应的污染事件影响范围值越高;
基于计算出的风险评估值,将污染源划分到相应的风险预测预警等级,风险评估值越高,风险预测预警等级越高。
(4)从环境监测部门资料及文献调研中初步确定环境污染风险评价的要素污染要素;
(5)对初步确定的要素污染要素进行筛选,获得影响污染事件的主要要素污染要素;
(6)采集历史污染事件数据,基于确定的主要要素污染要素分别对朴素贝叶斯、随机森林、KNN最近邻分类、支持向量机、决策树和基于卷积神经网络的高分辨率遥感图像识别技术的深度学习模型进行训练,生成多个环境风险预测预警模型;
(7)评估朴素贝叶斯、随机森林、KNN最近邻分类、支持向量机、决策树和基于卷积神经网络的高分辨率遥感图像识别技术的深度学习模型训练生成的环境风险预测预警模型的性能,选择性能最好的几个风险预测预警模型联合形成模糊综合风险预测预警模型;
所述的模糊综合风险预测预警模型的评价法,包括根据目标层、系统层、准则层、指标层间层次结构关系,建立隶属度函数,并计算出各污染要素对于风险预测预警等级的隶属度;根据污染要素体系各层级关系,建立结构模型,通过相对隶属度函数建立模糊关系矩阵;根据最大隶属度的原则确定最终风险预测预警结果。
(8)通过高精度遥感环境监测技术和传感网技术相互集成应用采集需要进行风险预测预警污染源所对应的主要要素污染要素的值,将主要要素污染要素的值输入联合形成的模糊综合风险预测预警模型,预测污染源污染事件的风险值。
实施例2
在实施例1的基础上,所述风险预测预警方法还包括,采用抽样评价方法进行流域污染源评估:
计算各污染源污染事件预警级别所对应污染源数占流域污染源总数的比例,设置抽样的样本总数,根据抽样样本总数及各污染事件预警级别的比例,计算各污染事件预警级别所对应的抽样样本数;
随机在各污染事件预警级别的污染源中抽取相应数量的污染源;
在不需要进行环境风险预测预警的污染源中进行抽取,直到抽取的污染源数量达到抽样的样本总数;
根据抽样的污染源样本,计算流域的整体污染事件风险值,将各污染源样本的污染事件风险值的平均值作为流域性污染源的污染事件风险值。
Claims (4)
- 一种水环境风险预测预警方法,其特征在于,包括以下步骤:(1)基于水环境模型预测流域内所有污染源的排污信息;(2)基于所述排污信息对流域内的污染源进行筛选,选出需要进行环境风险预测预警的污染源;(3)对需要进行环境风险预测预警的污染源根据其基本污染指标参数划分为不同的风险预测预警等级;不同的污染源根据其风险预测预警等级对应的风险预测预警周期进行预测;(4)从环境监测部门资料及文献调研中初步确定环境污染风险评价的要素污染要素;(5)对初步确定的要素污染要素进行筛选,获得影响污染事件的主要要素污染要素;(6)采集历史污染事件数据,基于确定的主要要素污染要素分别对朴素贝叶斯、随机森林、KNN最近邻分类、支持向量机、决策树和基于卷积神经网络的高分辨率遥感图像识别技术的深度学习模型进行训练,生成多个环境风险预测预警模型;(7)评估朴素贝叶斯、随机森林、KNN最近邻分类、支持向量机、决策树和基于卷积神经网络的高分辨率遥感图像识别技术的深度学习模型训练生成的环境风险预测预警模型的性能,选择性能最好的几个风险预测预警模型联合形成模糊综合风险预测预警模型;(8)通过高精度遥感环境监测技术和传感网技术相互集成应用采集需要进行风险预测预警污染源所对应的主要要素污染要素的值,将主要要素污染要素的值输入联合形成的模糊综合风险预测预警模型,预测污染源污染事件的风险值。
- 根据权利要求1所述的水环境风险预测预警方法,其特征在于,所述根据其基本污染指标参数划分为不同的风险预测预警等级具体为:设置历史污染排放量、污染物种类、污染物特性、污染物排放点、污染事件影响范围的权重依次为w 1、w 2、w 3、w 4、w 5,其中,w 1+w 2+w 3+w 4+w 5=1;污染源对应的污染事件风险评估值为:V=V 1*w 1+V 2*w 2+V 3*w 3+V 3*w 4+V 5*w 5其中,V 1、V 2、V 3、V 4、V 5分别为历史污染排放量、污染物种类、污染物特性、污染物排放点、污染事件影响范围的值;历史污染排放量的值为该污染源历史污染排放量与全国范围内历史污染排放量平均值的比值;污染物种类的值为分别赋予不同污染物种类的值,污染物种类危害越陡,相应的污染物种类值越高;污染物特性为赋予不同浓度的值,危害越高,相应的污染物特性值越高,污染物排放点越多,相应的污染物排放点分布值越高;污染事件影响范围的值为分别赋予不同影响范围的值,对生态环境的影响越大,相应的污染事件影响范围值越高;基于计算出的风险评估值,将污染源划分到相应的风险预测预警等级,风险评估值越高,风险预测预警等级越高。
- 根据权利要求1所述的水环境风险预测预警方法,其特征在于,所述的模糊综合风险预测预警模型的评价法,包括根据目标层、系统层、准则层、指标层间层次结构关系,建立隶属度函数,并计算出各污染要素对于风险预测预警等级的隶属度;根据污染要素体系各层级关系,建立结构模型,通过相对隶属度函数建立模糊关系矩阵;根据最大隶属度的原则确定最终风险预测预警结果。
- 根据权利要求1所述的水环境风险预测预警方法,其特征在于,所述风险预测预警方法还包括,采用抽样评价方法进行流域污染源评估:计算各污染源污染事件预警级别所对应污染源数占流域污染源总数的比例,设置抽样的样本总数,根据抽样样本总数及各污染事件预警级别的比例,计算各污染事件预警级别所对应的抽样样本数;随机在各污染事件预警级别的污染源中抽取相应数量的污染源;在不需要进行环境风险预测预警的污染源中进行抽取,直到抽取的污染源数量达到抽样的样本总数;根据抽样的污染源样本,计算流域的整体污染事件风险值,将各污染源样本的污染事件风险值的平均值作为流域性污染源的污染事件风险值。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US17/609,991 US11335179B1 (en) | 2020-08-03 | 2020-12-28 | Water environment risk prediction and early warning method |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010765484.4A CN111861274A (zh) | 2020-08-03 | 2020-08-03 | 一种水环境风险预测预警方法 |
CN202010765484.4 | 2020-08-03 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021174971A1 true WO2021174971A1 (zh) | 2021-09-10 |
Family
ID=72952665
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/140224 WO2021174971A1 (zh) | 2020-08-03 | 2020-12-28 | 一种水环境风险预测预警方法 |
Country Status (3)
Country | Link |
---|---|
US (1) | US11335179B1 (zh) |
CN (1) | CN111861274A (zh) |
WO (1) | WO2021174971A1 (zh) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114066077A (zh) * | 2021-11-22 | 2022-02-18 | 哈尔滨工业大学 | 基于应急事件空间警兆分析的环卫风险预测方法 |
CN115471115A (zh) * | 2022-10-01 | 2022-12-13 | 浙江嘉园智能科技有限公司 | 一种全域水体统一联治的电子河长控制系统 |
CN115774953A (zh) * | 2022-11-09 | 2023-03-10 | 安徽新宇环保科技股份有限公司 | 一种基于数据处理的污染时空风险监管评估系统及方法 |
CN116307385A (zh) * | 2023-03-16 | 2023-06-23 | 深圳市勘察测绘院(集团)有限公司 | 一种基于极端环境勘探作业档案数据分析方法 |
CN116363047A (zh) * | 2022-08-23 | 2023-06-30 | 生态环境部卫星环境应用中心 | 一种秸秆焚烧大气污染风险预警方法 |
CN116882753A (zh) * | 2023-07-20 | 2023-10-13 | 生态环境部南京环境科学研究所 | 一种水环境生态健康风险评价方法及系统 |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111861274A (zh) * | 2020-08-03 | 2020-10-30 | 生态环境部南京环境科学研究所 | 一种水环境风险预测预警方法 |
CN112507048B (zh) * | 2020-11-11 | 2022-06-17 | 中国地质调查局水文地质环境地质调查中心 | 一种污染场地水土环境多要素一站式管理系统 |
CN112344998A (zh) * | 2020-11-20 | 2021-02-09 | 生态环境部南京环境科学研究所 | 一种流域水环境功能分区水环境生态安全预警方法 |
CN112529303A (zh) * | 2020-12-15 | 2021-03-19 | 建信金融科技有限责任公司 | 基于模糊决策的风险预测方法、装置、设备和存储介质 |
CN112668911B (zh) * | 2020-12-31 | 2021-09-24 | 哈尔滨工业大学 | 水域岸线污染风险评估方法及控制智能决策方法和系统 |
CN113159425B (zh) * | 2021-04-24 | 2022-10-04 | 杭州尚青科技有限公司 | 一种区域工业水污染日排放量预测方法和装置 |
CN113537328B (zh) * | 2021-07-07 | 2023-10-31 | 大连理工大学人工智能大连研究院 | 一种基于深度学习的旋转机械故障诊断方法和装置 |
CN113537515A (zh) * | 2021-07-27 | 2021-10-22 | 江苏蓝创智能科技股份有限公司 | Pm2.5预测方法、系统、装置及存储介质 |
CN113688940A (zh) * | 2021-09-09 | 2021-11-23 | 浙江大学 | 一种基于公开数据的疑似污染工业企业识别方法 |
CN113869562A (zh) * | 2021-09-10 | 2021-12-31 | 中铁二十局集团有限公司 | 异常事件响应等级确定方法、装置、设备及可读存储介质 |
CN116703679A (zh) * | 2023-06-21 | 2023-09-05 | 北京市生态环境保护科学研究院 | 一种用于工业企业和工业园区的环保管理系统及管理方法 |
CN117216667B (zh) * | 2023-11-08 | 2024-02-06 | 深圳市芯科云科技有限公司 | 一种基于智能手表监测环境污染度的处理方法及系统 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104992245A (zh) * | 2015-07-09 | 2015-10-21 | 南京信息工程大学 | 一种基于广义熵理论的水环境风险管理动态智能综合分析方法 |
CN105426993A (zh) * | 2015-11-10 | 2016-03-23 | 中国环境科学研究院 | 一种流域水环境安全预警方法及系统 |
CN107609742A (zh) * | 2017-08-14 | 2018-01-19 | 环境保护部华南环境科学研究所 | 一种水环境预警综合管理平台 |
CN108009736A (zh) * | 2017-12-13 | 2018-05-08 | 北京北华中清环境工程技术有限公司 | 一种水质预警预报系统及水质预警预报方法 |
US20180373993A1 (en) * | 2017-06-23 | 2018-12-27 | University Of Alaska Fairbanks | Method Of Predicting Streamflow Data |
CN111861274A (zh) * | 2020-08-03 | 2020-10-30 | 生态环境部南京环境科学研究所 | 一种水环境风险预测预警方法 |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9726782B2 (en) * | 2012-11-30 | 2017-08-08 | International Business Machines Corporation | Methods, systems and computer program storage devices for generating a response to flooding |
US11519146B2 (en) * | 2018-04-17 | 2022-12-06 | One Concern, Inc. | Flood monitoring and management system |
TWI662422B (zh) * | 2018-04-23 | 2019-06-11 | 國家中山科學研究院 | Air quality prediction method based on machine learning model |
US10977924B2 (en) * | 2018-12-06 | 2021-04-13 | Electronics And Telecommunications Research Institute | Intelligent river inundation alarming system and method of controlling the same |
CN111047099B (zh) * | 2019-12-16 | 2020-08-21 | 杭州鲁尔物联科技有限公司 | 一种区域性山洪风险预测方法及系统 |
-
2020
- 2020-08-03 CN CN202010765484.4A patent/CN111861274A/zh active Pending
- 2020-12-28 WO PCT/CN2020/140224 patent/WO2021174971A1/zh active Application Filing
- 2020-12-28 US US17/609,991 patent/US11335179B1/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104992245A (zh) * | 2015-07-09 | 2015-10-21 | 南京信息工程大学 | 一种基于广义熵理论的水环境风险管理动态智能综合分析方法 |
CN105426993A (zh) * | 2015-11-10 | 2016-03-23 | 中国环境科学研究院 | 一种流域水环境安全预警方法及系统 |
US20180373993A1 (en) * | 2017-06-23 | 2018-12-27 | University Of Alaska Fairbanks | Method Of Predicting Streamflow Data |
CN107609742A (zh) * | 2017-08-14 | 2018-01-19 | 环境保护部华南环境科学研究所 | 一种水环境预警综合管理平台 |
CN108009736A (zh) * | 2017-12-13 | 2018-05-08 | 北京北华中清环境工程技术有限公司 | 一种水质预警预报系统及水质预警预报方法 |
CN111861274A (zh) * | 2020-08-03 | 2020-10-30 | 生态环境部南京环境科学研究所 | 一种水环境风险预测预警方法 |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114066077A (zh) * | 2021-11-22 | 2022-02-18 | 哈尔滨工业大学 | 基于应急事件空间警兆分析的环卫风险预测方法 |
CN114066077B (zh) * | 2021-11-22 | 2022-09-13 | 哈尔滨工业大学 | 基于应急事件空间警兆分析的环卫风险预测方法 |
CN116363047A (zh) * | 2022-08-23 | 2023-06-30 | 生态环境部卫星环境应用中心 | 一种秸秆焚烧大气污染风险预警方法 |
CN116363047B (zh) * | 2022-08-23 | 2024-01-30 | 生态环境部卫星环境应用中心 | 一种秸秆焚烧大气污染风险预警方法 |
CN115471115A (zh) * | 2022-10-01 | 2022-12-13 | 浙江嘉园智能科技有限公司 | 一种全域水体统一联治的电子河长控制系统 |
CN115471115B (zh) * | 2022-10-01 | 2023-10-31 | 浙江嘉园智能科技有限公司 | 一种全域水体统一联治的电子河长控制系统 |
CN115774953A (zh) * | 2022-11-09 | 2023-03-10 | 安徽新宇环保科技股份有限公司 | 一种基于数据处理的污染时空风险监管评估系统及方法 |
CN115774953B (zh) * | 2022-11-09 | 2024-04-26 | 安徽新宇环保科技股份有限公司 | 一种基于数据处理的污染时空风险监管评估系统及方法 |
CN116307385A (zh) * | 2023-03-16 | 2023-06-23 | 深圳市勘察测绘院(集团)有限公司 | 一种基于极端环境勘探作业档案数据分析方法 |
CN116307385B (zh) * | 2023-03-16 | 2023-08-25 | 深圳市勘察测绘院(集团)有限公司 | 一种基于极端环境勘探作业档案数据分析方法 |
CN116882753A (zh) * | 2023-07-20 | 2023-10-13 | 生态环境部南京环境科学研究所 | 一种水环境生态健康风险评价方法及系统 |
Also Published As
Publication number | Publication date |
---|---|
CN111861274A (zh) | 2020-10-30 |
US20220157149A1 (en) | 2022-05-19 |
US11335179B1 (en) | 2022-05-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11335179B1 (en) | Water environment risk prediction and early warning method | |
CN112506990B (zh) | 一种基于时空信息的水文数据异常检测方法 | |
CN110807562B (zh) | 一种区域性桥梁风险预测方法及系统 | |
CN106204392A (zh) | 环境风险源预警系统 | |
CN112465243B (zh) | 一种空气质量预报方法及系统 | |
CN113379267B (zh) | 一种基于风险分级预测的城市火灾事件处理方法、系统及存储介质 | |
Yang et al. | A novel comprehensive risk assessment method for sudden water accidents in the Middle Route of the South–North Water Transfer Project (China) | |
CN109784752A (zh) | 一种三峡库区水体富营养化风险评估预警系统及其分析方法 | |
Dimitriou et al. | Fuzzy modeling of freeway accident duration with rainfall and traffic flow interactions | |
CN102694800A (zh) | 网络安全态势预测的高斯过程回归方法 | |
CN110046812A (zh) | 城市安全发展水平的综合评价方法 | |
CN111223027A (zh) | 一种城市地震灾害风险评估方法及系统 | |
CN104376716A (zh) | 一种基于贝叶斯网络模型的公交时刻表动态生成方法 | |
CN111179592B (zh) | 基于时空数据流融合分析的城市交通预测方法和系统 | |
CN108537336B (zh) | 一种基于深度神经网络的空气质量预测方法 | |
CN113887872A (zh) | 一种基于态势评估技术的交通风险分级方法 | |
CN106327867A (zh) | 一种基于gps数据的公交准点预测方法 | |
CN106022635A (zh) | 一种区域水环境风险评估方法 | |
CN112434887A (zh) | 一种结合网络核密度估计和svm的供水管网风险预测方法 | |
CN116432864A (zh) | 一种区域营运驾驶员群体安全态势的预测方法及系统 | |
CN116681330A (zh) | 一种公路隧道机电系统运行状态分类及综合评价方法 | |
CN113642162B (zh) | 一种城市道路交通应急预案仿真综合分析方法 | |
CN115392618A (zh) | 一种基于ahp-ew和ae-rnn融合的食品安全风险预警模型及其建立方法 | |
CN111143774B (zh) | 一种基于影响因素多状态模型的电力负荷预测方法和装置 | |
Vekaria et al. | Using artificial intelligence for water pipeline infrastructure asset management |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20922830 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20922830 Country of ref document: EP Kind code of ref document: A1 |