Geographic information data processing method and system based on multi-source data fusion

Abstract

The application discloses a geographic information data processing method and system based on multi-source data fusion, relates to the technical field of digital data processing, and comprises the following steps: analyzing and processing multi-source geographic data after preliminary processing to obtain first weather characteristics, dynamically correcting the first weather characteristics to obtain second weather characteristics, and performing fusion calculation on the second weather characteristics to obtain target geographic data; in combination with public control points and iterative optimization, traditional spatial misplacement is solved, data consistency is consolidated, weather data is extracted by distinguishing effective color value ranges, weather characteristics are corrected according to seasonal time periods in combination with historical same-period data, interference is avoided, and recognition accuracy is improved; and after spatial alignment, data screening and integrity checking, target geographic data is ensured to be complete and controllable, and high-precision requirements of smart cities, disaster early warning and land planning are met.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric digital data processing, and in particular to a geographic information data processing method and system based on multi-source data fusion. BACKGROUND

[0002] In recent years, with the rapid development of smart city construction, ecological environment monitoring, natural disaster early warning and land space planning fields, the application scenarios of geographic information data are continuously expanding, and the demand for its precision, timeliness and multi-dimensional correlation is increasingly stringent. Digital data processing technology, as the core support of geographic information system, directly determines the reliability and application value of geographic information services. Current geographic information data mainly comes from multi-source channels of remote sensing images and GIS vectors. Remote sensing image data has the advantage of macro dynamic monitoring, and GIS vector data has precise spatial topological properties. The fusion processing of the two can effectively make up for the limitations of single-source data. Therefore, multi-source geographic data fusion has become the core development direction of the geographic information field, especially in cross-period geographic change analysis and complex weather terrain evaluation scenarios, higher requirements are put forward for the collaborative processing capability of multi-source data.

[0003] However, there are still many problems to be solved in the existing multi-source geographic data processing technology: firstly, multi-source data often causes spatial position dislocation due to non-uniform original coordinate system, and the number of public control points is fixedly set, which cannot be adjusted by iteration optimization to reduce coordinate conversion error, directly affecting the spatial consistency of subsequent data fusion; secondly, in the process of obtaining weather characteristics, only a single color value is relied on for judgment, without effectively distinguishing invalid data such as abnormal color value and non-sky area color value, and lacking a dynamic correction mechanism combining historical same period data and seasonal and period differences, resulting in that the extraction accuracy of weather characteristics is greatly affected by environmental interference; thirdly, the multi-source data fusion stage lacks a unified spatial reference as the core alignment mechanism, and the associated data of geographic coordinates, weather characteristics and terrain information lack strict screening, so that the generated geographic data is prone to error exceeding the standard and key element missing, which is difficult to meet the application requirements of high-precision geographic information. SUMMARY

[0004] The technical problems solved by the present application are: there are still many problems to be solved in the existing multi-source geographic data processing technology: first, multi-source data often causes spatial position dislocation due to non-uniform original coordinate system, and the number of public control points is fixedly set, which cannot be adjusted by iteration optimization to reduce coordinate conversion error, directly affecting the spatial consistency of subsequent data fusion, second, in the process of obtaining weather characteristics, only a single color value is relied on for judgment, invalid data such as abnormal color value and non-sky area color value are not effectively distinguished, and there is a lack of dynamic correction mechanism combined with historical same period data and seasonal and time period differences, resulting in that the extraction accuracy of weather characteristics is greatly affected by environmental interference, third, there is a lack of alignment mechanism with unified spatial reference as the core in the multi-source data fusion stage, and the related data of geographic coordinates, weather characteristics and terrain information lack strict screening, and the finally generated geographic data is prone to problems such as error exceeding the standard and missing key elements, which is difficult to meet the application requirements of high-precision geographic information.

[0005] To solve the above technical problems, the present application provides the following technical scheme: a geographic information data processing method based on multi-source data fusion includes the following steps:

[0006] Step S100, the multi-source geographic data after preliminary processing is analyzed and processed to obtain a first weather characteristic, and the first weather characteristic is dynamically corrected to obtain a second weather characteristic;

[0007] Step S200, the second weather characteristic is fused and calculated to obtain target geographic data.

[0008] As a preferred scheme of the geographic information data processing method based on multi-source data fusion, wherein: the multi-source geographic data is preliminarily processed, and the preliminary processing specifically includes:

[0009] The multi-source geographic data includes remote sensing image data of an object to be analyzed and GIS vector data of the object to be analyzed;

[0010] The remote sensing image data and the GIS vector data are subjected to coordinate conversion;

[0011] The coordinate conversion logic includes:

[0012] The public control points of the remote sensing image data and the public control points of the GIS vector data are selected, the public control points of the remote sensing image data are n non-collinear points in the geographic range of the remote sensing image data, and the public control points of the GIS vector data are p corner points on the boundary of the geographic range of the GIS vector data;

[0013] And the n and the p are positive integers greater than or equal to 3;

[0014] The remote sensing image data and the GIS vector data in the multi-source geographic data are converted to the geodetic coordinate system, a coordinate mapping relationship is established based on the common control points by using an affine transformation algorithm, and the coordinate conversion is realized.

[0015] The remote sensing image data after the coordinate conversion comprises first terrain feature information of an analysis area.

[0016] The GIS vector data after the coordinate conversion comprises second terrain feature information of the analysis area.

[0017] The mapping relationship comprises a first mapping relationship and a second mapping relationship.

[0018] The first mapping relationship is a mapping relationship between an original coordinate system of the remote sensing image data and a geodetic coordinate system of the remote sensing image data.

[0019] The second mapping relationship is a mapping relationship between an original coordinate system of the GIS vector data and a geodetic coordinate system of the GIS vector data.

[0020] As a preferred scheme of the geographic information data processing method based on multi-source data fusion, the number n and p of the common control points are iteratively optimized by adding the common control points.

[0021] The condition for the iterative optimization comprises:

[0022] When the error value of any common control point after the coordinate conversion and the corresponding actual coordinate point is greater than or equal to a first value, n and p are increased by 1 based on the current values, the added common control points are brought into the coordinate mapping relationship, the coefficients in the coordinate mapping relationship are adaptively changed, the input value and the output value meet the mathematical relationship of the affine transformation, when the error value of any common control point after the coordinate conversion and the corresponding actual coordinate point is less than the first value, the values of n and p are stopped from being iterated.

[0023] The first value is represented as the maximum value of the straight-line distance between the common control point after the conversion and the actual coordinate point.

[0024] As a preferred scheme of the geographic information data processing method based on multi-source data fusion, adding a time stamp to the multi-source geographic data after the preliminary processing and performing analysis and processing comprise:

[0025] The multi-source geographic data after the preliminary processing is the remote sensing image data and the GIS vector data after the coordinate conversion.

[0026] After the time stamp is added to the multi-source geographic data after the preliminary processing, the remote sensing image data is selected from the multi-source geographic data as a weather type feature extraction source.

[0027] The weather type features include a sunny day feature, an overcast day feature, a cloudy day feature, and a precipitation feature;

[0028] The effective data of the weather is extracted according to color values of pixels in the remote sensing image data, and the logic of the extraction includes:

[0029] When the color value is within a first effective value range, it is determined that corresponding color information is effective data and is extracted, the color information is parameter information corresponding to the color value, and the parameter information includes a hue, a saturation, and a brightness;

[0030] When the color value is outside a second effective value range, it is determined that corresponding color information is invalid data and is not extracted, the color information is parameter information corresponding to an abnormal color value, a non-sky region color value, or a distorted color value generated due to blurring or blocking of the remote sensing image data, and the second effective value range refers to a color value range in which effective parameter information cannot be extracted.

[0031] As a preferred scheme of the geographic information data processing method based on multi-source data fusion, the application establishes an association between the extracted color information and the weather type features.

[0032] The color parameter intervals of the association are divided based on a hue value range, a saturation value range, and a brightness value range within the first effective value range, and specifically include:

[0033] The first color parameter interval corresponds to the sunny day feature, the second color parameter interval corresponds to the overcast day feature, the third color parameter interval corresponds to the cloudy day feature, and the fourth color parameter interval corresponds to the precipitation feature.

[0034] According to the association, the extracted effective color information is matched to a corresponding color parameter interval and is converted into corresponding first weather feature data.

[0035] As a preferred scheme of the geographic information data processing method based on multi-source data fusion, the application automatically compensates the first weather feature data based on historical data, which includes:

[0036] Color information in historical remote sensing image data of the same period and the same region is obtained, and corresponding data between the color information and actual weather type features of the same period and the same region is obtained, a compensation coefficient is generated by analyzing a deviation rule of color parameter intervals and actual weather type features in the corresponding data.

[0037] Color information in historical remote sensing image data of the same period and the same region is classified according to weather type features, and corresponding data between the color information and actual weather type features of the same period and the same region is classified according to weather type features.

[0038] Calculate the color parameter interval extracted under each weather type feature, and according to the deviation value of the median value of the color parameter interval from the median value of the standard color parameter corresponding to the actual weather type feature, the distribution frequency and fluctuation amplitude of the deviation value in different seasons and different time periods are counted.

[0039] The seasons include spring, summer, autumn and winter, and the time periods include the early morning period, the morning period, the noon period, the afternoon period and the night period.

[0040] The deviation rule is that the color parameter interval corresponding to the sunny feature deviates to the high value of the brightness parameter in the summer noon period, the color parameter interval corresponding to the overcast feature deviates to the low value of the saturation parameter in the winter morning period, and the color parameter interval corresponding to the precipitation feature deviates to the low value of the brightness parameter and the high value of the saturation parameter in the summer.

[0041] As a preferred scheme of the geographic information data processing method based on multi-source data fusion, the first weather feature data is dynamically corrected by using the compensation coefficient to obtain second weather feature data.

[0042] The dynamic correction includes a first operation and a second operation.

[0043] The first operation is to match the target compensation coefficient from the generated compensation coefficient according to the weather type feature, season and time period corresponding to the first weather feature data.

[0044] The second operation is to adjust the median value of the color parameter interval corresponding to the weather type feature in the first weather feature data by using the target compensation coefficient, so that the deviation of the adjusted median value from the median value of the standard color parameter corresponding to the actual weather type feature falls within a preset allowable range.

[0045] The adaptability of the adjusted color parameter interval and the first weather feature data is judged in real time, if the adaptability does not reach a preset adaptation threshold, the compensation coefficient is updated based on the color information in the latest acquired historical same period and same area remote sensing image data and the corresponding data between the same period and same area actual weather type feature, and the first operation and the second operation are repeatedly executed until the adaptability reaches the preset adaptation threshold, and the second weather feature data is obtained.

[0046] The second weather feature parameter includes the color parameter interval corresponding to the sunny feature, the overcast feature, the cloudy feature and the precipitation feature after dynamic correction, the deviation of the median value of the color parameter interval from the median value of the standard color parameter corresponding to the actual weather type feature is within a preset allowable range, and the weather type feature, season and time period identifier corresponding to the color parameter interval.

[0047] As a preferred scheme of the geographic information data processing method based on multi-source data fusion provided in the application, wherein: the second weather characteristic parameter is calculated to obtain target geographic data, and the calculation specifically includes:

[0048] The geographic range corresponding to the second weather characteristic parameter is aligned with the geographic range of the GIS vector data and the remote sensing image data after the coordinate conversion, so that the second weather characteristic parameter under the same geographic coordinate point is matched with the spatial position of the multi-source geographic data based on the common control point after the geodetic coordinate system conversion;

[0049] According to the season and the time period in the second weather characteristic parameter, the second weather characteristic parameter is combined and grouped again by season and time period, and the weather type characteristic under the same geographic coordinate is corresponded with the second terrain feature information in the GIS vector data in each group to form a geographic coordinate, season, time period, weather type and terrain feature information associated data pair;

[0050] Based on the first value, the associated data pairs meeting the conditions are screened;

[0051] The conditions include:

[0052] The geographic coordinate corresponding to the associated data pair is in the overlapping geographic range of the remote sensing image data and the GIS vector data after the coordinate conversion;

[0053] The weather type characteristic in the associated data pair is consistent with the color information and the weather type characteristic association relationship, and the consistent association relationship is that the color parameter interval corresponding to the weather type characteristic is in the first effective value range;

[0054] The second terrain feature information of the GIS vector data in the associated data pair has no conflict with the original second terrain feature information of the GIS vector data, and the no conflict is that the error between the second terrain feature information and the original second terrain feature information under the same geographic coordinate is less than the first value.

[0055] As a preferred scheme of the geographic information data processing method based on multi-source data fusion provided in the application, wherein: the associated data pairs after the screening are arranged in order of geographic coordinates to form a structured data set including geodetic coordinate system geographic coordinate values, weather type characteristics, seasons, time periods and terrain feature parameters, the data set is subjected to integrity check and the entries missing any data element are removed to obtain target geographic data;

[0056] The data elements include geodetic coordinate system geographic coordinate values, weather type characteristics, seasons, time periods and terrain feature parameters;

[0057] The decision criterion of the integrity check is that each entry in the structured data set includes complete geodetic coordinate system geographic coordinate values, weather type features, seasons, time periods, and terrain feature parameters.

[0058] The geographic coordinate precision of the target geographic data is consistent with the coordinate conversion precision, the weather type feature precision is consistent with the second weather feature parameter precision, and the overall data error is less than the first value.

[0059] A geographic information data processing system based on multi-source data fusion, comprising a processing module and a fusion module.

[0060] The processing module analyzes and processes the multi-source geographic data after preliminary processing to obtain first weather features, and dynamically corrects the first weather features to obtain second weather features.

[0061] The fusion module performs fusion calculation on the second weather features to obtain target geographic data.

[0062] The beneficial effects of the present application are: through the geodetic coordinate system, remote sensing image data and GIS vector data coordinates, combined with public control points iterative optimization, the spatial misplacement problem caused by traditional fixed control points is solved, the data spatial consistency foundation is built, the weather data is extracted by distinguishing the effective range of color value, the weather features are dynamically corrected according to the historical data of the same period according to seasons, the feature deviation caused by environmental interference is avoided, the weather type recognition precision is improved, finally through spatial alignment, correlation data pair screening and integrity check, the target geographic data elements are complete and the overall error is controllable, which can efficiently meet the demand of high-precision geographic information in the scene of smart city, disaster warning and land planning. BRIEF DESCRIPTION OF DRAWINGS

[0063] Figure 1 The step flowchart of the geographic information data processing method based on multi-source data fusion provided by an embodiment of the present application is shown.

[0064] Figure 2 The basic flowchart of the geographic information data processing system based on multi-source data fusion provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0065] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present application, not all embodiments.

[0066] Embodiment 1, refer to Figure 1 For an embodiment of the present application, a geographic information data processing method based on multi-source data fusion is provided, comprising the following steps:

[0067] In step S100, the preliminary processed multi-source geographic data is analyzed and processed to obtain a first weather feature, and the first weather feature is dynamically corrected to obtain a second weather feature.

[0068] In step S200, the second weather feature is fused and calculated to obtain target geographic data.

[0069] In one embodiment, the preliminary processed multi-source geographic data is analyzed and processed to obtain a first weather feature from the above data, and the first weather feature is further dynamically corrected to obtain a second weather feature with higher accuracy. The second weather feature is fused and calculated to integrate the second weather feature with geographic related information in the multi-source geographic data, and finally target geographic data is generated. Through extraction and optimization of the weather feature, the accuracy of the weather feature data can be effectively improved, and the deviation of the preliminary feature can be avoided to affect subsequent application. The fusion calculation realizes effective association of the weather feature and the geographic information, and the generated target geographic data can meet the demand of regional environmental monitoring and agricultural production planning for geographic and weather related data, and ensures the practical value and reliability of the system in actual application.

[0070] The multi-source geographic data is preliminarily processed, and the preliminary processing specifically includes:

[0071] The multi-source geographic data includes remote sensing image data of an object to be analyzed and GIS vector data of the object to be analyzed;

[0072] The remote sensing image data and the GIS vector data are coordinate-converted;

[0073] The coordinate conversion logic includes:

[0074] The common control points of the remote sensing image data and the common control points of the GIS vector data are selected, the common control points of the remote sensing image data are n non-collinear points in the geographic range of the remote sensing image data, and the common control points of the GIS vector data are p corner points on the boundary of the geographic range of the GIS vector data;

[0075] And n and p are positive integers greater than or equal to 3;

[0076] The remote sensing image data and the GIS vector data in the multi-source geographic data are converted to the geodetic coordinate system, the coordinate mapping relationship is established based on the common control points through the affine transformation algorithm, and the coordinate conversion is realized;

[0077] The remote sensing image data after coordinate conversion includes first terrain feature information of the region to be analyzed;

[0078] The GIS vector data after coordinate conversion comprises second terrain feature information of the region to be analyzed;

[0079] The mapping relationship comprises a first mapping relationship and a second mapping relationship;

[0080] The first mapping relationship is a mapping relationship between a remote sensing image data original coordinate system and a remote sensing image data geodetic coordinate system;

[0081] The second mapping relationship is a mapping relationship between a GIS vector data original coordinate system and a GIS vector data geodetic coordinate system.

[0082] For the number n and p of common control points, iterative optimization is performed by increasing the common control points;

[0083] The condition for performing iterative optimization comprises:

[0084] When the error value of any common control point after coordinate conversion and the corresponding actual coordinate point is greater than or equal to a first value, n and p are increased by 1 respectively on the basis of the current values, the newly added common control points are brought into the coordinate mapping relationship, the coefficients in the coordinate mapping relationship are adaptively changed, so that the input value and the output value meet the mathematical relationship of affine transformation, when the error value of any common control point after coordinate conversion and the corresponding actual coordinate point is less than the first value, the values of n and p are stopped from being iterated;

[0085] The first value is represented as the maximum value of the straight line distance between the converted common control points and the actual coordinate points.

[0086] In one of the embodiments, the multi-source geographic data is preliminarily processed, taking remote sensing image data (such as satellite remote sensing image of a county) and GIS vector data (such as GIS terrain vector map of the county) of an analysis object as processing objects, and the core is developed around coordinate conversion and iterative optimization. The specific process is as follows: first, coordinate conversion operation is performed, and common control points of the two types of data are selected, wherein the common control points of the remote sensing image data are n non-collinear points (n is a positive integer greater than or equal to 3, for example, 3 evenly distributed road intersections in the county) in the geographic range thereof, and the common control points of the GIS vector data are p corner points (p is a positive integer greater than or equal to 3, for example, 3 corner vertices of the county boundary) on the boundary of the geographic range thereof. Subsequently, the two types of data are converted to a geodetic coordinate system (such as 2000 geodetic coordinate system) and are unified to the geodetic coordinate system, and based on the above common control points, mapping relationships (the first mapping relationship is the corresponding relationship between the original coordinate system of the remote sensing image data and the geodetic coordinate system, and the second mapping relationship is the corresponding relationship between the original coordinate system of the GIS vector data and the geodetic coordinate system) are respectively established by using an affine transformation algorithm, the coordinate conversion is completed, and the converted remote sensing image data includes first terrain feature information (such as the elevation gradient in the region) of the region to be analyzed, and the converted GIS vector data includes second terrain feature information (such as the contour line parameters in the region) of the region to be analyzed. At the same time, iterative optimization is performed for the number n and p of common control points. The condition for iterative optimization is set as follows: when the error value of any common control point after coordinate conversion and the corresponding actual coordinate point (such as the actually measured coordinate of the road intersection) is greater than or equal to a first value, n and p are respectively increased by 1 (for example, n is increased from 3 to 4, and p is increased from 3 to 4) on the basis of the current values, and the newly added common control points are brought into the coordinate mapping relationship, and the mapping relationship coefficients are adaptively changed to conform to the mathematical relationship of affine transformation. When the error value is less than the first value, the iteration is stopped. The first value is set to 5 meters (i.e., the maximum straight line distance between the converted common control point and the actual coordinate point), and the setting is based on the combination of historical multi-source geographic data processing experience in the same region, the high precision requirement of geographic data in the scenarios of smart city and disaster warning, and the consideration of precision and processing efficiency. In this preliminary processing process, the targeted selection of common control points can guarantee the geometric stability of coordinate mapping, and the iterative optimization mechanism can control the coordinate conversion error within 5 meters, effectively solving the coordinate system difference problem of remote sensing image and GIS vector data, avoiding spatial misplacement in subsequent data processing, and at the same time, the retained terrain feature information also provides reliable geographic basic data support for subsequent weather feature extraction and data fusion.

[0087] Adding time stamps to the preliminarily processed multi-source geographic data and performing analysis and processing include:

[0088] The preliminarily processed multi-source geographic data is remote sensing image data and GIS vector data after coordinate conversion.

[0089] After adding time stamp to the preliminary processed multi-source geographic data, remote sensing image data is selected from the multi-source geographic data as a weather type feature extraction source;

[0090] The weather type features include sunny day feature, overcast day feature, cloudy day feature and precipitation feature;

[0091] Effective data of the weather is extracted according to color values of pixels in the remote sensing image data, and the extraction logic includes:

[0092] When the color value is within a first effective value range, it is determined that corresponding color information is effective data and is extracted, the color information is parameter information corresponding to the color value, and the parameter information includes hue, saturation and brightness;

[0093] When the color value is out of a second effective value range, it is determined that corresponding color information is invalid data and is not extracted, the color information refers to parameter information corresponding to abnormal color value, non-sky region color value and distorted color value caused by blurring or blocking of the remote sensing image data, and the second effective value range refers to a color value range in which effective parameter information cannot be extracted.

[0094] In one of the embodiments, the preliminary processed multi-source geographic data (i.e. remote sensing image data converted by the geodetic coordinate system, such as high-resolution satellite remote sensing image of a township in September 2024; and GIS vector data converted by the same coordinate system, such as the topographic vector map of the township) is added with time stamp and analyzed, the specific process is as follows: first, add time stamp to the two types of preliminary processed multi-source geographic data, the time stamp is accurate to the hour according to the actual data collection time (for example, the remote sensing image data is collected on 2024-09-10 10:00, then the corresponding time stamp is added, and the GIS vector data is associated with the time stamp of the period); then select the remote sensing image data from the multi-source geographic data as the source of weather type feature extraction, the weather type features to be extracted include sunny feature, overcast feature, cloudy feature and precipitation feature, then according to the color value RGB of the pixel in the remote sensing image data, extract the weather effective data, the logic of extraction is set as follows: the first effective value range is set as R (180-255), G (180-255), B (200-255) based on the pixel color statistics of the historical clear weather remote sensing image in the same region, when the pixel color value is within the range, the corresponding color information (including the parameter information of hue 180-220°, saturation 20%-40%, brightness 70%-90%) is determined as effective data and extracted, the second effective value range is set as R (0-50), G (0-50), B (0-50) (corresponding to abnormal dark color) and R (30-80), G (100-180), B (30-80) (corresponding to ground vegetation non-sky area), when the pixel color value is out of the range, the corresponding color information (such as distorted color value caused by cloud cover, parameter information corresponding to non-sky area color value) is determined as invalid data and not extracted. In this process, the addition of time stamp can realize the accurate association of weather features and collection period, the logic of effective data extraction based on the clear color value range can eliminate invalid interference data, significantly improve the accuracy of subsequent weather type feature recognition, and focusing on remote sensing image data as the extraction source can fully utilize its intuitive visual information advantage, laying a reliable data foundation for the subsequent first weather feature.

[0095] Establish the correlation between the extracted color information and the weather type feature;

[0096] The color parameter interval of the correlation is divided based on the hue value range, saturation value range and brightness value range in the first effective value range, specifically including:

[0097] The first color parameter interval corresponds to the sunny feature, the second color parameter interval corresponds to the overcast feature, the third color parameter interval corresponds to the cloudy feature, and the fourth color parameter interval corresponds to the precipitation feature;

[0098] According to the association relationship, the extracted effective color information is matched to the corresponding color parameter interval, and is converted into the corresponding first weather feature data.

[0099] In one of the embodiments, after the effective color information is obtained, an association relationship between the effective color information and the weather type feature is further established: the color parameter interval of the association relationship is divided based on the hue, saturation, and brightness value ranges in the first effective value range, and each interval value is set according to the statistical results of the color parameters of the remote sensing images in the same region under different weather conditions in history, wherein the first color parameter interval is hue 190-210°, saturation 25%-35%, and brightness 80%-90%, corresponding to the sunny day feature (matching the color rule of the bright and moderately saturated sky in the historical sunny day image), the second color parameter interval is hue 180-190°, saturation 20%-25%, and brightness 70%-75%, corresponding to the overcast day feature (matching the characteristics of the dark and low-saturated sky in the historical overcast day image), the third color parameter interval is hue 190-205°, saturation 22%-32%, and brightness 75%-80%, corresponding to the cloudy day feature (between the sunny day and overcast day parameters, adapting to the visual properties of the uneven brightness of the sky in the cloudy day), and the fourth color parameter interval is hue 180-195°, saturation 30%-38%, and brightness 70%-78%, corresponding to the precipitation feature (referring to the parameter characteristics of the dark and slightly high-saturated sky in the historical precipitation weather image). Finally, according to the above association relationship, the extracted effective color information (such as the hue 200°, saturation 30%, and brightness 85% of a pixel of a remote sensing image) is matched to the corresponding color parameter interval, and if it falls into the first color parameter interval, it is converted into the first weather feature data corresponding to the sunny day, and if it falls into other intervals, it is converted into the first weather feature data corresponding to the overcast day, cloudy day, or precipitation.

[0100] The automatic compensation of the first weather feature data based on the historical data includes:

[0101] The color information in the historical remote sensing image data of the same period and the same region is obtained, and the corresponding data between the color information and the actual weather type feature of the same period and the same region is obtained, and a compensation coefficient is generated by analyzing the deviation rule of the color parameter interval and the actual weather type feature in the corresponding data;

[0102] The color information in the historical remote sensing image data of the same period and the same region is classified according to the weather type feature, and the corresponding data between the color information and the actual weather type feature of the same period and the same region is classified according to the weather type feature;

[0103] The color parameter interval extracted under each weather type feature is calculated, the deviation value between the color parameter interval and the standard color parameter interval corresponding to the actual weather type feature is calculated, and the distribution frequency and fluctuation amplitude of the deviation value in different seasons and different time periods are calculated;

[0104] The seasons include spring, summer, autumn and winter, and the time periods include a pre-dawn time period, a morning time period, a noon time period, an afternoon time period and a night time period;

[0105] The deviation rule is that the color parameter interval corresponding to the sunny day feature deviates to a high value of the brightness parameter in the noon time period in summer, the color parameter interval corresponding to the overcast day feature deviates to a low value of the saturation parameter in the morning time period in winter, and the color parameter interval corresponding to the precipitation feature deviates to a low value of the brightness parameter and a high value of the saturation parameter in summer.

[0106] The first weather feature data is dynamically corrected by using the compensation coefficient to obtain second weather feature data;

[0107] The dynamic correction includes a first operation and a second operation.

[0108] The first operation is to match a target compensation coefficient from the generated compensation coefficients according to a weather type feature, a season and a time period corresponding to the first weather feature data.

[0109] The second operation is to apply the target compensation coefficient to a color parameter interval of the corresponding weather type feature in the first weather feature data, adjust a median value of the color parameter interval, and make a deviation of the adjusted median value from a standard median value of a color parameter corresponding to the actual weather type feature fall within a preset allowable range.

[0110] The adjusted color parameter interval is judged for adaptability to the first weather feature data in real time, and if the adaptability does not reach a preset adaptation threshold, the compensation coefficient is updated based on color information in historical remote sensing image data of the same period and the same region and corresponding data between the color information and the actual weather type feature of the same period and the same region, and the first operation and the second operation are repeatedly executed until the adaptability reaches the preset adaptation threshold, to obtain the second weather feature data.

[0111] The second weather feature parameter includes color parameter intervals corresponding to the sunny day feature, the overcast day feature, the cloudy day feature and the precipitation feature respectively after dynamic correction, a deviation of a median value of the color parameter interval from a standard median value of a color parameter corresponding to the actual weather type feature is within a preset allowable range, and the second weather feature parameter further includes a weather type feature, a season and a time period identifier corresponding to the color parameter interval.

[0112] In one of the embodiments, the first weather feature data is automatically compensated and dynamically corrected based on historical data to obtain the second weather feature data, and the specific process is as follows: first, the automatic compensation operation is carried out to obtain the relevant data of the historical same period and the same region of the area to be analyzed (such as a county), that is, the color information of the remote sensing image of the same period (such as the current processing data of June 2024, the remote sensing image of June of each year from 2021 to 2023 is taken) in the past three years, and the actual weather type feature (sunny feature, cloudy feature, cloudy feature and precipitation feature) corresponding data recorded by the meteorological station in the same period and the same region are selected. After classifying the corresponding data according to the weather type feature, the median value of the color parameter interval extracted under each type of weather (such as the median value of the hue 195°, the saturation 30% and the brightness 85% under the sunny classification) is calculated, and the deviation value is obtained by comparing the median value of the standard color parameter of the weather type (industry recognized standard: sunny hue 200°, saturation 30%, brightness 85%; cloudy hue 185°, saturation 22%, brightness 72%). Then, the distribution frequency and fluctuation amplitude of the deviation value in different seasons (spring from March to May, summer from June to August, autumn from September to November, and winter from December to February) and different time periods (morning period from 0 to 6, morning period from 6 to 12, noon period from 12 to 14, afternoon period from 14 to 18, and night period from 18 to 24) are calculated, and the deviation rule is analyzed: the color parameter interval of the sunny feature is offset to the high value of the brightness in the summer noon (such as the brightness median value is 3%-5% higher than the standard), the cloudy feature is offset to the low value of the saturation in the winter morning (such as the saturation median value is 2%-4% lower than the standard), and the precipitation feature is offset to the low value of the brightness and the high value of the saturation in the summer (such as the brightness median value is 4%-6% lower and the saturation median value is 3%-5% higher). And based on this, the compensation coefficient is generated (such as the sunny brightness compensation coefficient of summer noon is-4%, and the cloudy saturation compensation coefficient of winter morning is+3%).

[0113] Subsequently, the first weather characteristic data is dynamically corrected using the compensation coefficient, including two steps: the first operation is to match the target compensation coefficient (such as brightness-4%) from the generated coefficient according to the weather type (such as sunny day), season (summer) and time period (noon) corresponding to the first weather characteristic data; the second operation is to apply the target compensation coefficient to the color parameter interval of the corresponding weather type, adjust the interval median value (such as the original sunny day brightness median value 88%, adjusted to 84%), so that the deviation of the adjusted median value from the standard median value falls within the preset allowed range (±2%, set according to the historical data processing error control requirement), while judging the adaptability of the adjusted color parameter interval to the first weather characteristic data in real time (adaptability is calculated by data matching degree, preset adaptability threshold 90%, set according to data accuracy standard), if the adaptability does not reach 90%, update the compensation coefficient based on the latest supplemented historical corresponding data of the same period and the same region (such as new summer noon sunny day data in June 2023), repeat the above two steps of operation, until the adaptability meets the standard, and finally obtain the second weather characteristic data. The second weather characteristic data includes the color parameter interval (deviation less than or equal to ±2%) corresponding to each type of weather after correction, and the corresponding weather type, season, time period identifier. This process effectively eliminates the weather characteristic deviation caused by seasonal and time period differences by mining the precise deviation rules from historical data and combining a dynamic iterative correction mechanism, significantly improving the accuracy and reliability of the second weather characteristic data, and providing high-precision weather characteristic support for subsequent geographic data fusion.

[0114] The second weather characteristic parameter is fused and calculated to obtain target geographic data, specifically including:

[0115] Taking the public control points converted by the geodetic coordinate system as the reference, the geographic range corresponding to the second weather characteristic parameter is aligned with the geographic range of the GIS vector data and the remote sensing image data converted by the coordinate, so that the second weather characteristic parameter under the same geographic coordinate point is matched with the spatial position of the multi-source geographic data;

[0116] According to the season and time period in the second weather characteristic parameter, the second weather characteristic parameter is grouped by season and time period, and the weather type characteristics under the same geographic coordinate are matched with the second terrain feature information in the GIS vector data in each group to form a geographic coordinate, season, time period, weather type and terrain feature information association data pair;

[0117] Based on the first value, the association data pairs meeting the conditions are screened;

[0118] The conditions include:

[0119] The geographic coordinates corresponding to the association data pair are within the overlapping geographic range of the remote sensing image data and the GIS vector data converted by the coordinate;

[0120] The weather type feature in the associated data pair is consistent with the color information and the weather type feature association, and the consistent association is that the color parameter interval corresponding to the weather type feature is in the first effective value range.

[0121] The second terrain feature information of the GIS vector data in the associated data pair has no conflict with the original second terrain feature information of the GIS vector data, and no conflict means that the error between the second terrain feature information and the original second terrain feature information at the same geographic coordinate is less than the first value.

[0122] The filtered associated data pairs are sorted in geographic coordinate order to form a structured data set including geodetic coordinate system geographic coordinate values, weather type features, seasons, time periods, and terrain feature parameters. The data set is checked for completeness and entries missing any data element are removed to obtain target geographic data.

[0123] The data elements include geodetic coordinate system geographic coordinate values, weather type features, seasons, time periods, and terrain feature parameters.

[0124] The completeness check criterion is that each entry in the structured data set includes complete geodetic coordinate system geographic coordinate values, weather type features, seasons, time periods, and terrain feature parameters.

[0125] The geographic coordinate accuracy of the target geographic data is consistent with the coordinate conversion accuracy, the weather type feature accuracy is consistent with the second weather feature parameter accuracy, and the overall data error is less than the first value.

[0126] In one embodiment, the second weather feature parameters (including the dynamically corrected color parameter intervals corresponding to sunny, cloudy, overcast, and precipitation, as well as weather type, season, and time period identifiers) are fused to generate target geographic data. The specific process is as follows: First, using the public control points (such as the four road intersections and boundary corner points previously selected in a county) converted by the geodetic coordinate system (such as the 2000 National Geodetic Coordinate System) as the reference, the geographic range corresponding to the second weather feature parameters (such as the weather feature coverage area of the county in June 2024 summer noon period), is spatially aligned with the geographic range of the GIS vector data (including the second terrain feature information, such as contour parameters) and remote sensing image data converted by the same coordinate system, to ensure that the same geographic coordinate point (such as the location of 118.5°E, 32.3°N in the county) is accurately matched with the spatial position of the multi-source geographic data, avoiding spatial misplacement.

[0127] Then according to the season (such as spring 3-5 months, summer 6-8 months) and time period (such as 0-6 am, 12-14 pm) in the second weather feature parameter, it is grouped according to the season + time period combination (such as summer + noon group, winter + morning group), and in each group, the weather type feature (such as the sunny day feature of a certain coordinate point) under the same geographic coordinates is corresponded with the second terrain feature information (such as the 250-meter elevation of the coordinate point, the contour density) in the GIS vector data one by one, forming the associated data pair of geographic coordinates-season-time period-weather type-terrain feature (such as 118.5°E, 32.3°N-summer-noon-sunny day-elevation 250 meters).

[0128] Subsequently, based on the first value (the maximum value of the straight line distance between the converted public control point and the actual coordinate point, which is set to 5 meters according to historical processing experience in the same region), the associated data pairs that meet the following three conditions are screened: first, the geographic coordinates corresponding to the associated data pair are within the overlapping geographic range of the converted remote sensing image and the GIS vector data (i.e. the coordinates are covered by both types of data), second, the color parameter interval corresponding to the weather type feature in the associated data pair is within the first effective value range (previously set as RGB R180-255, G180-255, B200-255), ensuring that the weather type and color information are consistent, and third, under the same geographic coordinates, the error between the second terrain feature information (such as elevation 250 meters) in the associated data pair and the original second terrain feature information (such as the actual measured elevation 252 meters) is less than 5 meters, ensuring that the terrain data is conflict-free.

[0129] Finally, the screened associated data pairs are sorted according to the longitude and latitude of the geographic coordinates, forming a structured data set including geographic coordinate values in the geodetic coordinate system, weather type features, seasons, time periods, and terrain feature parameters. The data set is checked for integrity, with the criterion being that each entry includes all five types of data elements, and entries missing any element (such as missing time period identification) are excluded. The final target geographic data is obtained. The geographic coordinate accuracy of the target geographic data is consistent with the previous coordinate conversion accuracy (error less than or equal to 5 meters), the weather type feature accuracy is consistent with the second weather feature parameter accuracy (the color parameter mean value deviates from the standard mean value by less than or equal to ±2%), and the overall data error is less than 5 meters.

[0130] This fusion calculation process ensures data location accuracy through spatial alignment, eliminates invalid and conflicting data through multi-condition screening, and ensures data specification through integrity checking. The final target geographic data can accurately associate geographic coordinates, weather, terrain, and spatio-temporal information, and can directly meet the scene needs of agricultural production planning (such as crop irrigation planning in summer noon sunny area) and regional environmental monitoring (such as humidity monitoring in winter cloudy low elevation area), effectively improving the practical value and application accuracy of geographic information data.

[0131] Embodiment 2, refer to Figure 2 For another embodiment of the application, which is different from the first embodiment, a geographic information data processing system based on multi-source data fusion is provided, comprising a processing module and a fusion module;

[0132] The processing module analyzes and processes the multi-source geographic data after preliminary processing to obtain a first weather feature, and dynamically corrects the first weather feature to obtain a second weather feature.

[0133] The fusion module performs fusion calculation on the second weather feature to obtain target geographic data.

[0134] In one embodiment, the processing module and the fusion module cooperatively realize the processing and fusion of multi-source geographic data to output target geographic data meeting the requirements, wherein the core role of the processing module is to analyze and process the multi-source geographic data after preliminary processing to obtain a first weather feature from the above data, and further dynamically correct the first weather feature to obtain a second weather feature with higher precision, and the fusion module receives the second weather feature output by the processing module and performs fusion calculation thereon to integrate the second weather feature with geographic related information in the multi-source geographic data, and finally generate target geographic data. Through the extraction and optimization of weather features by the processing module, the accuracy of weather feature data can be effectively improved, and the deviation of the preliminary features is avoided to affect the subsequent application, and the fusion calculation of the fusion module realizes the effective association of weather features and geographic information, and the generated target geographic data can meet the demand of regional environmental monitoring and agricultural production planning for geographic and weather related data, and guarantee the practical value and reliability of the system in actual application.

[0135] The present application solves the spatial misalignment problem caused by traditional fixed control points by matching the coordinates of remote sensing image data and GIS vector data with the geodetic coordinate system and iteratively optimizing public control points, builds a solid foundation for data spatial consistency, extracts weather data by distinguishing the effective range of color values, dynamically corrects weather features according to seasonal periods combined with historical data of the same period, avoids feature deviation caused by environmental interference, improves weather type recognition accuracy, and finally performs spatial alignment, related data screening and integrity check to ensure that the target geographic data elements are complete and the overall error is controllable, which can efficiently meet the demand of smart city, disaster warning and land planning for high-precision geographic information.

[0136] Those skilled in the art will appreciate that embodiments of the present application can be readily used as a method, a system or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (or computer- readable storage media) having computer-usable program code embodied in the medium. The medium can be any available medium or combination thereof that is accessible by a general purpose or special purpose computer. By way of example, such computer-usable storage media can include a volatile memory, a non-volatile memory, a hard disk drive, a solid state drive, a magnetic diskette, an optical disk (e.g., a compact disk (CD) or a digital versatile disk (DVD)), or a floppy disk, all of which are tangible of computer- readable media. The computer-usable program code, when executed, can enable a general purpose computer, special purpose computer, or other programmable data processing apparatus to perform a method, process, or procedure as described in the above embodiments. The computer-usable program code can also be loaded onto a computer and / or other programmable instruction execution devices to cause a series of operations to be performed on the computer and / or other Figure 1 one or more flows and / or blocks Figure 1 one or more flows and / or blocks

[0137] It should be noted that the above-mentioned embodiments are only used to illustrate but not to limit the technical solutions of the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application, and they should be covered in the scope of the claims of the present application.

Claims

1. A geographic information data processing method based on multi-source data fusion, characterized in that, Includes the following steps: Step S100: Analyze and process the pre-processed multi-source geographic data to obtain the first weather feature, and dynamically correct the first weather feature to obtain the second weather feature; Step S200: Perform fusion calculation on the second weather feature to obtain target geographic data; Automatic compensation of the first weather feature data based on historical data includes: Obtain color information from historical remote sensing image data of the same period and region, and the corresponding data between the corresponding data and the actual weather type characteristics of the same period and region. By analyzing the deviation pattern between the color parameter range in the corresponding data and the actual weather type characteristics, a compensation coefficient is generated. The color information in the remote sensing image data of the same historical period and the same region is classified according to the weather type characteristics, corresponding to the actual weather type characteristics of the same period and the same region. Calculate the color parameter range extracted under each weather type feature, and based on the deviation between the median of the color parameter range and the median of the standard color parameter corresponding to the actual weather type feature, statistically analyze the distribution frequency and fluctuation amplitude of the deviation value under different seasons and time periods. The seasons include spring, summer, autumn and winter, and the time periods include early morning, morning, noon, afternoon and night. The deviation pattern is that the color parameter range corresponding to the sunny day feature shifts towards higher values ​​of the brightness parameter during the midday period in summer; the color parameter range corresponding to the cloudy day feature shifts towards lower values ​​of the saturation parameter during the morning period in winter; and the color parameter range corresponding to the precipitation feature shifts towards lower values ​​of the brightness parameter and higher values ​​of the saturation parameter during summer. The first weather feature data is dynamically corrected using the compensation coefficient to obtain the second weather feature data; The dynamic correction includes a first operation and a second operation; The first operation is to match a suitable target compensation coefficient from the generated compensation coefficients based on the weather type characteristics, season, and time period corresponding to the first weather feature data. The second operation is to apply the target compensation coefficient to the color parameter range corresponding to the weather type feature in the first weather feature data, adjust the median of the color parameter range, and make the deviation between the adjusted median and the median of the standard color parameter corresponding to the actual weather type feature fall within a preset allowable range. The compatibility between the adjusted color parameter range and the first weather feature data is judged in real time. If the compatibility does not reach the preset compatibility threshold, the compensation coefficient is updated based on the color information in the latest historical remote sensing image data of the same period and the same region and the corresponding data between the actual weather type features of the same period and the same region. The first and second operations are repeated until the compatibility reaches the preset compatibility threshold to obtain the second weather feature data. The second weather feature parameter includes color parameter intervals corresponding to sunny, cloudy, partly cloudy, and precipitation features after dynamic correction. The deviation between the median of the color parameter interval and the median of the standard color parameter corresponding to the actual weather type feature is within a preset allowable range. It also includes the weather type feature, season, and time period identifier corresponding to the color parameter interval.

2. The geographic information data processing method based on multi-source data fusion as described in claim 1, characterized in that: Preliminary processing of multi-source geographic data is performed, specifically including: The multi-source geographic data includes remote sensing image data of the object to be analyzed and GIS vector data of the object to be analyzed. Perform coordinate transformation on the remote sensing image data and GIS vector data; The coordinate transformation logic includes: Select common control points of the remote sensing image data and common control points of the GIS vector data. The common control points of the remote sensing image data are n non-collinear points within the geographic range of the remote sensing image data, and the common control points of the GIS vector data are p corner points on the boundary of the geographic range of the GIS vector data. Furthermore, both n and p are positive integers greater than or equal to 3; Using a geodetic coordinate system, remote sensing image data and GIS vector data from multi-source geographic data are uniformly converted to the geodetic coordinate system. Based on the common control points, a coordinate mapping relationship is established through an affine transformation algorithm to achieve coordinate transformation. The remote sensing image data after coordinate transformation includes the first topographic feature information of the area to be analyzed; The GIS vector data after coordinate transformation includes the second terrain feature information of the area to be analyzed; The mapping relationship includes a first mapping relationship and a second mapping relationship; The first mapping relationship is the mapping relationship between the original coordinate system of the remote sensing image data and the geodetic coordinate system of the remote sensing image data; The second mapping relationship is the mapping relationship between the original coordinate system of GIS vector data and the geodetic coordinate system of GIS vector data.

3. The geographic information data processing method based on multi-source data fusion as described in claim 2, characterized in that: For the number of common control points n and p, iterative optimization is performed by increasing the number of common control points; The conditions for iterative optimization include: When the error between any common control point after coordinate transformation and its corresponding actual coordinate point is greater than or equal to the first value, n and p are increased by 1 respectively based on the current values, and the newly added common control point is introduced into the coordinate mapping relationship. The coefficients in the coordinate mapping relationship are adaptively modified so that the input and output values ​​conform to the mathematical relationship of affine transformation. When the error between any common control point after coordinate transformation and its corresponding actual coordinate point is less than the first value, the iteration of the values ​​of n and p is stopped. The first value represents the maximum straight-line distance between the converted common control point and the actual coordinate point.

4. The geographic information data processing method based on multi-source data fusion as described in claim 3, characterized in that: Adding timestamps to the pre-processed multi-source geographic data and performing analysis includes: The pre-processed multi-source geographic data consists of remote sensing image data and GIS vector data after coordinate transformation. After adding timestamps to the pre-processed multi-source geographic data, remote sensing image data is selected from the multi-source geographic data as the source for weather type feature extraction. The weather type characteristics include sunny weather characteristics, cloudy weather characteristics, partly cloudy weather characteristics, and precipitation characteristics; The effective weather data is extracted based on the color values ​​of pixels in the remote sensing image data. The extraction logic includes: When the color value is within the first valid value range, the corresponding color information is determined to be valid data and extracted. The color information is the parameter information corresponding to the color value, and the parameter information includes hue, saturation and brightness. When the color value exceeds the second valid value range, the corresponding color information is determined to be invalid data and is not extracted. The color information refers to the parameter information corresponding to abnormal color values, non-sky area color values, and distorted color values ​​caused by blurring or occlusion of remote sensing image data. The second valid value range refers to the range of color values ​​from which valid parameter information cannot be extracted.

5. The geographic information data processing method based on multi-source data fusion as described in claim 4, characterized in that: Establish the correlation between the extracted color information and weather type characteristics; The color parameter range of the association relationship is obtained by dividing the hue value range, saturation value range, and brightness value range within the first valid value range, specifically including: The first color parameter range corresponds to sunny weather characteristics, the second color parameter range corresponds to cloudy weather characteristics, the third color parameter range corresponds to partly cloudy weather characteristics, and the fourth color parameter range corresponds to precipitation characteristics. Based on the aforementioned correlation, the extracted valid color information is matched to the corresponding color parameter range and transformed into the corresponding first weather feature data.

6. The geographic information data processing method based on multi-source data fusion as described in claim 5, characterized in that: The second weather characteristic parameter is fused and calculated to obtain the target geographic data, specifically including: Using the public control point after geodetic coordinate system transformation as the benchmark, the geographical range corresponding to the second weather feature parameter is aligned with the geographical range of the GIS vector data and remote sensing image data after coordinate transformation, so that the second weather feature parameter under the same geographical coordinate point matches the spatial location of the multi-source geographical data. Based on the season and time period in the second weather feature parameters, the second weather feature parameters are combined and grouped according to the season and time period. Within each group, the weather type features under the same geographic coordinates are matched with the second terrain feature information in the GIS vector data, forming a data pair of geographic coordinates, season, time period, weather type and terrain feature information. Based on the first value, filter the related data pairs that meet the conditions; The conditions include: The associated data pairs correspond to geographic coordinates that are within the overlapping geographic range of the coordinate-transformed remote sensing image data and GIS vector data. The weather type feature in the associated data pair is consistent with the color information and the weather type feature, and the consistent association means that the color parameter range corresponding to the weather type feature is within the first valid value range. The second terrain feature information of the GIS vector data in the associated data pair does not conflict with the original second terrain feature information of the GIS vector data. The lack of conflict means that the second terrain feature information is under the same geographic coordinates, and the error between the second terrain feature information and the original second terrain feature information is less than the first value.

7. The geographic information data processing method based on multi-source data fusion as described in claim 6, characterized in that: The filtered associated data pairs are organized in geographic coordinate order to form a structured dataset that includes geographic coordinate values ​​in the geodetic coordinate system, weather type characteristics, season, time period, and terrain feature parameters. The dataset is then checked for completeness and entries with any missing data element are removed to obtain the target geographic data. The data elements include geographic coordinates in the geodetic coordinate system, weather type characteristics, season, time period, and terrain feature parameters; The criteria for the integrity check are that each entry in the structured dataset includes complete geodetic coordinate system geographic coordinates, weather type characteristics, season, time period, and terrain feature parameters. The geographic coordinate accuracy of the target geographic data is consistent with the accuracy of the coordinate transformation, the weather type feature accuracy is consistent with the accuracy of the second weather feature parameter, and the overall data error is less than the first value.

8. A geographic information data processing system based on multi-source data fusion, applied to the geographic information data processing method based on multi-source data fusion as described in any one of claims 1-7, characterized in that, Includes a processing module and a fusion module; The processing module analyzes and processes the pre-processed multi-source geographic data to obtain a first weather feature, and then dynamically corrects the first weather feature to obtain a second weather feature. The fusion module performs fusion calculations on the second weather feature to obtain the target geographic data.

Images