CN114511784A - Environment monitoring and early warning method, device, equipment and storage medium - Google Patents
Environment monitoring and early warning method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114511784A CN114511784A CN202210143538.2A CN202210143538A CN114511784A CN 114511784 A CN114511784 A CN 114511784A CN 202210143538 A CN202210143538 A CN 202210143538A CN 114511784 A CN114511784 A CN 114511784A
- Authority
- CN
- China
- Prior art keywords
- data
- environment
- remote sensing
- sensing image
- image data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Remote Sensing (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The application relates to the field of artificial intelligence, and particularly discloses an environment monitoring and early warning method, device, equipment and storage medium, wherein the method comprises the following steps: acquiring environment actual measurement data and remote sensing image data, wherein the environment actual measurement data and the remote sensing image data comprise time data and positioning data; inputting the remote sensing image data into a pre-trained convolutional neural network model to generate environment element data corresponding to the remote sensing image data and a corresponding environment element label; generating a thermodynamic diagram according to the environment element data and the corresponding environment element label; creating a map model based on a geographic information system, and importing the environment measured data and the thermodynamic diagram into the map model; and generating a comparison result of the thermodynamic diagram and the environment measured data on the map model according to the time data and the positioning data, and displaying the comparison result. Based on the method, an environment monitoring system for realizing multi-dimensional and automatic early warning can be constructed.
Description
Technical Field
The application relates to the field of artificial intelligence, in particular to an environment monitoring and early warning method, device, equipment and storage medium.
Background
In the existing environment monitoring system, the environment monitoring system depends on a large number of monitoring devices arranged at earth surface points, so that the monitoring dimension is single, the monitoring range is small, missing situations often occur in monitoring and screening, the integrity and the macroscopicity are lacked, and meanwhile, the accuracy and the authenticity of monitoring data are difficult to verify, so that the aims of 'speaking with data, managing with data and making a decision with data' of a management department can not be really realized, and powerful support can not be provided for comprehensive supervision and scientific decision.
Disclosure of Invention
The application provides an environment monitoring and early warning method, device, equipment and storage medium, which are used for constructing an environment monitoring system for realizing multi-dimensional and automatic early warning.
In a first aspect, the present application provides an environmental monitoring and early warning method, including:
acquiring environment actual measurement data and remote sensing image data, wherein the environment actual measurement data and the remote sensing image data comprise time data and positioning data;
inputting the remote sensing image data into a pre-trained convolutional neural network model to generate environment element data corresponding to the remote sensing image data and a corresponding environment element label;
generating a thermodynamic diagram according to the environment element data and the corresponding environment element label;
creating a map model based on a geographic information system, and importing the environment measured data and the thermodynamic diagram into the map model;
and generating a comparison result of the thermodynamic diagram and the environment measured data on the map model according to the time data and the positioning data, and displaying the comparison result.
In a second aspect, the present application further provides an environmental monitoring and early warning device, the environmental monitoring and early warning device includes: the system comprises a data acquisition module, an element output module, an element synthesis module, a model construction module and a result comparison module;
the data acquisition module is used for inputting the remote sensing image data into a pre-trained convolutional neural network model and generating environment element data corresponding to the remote sensing image data and a corresponding environment element label;
the element output module is used for acquiring environmental element data and corresponding environmental element labels in the remote sensing image data based on a pre-trained convolutional neural network model;
the element synthesis module is used for generating a thermodynamic diagram according to the environment element data and the corresponding environment element label;
the model construction module is used for creating a map model based on a geographic information system and importing the environment measured data and the thermodynamic diagram into the map model;
and the result comparison module is used for generating a comparison result of the thermodynamic diagram and the environment actual measurement data on the map model according to the time data and the positioning data and displaying the comparison result.
In a third aspect, the present application further provides a computer device comprising a memory and a processor; the memory is used for storing a computer program; the processor is configured to execute the computer program and implement any one of the environmental monitoring and warning methods provided in the embodiments of the present application when the computer program is executed.
In a fourth aspect, the present application further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the processor is enabled to implement any one of the environmental monitoring and early warning methods provided in the embodiments of the present application.
The application discloses an environmental monitoring and early warning method, device, equipment and storage medium, wherein the method comprises the following steps: acquiring environment actual measurement data and remote sensing image data, wherein the environment actual measurement data and the remote sensing image data comprise time data and positioning data; inputting the remote sensing image data into a pre-trained convolutional neural network model to generate environment element data corresponding to the remote sensing image data and a corresponding environment element label; generating a thermodynamic diagram according to the environment element data and the corresponding environment element label; creating a map model based on a geographic information system, and importing the environment measured data and the thermodynamic diagram into the map model; and generating a comparison result of the thermodynamic diagram and the environment measured data on the map model according to the time data and the positioning data, and displaying the comparison result. According to the environment monitoring and early warning method provided by the application, the remote sensing image data is processed through the convolutional neural network model to generate the thermodynamic diagram, and the thermodynamic diagram and the environment measured data of the ground monitoring station are integrated through the geographic information system, so that a multi-dimensional environment monitoring system is realized, monitoring, screening and omission can be reduced, and automatic early warning of environment monitoring abnormity is realized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic view of an application scenario of an environment monitoring and early warning method provided in an embodiment of the present application;
fig. 2 is a schematic flow chart of an environment monitoring and early warning method provided in an embodiment of the present application;
FIG. 3 is a schematic diagram of monitoring water eutrophication provided by an embodiment of the present application;
fig. 4 is a schematic block diagram of an environment monitoring and early warning apparatus provided in an embodiment of the present application;
fig. 5 is a schematic block diagram of a structure of a computer device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The flow diagrams depicted in the figures are merely illustrative and do not necessarily include all of the elements and operations/steps, nor do they necessarily have to be performed in the order depicted. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
It is to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
In order to reduce monitoring screening omission and realize automatic early warning of environment monitoring abnormity, the application provides an environment monitoring early warning method, device, equipment and storage medium.
Embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a schematic view of an application scenario of an environment monitoring and early warning method, and as shown in fig. 1, the method may be applied to various environment data acquisition devices and data centers, and in particular, to an aviation flight device 11, an aerospace flight device 12, a ground monitoring device 13, and a data center 14. The aviation flight equipment 11 comprises an airplane and an unmanned aerial vehicle; space flight device 12 includes a satellite, for example, a high-resolution two-satellite; the ground monitoring device 13 is a plurality of environmental data collecting instruments arranged on the ground surface, for example, a sulfur dioxide concentration collecting instrument, an inhalable particle concentration collecting instrument and a water body temperature collecting instrument, and it should be noted that the ground monitoring device 13 can transmit the collected environmental data to the data center 14 by means of wired transmission or wireless transmission.
Referring to fig. 2, fig. 2 is a schematic flow chart of an environment monitoring and early warning method according to an embodiment of the present disclosure.
As shown in fig. 2, the environmental monitoring and early warning method at least includes the following steps: S101-S105.
S101, acquiring environment actual measurement data and remote sensing image data, wherein the environment actual measurement data and the remote sensing image data comprise time data and positioning data.
Specifically, the method comprises the steps of obtaining environment measured data of a plurality of monitoring stations laid on the earth surface, obtaining remote sensing image data of a space satellite and an aircraft shooting a monitoring area, and analyzing the obtained environment measured data and the obtained remote sensing image data at least to obtain time data and positioning data, wherein the time data is used for recording the moment or time interval when the environment measured data and the remote sensing image data are generated, and the positioning data is used for recording the longitude and latitude of the areas where the plurality of monitoring stations and the remote sensing image data are generated.
It should be noted that the monitoring station includes: the system comprises a monitoring sensor, an analyzer, communication node equipment, a collector and a wireless data transmission terminal. The communication node equipment is used for inputting the multi-channel test signals to a Data Transfer Unit (DTU) transmission channel inside the equipment in sequence through an interface protocol, inputting the multi-channel test signals to a Data collector inside the equipment after lightning protection processing, the Data collector is used for transmitting the collected Data to a Data storage center of an environment monitoring system through a wireless Data transmission terminal and a TCP/IP network, the Data storage center receives and stores the monitoring Data uploaded by a monitoring station according to the content specified by the transmission protocol, and the received Data is analyzed, stored, processed, audited, uploaded and the like, and is subjected to Data statistics, analysis and display on the Data storage center.
In some embodiments, the environmental measurement data includes at least: air quality data, water quality data, wherein, air quality data includes: sulfur dioxide concentration, nitrogen dioxide concentration, inhalable particle concentration and urban heat island effect, and the water quality data comprise: water body nutrition degree, suspended matter concentration and water body temperature.
In some embodiments, the remote sensing image data includes different bands, wherein the red band (0.63-0.69 microns) is used to measure plant chlorophyll absorption rate for vegetation classification; the green band (0.51-0.60 microns) is used for detecting the green reflectivity of the healthy plants and reflecting underwater characteristics; the blue band (0.45-0.52 microns) is used for obtaining boundary information of ground object intersection, and the function of the band in drawing is great; the near infrared band (0.76-0.90 microns) is used for measuring biomass and crop trend and determining the water body profile; the method can further comprise the following steps: a coast band (0.40-0.45 microns), a yellow band (0.585-0.625 microns), and a red edge band (0.7055-0.745 microns).
For example, taking an ocean water quality monitoring and analyzing scenario as an example, the environment measured data includes: monitoring point position, monitoring time, ammonia nitrogen concentration, total phosphorus concentration, chemical oxygen demand, dissolved oxygen concentration, anionic surfactant, transparency, redox point position, flow rate and suspended matter. The remote sensing image data includes: the satellite remote sensing image and the aerial remote sensing image at the same time and the same position as the environment actual measurement data are mainly high-grade No. 2 satellite remote sensing image data, and are supplemented with data such as ZY3, GF1, Worldview and the like.
In some embodiments, after acquiring the remote sensing image data, the remote sensing image may be processed by: correcting the remote sensing image, enhancing the remote sensing image, inlaying the remote sensing image and fusing the remote sensing image.
And correcting the remote sensing image to correct the deformed image data or the low-quality image data so as to reflect the scene more truly.
Remote sensing image enhancement is used to increase the contrast in appearance of certain features in an image to improve the visual interpretation performance of the image. The main treatment steps comprise: contrast transformation, spatial filtering, color transformation, image operation, multispectral transformation, and the like.
Remote sensing image mosaicing is used to stitch two or more digital images (which may have been acquired under different photographic conditions) to form a wider range of remote sensing images.
And remote sensing image fusion, which is used for generating a group of new information or a synthetic image from the remote sensing image data of multiple sources in a unified geographic coordinate system by adopting a preset algorithm.
And S102, inputting the remote sensing image data into a pre-trained convolutional neural network model to generate environment element data corresponding to the remote sensing image data and a corresponding environment element label.
Specifically, a convolutional neural network model is trained by using historical data, remote sensing image data is input into the convolutional neural network model which is trained in advance, digital information contained in the remote sensing image data is extracted, and digitized environment element data and a corresponding environment element label are generated.
It should be noted that, the embodiment of the present application may acquire and process related data based on an artificial intelligence technique. For example, based on a pre-trained convolutional neural network model, environment element data and a corresponding environment element label in remote sensing image data are obtained, wherein Artificial Intelligence (AI) is a theory, method, technology and application system for simulating, extending and expanding human Intelligence by using a digital computer or a machine controlled by a digital computer, perceiving the environment, obtaining knowledge and obtaining an optimal result by using the knowledge.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
For example, referring to fig. 3, fig. 3 shows a schematic diagram of monitoring water body eutrophication, as shown in fig. 3, a chlorophyll remote sensing image of a water body shot by a high-resolution secondary satellite is obtained, data of the remote sensing image is input into a trained convolutional neural network model, chlorophyll concentration information contained in a red band (0.63-0.69 micrometers) in the remote sensing image data is captured in a graded manner, information of water body eutrophication, such as primary, secondary and tertiary water body eutrophication, is obtained according to the chlorophyll concentration information, and a data label of water body eutrophication is generated at the same time, for example, the data label is a water body eutrophication degree, and the information of water body eutrophication is displayed on the data label of water body eutrophication.
It should be noted that the environmental monitoring and early warning method further includes acquiring a pre-trained convolutional neural network model, and the method mainly includes the following steps:
acquiring a training sample, wherein the training sample comprises historical remote sensing image data and a historical thermodynamic diagram;
calling a convolutional neural network model, wherein the convolutional neural network model comprises a convolutional layer, a pooling layer and a full-connection layer;
inputting a training sample into the convolutional neural network model, wherein a convolutional layer is used for carrying out convolution processing on historical remote sensing image data and historical thermodynamic diagrams to generate a digital characteristic matrix; the pooling layer is used for processing the digital characteristic matrix and outputting a sampling characteristic matrix, and the full-connection layer is used for processing the sampling characteristic matrix and outputting environment element data corresponding to the historical remote sensing image data and a corresponding environment element label.
In one embodiment, the Convolutional Neural network model is a deep learning CNN (CNN) model, including: a convolution layer, a pooling layer, and a full-link layer. Typically including several convolutional layers, pooling layers, and fully-connected layers; the convolution layer and the pooling layer can be alternately used in multiple layers, and the full-connection layer can also be laid in multiple layers.
The convolutional layer is used for carrying out convolution processing on the historical remote sensing image data and the historical thermodynamic diagrams to generate a digital feature matrix, specifically, carrying out inner product operation (element-by-element multiplication and summation) on the historical remote sensing image data, the historical thermodynamic diagrams and a filter matrix (a group of fixed weights: a plurality of weights of each neuron are fixed and can be regarded as a constant filter), and therefore the convolutional layer has the function of being responsible for extracting the digital features of the historical remote sensing image data and the historical thermodynamic diagrams and learning information shared among the images.
The convolution layer is composed of convolution kernel and nonlinear activation function, the feature mapping of the i-1 th layer and the convolution kernel do convolution operation, the feature mapping of the i-th layer can be obtained through the activation function after the convolution result, and the calculation process is as follows:
in the formula: l and h are the size of the convolution kernel, wjkAs weights of convolution kernels, Xi-1A digitized feature matrix for the i-1 th convolutional layer, biIs the offset of the ith layer, fact(. cndot.) is an activation function.
The pooling layer is arranged after the convolution layer and is used for processing the digital feature matrix and outputting a sampling feature matrix, and specifically, the scale of the image data is reduced through a down-sampling process which comprises the following steps: the new sequence is obtained by sampling a sample sequence several samples apart, and thus is a down-sampling of the original sequence.
The process of down-sampling includes: average pooling, maximum pooling, and random pooling. The purpose of adding the pooling layer is to extract effective data characteristics, improve the calculation efficiency and prevent network overfitting, and the calculation process of the pooling layer is as follows:
xi＝fact(k(xi-1)+bi)
in the formula: k (-) denotes pooling, mainly maximum pooling and average pooling. x is the number ofi-1As input to the pooling layer i, xiSampling feature matrix output for pooling layer i, biIs the offset of the pooling layer i, fact(. cndot.) is an excitation function.
The full connection layer is used for processing the sampling feature matrix and outputting the mapping relation between the historical remote sensing image data and the historical thermodynamic diagram, so that the convolutional neural network model can output the environmental element data corresponding to the historical remote sensing image data and the corresponding environmental element labels.
Specifically, the full connection layer outputs environment element data and an environment element label for each node of the historical remote sensing image data according to the input sampling feature matrix after the pooling layer sampling, so that the identification of targets such as air quality, water quality and the like in the remote sensing image data is realized, and if the ith layer is full connection layerIs given as viThen v isiThe calculation formula of (2) is as follows:
vi＝fact(Wiv(i-1)+Bi)
in the formula: v. ofi-1For input to the i-th fully-connected layer, WiAs weight value of the network, BiIs the offset value of the network, fact(. cndot.) is an excitation function, where v is specifiedi-1Sampling characteristic matrix x according to historical remote sensing image data and historical thermodynamic diagramiOperation generation, viIs a mapping relation matrix of historical remote sensing image data and historical thermodynamic diagram according to viAnd obtaining the mapping relation between the historical remote sensing image data and the historical thermodynamic diagram.
And acquiring the convolutional neural network model of the mapping relation, and analyzing the unprocessed remote sensing image data to generate corresponding digital environment element data and a corresponding environment element label.
Therefore, the trained convolutional neural network can output the environmental element data corresponding to the remote sensing image data and the corresponding environmental element label.
And S103, generating a thermodynamic diagram according to the environment element data and the corresponding environment element label.
Specifically, determining an area to which the environmental element data belongs according to a preset value range, dividing the remote sensing image data into a plurality of areas according to the area to which the environmental element data belongs, and marking the plurality of areas by using different identifiers; and displaying the corresponding environment element data and the environment element label on each area to generate a thermodynamic diagram.
It should be noted that the different identifiers for generating the thermodynamic diagram include: different colors and brightness, the greater the concentration of contaminants in the environmental element data, the more noticeable the colors used are when generating the thermodynamic diagram, e.g., red and orange; meanwhile, the contrast color can be used for distinguishing the concentration of the pollutants, so that the user can more easily acquire the information in the graph.
And S104, creating a map model based on the geographic information system, and importing the environment measured data and the thermodynamic diagram into the map model.
Specifically, a map model of the monitored area is generated based on a Geographic Information System (GIS), which is referred to as GIS for short, and the map model includes a plurality of map nodes set according to latitude and longitude Information; according to the positioning data of the monitoring sites, environment measured data collected by the monitoring sites are uploaded to map nodes corresponding to a map model, different types of environment measured data are marked by data labels, and the types of the data labels are the same as those of the environment element labels; and uploading the thermodynamic diagrams to map nodes corresponding to the map model according to the positioning data of the thermodynamic diagrams.
It should be noted that the geographic information system is a technical system for collecting, storing, managing, calculating, analyzing, displaying and describing geographic distribution data in the whole or part of the space of the earth surface layer (including the atmosphere) under the support of a computer hardware and software system.
The process of importing the environmental measured data and the thermodynamic diagram into the map model is essentially data integration, and in order to achieve comparison of the two data, it is necessary to perform unified processing on the time data, the space data and the tag data (environmental element tags and data tags) included in the data, for example, to perform full or partial adjustment, conversion, decomposition, synthesis and the like on the form characteristics (such as format, unit, projection and the like) and the internal characteristics (attributes, content, integration degree and the like) of the data to form a fully compatible data set.
In some embodiments, based on a geographic information system, a digitized map model of a monitoring area is generated according to existing map information, for example, topographic features and latitude and longitude information of the monitoring area, longitude lines and latitude lines are acquired according to preset longitude and latitude sampling densities, the greater the longitude and latitude sampling densities are, the more the acquired longitude lines and latitude lines are, a longitude and latitude grid of the map model is generated according to the longitude lines and the latitude lines, and an intersection point of the longitude lines and the latitude lines is set as a map node of the map model.
In some embodiments, the thermodynamic diagrams are uploaded to map nodes corresponding to the map model according to the positioning data of the thermodynamic diagrams, specifically, longitude and latitude information of the thermodynamic diagrams is acquired according to a preset scale, and the thermodynamic diagrams are overlapped with the map nodes of the map model according to the longitude and latitude information.
In other embodiments, the map model is quantized with the image resolution of the thermodynamic diagram as the latitude and longitude GRID size, and the vector image of the thermodynamic diagram is converted to a GRID (GRID), which facilitates spatial overlay correction of the map information and the remotely sensed image data.
In some embodiments, the method includes acquiring positioning data of a monitored site, determining longitude and latitude of the monitored site, determining a corresponding map node of the monitored site, for example, calculating longitude and latitude differences between the monitored site and the map node, calculating a sum of the longitude and latitude differences, setting the map node with the smallest sum as a data uploading point of the monitored site, and uploading data collected by the monitored site to the map node.
In some embodiments, multiple information storage layers may be further provided according to the data tag (or the environment element tag), so that errors in data reference can be reduced.
And S105, generating a comparison result of the thermodynamic diagram and the environment measured data on the map model according to the time data and the positioning data, and displaying the comparison result.
Specifically, in order to ensure that the positioning data is the same, the environment measured data and the environment element data of a single map node are obtained, first matching is performed according to time data, for example, the environment measured data and the environment element data of the yellow river at 16 days, 17 months and 16 days, second matching is performed according to tag data (namely a data tag and an environment element tag), if the time data and the tag are the same, the matching value of the environment measured data and the environment element data of the map node is calculated, a comparison result of the environment measured data and the environment element data contained in the map node is generated on a map model according to the matching value, and the comparison result is displayed.
In some embodiments, a matching value is obtained by dividing the environment measured data by the environment element data, and if the matching value is smaller than a preset threshold, for example, the preset threshold is 90%, the calculated matching value is 85%, and since 85% < 90%, it is determined that a comparison result between the environment element data and the environment measured data is an environment monitoring abnormality, and early warning information is output on a map node corresponding to the map model.
It should be noted that the comparison result is an intuitive and understandable graphic form or data relationship.
In some embodiments, if the comparison result is that the environmental monitoring is abnormal, outputting early warning information, wherein the early warning information comprises one or more of longitude and latitude information of a map node, time data, a name of a monitoring station, a data tag, an environmental element tag and a matching value; and the type of the early warning information comprises at least one of the following items: audio cues, graphical cues, and text cues.
Illustratively, if the remote sensing monitoring recognition result of a certain area is abnormal in environmental monitoring, the system can automatically identify, output relevant geographic position coordinates, early warn managers, and the managers can perform troubleshooting according to the geographic position coordinates of the early warning area to obtain troubleshooting results and correct the system.
In some embodiments, if the remote sensing monitoring identification result of a certain area is abnormal in environmental monitoring and the area lacks of the actual environmental measurement data of the monitoring station, the management personnel is warned, and the management personnel investigates whether the monitoring equipment in the area is damaged or the monitoring station is laid after evaluation according to warning information.
In other embodiments, if the result of the sampling verification performed by the administrator on the early warning area is a system analysis error, the sampling result is returned to the training model, and the training model is corrected.
The environmental monitoring and early warning method provided by the embodiment processes the remote sensing image data through the convolutional neural network model to generate the thermodynamic diagram, and integrates the thermodynamic diagram and the environmental measured data of the ground monitoring station through the geographic information system to realize a multi-dimensional environmental monitoring system. Based on the environment monitoring and early warning method, monitoring and screening omission can be reduced, and automatic early warning of environment monitoring abnormity can be realized.
Referring to fig. 4, fig. 4 is a schematic block diagram of an environmental monitoring and warning device 300 for executing the environmental monitoring and warning method according to an embodiment of the present application. The environment monitoring and early warning device can be configured in a server or a terminal.
The server may be an independent server, a server cluster, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like. The terminal can be an electronic device such as a wireless data transmission terminal, an environment monitoring device, a mobile phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant and a wearable device.
As shown in fig. 4, the environment monitoring and warning apparatus 300 includes: a data acquisition module 301, an element output module 302, an element synthesis module 303, a model construction module 304, and a result comparison module 305.
The data acquisition module 301 is configured to acquire environment measured data and remote sensing image data, where the environment measured data and the remote sensing image data include time data and positioning data.
Wherein, the environment measured data at least comprises: air quality data, water quality data, wherein, air quality data includes: sulfur dioxide concentration, nitrogen dioxide concentration, inhalable particle concentration and urban heat island effect, and the water quality data comprise: water body nutrition degree, suspended matter concentration and water body temperature.
And the element output module 302 is configured to input the remote sensing image data into a pre-trained convolutional neural network model, and generate environment element data corresponding to the remote sensing image data and a corresponding environment element label.
The element output module 302 is further specifically configured to obtain a training sample, where the training sample includes historical remote sensing image data and a historical thermodynamic diagram; calling a convolutional neural network model, wherein the convolutional neural network model comprises a convolutional layer, a pooling layer and a full-connection layer; inputting a training sample into a convolutional neural network model, wherein a convolutional layer is used for carrying out convolution processing on historical remote sensing image data and a historical thermodynamic diagram to generate a digital characteristic matrix; the pooling layer is used for processing the digital characteristic matrix and outputting a sampling characteristic matrix, and the full-connection layer is used for processing the sampling characteristic matrix and outputting environment element data corresponding to the historical remote sensing image data and a corresponding environment element label.
And an element synthesis module 303, configured to generate a thermodynamic diagram according to the environment element data and the corresponding environment element tag.
The element synthesis module 303 is further specifically configured to determine an area to which the environmental element data belongs according to a preset value range, divide the remote sensing image data into a plurality of areas according to the area to which the environmental element data belongs, and mark the plurality of areas by using different identifiers; and displaying the corresponding environment element data and the environment element label on each area to generate a thermodynamic diagram.
And the model building module 304 is used for creating a map model based on the geographic information system and importing the environmental measured data and the thermodynamic diagram into the map model.
The model building module 304 is further specifically configured to generate a map model of the monitored area based on the geographic information system, where the map model includes a plurality of map nodes set according to latitude and longitude information; according to the positioning data of the monitoring sites, environment measured data collected by the monitoring sites are uploaded to map nodes corresponding to a map model, different types of environment measured data are marked by data labels, and the types of the data labels are the same as those of the environment element labels; and uploading the thermodynamic diagrams to map nodes corresponding to the map model according to the positioning data of the thermodynamic diagrams.
And the result comparison module 305 generates a comparison result of the thermodynamic diagram and the environmental measured data on the map model according to the time data and the positioning data, and displays the comparison result.
The result comparison module 305 is further specifically configured to obtain environment measured data and environment element data of a single map node, perform first matching according to the time data, and perform second matching according to the data tag and the environment element tag; if the time data and the labels are the same, calculating a matching value of the environment actual measurement data and the environment element data of the map node; and if the matching value is smaller than the preset threshold value, judging that the comparison result of the environmental element data and the environmental measured data is abnormal in environmental monitoring.
The result comparison module 305 is further specifically configured to output early warning information when the comparison result is that the environmental monitoring is abnormal, where the early warning information includes one or more of longitude and latitude information of a map node, time data, a name of a monitored site, a data tag, an environmental element tag, and a matching value; the type of the early warning information comprises at least one of the following items: audio cues, graphical cues, and text cues.
It should be noted that, as will be clearly understood by those skilled in the art, for convenience and brevity of description, the specific working processes of the modules described above may refer to corresponding processes in the foregoing embodiment of the environment monitoring and early warning method, and are not described herein again.
The environment monitoring and early warning device can be implemented in a form of a computer program, and the computer program can be run on a computer device as shown in fig. 5.
Referring to fig. 5, fig. 5 is a schematic block diagram of a computer device according to an embodiment of the present disclosure. The computer device may be a server or a terminal.
Referring to fig. 5, the computer device includes a processor, a memory, and a network interface connected through a system bus, wherein the memory may include a storage medium and an internal memory.
The storage medium may store an operating system and a computer program. The computer program includes program instructions, which when executed, can cause a processor to execute any one of the environmental monitoring and warning methods provided by the embodiments of the present application.
The processor is used for providing calculation and control capability and supporting the operation of the whole computer equipment.
The internal memory provides an environment for running a computer program in the storage medium, and when the computer program is executed by the processor, the processor may be caused to execute any one of the environment monitoring and early warning methods provided by the embodiments of the present application. The storage medium may be non-volatile or volatile.
The network interface is used for network communication, such as sending assigned tasks and the like. Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
It should be understood that the Processor may be a Central Processing Unit (CPU), and the Processor may be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Illustratively, in one embodiment, the processor is configured to execute a computer program stored in the memory to perform the steps of:
acquiring environment actual measurement data and remote sensing image data, wherein the environment actual measurement data and the remote sensing image data comprise time data and positioning data;
inputting the remote sensing image data into a pre-trained convolutional neural network model to generate environment element data corresponding to the remote sensing image data and a corresponding environment element label;
generating a thermodynamic diagram according to the environment element data and the corresponding environment element label;
creating a map model based on a geographic information system, and importing the environment measured data and the thermodynamic diagram into the map model;
and generating a comparison result of the thermodynamic diagram and the environment measured data on the map model according to the time data and the positioning data, and displaying the comparison result.
In some embodiments, the processor is further configured to execute a computer program stored in the memory to perform the steps of:
acquiring a training sample, wherein the training sample comprises historical remote sensing image data and a historical thermodynamic diagram;
calling a convolutional neural network model, wherein the convolutional neural network model comprises a convolutional layer, a pooling layer and a full-connection layer;
inputting a training sample into a convolutional neural network model, wherein a convolutional layer is used for carrying out convolution processing on historical remote sensing image data and a historical thermodynamic diagram to generate a digital characteristic matrix; the pooling layer is used for processing the digital characteristic matrix and outputting a sampling characteristic matrix, and the full-connection layer is used for processing the sampling characteristic matrix and outputting environment element data corresponding to the historical remote sensing image data and a corresponding environment element label.
In some embodiments, the processor, when implementing generating the thermodynamic diagram from the environmental data, is specifically configured to implement:
determining an affiliated interval of the environmental element data according to a preset value range, dividing the remote sensing image data into a plurality of areas according to the affiliated interval, and marking the plurality of areas by using different identifiers;
and displaying the corresponding environment element data and the environment element label on each area to generate a thermodynamic diagram.
In some embodiments, the processor is specifically configured to, when implementing creation of a map model based on a geographic information system and importing environmental measurement data and a thermodynamic diagram into the map model, implement:
generating a map model of the monitored area based on a geographic information system, wherein the map model comprises a plurality of map nodes which are set according to longitude and latitude information;
according to the positioning data of the monitoring sites, environment measured data collected by the monitoring sites are uploaded to map nodes corresponding to a map model, different types of environment measured data are marked by data labels, and the types of the data labels are the same as those of the environment element labels;
and uploading the thermodynamic diagrams to map nodes corresponding to the map model according to the positioning data of the thermodynamic diagrams.
In some embodiments, when the processor generates a comparison result between the thermodynamic diagram and the environmental measured data according to the time data and the positioning data, the processor is specifically configured to:
acquiring environment actual measurement data and environment element data of a single map node, performing first matching according to time data, and performing second matching according to a data tag and an environment element tag;
if the time data and the labels are the same, calculating a matching value of the environment actual measurement data and the environment element data of the map node;
and if the matching value is smaller than the preset threshold value, judging that the comparison result of the environmental element data and the environmental measured data is abnormal in environmental monitoring.
In some embodiments, the processor, when being configured to present the comparison result on the map model, is further specifically configured to implement:
if the comparison result is that the environmental monitoring is abnormal, outputting early warning information, wherein the early warning information comprises one or more of longitude and latitude information of map nodes, time data, names of monitoring sites, data labels, environmental element labels and matching values; the type of the early warning information comprises at least one of the following items: audio cues, graphical cues, and text cues.
The embodiment of the application further provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, the computer program comprises program instructions, and the processor executes the program instructions to realize any one of the environment monitoring and early warning methods provided by the embodiment of the application.
The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the computer device.
While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. An environmental monitoring and early warning method is characterized by comprising the following steps:
acquiring environment actual measurement data and remote sensing image data, wherein the environment actual measurement data and the remote sensing image data comprise time data and positioning data;
inputting the remote sensing image data into a pre-trained convolutional neural network model to generate environment element data corresponding to the remote sensing image data and a corresponding environment element label;
generating a thermodynamic diagram according to the environment element data and the corresponding environment element label;
creating a map model based on a geographic information system, and importing the environment measured data and the thermodynamic diagram into the map model;
and generating a comparison result of the thermodynamic diagram and the environment measured data on the map model according to the time data and the positioning data, and displaying the comparison result.
2. The method of claim 1, further comprising:
obtaining a training sample, wherein the training sample comprises historical remote sensing image data and a historical thermodynamic diagram;
calling a convolutional neural network model, wherein the convolutional neural network model comprises a convolutional layer, a pooling layer and a full-connection layer;
inputting the training samples into the convolutional neural network model, wherein the convolutional layer is used for carrying out convolution processing on the historical remote sensing image data and the historical thermodynamic diagram to generate a digital feature matrix; the pooling layer is used for processing the digital characteristic matrix and outputting a sampling characteristic matrix, and the full-connection layer is used for processing the sampling characteristic matrix and outputting environment element data corresponding to the historical remote sensing image data and a corresponding environment element label.
3. The method of claim 2, wherein generating a thermodynamic diagram from the environmental data comprises:
determining an affiliated section of the environment element data according to a preset value range, dividing the remote sensing image data into a plurality of regions according to the affiliated section, and marking the plurality of regions by using different identifications;
displaying the corresponding environment element data and the environment element label on each area, and generating the thermodynamic diagram.
4. The method of claim 1, wherein creating a map model based on the geographic information system, and importing the environmental survey data and the thermodynamic diagram into the map model comprises:
generating a map model of a monitored area based on a geographic information system, wherein the map model comprises a plurality of map nodes which are set according to longitude and latitude information;
uploading the environment measured data collected by a plurality of monitoring sites to the map nodes corresponding to the map model according to the positioning data of the monitoring sites, and marking different types of environment measured data by using data tags, wherein the types of the data tags are the same as the types of the environment element tags;
and uploading the thermodynamic diagrams to the map nodes corresponding to the map model according to the positioning data of the thermodynamic diagrams.
5. The method of claim 4, wherein generating the comparison of the thermodynamic diagram and the environmental measured data from the time data and the positioning data comprises:
acquiring the environment actual measurement data and the environment element data of a single map node, performing first matching according to the time data, and performing second matching according to the data label and the environment element label;
if the time data and the labels are the same, calculating a matching value of the environment measured data and the environment element data of the map node;
and if the matching value is smaller than a preset threshold value, judging that the comparison result of the environmental element data and the environmental measured data is abnormal in environmental monitoring.
6. The method of claim 5, wherein said displaying the comparison results on the map model comprises:
if the comparison result is that the environmental monitoring is abnormal, outputting early warning information, wherein the early warning information comprises one or more of longitude and latitude information of the map node, the time data, the name of a monitoring station, the data label, the environmental element label and the matching value;
the type of the early warning information comprises at least one of the following items: audio cues, graphical cues, and text cues.
7. The method of claim 1, wherein the environmental measurement data comprises at least: air quality data, water quality data, wherein, the air quality data includes: sulfur dioxide concentration, nitrogen dioxide concentration, inhalable particulate matter concentration and urban heat island effect, the water quality data comprising: water body nutrition degree, suspended matter concentration and water body temperature.
8. An environmental monitoring early warning device which characterized in that includes:
the data acquisition module is used for acquiring environment actual measurement data and remote sensing image data, wherein the environment actual measurement data and the remote sensing image data comprise time data and positioning data;
the element output module is used for inputting the remote sensing image data into a pre-trained convolutional neural network model to generate environment element data corresponding to the remote sensing image data and a corresponding environment element label;
the element synthesis module is used for generating a thermodynamic diagram according to the environment element data and the corresponding environment element label;
the model construction module is used for creating a map model based on a geographic information system and importing the environment measured data and the thermodynamic diagram into the map model;
and the result comparison module is used for generating a comparison result of the thermodynamic diagram and the environment actual measurement data on the map model according to the time data and the positioning data and displaying the comparison result.
9. A computer device, wherein the computer device comprises a memory and a processor;
the memory is used for storing a computer program;
the processor is configured to execute the computer program and to implement the environmental monitoring and warning method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, causes the processor to implement the environmental monitoring and warning method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210143538.2A CN114511784A (en) | 2022-02-16 | 2022-02-16 | Environment monitoring and early warning method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210143538.2A CN114511784A (en) | 2022-02-16 | 2022-02-16 | Environment monitoring and early warning method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114511784A true CN114511784A (en) | 2022-05-17 |
Family
ID=81552445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210143538.2A Pending CN114511784A (en) | 2022-02-16 | 2022-02-16 | Environment monitoring and early warning method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114511784A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115993488A (en) * | 2023-03-24 | 2023-04-21 | 天津安力信通讯科技有限公司 | Intelligent monitoring method and system for electromagnetic environment |
| CN116481600A (en) * | 2023-06-26 | 2023-07-25 | 四川省林业勘察设计研究院有限公司 | Plateau forestry ecological monitoring and early warning system and method |
| CN116546431A (en) * | 2023-07-04 | 2023-08-04 | 北京江云智能科技有限公司 | Beidou all-network communication-based multi-network fusion data acquisition communication system and method |
| CN116824305A (en) * | 2023-08-09 | 2023-09-29 | 中国气象服务协会 | Ecological environment monitoring data processing method and system applied to cloud computing |
| CN116883755A (en) * | 2023-07-20 | 2023-10-13 | 广州新城建筑设计院有限公司 | Rural construction environment monitoring method, system, equipment and storage medium |
-
2022
- 2022-02-16 CN CN202210143538.2A patent/CN114511784A/en active Pending
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115993488A (en) * | 2023-03-24 | 2023-04-21 | 天津安力信通讯科技有限公司 | Intelligent monitoring method and system for electromagnetic environment |
| CN116481600A (en) * | 2023-06-26 | 2023-07-25 | 四川省林业勘察设计研究院有限公司 | Plateau forestry ecological monitoring and early warning system and method |
| CN116481600B (en) * | 2023-06-26 | 2023-10-20 | 四川省林业勘察设计研究院有限公司 | Plateau forestry ecological monitoring and early warning system and method |
| CN116546431A (en) * | 2023-07-04 | 2023-08-04 | 北京江云智能科技有限公司 | Beidou all-network communication-based multi-network fusion data acquisition communication system and method |
| CN116546431B (en) * | 2023-07-04 | 2023-09-19 | 北京江云智能科技有限公司 | Beidou all-network communication-based multi-network fusion data acquisition communication system and method |
| CN116883755A (en) * | 2023-07-20 | 2023-10-13 | 广州新城建筑设计院有限公司 | Rural construction environment monitoring method, system, equipment and storage medium |
| CN116883755B (en) * | 2023-07-20 | 2024-03-26 | 广州新城建筑设计院有限公司 | Rural construction environment monitoring method, system, equipment and storage medium |
| CN116824305A (en) * | 2023-08-09 | 2023-09-29 | 中国气象服务协会 | Ecological environment monitoring data processing method and system applied to cloud computing |
| CN116824305B (en) * | 2023-08-09 | 2024-06-04 | 中国气象服务协会 | Ecological environment monitoring data processing method and system applied to cloud computing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114511784A (en) | Environment monitoring and early warning method, device, equipment and storage medium | |
| Jianya et al. | A review of multi-temporal remote sensing data change detection algorithms | |
| CN112734694A (en) | Water quality monitoring method based on big data | |
| CN111914767B (en) | Scattered sewage enterprise detection method and system based on multi-source remote sensing data | |
| CN113160150B (en) | AI (Artificial intelligence) detection method and device for invasion of foreign matters in wire mesh | |
| CN110414359A (en) | The analysis of long distance pipeline unmanned plane inspection data and management method and system | |
| Congalton | Remote sensing: an overview | |
| CN112668461B (en) | Intelligent supervision system with wild animal identification function | |
| Culman et al. | A novel application for identification of nutrient deficiencies in oil palm using the internet of things | |
| CN116257792A (en) | Smart city carbon neutralization data analysis system | |
| CN115585731A (en) | Space-air-ground integrated hydropower station space state intelligent monitoring management system and method thereof | |
| CN117575550B (en) | BIM technology-based three-dimensional visual management system for wind farm data | |
| CN113780175B (en) | Remote sensing identification method for typhoon and storm landslide in high vegetation coverage area | |
| CN117372875A (en) | Aerial remote sensing target identification method | |
| Morgan et al. | A post-classification change detection model with confidences in high resolution multi-date sUAS imagery in coastal south carolina | |
| CN116091940B (en) | Crop classification and identification method based on high-resolution satellite remote sensing image | |
| Sui et al. | Processing of multitemporal data and change detection | |
| CN113240340B (en) | Soybean planting area analysis method, device, equipment and medium based on fuzzy classification | |
| CN115545427A (en) | Ecological land use protection method and system based on sound landscape intelligent analysis | |
| CN115184563A (en) | Chemical workshop field data acquisition method based on digital twinning | |
| Serhani et al. | Drone-assisted inspection for automated accident damage estimation: A deep learning approach | |
| CN117458450B (en) | Power data energy consumption prediction analysis method and system | |
| CN117874273B (en) | Iron tower video image classification identification method and device based on geographic mapping | |
| CN117171533B (en) | Real-time acquisition and processing method and system for geographical mapping operation data | |
| CN116522261B (en) | Risk information monitoring method and system based on big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |