A method, system, device and medium for digitalization of lake water resources

Abstract

The application provides a kind of lake water resource digitalization method, system, equipment and medium, related to the technical field of hydrogeology monitoring, the method comprises: obtaining the Landsat series image and high-resolution series image of the specified geographical area in the historical time period, carrying out ground-based, ship-based dynamic scanning on each lake in the specified geographical area, and collecting three-dimensional point cloud data and image data of each blank area to realize the linkage and cooperation architecture of "star sky ground ship" full element for the all-round measurement and evaluation of the lake water resources in the region. All related data of each lake are fused to construct a multidimensional database for each lake. Based on the multidimensional database, each lake is visualized to generate a digital lake comprehensive display map for each lake. Since the digital lake comprehensive display map covers the multidimensional data of the lake, it can solve the technical problem of insufficient lake hydrogeological structure survey data in the prior art.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of hydrogeological monitoring, and in particular to a digital method, system, device and medium for lake water resources. BACKGROUND

[0002] Lakes are an important component of land surface water resources. Lake water resources investigation and evaluation is an important part of China's water resources national conditions basic investigation. Since the exploration was launched in 2023, the investigation technology method has made great progress. However, the traditional lake water resources investigation method is limited to single technical data collection, such as using remote sensing image to interpret lake water area; and limited by single point data collection, using water level observation station to observe lake water level dynamic change, which cannot meet the description of inclined large water surface water potential field, and the investigation and research of lake hydrogeological structure is insufficient, which cannot meet the demand of hydrogeological and water resources investigation and monitoring evaluation. SUMMARY

[0003] The purpose of the present application is to provide a digital method, system, device and medium for lake water resources, to alleviate the technical problem of insufficient lake hydrogeological structure investigation data in the prior art.

[0004] In a first aspect, the present application provides a method for digitizing lake water resources, comprising: obtaining a land digital elevation model of a specified geographic area, Landsat series images and high-resolution series images of the specified geographic area in a historical time period; determining the number of lakes in the specified geographic area, the distribution of the lakes, the classification label, the cause label of each lake, the zoning result of the lake shoreline and the time series data of the first target parameter based on the Landsat series images and the high-resolution series images in the historical time period; wherein the first target parameter includes water temperature, water quality, water surface area and water level; performing ground-based dynamic scanning on each lake to determine the classification label, the cause label, the zoning result of the lake shoreline and the ground observation data set of each lake; wherein the ground observation data set includes the time series data of water level, water temperature, water quality, water outflow and water inflow; performing ship-based dynamic scanning on each lake to determine the standard terrain model and the water storage capacity of each lake; obtaining three-dimensional point cloud data of each blank area in the specified geographic area by airborne laser radar, and obtaining image data of each blank area by oblique photography technology; wherein the blank area represents the junction area of water area and land area; constructing a three-dimensional model of each blank area based on the three-dimensional point cloud data and the image data of each blank area; constructing a three-dimensional terrain model of the specified geographic area based on the land digital elevation model of the specified geographic area, the standard terrain model of each lake in the specified geographic area and the three-dimensional model of each blank area; intelligently fusing all related data of each lake to construct a multi-dimensional database of each lake; performing visualization processing on each lake based on the three-dimensional terrain model of the specified geographic area and the multi-dimensional database of each lake to generate a digital lake comprehensive display diagram of each lake.

[0005] Optionally, based on the Landsat series images and the Gaofen series images in the historical time period, the number of lakes in the specified geographic area, the lake distribution, the hierarchical label of each lake, the cause label of each lake, the zoning result of the lake shorelines, and the time series data of the first target parameters are determined, including: screening the thermal infrared image set, the hyperspectral image set, the optical image set, and the laser radar image set from the Landsat series images and the Gaofen series images in the historical time period; performing radiation correction, atmospheric correction, and image splicing processing on the thermal infrared image set, the hyperspectral image set, the optical image set, and the laser radar image set respectively to obtain a pre-processed image set; screening the image set of the lake in the wet season and the dry season from the pre-processed image set to obtain a target image set, the number of lakes in the specified geographic area, and the lake distribution; interpreting the images in the target image set to obtain the time series data of the first target parameters of each lake in the specified geographic area; wherein the first target parameters include: water temperature, water quality, water surface area, and water level; determining the hierarchical label of each lake based on the preset lake hierarchical rule and the water surface area of each lake; obtaining the target data of each lake; wherein the target data includes: evolution data of the geological structure unit where the lake is located, paleogeographic environment data of the lake, and major geological event information; determining the cause label of each lake and the zoning result of the lake shorelines based on the target data of each lake, the image data of each lake in the target image set, and the preset expert experience library.

[0006] Optionally, each lake is dynamically scanned on the ground to determine a ground observation data set of each lake, including: obtaining the time series data of the second target parameters of each lake by setting a hydrological and water temperature observation station, a water quality monitoring point, and an inflow and outflow observation section in each lake; wherein the second target parameters include: water level, water temperature, water quality, outflow, and inflow; performing standardization processing on the time series data of the second target parameters of each lake to obtain the ground observation data set of each lake.

[0007] Optionally, a ship-based dynamic scanning is performed on each lake to determine a standard terrain model and a water storage capacity of each lake, comprising: dividing a water area of a target lake according to water depth and water grass distribution of the target lake to obtain a divided target lake; wherein the target lake represents any lake in a specified geographical area; performing multi-point sounding on each division in the target lake according to a preset sounding mode matched with the division to obtain water depth data of the multi-point; constructing underwater terrain point cloud data of the target lake based on the water depth data of the multi-point; performing data cleaning on the underwater terrain point cloud data to obtain target point cloud data of the target lake; constructing a water depth model of the target lake based on the target point cloud data; converting the water depth model of the target lake to an 85 elevation system through a geographic coordinate conversion technology to obtain a standard terrain model of the target lake; and calculating the water storage capacity of the target lake based on the water depth model of the target lake and the water depth data of the target lake.

[0008] Optionally, based on the three-dimensional point cloud data and the image data of each blank area, a three-dimensional model of each blank area is constructed, comprising: performing denoising processing on the three-dimensional point cloud data and the image data of a target blank area to obtain denoised point cloud data and denoised image data; wherein the target blank area represents any blank area in a specified geographical area; processing the denoised point cloud data and the denoised image data using an irregular triangle mesh method to obtain a raster vector three-dimensional model of the target blank area; performing Gaussian filter smoothing processing on the raster vector three-dimensional model to obtain a filtered raster vector three-dimensional model; and performing feature enhancement processing on key terrains in the filtered raster vector three-dimensional model to obtain a three-dimensional model of the blank area.

[0009] Optionally, based on the land digital elevation model of the specified geographical area, the standard terrain model of each lake in the specified geographical area, and the three-dimensional model of each blank area, a three-dimensional terrain model of the specified geographical area is constructed, comprising: splicing the land digital elevation model of the specified geographical area, the standard terrain model of each lake in the specified geographical area, and the three-dimensional model of each blank area to obtain an initial three-dimensional model of the specified geographical area; taking the boundary of the standard terrain model of each lake as a starting point, creating a buffer zone of a specified width under a preset terrain curvature constraint, so that the buffer zone has an overlapping area with the land of the specified geographical area; performing weighted summation on the elevation data of each position point in the overlapping area in the buffer zone and the elevation data of each position point in the land digital elevation model to obtain target elevation data of each position point in the overlapping area; identifying and deleting elevation outliers in the overlapping area based on the target elevation data of all position points in the overlapping area to obtain an updated overlapping area; and updating the initial three-dimensional model of the specified geographical area based on the target elevation data of all position points in the updated overlapping area to obtain a three-dimensional terrain model of the specified geographical area.

[0010] Optionally, the method further comprises: obtaining a training sample set, wherein the training sample set comprises a plurality of groups of training samples, each group of training samples comprising Landsat series images and high-resolution series images of a same geographical region in a same time period; taking the Landsat series images in each group of training samples as input data of an initial image enhancement model, taking the high-resolution series images in each group of training samples as training labels of the initial image enhancement model, training the initial image enhancement model until a preset termination condition is reached, and obtaining a target image enhancement model; processing the Landsat series images of a specified geographical region in a target historical time period by using the target image enhancement model, and obtaining predicted high-resolution series images of the specified geographical region in the target historical time period; wherein the target historical time period represents a historical time period before the high-resolution satellite is launched.

[0011] In a second aspect, the present application provides a digital system for lake water resources, comprising: a first obtaining module configured to obtain a land digital elevation model of a specified geographical region, Landsat series images of the specified geographical region in a historical time period, and high-resolution series images of the specified geographical region in the historical time period; a determining module configured to determine, based on the Landsat series images and the high-resolution series images in the historical time period, a number of lakes in the specified geographical region, a lake distribution, a classification label, a cause label of each lake, a zoning result of a lake shoreline, and time series data of first target parameters; wherein the first target parameters comprise water temperature, water quality, water surface area, and water level; a first scanning module configured to perform ground-based dynamic scanning on each lake to determine the classification label, the cause label, the zoning result of the lake shoreline, and a ground-based observation data set of each lake; wherein the ground-based observation data set comprises time series data of water level, water temperature, water quality, water outflow, and water inflow; a second scanning module configured to perform ship-based dynamic scanning on each lake to determine a standard terrain model and a water storage capacity of each lake; a second obtaining module configured to obtain, by using airborne laser radar, three-dimensional point cloud data of each blank area in the specified geographical region, and obtain, by using oblique photography technology, image data of each blank area; wherein the blank area represents an intersection area between a water area and a land area; a first constructing module configured to construct, based on the three-dimensional point cloud data and the image data of each blank area, a three-dimensional model of each blank area; a second constructing module configured to construct, based on the land digital elevation model of the specified geographical region, the standard terrain model of each lake in the specified geographical region, and the three-dimensional model of each blank area, a three-dimensional terrain model of the specified geographical region; a fusion module configured to intelligently fuse all related data of each lake to construct a multi-dimensional database of each lake; and a visualization processing module configured to perform visualization processing on each lake based on the three-dimensional terrain model of the specified geographical region and the multi-dimensional database of each lake, and generate a digital lake comprehensive display map of each lake.

[0012] In a third aspect, the present application provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program capable of running on the processor, and the processor implements the lake digitalization method of any one of the preceding embodiments when executing the computer program.

[0013] In a fourth aspect, the present application provides a computer readable storage medium storing computer instructions, wherein the computer instructions are executed by a processor to implement the lake digitalization method of any one of the preceding embodiments.

[0014] The present application firstly acquires Landsat series images and high-resolution series images of a specified geographic area in a historical time period, performs ground-based dynamic scanning and ship-based dynamic scanning on each lake in the specified geographic area, and collects three-dimensional point cloud data and image data of each blank area, so as to realize the "star-sky-ground-ship" full-element linkage and collaborative architecture for the lakes in the region to conduct comprehensive measurement and evaluation of the lake water resources. Then, the intelligent data fusion technology is used to fuse and process all related data of each lake, to construct a multi-dimensional database of each lake, and then to perform visualization processing on each lake based on the multi-dimensional database, to generate a digital lake comprehensive display diagram of each lake. Since the digital lake comprehensive display diagram covers the multi-dimensional data of the lake, the technical problem of insufficient lake hydrogeological structure survey data in the prior art can be solved. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the drawings needed in the specific embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0016] Figure 1 A flowchart of a lake water resource digitalization method provided by an embodiment of the present application;

[0017] Figure 2 A flowchart for determining the number of lakes, lake distribution, and hierarchical label, cause label, zoned result of lake shoreline, and time series data of first target parameter of each lake in a specified geographic area based on Landsat series images and high-resolution series images in a historical time period provided by an embodiment of the present application;

[0018] Figure 3 A functional module diagram of a lake water resource digitalization device provided by an embodiment of the present application;

[0019] Figure 4A schematic diagram of an electronic device is provided for the embodiments of the present application. DETAILED DESCRIPTION

[0020] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0021] Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative labor are within the scope of protection of the present application.

[0022] Some embodiments of the present application will be described in detail below with reference to the drawings. The following embodiments and features in the embodiments can be combined with each other without conflict.

[0023] Embodiment one

[0024] Figure 1 A flowchart of a digital method of lake water resources is provided for the embodiments of the present application, as shown in Figure 1 The method specifically includes the following steps:

[0025] Step S101, acquiring a land digital elevation model of a specified geographic area, Landsat series images of the specified geographic area in a historical time period and high-resolution series images.

[0026] The embodiments of the present application do not specifically limit the range of the specified geographic area, and the user can configure according to actual needs, which can specify the latitude and longitude range, or specify one or more provinces / cities. The land digital elevation model of the specified geographic area can be obtained from the national basic geographic information database.

[0027] The purpose of the embodiment of the present application is to comprehensively investigate the lake hydrogeological structure in a specified geographical area, therefore, a full range of measurement and evaluation of the lake water resources in the area is proposed through four channels of star, space, ground and ship, wherein, the "star" refers to obtaining the Landsat series images and high-resolution series images of the specified geographical area in the historical time period through satellites; the "space" refers to obtaining the three-dimensional point cloud data of each blank area (the junction area of water area and land area) in the specified geographical area through airborne laser radar, and obtaining the image data of each blank area through oblique photography technology; the "ground" refers to ground-based dynamic scanning of each lake; the "ship" refers to ship-based dynamic scanning of each lake. The above aspects will be specifically introduced below.

[0028] According to the satellite launch time limit, the Landsat series images (15m, 30m resolution multispectral data) of the specified geographical area after 2000 can be obtained through the NASA / USGS platform, but the high-resolution series images (2m resolution multispectral data) of the specified geographical area after 2013 can only be obtained through the Chinese high-resolution satellite platform.

[0029] Step S102, based on the Landsat series images and high-resolution series images in the historical time period, the number of lakes in the specified geographical area, the lake distribution, the hierarchical label of each lake, the genetic label of each lake, the zoning result of the lake shoreline and the time series data of the first target parameter are determined.

[0030] Each satellite is equipped with multiple image sensors, such as thermal infrared sensors, hyperspectral sensors, optical sensors, etc. Different types of data can be interpreted from the image data returned by different sensors. According to the Landsat series images and high-resolution series images in the historical time period, the number and distribution of lakes in the area can be determined, and through the interpretation of the images of each lake in the historical time period, the time series data of the first target parameter of each lake can also be obtained, wherein the first target parameter includes water temperature, water quality, water surface area and water level.

[0031] Further, according to the water surface area of each lake interpreted by remote sensing, the grade of the lake can be determined, that is, the hierarchical label of the lake is determined; combined with the evolution history of each lake in the geological structure unit and the lake paleogeographic environment and major geological events, the cause of each lake can be determined, so that the genetic label of each lake is obtained; according to the shape of each lake interpreted by remote sensing, the lake shoreline of each lake can be further zoned, and the zoning result of the lake shoreline is obtained.

[0032] Step S103, ground-based dynamic scanning is performed on each lake to determine the ground-based observation data set of each lake.

[0033] Through interpretation of images taken by satellites, only data related to the lake surface can be obtained, but data under the lake surface cannot be determined, therefore, the embodiment of the present application proposes to perform ground dynamic scanning on each lake in the specified geographical area, specifically, a plurality of monitoring devices are arranged at specified positions in each lake to obtain data such as water level, water temperature, water quality, water outflow and water inflow of the lake, through continuous and periodic sampling, ground observation data set of each lake can be obtained. The ground observation data set includes time series data of water level, time series data of water temperature, time series data of water quality, time series data of water outflow and time series data of water inflow.

[0034] Step S104, ship-based dynamic scanning is performed on each lake to determine the standard terrain model and water storage of each lake.

[0035] Through ground dynamic scanning, the ground observation data set of the lake can be obtained, the embodiment of the present application further utilizes ship-based dynamic scanning to obtain morphological data under the water of the lake, specifically, according to the underwater conditions of each lake, an unmanned ship or a manned ship is adaptively adopted to obtain water depth data of a large number of position points in the lake through single-beam sounding or manual lead sounding, and then a water depth model of the lake is constructed. After the water depth model of the lake is constructed, it is imported into ARCGIS software, and then water level data of the lake is input, and the ARCGIS software can output the water storage of the lake.

[0036] The above water depth model is a model constructed based on the lake surface as a reference surface, in order to subsequently cooperate with land digital elevation model for modeling, it is necessary to convert the water depth model of the lake to the same 85 elevation system as the land digital elevation model, so as to obtain the standard terrain model of the lake.

[0037] Step S105, three-dimensional point cloud data of each blank area in the specified geographical area is obtained through airborne laser radar, and image data of each blank area is obtained through oblique photography technology.

[0038] Step S106, based on the three-dimensional point cloud data and the image data of each blank area, a three-dimensional model of each blank area is constructed.

[0039] The land digital elevation model of the specified geographic region and the standard terrain model of each lake in the region have been determined, and it is known that there are also blank areas in the specified geographic region, wherein the blank area represents the junction area of water area and land area, and therefore, in order to construct the three-dimensional terrain model of the specified geographic region, it is also necessary to construct the three-dimensional model of each blank area. Specifically, the three-dimensional point cloud data of each blank area is obtained by the airborne laser radar (the elevation of the blank area is measured by laser beam reflection), and the image acquisition of each blank area is performed by using the aerial platform (such as a drone or an airplane) equipped with multiple tilt cameras, and the above two kinds of data are integrated and optimized, so as to construct the three-dimensional model of each blank area in the specified geographic region.

[0040] It should be noted that, in order to ensure the accuracy of the three-dimensional model of the blank area, the elevation accuracy control and the point cloud density control can be performed during the data acquisition process. Specifically, the positioning accuracy of the flight platform is corrected in real time by using the ground reference station and the GPS auxiliary system. The terrain data obtained by the laser radar is ensured to have an error within ±1 cm in the vertical direction by using the high-precision positioning system. The parameters of the laser radar are adjusted according to the factors such as the flight height, the laser emission frequency and the flight speed, so as to ensure that the point cloud density reaches or exceeds 200 points / m 2 , so as to ensure the high accuracy and high resolution of the data.

[0041] Step S107, based on the land digital elevation model of the specified geographic region, the standard terrain model of each lake in the specified geographic region and the three-dimensional model of each blank area, a three-dimensional terrain model of the specified geographic region is constructed.

[0042] The land digital elevation model of the specified geographic region, the standard terrain model of each lake and the three-dimensional model of each blank area are spliced and optimized by using the three-dimensional modeling software, so as to obtain the three-dimensional terrain model of the specified geographic region.

[0043] Step S108, intelligent data fusion is performed on all related data of each lake to construct a multi-dimensional database of each lake.

[0044] Through the above steps, the data of each lake in multiple dimensions can be obtained. Intelligent data fusion can use machine learning and artificial intelligence algorithms to clean and calibrate the data obtained by various sensors, so as to ensure that the data in the multi-dimensional database has high quality, and provide reliable basis for subsequent analysis and decision-making. In the embodiment of the present application, the multi-dimensional database of each lake stores and manages a large amount of historical and real-time data. Optionally, big data technology (such as Hadoop, cloud storage, etc.) is used to construct the multi-dimensional database, so as to uniformly store the data from different platforms, and provide a basis for long-term data accumulation and future data mining.

[0045] Step S109, based on the three-dimensional terrain model of the specified geographic area and the multi-dimensional database of each lake, visual processing is performed on each lake to generate a digital lake comprehensive display map of each lake.

[0046] Optionally, the fused data is visualized into a comprehensive display map of the lake through a GIS (Geographic Information System) platform, and various types of information including water level, water temperature, water quality, etc. of the lake are dynamically displayed in the map, facilitating real-time monitoring of the lake.

[0047] The embodiment of the present application first acquires Landsat series images and high-resolution series images of a specified geographic area in a historical time period, performs ground-based dynamic scanning, ship-based dynamic scanning on each lake in the specified geographic area, and collects three-dimensional point cloud data and image data of each blank area, to realize the "star-sky-ground-ship" full-element linkage and collaborative architecture to measure and evaluate the lake water resources in the region in all directions. Then, through intelligent data fusion technology, all related data of each lake are fused and processed to construct a multi-dimensional database of each lake, and then based on the multi-dimensional database, visual processing is performed on each lake to generate a digital lake comprehensive display map of each lake. Since the digital lake comprehensive display map covers multi-dimensional data of the lake, it can solve the technical problem of insufficient lake hydrogeological structure survey data in the prior art.

[0048] In an alternative embodiment, as shown in Figure 2 Step S102, based on the Landsat series images and high-resolution series images in the historical time period, the number of lakes in the specified geographic area, the distribution of the lakes, the hierarchical label, the genetic label of each lake, the zoning result of the lake shoreline, and the time series data of the first target parameter are determined, which specifically includes the following steps:

[0049] Step S1021, the thermal infrared image set, the hyperspectral image set, the optical image set and the laser radar image set are selected from the Landsat series images and the high-resolution series images in the historical time period.

[0050] From the above introduction, it can be known that each satellite is equipped with multiple image sensors, and the image data returned by different sensors can be interpreted into different types of data. According to the data investigation needs of the lake according to the embodiment of the present application, four types of images, i.e. thermal infrared, hyperspectral, optical and laser radar, are selected from the Landsat series images and the high-resolution series images in the historical time period to obtain the thermal infrared image set, the hyperspectral image set, the optical image set and the laser radar image set.

[0051] Step S1022, the radiation correction, the atmospheric correction and the image splicing processing are respectively performed on the thermal infrared image set, the hyperspectral image set, the optical image set and the laser radar image set, to obtain a preprocessed image set.

[0052] In order to eliminate the radiation distortion in the image caused by factors such as sensor characteristics, atmospheric conditions, illumination changes, etc., and ensure that the image data can truly reflect the reflection or emission characteristics of the ground object, the image data in the thermal infrared image set, the hyperspectral image set, the optical image set and the laser radar image set need to be respectively subjected to radiation correction and atmospheric correction. The method of radiation correction and atmospheric correction is not specifically limited in the embodiment of the application, and the user can select according to actual needs. For example, the image is processed by using the MODTRAN model to perform radiation correction; the image is processed by using the FLAASH algorithm to perform atmospheric correction.

[0053] In addition, since the collection of the image is limited by the width and band, the size of the image view area is fixed, and if a lake cannot be completely displayed in an image, it will affect the subsequent data analysis results, so after the image is corrected, the image needs to be spliced to obtain a complete image set of the specified geographic area in the historical time period, that is, a preprocessed image set, including a preprocessed thermal infrared image set, a preprocessed hyperspectral image set, a preprocessed optical image set and a preprocessed laser radar image set.

[0054] Step S1023, the image set of the lake in the wet season and the dry season is selected from the preprocessed image set, to obtain a target image set, the number of lakes in the specified geographic area and the lake distribution.

[0055] After obtaining the preprocessed image set, the lakes in the specified geographic area can be automatically identified by using machine learning algorithms such as normalized water index and random forest, and the water surface boundary can be further corrected by manual visual inspection. Thus, the number of lakes in the specified geographic area and the lake distribution can be determined.

[0056] In known lake research, the wet season (high water level period) and the dry season (low water level period) are two most typical and key hydrological stages, and the dynamic change of the lake in these two periods can reflect the spatial size of the lake storage capacity, and the seasonal dynamic has a great influence on the scheduling of water resources. Therefore, after obtaining the preprocessed image set, the embodiment of the application further selects the image set of the lake in the wet season and the dry season from the preprocessed image set according to the specified time period corresponding to the wet season and the dry season, for example, the wet season is from July to August, and the dry season is from January to February, to obtain a target image set.

[0057] Step S1024, the images in the target image set are interpreted to obtain the time series data of the first target parameter of each lake in the specified geographic area.

[0058] The first target parameter includes water temperature, water quality, water surface area, and water level.

[0059] It is known that different image data can resolve different parameters. Specifically, water temperature can be interpreted from thermal infrared images, water quality (for example, chlorophyll concentration) can be interpreted from hyperspectral images, the water surface area of the lake can be interpreted from optical images, and water level data can be interpreted from laser radar images. The methods of interpreting various images described above are mature technologies in the art, and will not be described in detail in this embodiment. Obviously, based on the multiple images in the target image set, the first target parameter of each lake in the specified geographic area at multiple time points during the wet and dry seasons can be resolved. Then, all the data interpreted are sorted in chronological order, so that the time series data of the water temperature, the time series data of the water quality, the time series data of the water surface area, and the time series data of the water level of each lake in the specified geographic area can be obtained.

[0060] Step S1025, based on the preset lake classification rule and the water surface area of each lake, the classification label of each lake is determined.

[0061] The size of the lake can provide a basis for subsequent monitoring and data collection planning. Therefore, according to the water surface area of each lake interpreted by remote sensing, the size of the lake is divided in scale. For example, the lake is classified according to the water surface area of the lake in advance: 0-1 (unit: square kilometers, the units of the following value ranges are the same) is the first level, 1-50 is the second level, 50-150 is the third level, 150-400 is the fourth level, etc. The values of the above ranges are exemplary, and the user can set the upper and lower limits of each value range according to actual needs. Based on this, after determining the water surface area of each lake, it is matched with the above value range, so that the classification result of each lake, i.e., the classification label, can be obtained. For example, if the water surface area of a lake is 30 square kilometers, the classification label of the lake is the second level.

[0062] Step S1026, obtaining target data of each lake; wherein the target data includes evolution data of the geological structure unit where the lake is located, paleogeographic environment data of the lake, and major geological event information.

[0063] Step S1027, based on the target data of each lake, the image data of each lake in the target image set, and the preset expert experience library, the genetic label of each lake and the partition result of the lake shoreline are determined.

[0064] Specifically, in combination with the evolution history of each lake in the geological tectonic unit, the lake paleogeographic environment and the major geological events, according to the preset expert experience library, the genetic label of each lake can be determined: tectonic lake, river lake, barrier lake, lagoon, etc. According to the genesis of the lake, the lake is classified, which is helpful to accurately evaluate the environmental characteristics of different types of lakes. According to the image data of each lake, the lake shore curvature (bend), shape (convex-concave) and attribute (natural shore or artificial shore) can be determined, and in combination with the preset expert experience library, the zoning result of the lake shore line of each lake can be determined, so that subsequent research can be carried out on different types of lake shore lines. The lake shore line zoning is divided into different sections or functional areas according to the natural attributes, functional characteristics and human utilization demand of the lake shore belt, so as to realize scientific management, ecological protection and rational utilization of resources.

[0065] In an optional embodiment, the above step S103, the foundation dynamic scanning is carried out on each lake to determine the foundation observation data set of each lake, specifically including the following steps:

[0066] Step S1031, by setting hydrological and water temperature observation station, water quality monitoring point and inflow and outflow observation section in each lake, the time series data of the second target parameter of each lake is obtained; wherein the second target parameter includes: water level, water temperature, water quality, outflow and inflow.

[0067] Step S1032, the time series data of the second target parameter of each lake is standardized to obtain the foundation observation data set of each lake.

[0068] The embodiment of the application sets up a hydrological and water temperature observation station to monitor the hydrological change, flow change and water temperature inside and outside the lake, and provides basic data for monitoring the change of water environment. Specifically, the hydrological and water temperature observation station is set up, that is, sensors and temperature detection instruments are deployed in the lake, and indicators such as water level, flow velocity and water temperature are measured regularly, and data is transmitted through wireless network.

[0069] By setting up water quality monitoring points to regularly monitor the water quality of the lake, key water quality parameters such as dissolved oxygen, PH value and pollutant concentration are detected. Specifically, a multi-point monitoring system is configured, and a variety of sensors (such as optical sensors, electrochemical sensors, etc.) are used to monitor water quality in real time, and data is managed centrally through network.

[0070] By setting up inflow and outflow observation section of the lake, the inflow and outflow of the lake are monitored, especially the water inflow of the river into the lake and the water outflow of the lake, which is helpful to analyze the water cycle and water quantity change of the lake. Specifically, the inflow and outflow observation section of the lake is to set up flow meter and water level sensor at the main inflow and outflow of the lake, and the water quantity is calculated by flow rate and water level change.

[0071] In order to accurately track the changes of the second target parameters of the lakes, the user can respectively make scientific sampling frequencies for various parameters included in the second target parameters according to the hierarchical labels and / or the cause labels of the lakes, or all the lakes use the same sampling period, and the embodiments of the present application do not specifically limit the data sampling period, which can be set by the user according to actual needs. For example, water level and water temperature (2 times / day), water quality (3 times / year), water outflow (1 time / day), and water inflow (1 time / day). After a large amount of data is collected, the time sequence data of the water level, the time sequence data of the water temperature, the time sequence data of the water quality, the time sequence data of the water outflow, and the time sequence data of the water inflow of each lake can be obtained by sorting according to the time sequence.

[0072] Considering the measurement error of the sensor, the abnormal working of the sensor, and the failure of data uploading, after obtaining the time sequence data of the second target parameters of each lake, it is necessary to standardize the time sequence data, including: removing abnormal data, filling blank data, so as to obtain the ground observation data set of each lake. Alternatively, the ICP algorithm is used to standardize the time sequence data of the second target parameters of each lake.

[0073] In an optional implementation, the above step S104, the ship-based dynamic scanning is performed on each lake to determine the standard terrain model and the water storage of each lake, and specifically includes the following steps:

[0074] Step S1041, according to the water depth and the distribution of the water grass of the target lake, the water area of the target lake is partitioned to obtain the partitioned target lake; wherein the target lake represents any lake in a specified geographical area.

[0075] Step S1042, for each partition in the target lake, multi-point sounding is performed according to the preset sounding mode matched with the partition to obtain water depth data of the multi-point.

[0076] The ship-based dynamic scanning is to use a ship to load measurement equipment and technical personnel, or only to load automatic measurement equipment, to map the terrain below the lake surface. Specifically, before mapping the target lake, first, according to the water depth and the distribution of the water grass of the target lake, the water area of the target lake is partitioned, for example, divided into: water depth greater than 1.5 meters, sparse water grass, no net zone; water depth greater than 1.5 meters, dense water grass zone; water depth greater than 1.5 meters, sparse water grass, net zone; water depth less than or equal to 1.5 meters, no water grass zone; water depth less than or equal to 1.5 meters, water grass zone.

[0077] It is known that the boat needs a certain water depth to move on the lake surface, and external factors such as the density of water grass will also affect the progress of the boat, so the detection methods matched with the above five partitions are respectively: Single-beam sounding or unmanned ship single-beam sounding technology is adopted to provide accurate water depth data; Artificial lead sounding is adopted to avoid interference and ensure data accuracy; Unmanned ship single-beam sounding; Unmanned ship single-beam sounding; Artificial lead sounding or shore control measurement (i.e., measuring the depth of the surrounding area and then interpolating) to ensure accurate measurement.

[0078] Users can arrange measurement points at intervals of 100 meters, 200 meters, 500 meters, etc. according to the size of the lake surface, obtain water depth data of multiple points, and take lake water samples, sediment samples, and biological samples according to the accuracy of lake investigation profiles or different lake area controls, and then combine physical and chemical analysis to provide accurate basis for subsequent water quality evaluation.

[0079] Step S1043, constructing underwater topographic point cloud data of the target lake based on the water depth data of multiple points.

[0080] Step S1044, data cleaning is performed on the underwater topographic point cloud data to obtain target point cloud data of the target lake.

[0081] Step S1045, constructing a water depth model of the target lake based on the target point cloud data.

[0082] Considering that water grass and water transparency will affect the accuracy of measurement data, in order to ensure data quality and ensure the reliability of subsequent data analysis, after obtaining the underwater topographic point cloud data of the target lake, it needs to be processed for data cleaning to eliminate abnormal values, and then fill in the blank data according to the interpolation algorithm, and finally obtain the target point cloud data. The data of each point in the point cloud is a specific water depth data, therefore, combined with digital elevation model (DEM) technology, the underwater topographic elevation model of the target lake, i.e., the water depth model of the target lake, can be constructed according to the target point cloud data.

[0083] Step S1046, converting the water depth model of the target lake to the 85 elevation system through geographic coordinate conversion technology to obtain the standard topographic model of the target lake.

[0084] In order to ensure the consistency of data in the global range, it is further needed to connect the underwater terrain data with the real elevation system, that is, to convert the water depth model measured by the geodetic height system to the 85 elevation system. Specifically, by means of the geographic coordinate conversion technology, the measured underwater terrain data is converted into the elevation data in the standard elevation reference system, so as to ensure the uniformity and compatibility of the data.

[0085] In step S1047, the water storage capacity of the target lake is calculated based on the water depth model of the target lake and the water depth data of the target lake.

[0086] Specifically, the water depth model of the target lake is combined with the water depth data, and a water depth change model can be established. Therefore, the water storage capacity of the target lake can be calculated according to a specific water depth data of the target lake.

[0087] In an alternative embodiment, the step S106 of constructing the three-dimensional model of each blank area based on the three-dimensional point cloud data and the image data of each blank area comprises the following steps:

[0088] Firstly, the three-dimensional point cloud data and the image data of the target blank area are subjected to denoising processing to obtain denoised point cloud data and denoised image data. Then, the denoised point cloud data and the denoised image data are processed by using the irregular triangle network method to obtain a raster vector three-dimensional model of the target blank area. That is, the missing data in the denoised point cloud data and the denoised image data is completed by using the irregular triangle method.

[0089] Next, the raster vector three-dimensional model is subjected to Gaussian filtering smoothing processing to eliminate the sawtooth in the raster vector three-dimensional model, and a filtered raster vector three-dimensional model is obtained. Finally, the key terrain in the filtered raster vector three-dimensional model is subjected to feature enhancement processing to obtain the three-dimensional model of the blank area. The key terrain and the feature enhancement technology are not specifically limited in the embodiment of the present application, and the user can set them according to the actual needs. For example, the key terrain includes a dam.

[0090] In an alternative embodiment, the step S107 of constructing the three-dimensional terrain model of the specified geographic area based on the land digital elevation model of the specified geographic area, the standard terrain model of each lake in the specified geographic area and the three-dimensional model of each blank area comprises the following steps:

[0091] In step S1071, the land digital elevation model of the specified geographic area, the standard terrain model of each lake in the specified geographic area and the three-dimensional model of each blank area are spliced to obtain an initial three-dimensional model of the specified geographic area.

[0092] Specifically, according to the distribution data of each lake and blank area in the specified geographic region, the land digital elevation model of the specified geographic region, the standard terrain model of each lake in the specified geographic region, and the three-dimensional model of each blank area can be directly spliced to obtain an initial three-dimensional model of the specified geographic region. Considering the measurement errors of different models, the embodiment of the present application needs to further optimize the above-mentioned initial three-dimensional model.

[0093] In step S1072, a buffer zone with a specified width is created under the constraint of a preset terrain curvature, taking the boundary of the standard terrain model of each lake as the starting point, so that the buffer zone has an overlapping area with the land of the specified geographic region.

[0094] In step S1073, the elevation data of each position point in the overlapping area in the buffer zone and the elevation data in the land digital elevation model are weighted and summed to obtain the target elevation data of each position point in the overlapping area.

[0095] In step S1074, based on the target elevation data of all position points in the overlapping area, the elevation abnormal points in the overlapping area are identified and deleted to obtain an updated overlapping area.

[0096] For ease of understanding, the following example is given. If the resolution of the standard terrain model is 10 meters, a 30-meter-wide buffer zone is created under the constraint of a preset terrain curvature, taking the lake water surface vector range as the reference (i.e., taking the boundary of the standard terrain model of the lake as the starting point), so that the buffer zone overlaps with the land. Next, the elevation abnormal points in the overlapping area need to be deleted. Specifically, multi-resolution pyramid fusion is introduced to process elevation data of different resolutions in different zones. For example, a high-resolution data measured by a laser radar (i.e., the elevation data in the land digital elevation model) is given a weighting weight of 0.5, and a data converted from a single-beam elevation measurement (the elevation data in the buffer zone) is given a weighting weight of 0.45. The weighted sum result is used as the target elevation data of the position points in the overlapping area. Finally, data cleaning is performed to identify and delete the elevation abnormal points in the overlapping area to obtain an updated overlapping area.

[0097] In step S107, the initial three-dimensional model of the specified geographic region is updated based on the target elevation data of all position points in the updated overlapping area to obtain a three-dimensional terrain model of the specified geographic region.

[0098] That is, the part of the initial three-dimensional model in the overlapping area is updated based on the processing result of the previous step, and a three-dimensional terrain model of the specified geographic region is obtained.

[0099] In an optional embodiment, the embodiment of the present application further includes the following steps:

[0100] Step S201, obtaining a training sample set; wherein the training sample set includes multiple groups of training samples, and each group of training samples includes Landsat series images and high-resolution series images of a same geographical region in a same time period.

[0101] Step S202, taking the Landsat series images in each group of training samples as input data of an initial image enhancement model, taking the high-resolution series images in each group of training samples as training labels of the initial image enhancement model, training the initial image enhancement model until a preset termination condition is reached, and obtaining a target image enhancement model.

[0102] Step S203, processing the Landsat series images of a specified geographical region in a target historical time period by using the target image enhancement model, and obtaining predicted high-resolution series images of the specified geographical region in the target historical time period; wherein the target historical time period represents a historical time period before the high-resolution satellite is launched.

[0103] Based on the above description, after the target image enhancement model is obtained by training, the target image enhancement model can be used to process low-resolution Landsat series images of any time period to upgrade the image resolution and obtain corresponding high-resolution predicted high-resolution series images, so as to achieve the purpose of uniform interpretation accuracy of different resolutions and comparable interpretation results.

[0104] In addition, on the basis of digitizing the lake, real-time sensor data and historical data can be combined to use intelligent algorithms (such as data mining, prediction models, etc.) to warn of possible dangerous situations. For example, in the prediction of dead water level, flood level, eutrophication, etc., combined with the pre-trained model and the real-time monitored data, warning information can be timely issued to enable lake managers and relevant personnel to respond quickly. Obviously, by applying intelligent data fusion algorithms and lake dynamic data collection and warning systems, efficient processing and intelligent risk prediction of multi-source data can be achieved, and the accuracy and foresight of lake management are improved.

[0105] Embodiment Two

[0106] The embodiment of the present application also provides a lake water resource digitization device, which is mainly used for executing the lake water resource digitization method provided in the above-mentioned embodiment one. The lake water resource digitization device provided in the embodiment of the present application is specifically introduced as follows.

[0107] Figure 3 The function module diagram of the lake water resource digitization device provided in the embodiment of the present application is shown in FIG. 2. Figure 2As shown, the device mainly comprises: a first acquisition module 11, a determination module 12, a first scanning module 13, a second scanning module 14, a second acquisition module 15, a first construction module 16, a second construction module 17, a fusion module 18, and a visualization processing module 19, wherein:

[0108] The first acquisition module 11 is configured to acquire a land digital elevation model of a specified geographic region, and Landsat series images and high-resolution series images of the specified geographic region in a historical time period.

[0109] The determination module 12 is configured to determine, based on the Landsat series images and the high-resolution series images in the historical time period, a number of lakes in the specified geographic region, a lake distribution, a classification label, a cause label of each lake, a zoned result of a lake shoreline, and time series data of first target parameters; wherein the first target parameters include water temperature, water quality, water surface area, and water level.

[0110] The first scanning module 13 is configured to perform ground-based dynamic scanning on each lake to determine a ground observation data set of each lake; wherein the ground observation data set includes time series data of water level, water temperature, water quality, water outflow, and water inflow.

[0111] The second scanning module 14 is configured to perform ship-based dynamic scanning on each lake to determine a standard terrain model and a water storage amount of each lake.

[0112] The second acquisition module 15 is configured to acquire, by an airborne laser radar, three-dimensional point cloud data of each blank area in the specified geographic region, and acquire, by a tilt photography technology, image data of each blank area; wherein the blank area represents an intersection area of a water area and a land area.

[0113] The first construction module 16 is configured to construct, based on the three-dimensional point cloud data and the image data of each blank area, a three-dimensional model of each blank area.

[0114] The second construction module 17 is configured to construct, based on the land digital elevation model of the specified geographic region, the standard terrain model of each lake in the specified geographic region, and the three-dimensional model of each blank area, a three-dimensional terrain model of the specified geographic region.

[0115] The fusion module 18 is configured to perform intelligent data fusion on all related data of each lake to construct a multi-dimensional database of each lake.

[0116] The visualization processing module 19 is configured to perform visualization processing on each lake based on the three-dimensional terrain model of the specified geographic region and the multi-dimensional database of each lake to generate a digital lake comprehensive display map of each lake.

[0117] The embodiment of the present application first acquires Landsat series images and high-resolution series images of a specified geographic area in a historical time period, performs ground-based dynamic scanning, ship-based dynamic scanning on each lake in the specified geographic area, and collects three-dimensional point cloud data and image data of each blank area, so as to realize the "star-sky-ground-ship" full-element linkage and cooperation architecture to comprehensively measure and evaluate the lake water resources in the region. Then, the intelligent data fusion technology is used to fuse and process all related data of each lake, and a multi-dimensional database of each lake is constructed. Based on the multi-dimensional database, each lake is visualized to generate a digital lake comprehensive display diagram of each lake. Since the digital lake comprehensive display diagram covers the multi-dimensional data of the lake, the technical problem of insufficient lake hydrogeological structure survey data in the prior art can be solved.

[0118] Optionally, the determining module 12 is specifically configured to:

[0119] The hot infrared image set, the hyperspectral image set, the optical image set and the laser radar image set are selected from the Landsat series images and the high-resolution series images in the historical time period.

[0120] The hot infrared image set, the hyperspectral image set, the optical image set and the laser radar image set are respectively subjected to radiation correction, atmospheric correction and image splicing processing to obtain a pre-processed image set.

[0121] The image set of the lake in the wet season and the dry season is selected from the pre-processed image set to obtain a target image set, the number of lakes in the specified geographic area and the lake distribution.

[0122] The images in the target image set are interpreted to obtain time series data of a first target parameter of each lake in the specified geographic area; wherein the first target parameter includes water temperature, water quality, water surface area and water level.

[0123] Based on the preset lake grading rule and the water surface area of each lake, a grading label of each lake is determined.

[0124] Target data of each lake is acquired; wherein the target data includes evolution data of a geological structure unit where the lake is located, paleogeographic environment data of the lake and major geological event information.

[0125] Based on the target data of each lake, the image data of each lake in the target image set and a preset expert experience library, a genetic label of each lake and a partition result of the lake shoreline are determined.

[0126] Optionally, the first scanning module 13 is specifically configured to:

[0127] The second target parameter of each lake is obtained by setting a hydrological water temperature observation station, a water quality monitoring point and an inflow and outflow observation section in each lake to obtain time series data of the second target parameter of each lake; wherein the second target parameter includes water level, water temperature, water quality, outflow and inflow.

[0128] The time series data of the second target parameter of each lake is standardized to obtain the ground observation data set of each lake.

[0129] Optionally, the second scanning module 14 is specifically configured to:

[0130] According to the water depth and the distribution of aquatic plants of the target lake, the water area of the target lake is divided into partitions to obtain the partitioned target lake; wherein the target lake represents any lake in a specified geographical area.

[0131] For each partition in the target lake, multi-point depth sounding is performed according to the preset sounding mode matched therewith to obtain water depth data of the multi-point.

[0132] Based on the water depth data of the multi-point, the underwater topographic point cloud data of the target lake is constructed.

[0133] The underwater topographic point cloud data is cleaned to obtain the target point cloud data of the target lake.

[0134] Based on the target point cloud data, the water depth model of the target lake is constructed.

[0135] The water depth model of the target lake is converted to the 85 elevation system by the geographic coordinate conversion technology to obtain the standard topographic model of the target lake.

[0136] Based on the water depth model of the target lake and the water depth data of the target lake, the water storage capacity of the target lake is calculated.

[0137] Optionally, the first construction module 16 is specifically configured to:

[0138] The three-dimensional point cloud data and the image data of the target blank area are denoised to obtain denoised point cloud data and denoised image data; wherein the target blank area represents any blank area in a specified geographical area.

[0139] The denoised point cloud data and the denoised image data are processed by using the irregular triangle network method to obtain a raster vector three-dimensional model of the target blank area.

[0140] The raster vector three-dimensional model is subjected to Gaussian filter smoothing processing to obtain a filtered raster vector three-dimensional model.

[0141] The key terrain in the filtered raster vector three-dimensional model is subjected to feature enhancement processing to obtain a three-dimensional model of the blank area.

[0142] Optionally, the second building module 17 is specifically configured to:

[0143] splicing the land digital elevation model of the specified geographic area, the standard terrain model of each lake in the specified geographic area and the three-dimensional model of each blank area to obtain an initial three-dimensional model of the specified geographic area.

[0144] starting from the boundary of the standard terrain model of each lake, creating a buffer zone with a specified width under a preset terrain curvature constraint, so that the buffer zone has an overlapping area with the land of the specified geographic area.

[0145] performing weighted summation on the elevation data of each position point in the overlapping area in the buffer zone and the elevation data in the land digital elevation model to obtain target elevation data of each position point in the overlapping area.

[0146] Based on the target elevation data of all position points in the overlapping area, identifying and deleting the elevation outliers in the overlapping area to obtain an updated overlapping area.

[0147] updating the initial three-dimensional model of the specified geographic area based on the target elevation data of all position points in the updated overlapping area to obtain a three-dimensional terrain model of the specified geographic area.

[0148] Optionally, the device is further configured to:

[0149] obtain a training sample set; wherein the training sample set includes multiple groups of training samples, and each group of training samples includes Landsat series images and high-resolution series images of the same geographic area in the same time period.

[0150] use the Landsat series images in each group of training samples as input data of an initial image enhancement model, and use the high-resolution series images in each group of training samples as training labels of the initial image enhancement model, train the initial image enhancement model until a preset termination condition is reached, and obtain a target image enhancement model.

[0151] use the target image enhancement model to process the Landsat series images of the specified geographic area in a target historical time period to obtain predicted high-resolution series images of the specified geographic area in the target historical time period; wherein the target historical time period represents a historical time period before the launch of the high-resolution satellite.

[0152] Embodiment three

[0153] Referring to Figure 4The electronic device provided by the embodiment of the present application comprises: a processor 60, a memory 61, a bus 62 and a communication interface 63, the processor 60, the communication interface 63 and the memory 61 are connected through the bus 62; the processor 60 is used for executing an executable module stored in the memory 61, for example, a computer program.

[0154] The memory 61 can comprise a high-speed random access memory (RAM) and can also comprise a non-volatile memory, for example, at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 63 (which can be wired or wireless), and the Internet, a wide area network, a local area network, a metropolitan area network, etc. can be used.

[0155] The bus 62 can be an ISA bus, a PCI bus or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 4 Only one bidirectional arrow is used to represent the bus, but it does not mean that there is only one bus or only one type of bus.

[0156] The memory 61 is used for storing a program, and the processor 60 executes the program after receiving an execution instruction. The method executed by the device defined by the process disclosed in any of the foregoing embodiments of the present application can be applied to the processor 60 or realized by the processor 60.

[0157] The processor 60 can be an integrated circuit chip with signal processing capability. In implementation, each step of the above method can be completed by integrated logic circuit of hardware in the processor 60 or by instructions in the form of software. The processor 60 described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. Each method, step and logic block diagram disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware code processor for execution, or can be executed by a combination of hardware and software modules in the code processor. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 61, and the processor 60 reads the information in the memory 61 and combines the hardware to complete the steps of the above method.

[0158] The computer program product of the digital method, system, device and medium provided by the embodiments of the present application includes a computer readable storage medium storing non-volatile program codes executable by a processor. The instructions included in the program codes can be used to execute the method described in the foregoing method embodiments. For specific implementation, reference can be made to the method embodiments, which will not be described here.

[0159] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit.

[0160] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a nonvolatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present application or the parts of the present application that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0161] It should be noted that similar reference numerals and letters refer to similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0162] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the present application is usually placed, and are only for the convenience of describing the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In addition, the terms "first", "second", "third", and the like are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0163] In addition, the terms "horizontal", "vertical", "overhanging", and the like do not mean that the components must be absolutely horizontal or overhanging, but can be slightly inclined. For example, "horizontal" only means that its direction is more horizontal relative to "vertical", and does not mean that the structure must be completely horizontal, but can be slightly inclined.

[0164] In the description of the present application, it should also be noted that, unless otherwise explicitly specified and limited, the terms "arrangement", "installation", "connection", "connection" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium; it can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0165] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions recorded in the above embodiments can be modified, or some or all of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of digitizing a lake water resource, characterized by, The method comprises the following steps: acquiring a land digital elevation model of a specified geographic area, Landsat series images and Gaofen series images of the specified geographic area in a historical time period; determining the number of lakes, lake distribution, hierarchical label of each lake, genetic label, zoned result of lake shorelines, and time series data of first target parameters of each lake in the specified geographic area based on the Landsat series images and Gaofen series images in the historical time period; wherein the first target parameters include water temperature, water quality, water surface area, and water level; performing ground-based dynamic scanning on each lake to determine a ground observation data set of each lake; wherein the ground observation data set includes time series data of water level, water temperature, water quality, water outflow, and water inflow; performing ship-based dynamic scanning on each lake to determine a standard terrain model and water storage of each lake; acquiring three-dimensional point cloud data of each blank area in the specified geographic area by airborne laser radar, and acquiring image data of each blank area by oblique photography technology; wherein the blank area represents a water-land boundary area; constructing a three-dimensional model of each blank area based on the three-dimensional point cloud data and image data of each blank area; constructing a three-dimensional terrain model of the specified geographic area based on the land digital elevation model of the specified geographic area, the standard terrain model of each lake in the specified geographic area, and the three-dimensional model of each blank area; performing intelligent data fusion on all related data of each lake to construct a multi-dimensional database of each lake; performing visualization processing on each lake based on the three-dimensional terrain model of the specified geographic area and the multi-dimensional database of each lake to generate a digital lake comprehensive display map of each lake.

2. The method for digitalization of lake water resources according to claim 1, characterized in that, The method for determining the number of lakes, lake distribution, hierarchical label of each lake, genetic label, zoned result of lake shorelines, and time series data of first target parameters of each lake in the specified geographic area based on the Landsat series images and Gaofen series images in the historical time period comprises the following steps: screening a thermal infrared image set, a hyperspectral image set, an optical image set, and a laser radar image set from the Landsat series images and Gaofen series images in the historical time period; performing radiation correction, atmospheric correction, and image stitching processing on the thermal infrared image set, the hyperspectral image set, the optical image set, and the laser radar image set respectively to obtain a pre-processed image set; screening a lake image set in the wet season and dry season from the pre-processed image set to obtain a target image set, the number of lakes, and lake distribution in the specified geographic area; interpreting images in the target image set to obtain time series data of first target parameters of each lake in the specified geographic area; wherein the first target parameters include water temperature, water quality, water surface area, and water level; determining a hierarchical label of each lake based on a preset lake hierarchical rule and water surface area of each lake; Obtaining target data of each lake; wherein, the target data comprises evolution data of a geological structural unit where the lake is located, paleogeographic environment data of the lake, and information of major geological events; Based on the target data of each lake, image data of each lake in the target image set, and a preset expert experience library, a genetic label of each lake and a partition result of the lake shore line are determined.

3. The method for digitalization of lake water resources according to claim 2, characterized in that, Ground dynamic scanning is performed on each lake to determine a ground observation data set of each lake, including: By setting hydrological and water temperature observation stations, water quality monitoring points, and inflow and outflow observation sections in each lake, time series data of second target parameters of each lake are obtained; wherein, the second target parameters include water level, water temperature, water quality, outflow, and inflow; The time series data of the second target parameters of each lake are standardized to obtain the ground observation data set of each lake.

4. The method for digitizing lake water resources according to claim 1, characterized in that, Ship-based dynamic scanning is performed on each lake to determine a standard terrain model and a water storage capacity of each lake, including: According to the water depth and the distribution of aquatic plants of a target lake, the water area of the target lake is partitioned to obtain a partitioned target lake; wherein, the target lake represents any lake in the specified geographic area; For each partition in the target lake, multi-point sounding is performed according to the preset sounding mode matched therewith to obtain water depth data of the multi-point positions; Based on the water depth data of the multi-point positions, underwater topographic point cloud data of the target lake are constructed; The underwater topographic point cloud data are cleaned to obtain target point cloud data of the target lake; Based on the target point cloud data, a water depth model of the target lake is constructed; The water depth model of the target lake is converted to the 85 elevation system by geographic coordinate conversion technology to obtain a standard terrain model of the target lake; Based on the water depth model of the target lake and the water depth data of the target lake, the water storage capacity of the target lake is calculated.

5. The method for digitization of lake water resources according to claim 1, characterized in that, Based on the three-dimensional point cloud data and image data of each blank area, a three-dimensional model of each blank area is constructed, including: The three-dimensional point cloud data and image data of a target blank area are denoised to obtain denoised point cloud data and denoised image data; wherein, the target blank area represents any blank area in the specified geographic area; The denoised point cloud data and the denoised image data are processed by using the irregular triangle mesh method to obtain a raster vector three-dimensional model of the target blank area; The raster vector three-dimensional model is subjected to Gaussian filter smoothing processing to obtain a filtered raster vector three-dimensional model; The key terrain in the filtered raster vector three-dimensional model is subjected to feature enhancement processing to obtain a three-dimensional model of the blank area.

6. The method for digitization of lake water resources according to claim 1, characterized in that, Based on the land digital elevation model of the specified geographic area, the standard terrain model of each lake in the specified geographic area, and the three-dimensional model of each blank area, a three-dimensional terrain model of the specified geographic area is constructed, including: stitching the land digital elevation model of the specified geographic region, the standard terrain model of each lake in the specified geographic region, and the three-dimensional model of each blank area to obtain an initial three-dimensional model of the specified geographic region; starting from the boundary of the standard terrain model of each lake, creating a buffer zone of a specified width under a preset terrain curvature constraint, so that the buffer zone has an overlapping area with the land of the specified geographic region; performing weighted summation on the elevation data of each location point in the overlapping area in the buffer zone and the elevation data of each location point in the land digital elevation model to obtain target elevation data of each location point in the overlapping area; based on the target elevation data of all location points in the overlapping area, identifying and deleting elevation outliers in the overlapping area to obtain an updated overlapping area; updating the initial three-dimensional model of the specified geographic region based on the target elevation data of all location points in the updated overlapping area to obtain a three-dimensional terrain model of the specified geographic region.

7. The method for digitization of lake water resources according to claim 1, characterized in that, Further comprising: obtaining a training sample set; wherein the training sample set includes multiple groups of training samples, and each group of training samples includes Landsat series images and high-resolution series images of the same geographic region in the same time period; using the Landsat series images in each group of training samples as input data of an initial image enhancement model, and using the high-resolution series images in each group of training samples as training labels of the initial image enhancement model, training the initial image enhancement model until a preset termination condition is reached to obtain a target image enhancement model; using the target image enhancement model to process the Landsat series images of the specified geographic region in a target historical time period to obtain predicted high-resolution series images of the specified geographic region in the target historical time period; wherein the target historical time period represents a historical time period before the launch of the high-resolution satellite.

8. A digital system for lake water resources, characterized by, Comprise: a first acquisition module configured to acquire a land digital elevation model of a specified geographic region, Landsat series images of the specified geographic region in a historical time period, and high-resolution series images of the specified geographic region in the historical time period; a determination module configured to determine, based on the Landsat series images and the high-resolution series images in the historical time period, a number of lakes in the specified geographic region, a lake distribution, a hierarchical label, a cause label of each lake, a zoning result of a lake shoreline, and time series data of a first target parameter in the specified geographic region; wherein the first target parameter includes water temperature, water quality, water surface area, and water level; a first scanning module configured to perform ground-based dynamic scanning on each of the lakes to determine a hierarchical label, a cause label, a zoning result of a lake shoreline, and a ground-based observation data set of each lake; wherein the ground-based observation data set includes time series data of water level, water temperature, water quality, water outflow, and water inflow; a second scanning module configured to perform ship-based dynamic scanning on each of the lakes to determine a standard terrain model and a water storage capacity of each lake; The second acquisition module is configured to acquire three-dimensional point cloud data of each blank area in the specified geographic region by an airborne laser radar, and acquire image data of each blank area by a tilt photography technology; wherein, the blank area represents a boundary area between a water area and a land area; The first construction module is configured to construct a three-dimensional model of each blank area based on the three-dimensional point cloud data and the image data of each blank area; The second construction module is configured to construct a three-dimensional terrain model of the specified geographic region based on a land area digital elevation model of the specified geographic region, a standard terrain model of each lake in the specified geographic region, and the three-dimensional model of each blank area; The fusion module is configured to intelligently fuse all related data of each lake to construct a multi-dimensional database of each lake; The visualization processing module is configured to perform a visualization processing on each lake based on the three-dimensional terrain model of the specified geographic region and the multi-dimensional database of each lake, and generate a digital lake comprehensive display map of each lake.

9. An electronic device comprising a memory, a processor, said memory having stored thereon a computer program operable to run on said processor, characterized in that, The processor executes the computer program to implement the lake digitalization method in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions, and the computer instructions are executed by the processor to implement the lake digitalization method in any one of claims 1 to 7.

Images