Multi-factor ecological environment access intelligent analysis system based on AI big model

Abstract

The present invention relates to the field of environmental detection technology, and in particular to a multi-factor ecological environment access intelligent analysis system based on an AI large model. The system comprises: a remote sensing unit, which is used to collect atmospheric environmental data, land images and water images of each plot area; a data collection unit, which is used to plan the collection route of the remote sensing unit; a data integration unit, which is used to obtain land vacancy values ​​and water parameters and generate atmospheric evaluation values; a model training unit, which is used to evaluate environmental projects and generate environmental project access values; an analysis and evaluation unit, which is used to generate water source sensitive areas according to water quality evaluation values, and correct the environmental project access values ​​based on the water source sensitive areas to obtain access correction values, so as to determine the plot areas where environmental projects can be established; the present invention utilizes the above-mentioned units to cooperate with each other, thereby further improving the accuracy of the multi-factor ecological environment access intelligent analysis system based on the AI ​​large model.

Description

Technical Field

[0001] The present invention relates to the field of environmental detection technology, and in particular to a multi-factor ecological environment access intelligent analysis system based on an AI large model. Background Art

[0002] Water resources are unevenly distributed geographically, which requires some regions to focus on the carrying capacity of water resources when making ecological and environmental access decisions, so as to avoid development restrictions or ecological damage due to water shortages. Protecting the integrity and stability of water ecosystems is one of the important goals of ecological and environmental access. In the current ecological and environmental protection and economic development work, the ecological and environmental and economic development departments undertake a large number of industry project approval and decision-making tasks and the responsibility of optimizing the business environment. The traditional approval and decision-making methods and the optimization of environmental services mainly rely on the experience of human experts to make judgments, which have many limitations and low efficiency. On the one hand, the knowledge and experience of experts are limited, and it is difficult to To comprehensively consider the multi-faceted impact of the project; on the other hand, there may be subjective differences between different experts, resulting in a lack of consistency in the approval decision-making results; thirdly, the timeliness of the manual judgment results also determines the degree of optimization of the business environment. Therefore, there is an urgent need for an intelligent ecological environment access analysis system that can comprehensively consider multiple factors and automatically, efficiently and accurately evaluate the impact of industry projects on the ecological environment, and provide scientific basis and efficient support for the approval decision-making and investment promotion work of the ecological environment and economic development departments. The AI ​​large model can integrate multi-source data such as water resources, land resources, climate, and ecosystems to explore the complex relationships and potential laws between various factors.

[0003] Chinese patent application publication number: CN118840680A discloses a method for identifying water surface algae based on drone images. The invention provides a method for identifying water surface algae based on drone images, including the following steps: step S101, collecting water surface images through drones and constructing a water area image dataset; step S102, training a water surface area semantic segmentation model based on the water area image dataset; step S103, constructing a water surface algae dataset; step S104, training a water surface algae recognition model based on the water surface algae dataset; step S105, inputting the water surface image with the background removed into the trained water surface algae recognition model, and outputting the water surface algae detection result; the invention adds feature receptive fields in both channel and spatial directions to the water surface area semantic segmentation model, thereby improving the recognition accuracy of the water area and reducing background interference, and adds a convolutional layer at the output end of the water surface algae recognition model to increase the range of the receptive field, thereby improving the accuracy of algae recognition.

[0004] Chinese patent application publication number: CN117557166A discloses a multimodal and real-time data user data environment intelligent monitoring system. The invention provides a multimodal and real-time data user data environment intelligent monitoring system, which specifically relates to the field of environmental detection technology, including a water surface image analysis module, a water surface ecological risk assessment module, a water quality appearance analysis module, a water quality appearance quality assessment module, an ecological risk analysis module, an ecological risk assessment module, and a control module. Multimodal information about water quality is acquired through real-time collection. Based on the acquired water quality color difference, floating matter content, heavy metal excess coefficient, and ecological parameter offset coefficient, control instructions are generated to control water quality. Based on the water surface plant risk status, water quality appearance quality, and ecological risk status before and after control, a control quality assessment coefficient is obtained. When the water quality control quality assessment coefficient is lower than a preset value, an early warning is issued to the management personnel, indicating control abnormalities and water quality abnormalities, which solves the problem of insufficient timeliness of water quality monitoring and lack of long-term monitoring of water quality status in the prior art.

[0005] However, the above method has the following problems: it fails to comprehensively evaluate the water source situation by combining multiple environmental factors, and fails to comprehensively evaluate the environmental conditions by combining multiple environmental factors and water source conditions. Summary of the Invention

[0006] To this end, the present invention provides a multi-factor ecological environment access intelligent analysis system based on an AI large model to overcome the problems in the existing technology that the water source situation cannot be comprehensively evaluated by combining multiple environmental factors, and the environmental conditions cannot be comprehensively evaluated by combining multiple environmental factors and water source conditions.

[0007] To achieve the above objectives, the present invention provides a multi-factor ecological environment access intelligent analysis system based on an AI large model, comprising:

[0008] Remote sensing units, which are used to collect atmospheric environmental data, land images, and water images of various plot areas;

[0009] a data collection unit connected to the remote sensing unit and configured to plan a data collection route for the remote sensing unit based on environmental demand data of the environmental project and historical environmental data of each of the land areas, wherein the environmental demand data includes water source demand value, land area demand value, and estimated atmospheric pollution value;

[0010] a data integration unit connected to the remote sensing unit, configured to process the land image and the water area image to obtain a land vacancy value and a water area parameter, analyze the atmospheric environment data to generate an atmospheric evaluation value, and adjust the acquisition state of the remote sensing unit according to the water area image, wherein the water area parameters include a water body type, a water quality evaluation value, and a water area;

[0011] a model training unit, connected to the remote sensing unit and the data integration unit, respectively, for constructing an ecological environment model based on the water area parameter, the land vacancy value, and the atmospheric evaluation value, and evaluating the environmental project in combination with the ecological environment model and the environmental demand data to generate an environmental project admission value;

[0012] An analysis and evaluation unit is connected to the model training unit and is used to generate a water source sensitive area according to the water quality evaluation value, and to correct the environmental project access value based on the water source sensitive area to obtain an access correction value to determine the land area where the environmental project can be established.

[0013] Furthermore, the data integration unit includes:

[0014] The water body type subunit is connected to the remote sensing unit and is used to identify the plant species in the water area image, collect plant distribution characteristics and growth conditions to generate plant density parameters to determine the water body type, and the water body type includes artificial water areas and natural water areas.

[0015] Furthermore, the data integration unit further includes:

[0016] A water quality evaluation subunit is connected to the remote sensing unit and is used to determine the water pollution situation based on identifying the water surface color and water surface transparency in the water area image, and to adjust the remote sensing unit to enter the detection and acquisition state to capture the polluted water area image when the water quality pollution situation is determined, and to generate the water quality evaluation value in combination with the water surface ripples and water surface reflection in the polluted water area image.

[0017] Furthermore, the data integration unit further includes:

[0018] The water area subunit is connected to the remote sensing unit and is used to analyze the water image through an edge detection algorithm to obtain a water contour line, and to adjust the remote sensing unit to enter the detection and acquisition state directly above the water contour line to continuously shoot a plurality of water contour images, and determine the water area by combining the plurality of water contour images.

[0019] Furthermore, the data integration unit further includes:

[0020] a land processing subunit connected to the remote sensing unit, configured to calculate the land vacancy value based on identifying the artificial building area and the area of ​​the land block in the land image;

[0021] An atmospheric processing subunit is connected to the remote sensing unit and is used to combine the atmospheric environment data and the atmospheric estimated pollution value to generate the atmospheric evaluation value.

[0022] Furthermore, the model training unit constructs the ecological environment model according to the water body type, the water area, the land vacancy value and the atmospheric evaluation value.

[0023] Furthermore, the model training unit compares the ecological environment model with the same environmental parameter items in the environmental demand data to obtain a number of ecological environment difference rates, and summarizes the several ecological environment difference rates to generate the environmental project access value.

[0024] Furthermore, the analysis and evaluation unit generates the water source sensitive area according to the water quality evaluation value, wherein:

[0025] If the water quality evaluation value is less than or equal to the preset evaluation value, the land area corresponding to the water quality evaluation value is determined to be the water source sensitive area;

[0026] The preset evaluation value is negatively correlated with the water area.

[0027] Furthermore, the analysis and evaluation unit corrects the environmental project access value based on the water source sensitive area to obtain an access correction value to determine the land area where the environmental project can be established, wherein:

[0028] If the access correction value is greater than or equal to the preset access value, it is determined that the land area corresponding to the access correction value can be used to establish the environmental project;

[0029] The preset admission value is negatively correlated with the area of ​​the plot.

[0030] Furthermore, the data collection unit compares the environmental demand data of the environmental project with the historical environmental data of each of the land areas to obtain a number of environmental demand difference rates, sorts the environmental demand difference rates from small to large, and generates a collection route for the remote sensing unit.

[0031] Compared with the prior art, the beneficial effect of the present invention is that the present invention generates plant density parameters by identifying plant species in water area images, collecting plant distribution characteristics and growth conditions, and determining the type of water body. Different water body types (such as rivers, lakes, wetlands, etc.) often have unique plant community structures. Lakes are dominated by submerged plants and floating-leaf plants, while wetlands are dominated by emergent plants. By accurately identifying plant species and analyzing their distribution and density, the ecological characteristics of water bodies can be understood in more detail, thereby improving the accuracy of water body type determination and avoiding the limitations of single indicators (such as water body area, depth, etc.). The growth conditions and distribution characteristics of plants are a comprehensive reflection of the ecological environment of water bodies. Healthy water bodies can usually support diverse and well-growing plant communities. If the water body is polluted or ecologically unhealthy, the water body will be polluted. If there is damage, the species, quantity and growth conditions of plants in water bodies will change. Understanding the distribution and growth of plants in water bodies will help to formulate targeted ecological protection and restoration measures. This method based on image recognition and data analysis requires the use of advanced computer vision, machine learning and other technologies, which has promoted the application and development of related technologies in the field of ecological monitoring. Through long-term monitoring of changes in plant density parameters and growth conditions, the evolution trend of water ecosystems can be predicted. With the influence of climate change or human activities, the species and distribution of plants in water bodies may change. Grasping these changing trends in advance will help to take corresponding response measures, reduce adverse effects, and protect the stability of water ecosystems, effectively improving the accuracy of the multi-factor ecological environment access intelligent analysis system based on the AI ​​large model.

[0032] Furthermore, the present invention determines the water pollution situation by identifying the water surface color and water surface transparency in the water area image, and at the same time adjusts the flight altitude of the remote sensing unit to hover over the water surface, and evaluates the water pollution situation by collecting the water surface ripple image generated by the remote sensing unit blowing the water surface and the water surface reflection situation. The water surface color and transparency are intuitive manifestations of water pollution. Different pollutants will cause the water surface color to change and the transparency to decrease, while the ripple image generated by the remote sensing unit blowing the water surface and the water surface reflection situation provide additional information from a dynamic and optical perspective. The remote sensing unit can be flexibly deployed quickly in different water areas and different locations, and collect image data in real time. By analyzing these data in real time, changes in water quality can be discovered in a timely manner, especially for sudden pollution incidents. Monitoring is of great significance. Using remote sensing units to collect images for water quality assessment does not require direct contact with the water body, avoiding direct contact between inspectors and polluted water bodies and ensuring the safety of inspectors. The image data is intuitive and visual. Through image processing and analysis technology, information such as water surface color, transparency, ripple shape and reflection can be quantified, which is convenient for analysis and comparison. Compared with traditional water quality detection methods, the use of remote sensing units for water quality monitoring reduces costs to a certain extent, reduces the manpower, material and time costs of manual sampling, and also reduces the sample processing and testing costs of laboratory analysis. Moreover, the remote sensing units can be reused, which reduces costs and further improves the accuracy of the multi-factor ecological environment access intelligent analysis system based on the AI ​​large model.

[0033] Furthermore, the present invention determines the area of ​​the water area by adjusting the flight altitude of the remote sensing unit to hover over the water surface, and collecting images of the collision between the water surface ripples generated by the remote sensing unit blowing the water surface and the water area contour line. Traditional water area measurement methods, such as measurements based on satellite remote sensing images, may be affected by factors such as image resolution and cloud cover, resulting in limited measurement accuracy. However, using the remote sensing unit to collect images of the collision between water surface ripples and water area contour lines at close range can obtain higher resolution information, clearly identify the water area boundary, and thus more accurately calculate the water area and reduce measurement errors. For some water areas with complex terrain and irregular shapes, such as the curved sections of rivers and the coastlines of lakes, traditional measurement methods may find it difficult to accurately define the boundaries, and the remote sensing unit can flexibly Actively adjusting the flight altitude and position and shooting close to the water surface can better capture the true contours of these complex waters, thereby accurately measuring their area. Even at the edge of the water covered by vegetation or blocked by obstacles, clear images can be obtained by adjusting the shooting angle, thereby improving the adaptability of the measurement. The collected images intuitively show the ripples on the water surface and the contour lines of the water area. Through image processing technology, such as edge detection, contour extraction and other algorithms, the boundaries of the water area can be easily identified, and then the area can be calculated. Compared with some traditional measurement methods, this image-based measurement method has simpler and faster data processing, which can improve work efficiency and further improve the accuracy of the multi-factor ecological environment access intelligent analysis system based on the AI ​​large model.

[0034] Furthermore, the present invention evaluates the ecological environment of each plot area by combining the water parameters, land parameters and atmospheric parameters in the ecological environment, and determines the appropriate plot area in combination with the environmental requirements of the project. By comprehensively considering the water parameters, land parameters and atmospheric parameters, it is possible to fully and deeply understand the ecological environment conditions of each plot area, avoid the one-sidedness of single parameter evaluation, make the evaluation results more scientific and accurate, and provide a reliable basis for subsequent decision-making. When evaluating a plot, not only the fertility of the land is considered, but also the pollution of the surrounding water bodies and the self-purification capacity of the atmosphere, which can more objectively judge the ecological environment quality of the plot. Different projects have different environmental requirements. By combining the environmental requirements of the project with the ecological environment parameters of each plot area, a reasonable match between the project and the environment can be achieved. For production projects with high water quality requirements, plots with excellent surrounding water quality and no pollution can be accurately screened out; for manufacturing projects that are sensitive to the atmospheric environment, plots with good air quality and high concentration of atmospheric pollutants can be selected. This evaluation and selection method helps protect ecologically sensitive areas. By identifying plots of land with important ecological value, inappropriate project development in these areas can be avoided, thereby protecting biodiversity and the integrity of the ecosystem. At the same time, reasonable project site selection can reduce damage to the ecological environment, promote the rational use of resources, achieve a virtuous interaction between economic development and ecological environmental protection, and promote sustainable development. The evaluation and selection of plot areas based on ecological and environmental parameters and project environmental requirements can help optimize regional planning. According to the ecological and environmental characteristics and project requirements of different plots, the layout of various projects can be reasonably arranged to achieve optimal allocation of resources. Industrial projects can be concentrated in areas with large environmental capacity and complete infrastructure, and ecological agricultural projects can be arranged in plots with fertile soil and sufficient water resources. The overall development efficiency and quality of the region are improved, and the accuracy of the multi-factor ecological and environmental access intelligent analysis system based on the AI ​​large model is further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a structural diagram of the multi-factor ecological environment access intelligent analysis system based on the AI ​​large model of the present invention;

[0036] Figure 2 This is a structural block diagram of a data integration unit according to an embodiment of the present invention;

[0037] Figure 3 A determination diagram for determining water source sensitive areas according to an embodiment of the present invention;

[0038] Figure 4 This is a determination diagram for determining a land area where an environmental project can be established according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0040] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0041] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0042] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0043] See also Figure 1 As shown in FIG, which is a structural block diagram of the multi-factor ecological environment access intelligent analysis system based on the AI ​​big model of the present invention, an embodiment of the present invention provides a multi-factor ecological environment access intelligent analysis system based on the AI ​​big model, including:

[0044] Remote sensing units, which are used to collect atmospheric environmental data, land images, and water images of various plot areas;

[0045] A data collection unit connected to the remote sensing unit is used to plan the remote sensing unit's collection route based on the environmental demand data of the environmental project and the historical environmental data of each block area. The environmental demand data includes water source demand value, land area demand value and atmospheric pollution estimated value;

[0046] a data integration unit connected to the remote sensing unit, for processing land images and water area images to obtain land vacancy values ​​and water area parameters, analyzing atmospheric environmental data to generate atmospheric evaluation values, and adjusting the acquisition state of the remote sensing unit according to the water area images; the water area parameters include water body type, water quality evaluation value, and water area;

[0047] The model training unit is connected to the remote sensing unit and the data integration unit respectively, and is used to construct an ecological environment model based on water parameters, land vacancy values ​​and atmospheric evaluation values, and to evaluate environmental projects in combination with the ecological environment model and environmental demand data to generate environmental project access values;

[0048] The analysis and evaluation unit is connected to the model training unit and is used to generate water source sensitive areas according to the water quality evaluation value, and to correct the environmental project access value based on the water source sensitive area to obtain the access correction value to determine the land area where the environmental project can be established.

[0049] It is understandable that the remote sensing unit is equipped with several drones to collect images and data.

[0050] See also Figure 2 , which is a structural block diagram of a data integration unit according to an embodiment of the present invention, the data integration unit includes:

[0051] The water body type subunit is connected to the remote sensing unit and is used to identify plant species in water area images, collect plant distribution characteristics and growth conditions to generate plant density parameters to determine the water body type, which includes artificial water areas and natural water areas.

[0052] In implementation, the density of the plants is calculated based on the distribution range and individual number of the plants. The density can be measured by the number of individuals per unit area, for example, the number of individual plants per square meter is calculated.

[0053] It is understandable that for different types of plants, their density parameters can be calculated separately, or the comprehensive density parameter of the entire plant community can be calculated. The comprehensive density parameter can be a weighted average of the densities of various plants, and the weight can be determined according to the relative importance of the plants.

[0054] It can be understood that the type of water body can be determined based on plant density parameters or comprehensive density parameters, combined with existing water body type classification standards or experience. For example, eutrophic water bodies in artificial waters have a higher density of aquatic plants, especially some plant species with strong pollution resistance; while the plant density in clean water bodies in natural waters is relatively low, and is dominated by some plants with higher water quality requirements.

[0055] Specifically, the present invention generates plant density parameters to determine the type of water body by identifying plant species in water area images, collecting plant distribution characteristics and growth conditions. Different water body types (such as rivers, lakes, wetlands, etc.) often have unique plant community structures. Lakes are dominated by submerged plants and floating-leaf plants, while wetlands are dominated by emergent plants. By accurately identifying plant species and analyzing their distribution and density, we can understand the ecological characteristics of water bodies in more detail, thereby improving the accuracy of water body type determination and avoiding the limitations of single indicators (such as water body area, depth, etc.). The growth status and distribution characteristics of plants are a comprehensive reflection of the ecological environment of water bodies. Healthy water bodies can usually support diverse and well-growing plant communities. If the water body is polluted or ecologically damaged, the plant species The types, numbers and growth conditions of plants in water bodies will change. Understanding the distribution and growth of plants in water bodies will help to formulate targeted ecological protection and restoration measures. This method based on image recognition and data analysis requires the use of advanced computer vision, machine learning and other technologies, which has promoted the application and development of related technologies in the field of ecological monitoring. By monitoring the changes in plant density parameters and growth conditions over a long period of time, the evolution trend of water ecosystems can be predicted. With the influence of climate change or human activities, the types and distribution of plants in water bodies may change. Grasping these changing trends in advance will help to take corresponding response measures, reduce adverse effects, and protect the stability of water ecosystems, effectively improving the accuracy of the multi-factor ecological environment access intelligent analysis system based on the AI ​​large model.

[0056] Specifically, the data integration unit also includes:

[0057] The water quality evaluation subunit is connected to the remote sensing unit and is used to determine the water pollution situation based on the water surface color and water surface transparency in the water area image. When the water quality pollution is determined to be in a state, the remote sensing unit is adjusted to enter the detection and acquisition state to capture the polluted water area image, and the water quality evaluation value is generated based on the water surface ripples and water surface reflection in the polluted water area image.

[0058] It can be understood that the correspondence between color features and the degree of water pollution is established. By referring to existing research results or conducting field sampling analysis, the type and degree of water pollution corresponding to different color features can be determined. In the HSV (hue, saturation, value) color mode, the darker the color, the smaller the V (value) value; the transparency is judged by calculating the grayscale value distribution of pixels in the image. Water bodies with higher transparency have higher grayscale values, while water bodies with lower transparency have lower grayscale values; the weighted average method is used to assign different weights according to the degree of influence of V (value) value and grayscale value on water pollution, and calculate the comprehensive pollution index, which is grayscale value x0.6 + V (value) value x0.4x100. The comprehensive pollution index is compared with the preset standard value. If the comprehensive pollution index is less than or equal to the preset standard value, the water quality is judged to be polluted; if the comprehensive pollution index is greater than the preset standard value, the water quality is judged to be clean.

[0059] In a specific embodiment, a preset standard value is set to 152 (calculated when the grayscale value is 200 and the V (brightness) value is 80%). If the comprehensive pollution index is 183 and is greater than the preset standard value, the water quality is determined to be polluted; if the comprehensive pollution index is 137 and is less than the preset standard value, the water quality is determined to be clean.

[0060] It can be understood that the preset standard value is positively correlated with the water flow rate. The faster the water flow rate, the higher the self-cleaning ability, the higher its transparency, the lighter the color, the larger its grayscale value and V (brightness) value, and the larger the preset standard value. Therefore, the preset standard value is positively correlated with the water flow rate.

[0061] It can be understood that the water quality evaluation value = 100-(AxWxF+BxUxG), where A and B are coefficients, generally A is taken as 0.1, B is 0.05, W is the weight of the ripple frequency, U is the weight of the reflection intensity, W+U=1, generally W is taken as 0.4, V is 0.6, F is the water surface ripple frequency (per minute), and G is the water surface reflection intensity (brightness component of CIE Lab color space, with a value range of 0-100); the above parameters are taken as numerical values ​​in the formula for calculation.

[0062] In practice, F was measured to be 120 and G to be 80, so the water quality evaluation value = 100-(0.1x0.4x120+0.05x0.6x80) = 92.8.

[0063] The detection and collection state is that the drone hovers above the water surface at a preset distance and shoots directly below. The preset distance is positively correlated with the propeller speed of the drone.

[0064] It is understandable that when the drone hovers above the water surface, the drone propeller can stably blow the water surface to form ripples. When the water source is polluted, the water surface ripple period is less than that of normal water surface ripples; when the water surface ripples touch the edge of the water contour, the ripples will become turbulent, thereby detecting the accurate water contour edge.

[0065] It is understandable that when the propeller area of ​​the drone is constant, the greater the propeller speed, the greater the blowing force generated, and the larger the ripples on the water surface. At this time, the drone's altitude can be adjusted to obtain stable water waves, so the preset distance is positively correlated with the propeller speed of the drone.

[0066] Specifically, the present invention determines the water pollution situation by identifying the water surface color and water surface transparency in the water area image, and at the same time adjusts the flight altitude of the remote sensing unit to hover over the water surface, and evaluates the water pollution situation by collecting the water surface ripple image generated by the remote sensing unit blowing the water surface and the water surface reflection. The water surface color and transparency are intuitive manifestations of water pollution. Different pollutants will cause the water surface color to change and the transparency to decrease, while the ripple image generated by the remote sensing unit blowing the water surface and the water surface reflection provide additional information from a dynamic and optical perspective. The remote sensing unit can be flexibly deployed quickly in different water areas and different locations, and collect image data in real time. By analyzing these data in real time, changes in water quality can be discovered in a timely manner, especially for sudden pollution incidents. Monitoring is of great significance. Using remote sensing units to collect images for water quality assessment does not require direct contact with the water body, avoiding direct contact between inspectors and polluted water bodies and ensuring the safety of inspectors. The image data is intuitive and visual. Through image processing and analysis technology, information such as water surface color, transparency, ripple shape and reflection can be quantified, which is convenient for analysis and comparison. Compared with traditional water quality detection methods, the use of remote sensing units for water quality monitoring reduces costs to a certain extent, reduces the manpower, material and time costs of manual sampling, and also reduces the sample processing and testing costs of laboratory analysis. Moreover, the remote sensing units can be reused, which reduces costs and further improves the accuracy of the multi-factor ecological environment access intelligent analysis system based on the AI ​​large model.

[0067] Specifically, the data integration unit also includes:

[0068] The water area subunit is connected to the remote sensing unit and is used to analyze the water image through the edge detection algorithm to obtain the water contour line, and adjust the remote sensing unit to enter the detection and acquisition state directly above the water contour line to continuously shoot several water contour images, and combine the several water contour images to determine the water area.

[0069] It can be understood that the water contour is determined by continuously capturing a number of water contour images of the remote sensing unit entering a detection and acquisition state just above the water contour line and generating reflected ripples caused by ripples colliding with the water bank.

[0070] Specifically, the present invention determines the area of ​​the water area by adjusting the flight altitude of the remote sensing unit to hover over the water surface, and collecting images of the collision between the water surface ripples generated by the remote sensing unit blowing the water surface and the water area contour line. Traditional water area measurement methods, such as measurements based on satellite remote sensing images, may be affected by factors such as image resolution and cloud cover, resulting in limited measurement accuracy. However, using the remote sensing unit to collect images of the collision between water surface ripples and water area contour lines at close range can obtain higher resolution information, clearly identify the water area boundary, and thus more accurately calculate the water area and reduce measurement errors. For some water areas with complex terrain and irregular shapes, such as the curved sections of rivers and the coastlines of lakes, traditional measurement methods may find it difficult to accurately define the boundaries, and the remote sensing unit can flexibly Actively adjusting the flight altitude and position and shooting close to the water surface can better capture the true contours of these complex waters, thereby accurately measuring their area. Even at the edge of the water covered by vegetation or blocked by obstacles, clear images can be obtained by adjusting the shooting angle, thereby improving the adaptability of the measurement. The collected images intuitively show the ripples on the water surface and the contour lines of the water area. Through image processing technology, such as edge detection, contour extraction and other algorithms, the boundaries of the water area can be easily identified, and then the area can be calculated. Compared with some traditional measurement methods, this image-based measurement method has simpler and faster data processing, which can improve work efficiency and further improve the accuracy of the multi-factor ecological environment access intelligent analysis system based on the AI ​​large model.

[0071] Specifically, the data integration unit also includes:

[0072] a land processing subunit connected to the remote sensing unit for calculating the land vacancy value based on the area of ​​artificial buildings and the area of ​​the land plot in the land image;

[0073] It can be understood that the vacant land value = artificial building area / area of ​​the plot area.

[0074] The atmospheric processing subunit is connected to the remote sensing unit and is used to generate an atmospheric evaluation value by combining atmospheric environmental data and atmospheric pollution estimated values.

[0075] It is understandable that the atmospheric evaluation value = (|Estimated atmospheric pollution value - atmospheric environmental data| / atmospheric environmental data). Where i is the number of items of atmospheric environmental data collected, and n is the total number of items of atmospheric environmental data collected.

[0076] Specifically, the model training unit constructs an ecological environment model based on water body type, water area, land vacancy value and atmospheric evaluation value.

[0077] Specifically, the model training unit compares the same environmental parameter items in the ecological environment model and the environmental demand data to obtain several ecological environment difference rates, and summarizes several ecological environment difference rates to generate environmental project access values.

[0078] It can be understood that the environmental project access value = (|water source demand value - water area| / water area) + (|land area demand value - land vacancy value| / land vacancy value) + (|estimated atmospheric pollution value - atmospheric evaluation value| / atmospheric evaluation value).

[0079] During implementation, the water source demand value is set at 95 square meters, the water area is 100 square meters, the land area demand value is 120 square meters, the land vacancy value is 240 square meters, the atmospheric estimated pollution value is 48, and the atmospheric evaluation value is 56. The environmental project access value is 0.69.

[0080] See also Figure 3 As shown in FIG, it is a determination diagram for determining water source sensitive areas according to an embodiment of the present invention. The analysis and evaluation unit generates water source sensitive areas according to the water quality evaluation value, wherein:

[0081] If the water quality evaluation value is less than or equal to the preset evaluation value, the land area corresponding to the water quality evaluation value is determined to be a water source sensitive area;

[0082] If the water quality evaluation value is greater than the preset evaluation value, the land area corresponding to the water quality evaluation value is determined to be a non-water source sensitive area.

[0083] In a specific embodiment, the preset evaluation value is set to 95. If the water quality evaluation value is 84.4, which is less than the preset evaluation value, then the land area corresponding to the water quality evaluation value is determined to be a water source sensitive area;

[0084] If the water quality evaluation value is 96.3, which is greater than the preset evaluation value, the land area corresponding to the water quality evaluation value is determined to be a non-water source sensitive area.

[0085] The preset evaluation value is negatively correlated with the water area.

[0086] It is understandable that the larger the water area, the greater the probability of pollution, so the preset evaluation value is negatively correlated with the water area.

[0087] See also Figure 4 As shown, it is a determination diagram for determining the land area where an environmental project can be established in an embodiment of the present invention. The analysis and evaluation unit corrects the environmental project access value based on the water source sensitive area to obtain the access correction value to determine the land area where the environmental project can be established, wherein:

[0088] If the access correction value is less than or equal to the preset access value, it is determined that the land area corresponding to the access correction value can be used to establish an environmental project;

[0089] If the access correction value is greater than the preset access value, it is determined that the land area corresponding to the access correction value cannot be used to establish an environmental project;

[0090] It can be understood that the environmental project access value is corrected based on the water source sensitive area. If the land area corresponding to the water quality evaluation value is determined to be a water source sensitive area, the environmental project access value is multiplied by 2 to generate an access correction value; if the land area corresponding to the water quality evaluation value is determined to be a non-water source sensitive area, the environmental project access value remains unchanged.

[0091] In a specific embodiment, the preset access value is set to 0.5. If the access correction value is 0.23, which is smaller than the preset access value, then it is determined that the land area corresponding to the access correction value can be used to establish an environmental project.

[0092] If the access correction value is 0.69, which is greater than the preset access value, then it is determined that the land area corresponding to the access correction value cannot be used to establish an environmental project;

[0093] The preset entry value is negatively correlated with the area of ​​the plot.

[0094] It is understandable that the larger the area of ​​the plot, the more environmental factors there are, so the preset entry value is negatively correlated with the area of ​​the plot.

[0095] Specifically, the data collection unit compares the environmental demand data of the environmental project with the historical environmental data of each block area to obtain several environmental demand difference rates, sorts the environmental demand difference rates from small to large, and generates the collection route of the remote sensing unit.

[0096] Specifically, the present invention evaluates the ecological environment of each plot area by combining the water parameters, land parameters and atmospheric parameters in the ecological environment, and determines the appropriate plot area in combination with the environmental requirements of the project. By comprehensively considering the water parameters, land parameters and atmospheric parameters, it can fully and deeply understand the ecological environment conditions of each plot area, avoid the one-sidedness of single parameter evaluation, make the evaluation results more scientific and accurate, and provide a reliable basis for subsequent decision-making. When evaluating a plot, not only the fertility of the land is considered, but also the pollution of the surrounding water bodies and the self-purification capacity of the atmosphere, which can more objectively judge the ecological environment quality of the plot. Different projects have different environmental requirements. By combining the environmental requirements of the project with the ecological environment parameters of each plot area, a reasonable match between the project and the environment can be achieved. For production projects with high water quality requirements, plots with excellent surrounding water quality and no pollution can be accurately screened out; for manufacturing projects that are sensitive to the atmospheric environment, plots with good air quality and low concentration of atmospheric pollutants can be selected. This evaluation and selection method helps protect ecologically sensitive areas. By identifying plots of land with important ecological value, inappropriate project development in these areas can be avoided, thereby protecting biodiversity and the integrity of the ecosystem. At the same time, reasonable project site selection can reduce damage to the ecological environment, promote the rational use of resources, achieve a virtuous interaction between economic development and ecological environmental protection, and promote sustainable development. The evaluation and selection of plot areas based on ecological and environmental parameters and project environmental requirements can help optimize regional planning. According to the ecological and environmental characteristics and project requirements of different plots, the layout of various projects can be reasonably arranged to achieve optimal allocation of resources. Industrial projects can be concentrated in areas with large environmental capacity and complete infrastructure, and ecological agricultural projects can be arranged in plots with fertile soil and sufficient water resources. The overall development efficiency and quality of the region are improved, and the accuracy of the multi-factor ecological and environmental access intelligent analysis system based on the AI ​​large model is further improved.

[0097] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0098] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A multi-factor ecological environment access intelligent analysis system based on AI big model, characterized by: include: Remote sensing units, which are used to collect atmospheric environmental data, land images, and water images of various plot areas; a data collection unit connected to the remote sensing unit and configured to plan a data collection route for the remote sensing unit based on environmental demand data of the environmental project and historical environmental data of each of the land areas, wherein the environmental demand data includes water source demand value, land area demand value, and estimated atmospheric pollution value; a data integration unit connected to the remote sensing unit, configured to process the land image and the water area image to obtain a land vacancy value and a water area parameter, analyze the atmospheric environment data to generate an atmospheric evaluation value, and adjust the acquisition state of the remote sensing unit according to the water area image, wherein the water area parameters include a water body type, a water quality evaluation value, and a water area; a model training unit, connected to the remote sensing unit and the data integration unit, respectively, for constructing an ecological environment model based on the water area parameter, the land vacancy value, and the atmospheric evaluation value, and evaluating the environmental project in combination with the ecological environment model and the environmental demand data to generate an environmental project admission value; an analysis and evaluation unit connected to the model training unit, configured to generate a water source sensitive area based on the water quality evaluation value, and to modify the environmental project access value based on the water source sensitive area to obtain a modified access value, so as to determine the land area where the environmental project can be established; The data integration unit determines the water pollution situation by identifying the water surface color and water surface transparency in the water area image, and adjusts the flight altitude of the remote sensing unit to hover over the water surface, and evaluates the water pollution situation by collecting images of water surface ripples generated by the remote sensing unit blowing on the water surface and the reflection of the water surface, and adjusts the flight altitude of the remote sensing unit to hover over the water surface, and determines the area of ​​the water area by collecting images of water surface ripples generated by the remote sensing unit blowing on the water surface and the water area contour line.

2. The multi-factor ecological environment access intelligent analysis system based on AI large model according to claim 1 is characterized in that: The data integration unit includes: The water body type subunit is connected to the remote sensing unit and is used to identify the plant species in the water area image, collect plant distribution characteristics and growth conditions to generate plant density parameters to determine the water body type, and the water body type includes artificial water areas and natural water areas.

3. The multi-factor ecological environment access intelligent analysis system based on AI large model according to claim 2 is characterized in that: The data integration unit further includes: A water quality evaluation subunit is connected to the remote sensing unit and is used to determine the water pollution situation based on identifying the water surface color and water surface transparency in the water area image, and to adjust the remote sensing unit to enter the detection and acquisition state to capture the polluted water area image when the water quality pollution situation is determined, and to generate the water quality evaluation value in combination with the water surface ripples and water surface reflection in the polluted water area image.

4. The multi-factor ecological environment access intelligent analysis system based on AI large model according to claim 3 is characterized in that: The data integration unit further includes: The water area subunit is connected to the remote sensing unit and is used to analyze the water image through an edge detection algorithm to obtain a water contour line, and to adjust the remote sensing unit to enter the detection and acquisition state directly above the water contour line to continuously shoot a plurality of water contour images, and determine the water area by combining the plurality of water contour images.

5. The multi-factor ecological environment access intelligent analysis system based on AI large model according to claim 4 is characterized in that: The data integration unit further includes: a land processing subunit connected to the remote sensing unit, configured to calculate the land vacancy value based on identifying the artificial building area and the area of ​​the land block in the land image; An atmospheric processing subunit is connected to the remote sensing unit and is used to combine the atmospheric environment data and the atmospheric estimated pollution value to generate the atmospheric evaluation value.

6. The multi-factor ecological environment access intelligent analysis system based on AI large model according to claim 5 is characterized in that: The model training unit constructs the ecological environment model according to the water body type, the water area, the land vacancy value and the atmospheric evaluation value.

7. The multi-factor ecological environment access intelligent analysis system based on AI large model according to claim 6 is characterized in that: The model training unit compares the ecological environment model with the same environmental parameter items in the environmental demand data to obtain a number of ecological environment difference rates, and summarizes the several ecological environment difference rates to generate the environmental project access value.

8. The multi-factor ecological environment access intelligent analysis system based on AI large model according to claim 7 is characterized in that: The analysis and evaluation unit generates the water source sensitive area according to the water quality evaluation value, wherein: If the water quality evaluation value is less than or equal to the preset evaluation value, the land area corresponding to the water quality evaluation value is determined to be the water source sensitive area; The preset evaluation value is negatively correlated with the water area.

9. The multi-factor ecological environment access intelligent analysis system based on AI large model according to claim 8 is characterized in that: The analysis and evaluation unit corrects the environmental project access value based on the water source sensitive area to obtain an access correction value to determine the land area where the environmental project can be established, wherein: If the access correction value is greater than or equal to the preset access value, it is determined that the land area corresponding to the access correction value can be used to establish the environmental project; The preset admission value is negatively correlated with the area of ​​the plot.

10. The multi-factor ecological environment access intelligent analysis system based on AI large model according to claim 9 is characterized in that: The data collection unit compares the environmental demand data of the environmental project with the historical environmental data of each of the land areas to obtain a number of environmental demand difference rates, sorts the environmental demand difference rates from small to large, and generates a collection route for the remote sensing unit.

Images