Evaluation method and device for ecological restoration effect of high and steep slope

Abstract

The invention discloses a high and steep slope ecological restoration effect evaluation method and device, and the method comprises the steps: obtaining daily meteorological data, daily vegetation growth state data and daily soil moisture content data in a high and steep slope ecological restoration region, the vegetation growth state data comprises an unmanned aerial vehicle NDVI image shot by the unmanned aerial vehicle in the high and steep slope ecological restoration area; determining an initial restoration index value based on the daily vegetation growth state data and the daily soil moisture content data; determining a correction coefficient based on the daily meteorological data; and correcting the initial repair index value based on the correction coefficient to obtain a target repair index value. According to the invention, on one hand, the meteorological data is combined to evaluate the ecological restoration, and on the other hand, the unmanned aerial vehicle NDVI image shot by the unmanned aerial vehicle in the high and steep slope ecological restoration area is utilized to evaluate the ecological restoration, so that the evaluation accuracy of the high and steep slope ecological restoration effect can be improved.

Description

Technical Field

[0001] The present application relates to the field of ecological restoration technology, and specifically to a method and device for evaluating the ecological restoration effect of steep slopes. Background Art

[0002] Steep slopes are extremely challenging to restore due to their poor soil, difficulty in vegetation growth, and inaccessibility. Existing restoration evaluation methods often overlook the impact of meteorological data on ecological restoration. Data collected manually on steep slopes is subject to significant errors, resulting in inaccurate evaluation results and making it difficult to guide actual restoration efforts.

[0003] That is, the accuracy of evaluating the ecological restoration effect of high and steep slopes in existing technologies is low. Summary of the Invention

[0004] The embodiments of the present application provide a method and device for evaluating the ecological restoration effect of steep slopes, which can improve the accuracy of the evaluation of the ecological restoration effect of steep slopes.

[0005] First, the application provides a method for evaluating the ecological restoration effect of steep slopes, including: Obtain daily meteorological data, daily vegetation growth status data, and daily soil moisture data within the high-steep slope ecological restoration area, wherein the vegetation growth status data includes drone NDVI images taken within the high-steep slope ecological restoration area; Determine the initial restoration index value based on daily vegetation growth status data and daily soil moisture data; Determine the correction factor based on daily meteorological data; The initial repair index value is corrected based on the correction coefficient to obtain the target repair index value.

[0006] In an optional embodiment, the meteorological data includes temperature, humidity, wind speed, wind direction and atmospheric pressure, and the soil moisture data includes soil temperature and soil moisture.

[0007] In an optional embodiment, determining the correction coefficient based on daily meteorological data includes: The daily meteorological data are sequentially input into the meteorological coefficient prediction model to obtain the correction coefficient, wherein the meteorological coefficient prediction model is a long short-term memory network.

[0008] In an optional embodiment, determining the initial restoration index value based on daily vegetation growth status data and daily soil moisture data includes: Determine a growth status assessment value based on daily vegetation growth status data; The daily soil moisture data is input into the soil estimation model to obtain the soil assessment value, wherein the soil estimation model is a long short-term memory network; The growth status assessment value and soil assessment value are weighted and summed to obtain the initial restoration index value.

[0009] In an optional embodiment, the vegetation growth status data includes an average height of regional vegetation, and determining the growth status assessment value based on the daily vegetation growth status data includes: Perform curve fitting on the daily average height of regional vegetation to obtain the growth height fitting curve; Calculate the curve similarity between the growth height fitting curve and the standard plant growth curve; Determine the first vegetation coverage based on the UAV NDVI image to obtain the first vegetation coverage of each day; Determine the overall vegetation cover based on the daily first vegetation cover; The growth status assessment value is determined based on the overall vegetation coverage and curve similarity.

[0010] In an optional embodiment, determining the overall vegetation coverage based on the daily first vegetation coverage includes: The average of the first vegetation coverage of each day was determined as the overall vegetation coverage.

[0011] Secondly, the application provides a device for evaluating the ecological restoration effect of steep slopes, comprising: An acquisition module is used to obtain daily meteorological data, daily vegetation growth status data, and daily soil moisture data in the high-steep slope ecological restoration area, wherein the vegetation growth status data includes drone NDVI images taken in the high-steep slope ecological restoration area; A first determination module is used to determine an initial restoration index value based on daily vegetation growth status data and daily soil moisture data; a second determination module, configured to determine a correction coefficient based on daily meteorological data; The correction module is used to correct the initial repair index value based on the correction coefficient to obtain the target repair index value.

[0012] In an optional embodiment, the meteorological data includes temperature, humidity, wind speed, wind direction and atmospheric pressure, and the soil moisture data includes soil temperature and soil moisture.

[0013] In an optional embodiment, determining the correction coefficient based on daily meteorological data includes: The daily meteorological data are sequentially input into the meteorological coefficient prediction model to obtain the correction coefficient, wherein the meteorological coefficient prediction model is a long short-term memory network.

[0014] In an optional embodiment, determining the initial restoration index value based on daily vegetation growth status data and daily soil moisture data includes: Determine a growth status assessment value based on daily vegetation growth status data; The daily soil moisture data is input into the soil estimation model to obtain the soil assessment value, wherein the soil estimation model is a long short-term memory network; The growth status assessment value and soil assessment value are weighted and summed to obtain the initial restoration index value.

[0015] In an optional embodiment, the vegetation growth status data includes an average height of regional vegetation, and determining the growth status assessment value based on the daily vegetation growth status data includes: Perform curve fitting on the daily average height of regional vegetation to obtain the growth height fitting curve; Calculate the curve similarity between the growth height fitting curve and the standard plant growth curve; Determine the first vegetation coverage based on the UAV NDVI image to obtain the first vegetation coverage of each day; Determine the overall vegetation cover based on the daily first vegetation cover; The growth status assessment value is determined based on the overall vegetation coverage and curve similarity.

[0016] In an optional embodiment, determining the overall vegetation coverage based on the daily first vegetation coverage includes: The average of the first vegetation coverage of each day was determined as the overall vegetation coverage.

[0017] On the third aspect, the electronic device provided in this application includes a memory and a processor. The memory stores a computer program, and the processor is used to run the computer program in the memory to implement the steps in the method for evaluating the ecological restoration effect of steep slopes provided in this application.

[0018] Fourthly, the computer-readable storage medium provided in the present application stores a plurality of instructions, which are suitable for loading by a processor to implement the steps in the method for evaluating the ecological restoration effect of steep slopes provided in the present application.

[0019] In the fifth aspect, the computer program product provided in the present application includes a computer program or instructions, which, when executed by a processor, implements the steps in the method for evaluating the ecological restoration effect of steep slopes provided in the present application.

[0020] In this application, compared to related technologies, daily meteorological data, daily vegetation growth status data, and daily soil moisture data are obtained in the high-steep slope ecological restoration area, wherein the vegetation growth status data includes drone NDVI images taken by drones in the high-steep slope ecological restoration area; an initial restoration index value is determined based on the daily vegetation growth status data and the daily soil moisture data; a correction coefficient is determined based on the daily meteorological data; and the initial restoration index value is corrected based on the correction coefficient to obtain a target restoration index value. On the one hand, this application combines meteorological data to evaluate ecological restoration, and on the other hand, uses drone NDVI images taken by drones in the high-steep slope ecological restoration area to evaluate ecological restoration. This can reduce the data collected by manually reaching the high-steep slopes, thereby reducing the error in the data collected by manually reaching the high-steep slopes, and can improve the accuracy of the evaluation of the ecological restoration effect of the high-steep slopes. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 This is a schematic diagram of a scenario of a high and steep slope ecological restoration effect evaluation system provided in an embodiment of the present application; Figure 2 This is a flow chart of an embodiment of a method for evaluating the ecological restoration effect of a steep slope provided in an embodiment of the present application; Figure 3 This is a structural diagram of an embodiment of a device for evaluating the ecological restoration effect of a steep slope provided in an embodiment of the present application; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] It should be noted that the principles of this application are illustrated by implementing them in an appropriate computing environment. The following description is based on the illustrated specific embodiments of this application and should not be considered as limiting other specific embodiments not described in detail herein.

[0024] In the following description of this application, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.

[0025] In the following description of this application, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0027] To improve the effectiveness of evaluating the ecological restoration effects of steep slopes, embodiments of the present application provide a method for evaluating the ecological restoration effects of steep slopes, a device for evaluating the ecological restoration effects of steep slopes, an electronic device, a computer-readable storage medium, and a computer program product. The method can be performed by the device for evaluating the ecological restoration effects of steep slopes, or by an electronic device incorporating the device.

[0028] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0029] Please refer to Figure 1 , this application also provides a high steep slope ecological restoration effect evaluation system, such as Figure 1 As shown, the high-steep slope ecological restoration effect evaluation system includes an electronic device. The electronic device is integrated with the high-steep slope ecological restoration effect evaluation device provided by the present application.

[0030] Among them, electronic devices can be any devices equipped with a processor and have processing capabilities, such as mobile electronic devices with processors such as smartphones, tablets, PDAs, laptops, smart speakers, or fixed electronic devices with processors such as desktop computers, televisions, servers, and industrial equipment.

[0031] In addition, if Figure 1 As shown, the high steep slope ecological restoration effect evaluation system may further include a memory for storing original data, intermediate data and result data in the audio processing process. In the embodiments of the present application, the memory may be a cloud memory. Cloud storage is a new concept extended and developed from the concept of cloud computing. A distributed cloud storage system (hereinafter referred to as the storage system) refers to a storage system that uses cluster applications, grid technology, and distributed storage file systems to bring together a large number of different types of storage devices (storage devices are also called storage nodes) in the network through application software or application interfaces to work together and provide external data storage and business access functions.

[0032] Currently, storage systems utilize a storage method that creates logical volumes. During the creation of a logical volume, physical storage space is allocated for each logical volume. This physical storage space may consist of disks on a specific storage device or several storage devices. When a client stores data on a logical volume, it stores the data on a file system. The file system divides the data into multiple parts, each of which is an object. An object contains not only the data but also additional information such as the data identifier (ID entity). The file system writes each object to the physical storage space of the logical volume and records the storage location of each object. Therefore, when a client requests access to data, the file system can provide access based on the storage location information of each object.

[0033] The storage system allocates physical storage space to logical volumes by pre-dividing the physical storage space into stripes based on the estimated capacity of the objects to be stored in the logical volume (this estimate often has a large margin relative to the actual capacity of the objects to be stored) and the Redundant Array of Independent Disks (RAID) groupings. A logical volume can be understood as a stripe, thereby allocating physical storage space to the logical volume.

[0034] It should be noted that Figure 1 The scenario diagram of the high and steep slope ecological restoration effect evaluation system shown is only an example. The high and steep slope ecological restoration effect evaluation system and scenario described in the embodiment of this application are for more clearly illustrating the technical solution of the embodiment of this application, and do not constitute a limitation on the technical solution provided by the embodiment of this application. Ordinary technicians in this field can know that with the evolution of the high and steep slope ecological restoration effect evaluation system and the emergence of new business scenarios, the technical solution provided by the embodiment of this application is also applicable to similar technical problems.

[0035] It should be noted that the serial numbers of the following embodiments are not intended to limit the preferred order of the embodiments.

[0036] Please refer to Figure 2 , Figure 2This is a flow chart of an embodiment of the method for evaluating the ecological restoration effect of steep slopes provided in the embodiment of the present application. Figure 2 As shown, the process of the high steep slope ecological restoration effect evaluation method provided in this application is as follows: 201. Obtain daily meteorological data, daily vegetation growth status data, and daily soil moisture data in the high-steep slope ecological restoration area.

[0037] The vegetation growth status data includes drone NDVI images taken by drones in high and steep slope ecological restoration areas.

[0038] In the embodiment of the present application, the meteorological data includes temperature, humidity, wind speed, wind direction and atmospheric pressure, and the soil moisture data includes soil temperature and soil moisture.

[0039] In an embodiment of the present application, a method for evaluating the ecological restoration effect of a high-steep slope is applied to an evaluation system for the ecological restoration effect of a high-steep slope. The evaluation system for the ecological restoration effect of a high-steep slope includes multiple soil moisture sensors, multiple soil moisture sensors, multiple LORA terminals, a LORA base station, and electronic equipment. Each LORA terminal is connected to multiple soil moisture sensors and soil moisture sensors, multiple LORA terminals are connected to the LORA base station, and the LORA base station is connected to the electronic equipment through a 4G network. LORA is a low-power LAN wireless standard created by Semtech. Low power consumption generally makes it difficult to cover long distances, and long distances generally consume high power. The name of LORA is Long Range Radio. Its biggest feature is that it can transmit farther than other wireless methods under the same power consumption conditions, achieving the unity of low power consumption and long distance. It extends the communication distance by 3-5 times compared to traditional wireless radio frequency communication under the same power consumption.

[0040] Specifically, meteorological monitoring data from the weather station in the high-steep slope ecological restoration area is obtained, and daily meteorological data is obtained and displayed on the page, and the current real-time data is recorded in the database. Soil temperature and soil moisture can be measured by sensors. Data monitored by soil temperature sensors and soil moisture sensors in the high-steep slope ecological restoration area is obtained. The soil temperature sensors and soil moisture sensors upload the collected soil moisture data to the nearest LORA terminal. The LORA terminal transmits the data to the LORA base station. The LORA base station transmits the data to the electronic device via the 4G network, and the electronic device displays the data on the user page.

[0041] Specifically, multiple soil temperature sensors are arranged in a matrix in the high and steep slope ecological restoration area, and multiple soil moisture sensors are arranged in a matrix in the high and steep slope ecological restoration area.

[0042] In this embodiment, the vegetation growth status data includes drone NDVI images of the high-steep slope ecological restoration area and the average vegetation height in the area. The drone NDVI images of the high-steep slope ecological restoration area can be obtained using drone photography. The average vegetation height in the area represents the average height of vegetation within the high-steep slope ecological restoration area measured that day. The drone NDVI images include NDVI values ​​corresponding to each pixel. NDVI (Normalized Difference Vegetation Index) quantifies vegetation by measuring the difference between near-infrared (strongly reflected by vegetation) and red light (absorbed by vegetation). NDVI values ​​consistently range from -1 to +1. However, there are no clear boundaries for each type of land cover. For example, a negative NDVI value is likely water. On the other hand, an NDVI value close to +1 is likely to indicate lush green foliage. An NDVI value close to zero indicates a lack of green foliage and may even be an urban area. An NDVI value close to +1 in the blue area is likely to indicate lush green foliage and may be a vegetated area. An NDVI value close to zero in the red and yellow areas indicates a lack of green foliage and may even be an urban area.

[0043] When light strikes an object's surface, it selectively reflects electromagnetic waves of different wavelengths. Spectral reflectance, the ratio of the light flux reflected by an object within a certain wavelength band to the light flux incident on it, is an essential property of an object's surface. Therefore, different objects have different reflectivities for the same wavelength of electromagnetic waves. Multispectral technology is a spectral detection technique that simultaneously captures multiple optical spectrum bands (usually three or more), extending beyond visible light to infrared and ultraviolet light. A multispectral photograph is a color camera image that, from a spectral perspective, contains information from three bands: red, green, and blue. By adding more bands, such as the sum of the bands, to the camera or detector, a multispectral photograph containing multiple bands can be obtained. A common implementation involves combining various filters or beam splitters with multiple types of photographic films to simultaneously capture light signals radiated or reflected from the same target within different narrow spectral bands, resulting in images of the target in several different spectral bands. Vegetation indices are combinations of spectral values ​​from different bands that have specific biochemical significance. Vegetation indices derived from different band combinations have varying predictive power for different indicators. Plants and soil absorb and reflect sunlight wavelengths based on their composition. Plant leaves have strong absorption characteristics in the visible red band and strong reflection characteristics in the near-infrared band. The vegetation index, derived from combining these two bands, can clearly indicate vegetation coverage. Besides vegetation coverage, it can also indicate the effects of moisture, pests, and other factors.

[0044]

[0045] Healthy vegetation (chlorophyll) reflects more near-infrared (NIR) and green light compared to other wavelengths, but it absorbs more red and blue light, and the same applies to other vegetation parameters.

[0046] 202. Determine the initial restoration index value based on daily vegetation growth status data and daily soil moisture data.

[0047] In the embodiment of the present application, the initial restoration index value is determined based on the daily vegetation growth status data and the daily soil moisture data, including: (1) Determine the growth status assessment value based on daily vegetation growth status data.

[0048] In the embodiment of the present application, the vegetation growth status data includes drone NDVI images of the steep slope ecological restoration area and the average height of regional vegetation. The growth status assessment value is determined based on the daily vegetation growth status data, including: Step 1-1, curve fitting is performed on the daily average height of regional vegetation to obtain a growth height fitting curve.

[0049] The least squares method can be used to perform curve fitting on the daily average height of regional vegetation to obtain a growth height fitting curve.

[0050] Step 1-2, calculate the curve similarity between the growth height fitting curve and the standard plant growth curve.

[0051] A plant growth curve refers to the basic "slow-fast-slow" pattern of growth observed in plant organs or entire plants: growth begins slowly, gradually accelerates, then slows down and eventually stops. This overall growth process is called the grand period of growth. Plotting plant (or organ) volume against time yields a plant growth curve. A growth curve depicts the growth trend of a plant over its growth cycle, with a typical finite growth curve exhibiting an S-shape. Similar growth curves can be obtained by plotting parameters such as dry weight, height, surface area, cell number, or protein content against time. Based on this S-shaped curve, plant growth can be divided into three phases: the logarithmic phase, the linear phase, and the senescence phase. In the exponential phase, the absolute growth rate continues to increase, while the relative growth rate remains roughly unchanged; in the linear phase, the absolute growth rate is the maximum, while the relative growth rate decreases; in the decay phase, growth gradually decreases, and both the absolute and relative growth rates tend to zero.

[0052] In an embodiment of the present application, the highest point of the growth height fitting curve and the highest point of the standard plant growth curve are obtained, and the growth height fitting curve is moved until the highest point of the growth height fitting curve coincides with the highest point of the standard plant growth curve, thereby obtaining the moved fitting curve. The residual variance of the moved fitting curve and the standard plant growth curve is calculated, and the curve similarity is determined based on the residual variance of the moved fitting curve and the standard plant growth curve, wherein the smaller the residual variance, the greater the curve similarity. Specifically, the inverse of the residual variance is determined as the curve similarity.

[0053] Step 1-3: determine the first vegetation coverage based on the UAV NDVI image to obtain the first vegetation coverage of each day.

[0054] In one specific embodiment, pixels in the drone NDVI image with an NDVI value greater than a preset value are identified as suspected vegetation pixels, and pixels in the drone NDVI image with an NDVI value greater than a preset value are identified as suspected non-vegetation pixels. The preset value can be 0.4 or another value, depending on the specific situation. Each pixel is sequentially identified as a target pixel, and eight adjacent pixels surrounding the target pixel are obtained. The target pixel and the eight adjacent pixels form a nine-square grid, with the target pixel at the center of the grid and the eight adjacent pixels arranged around the target pixel. The first pixel percentage of the eight adjacent pixels surrounding the target pixel that are suspected vegetation pixels is calculated. For example, if the number of suspected vegetation pixels among the eight adjacent pixels is four, the first pixel percentage is 4 / 8 = 0.5. If the first pixel percentage is greater than the first preset percentage, the target pixel is identified as a suspected vegetation pixel. If the first pixel percentage is not greater than the second preset percentage, the target pixel is identified as a suspected non-vegetation pixel. The first preset percentage is greater than the second preset percentage. The first preset percentage and the second preset percentage can be set based on specific circumstances. For example, the first preset percentage can be 75% and the second preset percentage can be 25%. After traversing every pixel in the drone NDVI image, a new drone NDVI image is obtained. The percentage of suspected vegetation pixels in the new drone NDVI image is determined as the first vegetation coverage corresponding to the drone NDVI image. The first vegetation coverage corresponding to each drone NDVI image is determined sequentially.

[0055] Furthermore, the eight adjacent pixels surrounding the target pixel include four adjacent pixels and four diagonal pixels. The target pixel, the four adjacent pixels, and the four diagonal pixels form a nine-square grid, with the target pixel at the center of the grid, the four diagonal pixels at the four corners of the grid, and the four adjacent pixels and the four diagonal pixels arranged sequentially around the target pixel. A second pixel percentage of the four adjacent pixels suspected to be vegetation pixels and a third pixel percentage of the four diagonal pixels suspected to be vegetation pixels are obtained. A weighted sum of the second pixel percentage and the third pixel percentage is taken to obtain a fourth pixel percentage, where the weight coefficient of the second pixel percentage is greater than the weight coefficient of the third pixel percentage. For example, the weight coefficient of the second pixel percentage is 0.6, and the weight coefficient of the third pixel percentage is 0.4. If the fourth pixel percentage is greater than the first preset percentage, the target pixel is determined to be a suspected vegetation pixel. If the fourth pixel percentage is not greater than the second preset percentage, the target pixel is determined to be a suspected non-vegetation pixel. The first preset ratio is greater than the second preset ratio. The first preset ratio and the second preset ratio can be set according to specific circumstances. For example, the first preset ratio is 75% and the second preset ratio is 25%. After traversing every pixel of the drone NDVI image, a new drone NDVI image is obtained. The ratio of suspected vegetation pixels on the new drone NDVI image is determined as the first vegetation coverage corresponding to the drone NDVI image. The first vegetation coverage corresponding to each drone NDVI image is determined sequentially.

[0056] Step 1-4: determining the overall vegetation coverage based on the first vegetation coverage of each day.

[0057] In a specific embodiment, the average value of the first vegetation coverage on each day is determined as the overall vegetation coverage.

[0058] In another specific embodiment, daily RGB images taken by a drone of an ecological restoration area on a steep slope are obtained, vegetation segmentation is performed on the RGB images to obtain multiple vegetation segmentation areas, the area ratio of the multiple vegetation segmentation areas to the RGB image is determined as the second vegetation coverage to obtain the daily second vegetation coverage, the daily first vegetation coverage and the daily second vegetation coverage are averaged to obtain the overall vegetation coverage.

[0059] Steps 1-5: Determine the growth status evaluation value based on the overall vegetation coverage and curve similarity.

[0060] In a specific embodiment, the product of the overall vegetation coverage and the curve similarity is determined as the growth status evaluation value.

[0061] In another specific embodiment, determining the growth status evaluation value based on the overall vegetation coverage and the curve similarity includes: Step 2-1, based on the regional information of multiple vegetation segmentation regions in the RGB image, calculate the regional similarity between the vegetation segmentation region in the RGB image and each other vegetation segmentation region, and obtain multiple regional similarities corresponding to the vegetation segmentation region.

[0062] The area information includes the area altitude, area slope and area coordinates.

[0063] In the embodiment of the present application, the region information of the vegetation segmentation region is converted into a vector, and the cosine similarity of the vectors of the region information of two vegetation segmentation regions is determined as the region similarity.

[0064] Step 2-2: sort the multiple region similarities corresponding to the vegetation segmentation region from large to small and calculate the similarity difference between any two adjacent region similarities after sorting to obtain multiple similarity differences corresponding to the vegetation segmentation region.

[0065] Step 2-3: determining the coefficient of variation of the multiple similarity differences corresponding to the vegetation segmentation regions as the uniformity quantization value of the vegetation segmentation regions, and obtaining a quantitative average value of the uniformity quantization values ​​of the multiple vegetation segmentation regions.

[0066] Coefficient of Variation (CV): When comparing the degree of dispersion between two sets of data, if the measurement scales differ significantly or the data dimensions differ, directly using the standard deviation is inappropriate. Instead, the influence of the measurement scale and dimension should be eliminated. The CV can do this. It is the ratio of the standard deviation of the raw data to the mean of the raw data. CV is dimensionless, allowing for objective comparisons. In fact, the CV, like the range, standard deviation, and variance, can be considered an absolute value reflecting the degree of dispersion of the data. Its size is affected not only by the dispersion of the variable values ​​but also by the average level of the variable values.

[0067] Step 2-4: determining the regional feature uniformity of the RGB image based on the quantized average value, wherein the higher the quantized average value, the smaller the regional feature uniformity.

[0068] A smaller coefficient of variation indicates a more uniform difference in regional similarity between vegetation segments, meaning that the characteristics vary evenly across each vegetation segment. Lower uniformity quantification values ​​and lower quantified averages indicate a higher regional characteristic uniformity. This indicates that higher regional characteristic uniformity indicates a more uniform variation in characteristics across vegetation segments, effectively covering a wide range of regional conditions and improving the accuracy of plot selection for the survey.

[0069] For example, consider four vegetation segments. For one segment, the regional similarities corresponding to three segments are 0.5, 0.6, and 0.7, respectively, and the similarity differences are 0.1 and 0.1. The coefficient of variation for these similarity differences is 0. A smaller coefficient of variation indicates a lower uniformity quantization value, a lower quantization average, and a higher regional feature uniformity. This indicates that the regional similarity differences between the vegetation segments are relatively uniform, and that the features vary evenly across the segments, indicating good coverage.

[0070] Step 2-5: determining the regional feature uniformity of the RGB image based on the quantized average value, wherein the higher the quantized average value, the smaller the regional feature uniformity.

[0071] Step 2-6: The product of the overall vegetation coverage, the curve similarity, and the regional characteristic uniformity is determined as the growth status evaluation value.

[0072] Among them, the greater the overall vegetation coverage, the higher the growth status evaluation value, the greater the curve similarity, the higher the growth status evaluation value, and the greater the regional characteristic uniformity, the higher the growth status evaluation value.

[0073] (2) Input daily soil moisture data into the soil estimation model to obtain the soil assessment value.

[0074] The soil estimation model is a long short-term memory network. The soil estimation model is a pre-trained long short-term memory network. The input is daily soil moisture data and the output is the soil assessment value.

[0075] LSTM (Long Short-Term Memory) is a special type of recurrent neural network designed to address the performance issues of traditional RNNs when processing long-term dependencies. The key innovation of LSTM lies in the introduction of a specific gating mechanism, including the input gate, forget gate, and output gate. These gates allow for the selective transfer of information between different time steps, thereby better retaining and learning long-term dependencies. The basic structure of LSTM consists of multiple layers, including one or more hidden layers. Each hidden layer is composed of neurons that receive information from the previous layer and process it through nonlinear transformations. The output of LSTM depends not only on the neurons in the current layer but also on the cell state of all previous time steps—a special state variable used to store and transfer information. The LSTM training process involves updating the weights of these gates to optimize how they control the flow of information. This design enables LSTM to maintain high accuracy when processing long-term data while overcoming the limitations of traditional RNNs in handling long-term dependencies. Multi-layer network structure: LSTM consists of multiple hidden layers, each with adjusted weights to optimize information transfer.

[0076] It's important to note that artificial intelligence (AI) refers to the theories, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive technology within computer science that seeks to understand the essence of intelligence and produce new intelligent machines that can respond in a manner similar to human intelligence. AI also involves studying the design principles and implementation methods of various intelligent machines, enabling them to possess the capabilities of perception, reasoning, and decision-making.

[0077] Artificial intelligence (AI) technology is a comprehensive discipline encompassing a wide range of fields, encompassing both hardware and software technologies. Foundational AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass machine learning (ML). Deep learning (DL) is a new research direction within ML, introduced to bring ML closer to its original goal: artificial intelligence. Currently, deep learning is primarily used in fields such as machine vision and natural speech processing.

[0078] Deep learning involves studying the inherent patterns and representational hierarchies of sample data. The information gained from this learning process is highly useful for interpreting data such as text, images, and sound. Using deep learning techniques and corresponding sample sets, network models can be trained to achieve different functions.

[0079] (3) The growth status assessment value and the soil assessment value are weighted and summed to obtain the initial restoration index value.

[0080] In the embodiment of the present application, the weight coefficient of the growth status evaluation value and the weight coefficient of the soil evaluation value are set according to specific conditions.

[0081] 203. Determine the correction factor based on daily meteorological data.

[0082] In an embodiment of the present application, determining a correction coefficient based on daily meteorological data includes sequentially inputting the daily meteorological data into a meteorological coefficient estimation model to obtain the correction coefficient, wherein the meteorological coefficient estimation model is a long short-term memory network. The meteorological coefficient estimation model is a pre-trained model. The correction coefficient has a value range of [0.5-1].

[0083] 204. Correct the initial repair index value based on the correction coefficient to obtain a target repair index value.

[0084] Specifically, the correction coefficient and the initial repair index value are determined as the target repair index value.

[0085] Compared with related technologies, daily meteorological data, daily vegetation growth status data, and daily soil moisture data are obtained in the high-steep slope ecological restoration area, wherein the vegetation growth status data includes drone NDVI images taken by drones in the high-steep slope ecological restoration area; an initial restoration index value is determined based on the daily vegetation growth status data and the daily soil moisture data; a correction coefficient is determined based on the daily meteorological data; and the initial restoration index value is corrected based on the correction coefficient to obtain a target restoration index value. This application evaluates ecological restoration in combination with meteorological data on the one hand, and evaluates ecological restoration in combination with drone NDVI images taken by drones in the high-steep slope ecological restoration area on the other hand. This can reduce the data collected by manually reaching the high-steep slopes, thereby reducing the error in the data collected by manually reaching the high-steep slopes, and can improve the accuracy of the evaluation of the ecological restoration effect of the high-steep slopes.

[0086] To facilitate the implementation of the high-steep slope ecological restoration effectiveness evaluation method provided in the embodiments of this application, the embodiments of this application also provide a high-steep slope ecological restoration effectiveness evaluation device based on the above-mentioned high-steep slope ecological restoration effectiveness evaluation method. The meanings of the terms herein are the same as those in the above-mentioned high-steep slope ecological restoration effectiveness evaluation method. For specific implementation details, please refer to the description in the above method embodiment.

[0087] Please refer to Figure 3 , Figure 3 70 is a schematic diagram of the structure of an embodiment of a high-steep slope ecological restoration effect evaluation device provided in an embodiment of the present application. The high-steep slope ecological restoration effect evaluation device may include an acquisition module 701, a first determination module 702, a second determination module 703, and a correction module 704, wherein: An acquisition module is used to obtain daily meteorological data, daily vegetation growth status data, and daily soil moisture data in the high-steep slope ecological restoration area, wherein the vegetation growth status data includes drone NDVI images taken in the high-steep slope ecological restoration area; A first determination module is used to determine an initial restoration index value based on daily vegetation growth status data and daily soil moisture data; a second determination module, configured to determine a correction coefficient based on daily meteorological data; The correction module is used to correct the initial repair index value based on the correction coefficient to obtain the target repair index value.

[0088] In an optional embodiment, the meteorological data includes temperature, humidity, wind speed, wind direction and atmospheric pressure, and the soil moisture data includes soil temperature and soil moisture.

[0089] In an optional embodiment, determining the correction coefficient based on daily meteorological data includes: The daily meteorological data are sequentially input into the meteorological coefficient prediction model to obtain the correction coefficient, wherein the meteorological coefficient prediction model is a long short-term memory network.

[0090] In an optional embodiment, determining the initial restoration index value based on daily vegetation growth status data and daily soil moisture data includes: Determine a growth status assessment value based on daily vegetation growth status data; The daily soil moisture data is input into the soil estimation model to obtain the soil assessment value, wherein the soil estimation model is a long short-term memory network; The growth status assessment value and soil assessment value are weighted and summed to obtain the initial restoration index value.

[0091] In an optional embodiment, the vegetation growth status data includes an average height of regional vegetation, and determining the growth status assessment value based on the daily vegetation growth status data includes: Perform curve fitting on the daily average height of regional vegetation to obtain the growth height fitting curve; Calculate the curve similarity between the growth height fitting curve and the standard plant growth curve; Determine the first vegetation coverage based on the UAV NDVI image to obtain the first vegetation coverage of each day; Determine the overall vegetation cover based on the daily first vegetation cover; The growth status assessment value is determined based on the overall vegetation coverage and curve similarity.

[0092] In an optional embodiment, determining the overall vegetation coverage based on the daily first vegetation coverage includes: The average of the first vegetation coverage of each day was determined as the overall vegetation coverage.

[0093] The specific implementation of each of the above modules can be found in the previous embodiments and will not be described again here.

[0094] Compared with related technologies, daily meteorological data, daily vegetation growth status data, and daily soil moisture data are obtained in the high-steep slope ecological restoration area, wherein the vegetation growth status data includes drone NDVI images taken by drones in the high-steep slope ecological restoration area; an initial restoration index value is determined based on the daily vegetation growth status data and the daily soil moisture data; a correction coefficient is determined based on the daily meteorological data; and the initial restoration index value is corrected based on the correction coefficient to obtain a target restoration index value. This application evaluates ecological restoration in combination with meteorological data on the one hand, and evaluates ecological restoration in combination with drone NDVI images taken by drones in the high-steep slope ecological restoration area on the other hand. This can reduce the data collected by manually reaching the high-steep slopes, thereby reducing the error in the data collected by manually reaching the high-steep slopes, and can improve the accuracy of the evaluation of the ecological restoration effect of the high-steep slopes.

[0095] Please refer to Figure 4 , Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0096] The electronic device may include components such as a processor 101 with one or more processing cores, a memory 102 with one or more computer-readable storage media, a power supply 103, and an input unit 104. Those skilled in the art will appreciate that the electronic device structure shown in the figure does not limit the electronic device and may include more or fewer components than shown, or combine certain components, or arrange the components differently. Among them: Processor 101 is the control center of the electronic device. It connects all parts of the electronic device using various interfaces and circuits. It executes software programs and / or modules stored in memory 102 and accesses data stored in memory 102 to perform various functions of the electronic device and process data. Optionally, processor 101 may include one or more processing cores. Alternatively, processor 101 may integrate an application processor and a modem processor. The application processor primarily handles the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 101.

[0097] Memory 102 can be used to store software programs and modules. Processor 101 executes various functional applications and data processing by running the software programs and modules stored in memory 102. Memory 102 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as sound playback or image playback); the data storage area may store data generated based on the use of the electronic device. Furthermore, memory 102 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, memory 102 may also include a memory controller to provide processor 101 with access to memory 102.

[0098] The electronic device also includes a power supply 103 for supplying power to various components. Optionally, the power supply 103 can be logically connected to the processor 101 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The power supply 103 can also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0099] The electronic device may further include an input unit 104, which may be configured to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0100] Although not shown, the electronic device may also include a display unit, an image acquisition element, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 101 in the electronic device will load the executable code corresponding to one or more computer programs into the memory 102 according to the following instructions, and the processor 101 will execute the steps of the high and steep slope ecological restoration effect evaluation method provided in this application, such as: Obtain daily meteorological data, daily vegetation growth status data, and daily soil moisture data in the high-steep slope ecological restoration area, where the vegetation growth status data includes drone NDVI images taken by drones in the high-steep slope ecological restoration area; determine the initial restoration index value based on the daily vegetation growth status data and daily soil moisture data; determine the correction coefficient based on the daily meteorological data; and correct the initial restoration index value based on the correction coefficient to obtain the target restoration index value.

[0101] It should be noted that the electronic device provided in the embodiment of the present application belongs to the same concept as the method for evaluating the ecological restoration effect of steep slopes in the above embodiment. The specific implementation process is detailed in the above related embodiments and will not be repeated here.

[0102] This application also provides a computer-readable storage medium storing a computer program. When the stored computer program is executed on a processor of an electronic device provided in an embodiment of this application, the processor of the electronic device executes the steps of the method for evaluating the ecological restoration effect of steep slopes provided in this application. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0103] This application also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform various optional implementations of the above-mentioned high and steep slope ecological restoration effect evaluation method.

[0104] The above is a detailed introduction to the method and device for evaluating the ecological restoration effect of steep slopes provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0105] It should be noted that when the above embodiments of this application are applied to specific products or technologies, the relevant user data is involved, and the user's permission or consent must be obtained, and the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

Claims

1. A method for evaluating the ecological restoration effect of steep slopes, characterized in that: The method for evaluating the ecological restoration effect of high and steep slopes includes: Obtain daily meteorological data, daily vegetation growth status data, and daily soil moisture data within the high-steep slope ecological restoration area, wherein the vegetation growth status data includes drone NDVI images taken within the high-steep slope ecological restoration area; Determine the initial restoration index value based on daily vegetation growth status data and daily soil moisture data; Determine the correction factor based on daily meteorological data; The initial repair index value is corrected based on the correction coefficient to obtain the target repair index value.

2. The method for evaluating the ecological restoration effect of a high and steep slope according to claim 1, characterized in that: The meteorological data includes temperature, humidity, wind speed, wind direction and atmospheric pressure, and the soil moisture data includes soil temperature and soil moisture.

3. The method for evaluating the ecological restoration effect of a high and steep slope according to claim 2, characterized in that: The correction coefficient is determined based on daily meteorological data, including: The daily meteorological data are sequentially input into the meteorological coefficient prediction model to obtain the correction coefficient, wherein the meteorological coefficient prediction model is a long short-term memory network.

4. The method for evaluating the ecological restoration effect of a high and steep slope according to claim 3 is characterized in that: The initial restoration index value is determined based on daily vegetation growth status data and daily soil moisture data, including: Determine a growth status assessment value based on daily vegetation growth status data; The daily soil moisture data is input into the soil estimation model to obtain the soil assessment value, wherein the soil estimation model is a long short-term memory network; The growth status assessment value and soil assessment value are weighted and summed to obtain the initial restoration index value.

5. The method for evaluating the ecological restoration effect of a high and steep slope according to claim 4, characterized in that: The vegetation growth status data includes an average height of regional vegetation, and determining a growth status evaluation value based on the daily vegetation growth status data includes: Perform curve fitting on the daily average height of regional vegetation to obtain the growth height fitting curve; Calculate the curve similarity between the growth height fitting curve and the standard plant growth curve; Determine the first vegetation coverage based on the UAV NDVI image to obtain the first vegetation coverage of each day; Determine the overall vegetation cover based on the daily first vegetation cover; The growth status assessment value is determined based on the overall vegetation coverage and curve similarity.

6. The method for evaluating the ecological restoration effect of a high and steep slope according to claim 5, characterized in that: The determining of the overall vegetation coverage based on the daily first vegetation coverage comprises: The average of the first vegetation coverage of each day was determined as the overall vegetation coverage.

7. A device for evaluating the ecological restoration effect of a high and steep slope, characterized in that: The high and steep slope ecological restoration effect evaluation device includes: An acquisition module is used to obtain daily meteorological data, daily vegetation growth status data, and daily soil moisture data in the high-steep slope ecological restoration area, wherein the vegetation growth status data includes drone NDVI images taken in the high-steep slope ecological restoration area; A first determination module is used to determine an initial restoration index value based on daily vegetation growth status data and daily soil moisture data; a second determination module, configured to determine a correction coefficient based on daily meteorological data; The correction module is used to correct the initial repair index value based on the correction coefficient to obtain the target repair index value.

8. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and the processor is used to run the computer program in the memory to execute the steps in the method for evaluating the ecological restoration effect of a steep slope as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a plurality of instructions, which are suitable for loading by a processor to execute the steps in the method for evaluating the ecological restoration effect of steep slopes as described in any one of claims 1 to 6.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method for evaluating the ecological restoration effect of steep slopes described in any one of claims 1 to 6 are implemented.

Images