Analysis Methods and Systems for Flexible Photovoltaic Ecological Restoration in Karst Mountains

Abstract

This application relates to the field of data analysis technology and discloses a method and system for analyzing flexible photovoltaic ecological restoration in karst mountain areas. The method includes: obtaining karst desertification intensity classification data by detecting the bare rock ratio in the karst desertification area using the transect probe method; obtaining microenvironmental regulation parameters under the panels by correlating the height parameters of the flexible photovoltaic panels with microclimate monitoring data; calculating the water resource efficiency of the water collection trough based on the microenvironmental regulation parameters to obtain a water collection-irrigation synergy index; obtaining an ecological restoration effect evaluation index by comprehensively evaluating the karst desertification intensity classification data and vegetation restoration indicators using the membership function method; and obtaining a circular agriculture benefit assessment result by coupling the water collection-irrigation synergy index with the fungal residue substrate ratio data. This application improves the efficiency of the integrated development of photovoltaic industry and ecological restoration and the efficiency of water resource utilization in karst desertification areas.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, and in particular to a method and system for analyzing flexible photovoltaic ecological restoration in karst mountains. Background Technology

[0002] Currently, the control of rocky desertification in karst mountains mainly employs traditional vegetation restoration techniques, including artificial afforestation, forest closure for natural regeneration, and engineering control methods. These techniques can improve the situation of rocky desertification to a certain extent. Meanwhile, photovoltaic power generation technology is widely used in flat and gentle slope areas, converting solar radiation into electricity through solar panels, contributing to the development of clean energy. Traditional methods of rocky desertification control typically combine soil and water conservation engineering with vegetation establishment techniques, controlling soil erosion by improving soil conditions and increasing vegetation cover.

[0003] However, existing technologies have significant shortcomings. Traditional methods for combating desertification rely solely on vegetation restoration, lacking economic benefits and failing to establish a sustainable governance model. Furthermore, in the complex terrain of karst mountains, land use efficiency is low, and water resources are underutilized. While photovoltaic power generation projects offer good economic benefits, their application in karst mountains faces challenges such as poor terrain adaptability and insufficient ecological impact assessment, lacking organic integration with ecological restoration. Existing methods for monitoring desertification mainly rely on manual surveys and remote sensing, lacking precise analytical methods for assessing the degree of desertification under photovoltaic environments.

[0004] Based on the above analysis, existing technologies cannot solve the key technical problems in the integrated development of photovoltaic construction and rocky desertification control. The lack of quantitative analysis methods for the relationship between the microenvironment under photovoltaic panels and vegetation restoration makes it impossible to scientifically determine the optimal configuration parameters for photovoltaic systems; the lack of water resource efficiency assessment technology based on photovoltaic water collection and rocky desertification characteristics makes it impossible to fully utilize the water collection potential of photovoltaic panels for ecological restoration; and the lack of a systematic evaluation method that comprehensively considers the degree of rocky desertification, vegetation restoration effects, and the benefits of circular agriculture makes it impossible to establish a sustainable "photovoltaic + ecological restoration" integrated development model. Summary of the Invention

[0005] This application provides a flexible photovoltaic ecological restoration analysis method and system for karst mountains, which can be used to improve the efficiency of integrated development of photovoltaic industry and ecological restoration and water resource utilization in karst mountain rocky desertification areas.

[0006] Firstly, this application provides an analysis method for flexible photovoltaic ecological restoration in karst mountains, the method comprising:

[0007] Step S1: The bare rock ratio in the rocky desertification area is detected by transect probe method to obtain rocky desertification intensity classification data;

[0008] Step S2: Correlation analysis is performed between the height parameters of the flexible photovoltaic panel and the microclimate monitoring data to obtain the microenvironment control parameters under the panel;

[0009] Step S3: Calculate the water resource efficiency of the water collection tank based on the microenvironment control parameters to obtain the water collection-irrigation synergy index;

[0010] Step S4: The rocky desertification intensity classification data and vegetation restoration indicators are comprehensively evaluated using the membership function method to obtain the ecological restoration effect evaluation index;

[0011] Step S5: Couple the water collection-irrigation synergy index with the substrate ratio data to obtain the evaluation results of circular agriculture benefits.

[0012] Secondly, this application provides a flexible photovoltaic ecological restoration analysis system for karst mountains, the flexible photovoltaic ecological restoration analysis system for karst mountains comprising:

[0013] The detection module is used to detect the bare rock ratio in rocky desertification areas using the transect probe method, and obtain rocky desertification intensity classification data.

[0014] The correlation module is used to correlate and analyze the height parameters of flexible photovoltaic panels with microclimate monitoring data to obtain the microenvironment control parameters under the panels;

[0015] The calculation module is used to calculate the water resource efficiency of the water collection tank based on the microenvironment control parameters, and obtain the water collection-irrigation synergy index.

[0016] The evaluation module is used to comprehensively evaluate the rocky desertification intensity classification data and vegetation restoration indicators using the membership function method, and obtain the ecological restoration effect evaluation index.

[0017] The coupling module is used to couple the water collection-irrigation synergy index with the substrate ratio data to obtain the evaluation results of circular agriculture benefits.

[0018] Thirdly, a flexible photovoltaic ecological restoration analysis device for karst mountains is provided, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor invokes the instructions in the memory to cause the flexible photovoltaic ecological restoration analysis device for karst mountains to execute the aforementioned flexible photovoltaic ecological restoration analysis method for karst mountains.

[0019] Fourthly, a computer-readable storage medium is provided, wherein instructions are stored therein, which, when executed on a computer, cause the computer to perform the above-described analysis method for flexible photovoltaic ecological restoration of karst mountains.

[0020] The technical solution provided in this application uses the transect probe method to detect the bare rock ratio in rocky desertification areas and generate rocky desertification intensity classification data. This solves the problem of insufficient accuracy of traditional rocky desertification assessment methods under complex terrain conditions in karst mountains. This method, through standardized probe penetration detection and continuity judgment algorithms, can accurately identify the distribution of bare rock and quantify the degree of rocky desertification, providing reliable geological environmental data for the subsequent scientific layout of flexible photovoltaic systems. Correlation analysis between the height parameters of flexible photovoltaic panels and microclimate monitoring data yields the microenvironmental regulation parameters beneath the panels, breaking through the technical bottleneck of traditional photovoltaic system design neglecting microenvironmental regulation. Through multiple regression analysis, a quantitative relationship between photovoltaic panel configuration parameters and microclimate factors is established, realizing the active regulation of the ecological environment beneath the panels by the photovoltaic system. Based on the microenvironmental regulation parameters, water resource efficiency calculations are performed on the water collection volume of the catchment trough to obtain the water collection-irrigation synergy index. This innovatively transforms the photovoltaic panels into water collection devices. Through superhydrophobic surface modification and gradient flow design, the water resource utilization efficiency in karst mountains is significantly improved, solving the key problem of seasonal water shortage restricting ecological restoration in rocky desertification areas.

[0021] An ecological restoration effect evaluation index was obtained by comprehensively evaluating rocky desertification intensity classification data and vegetation restoration indicators using the membership function method. A multi-indicator integrated vegetation restoration evaluation system was established. The membership function algorithm, through standardization and weighted average calculation, eliminated the influence of dimensional differences between different indicators, improving the objectivity and comparability of the evaluation results and providing a scientific method for quantitative assessment of rocky desertification control effects. The water catchment-irrigation synergy index was coupled with the fungal substrate ratio data to obtain the circular agriculture benefit evaluation results, achieving a technological leap from single ecological restoration to circular agriculture development. The BP neural network algorithm played a key role in the analysis of flexible photovoltaic ecological restoration in karst mountains. Through multi-layer nonlinear mapping and backpropagation optimization, this algorithm can handle the complex coupling relationships between multiple factors such as water catchment efficiency, substrate ratio, and vegetation restoration, achieving accurate prediction and optimal allocation of circular agriculture benefits. The entire plan forms a complete technical chain of "rocky desertification assessment - photovoltaic microenvironment regulation - efficient water resource utilization - vegetation restoration evaluation - circular agricultural development", providing a systematic solution for the coordinated development of photovoltaic industry and ecological restoration in karst mountains, with significant ecological, economic and social benefits. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1This is a schematic diagram of an embodiment of the flexible photovoltaic ecological restoration analysis method for karst mountains in this application.

[0024] Figure 2 This is a schematic diagram of one embodiment of the karst mountain flexible photovoltaic ecological restoration analysis system in this application.

[0025] Figure 3 This is a schematic block diagram of the structure of the flexible photovoltaic ecological restoration analysis equipment for karst mountains in an embodiment of the present invention. Detailed Implementation

[0026] This application provides a method and system for analyzing flexible photovoltaic ecological restoration in karst mountains. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0027] For ease of understanding, the specific process of the embodiments of this application is described below. Please refer to [link / reference]. Figure 1 One embodiment of the karst mountain flexible photovoltaic ecological restoration analysis method in this application includes:

[0028] Step S1: The bare rock ratio in the rocky desertification area is detected by transect probe method to obtain rocky desertification intensity classification data;

[0029] Step S2: Correlation analysis is performed between the height parameters of the flexible photovoltaic panel and the microclimate monitoring data to obtain the microenvironment control parameters under the panel;

[0030] Step S3: Calculate the water resource efficiency of the water collection trough based on the microenvironment regulation parameters to obtain the water collection-irrigation synergy index;

[0031] Step S4: The membership function method is used to comprehensively evaluate the rocky desertification intensity classification data and vegetation restoration indicators to obtain the ecological restoration effect evaluation index;

[0032] Step S5: Couple the water collection-irrigation synergy index with the substrate ratio data of the fungal residue to obtain the evaluation results of the benefits of circular agriculture.

[0033] It is understood that the executing entity of this application can be a flexible photovoltaic ecological restoration analysis system for karst mountains, or it can be a terminal or a server; the specific implementation is not limited here. This application's embodiment uses a server as an example for illustration.

[0034] Specifically, the transect probe method is the fundamental data collection method for assessing the intensity of rocky desertification. Representative quadrats are set up at different slope positions (upper, middle, and lower) in the rocky desertification area. Three 50-meter-long transects are laid out in each quadrat, and probes are inserted vertically every 1 meter along the transects. A value of 1 is recorded when the probe hits the exposed ground two or more times consecutively with continuous exposed surface between probe points; otherwise, it is recorded as 0. The percentage of a single exposed patch is obtained by summing all the percentages of exposed patches, and then the bare rock coverage value for that transect is obtained by summing all the bare patch percentages. According to the "Technical Regulations for Rocky Desertification Monitoring in Southwest Karst Areas," the bare rock coverage value is divided into three levels of rocky desertification intensity: mild, moderate, and severe, forming a rocky desertification intensity classification data. The correlation analysis between the height parameters of flexible photovoltaic panels and microclimate uses a multiple regression analysis method. A 16m × 16m measurement plot is established in an area with consistent topographic conditions. The height and spacing of the photovoltaic panels are adjusted using an adjustable lifting device and a parallel moving track system to obtain the height change sequence parameters and the spacing change sequence parameters. Handheld weather stations are deployed in a grid pattern to continuously monitor light intensity, temperature, humidity, and wind speed in the area under the slab and between the slabs, creating a microclimate factor dataset. Multiple regression analysis is used, with height and spacing parameters as independent variables and microclimate factors as dependent variables, to establish a regression equation and determine the optimal microenvironment control parameters under the slab.

[0035] Water resource efficiency calculations determine the optimal placement of the water collection trough device based on the microenvironmental regulation parameters beneath the plate. The trough is modified through multi-layer coating with a superhydrophobic surface material, and a distributed water collection network unit is formed by combining this with a gradient tilt angle design. Water collection efficiency data is obtained by monitoring the collection volume of the water collection tank under different rainfall intensities. This data is then input into the intelligent water and fertilizer integrated machine control system for synergistic optimization calculations of rainy season water storage and dry season irrigation, ultimately yielding the water collection-irrigation synergy index.

[0036] A comprehensive evaluation was conducted using the membership function method. First, suitable native plants and superior forage were selected for a configuration experiment based on the rocky desertification intensity classification data. Vegetation restoration indicators such as plant species composition, density, plant height, canopy cover, and biomass were collected regularly within the experimental plots. The membership function calculation used a standardized formula to process each indicator, converting the indicator values ​​into membership degree values ​​between 0 and 1. A weighted average was then calculated to obtain the comprehensive membership degree evaluation value. The rocky desertification intensity classification data and the comprehensive membership degree evaluation value were coupled for analysis to form an ecological restoration effect evaluation index. A backpropagation (BP) neural network was used to assess the benefits of circular agriculture. The water collection-irrigation synergy index was used as input layer data, and the network weight matrix was trained using a backpropagation algorithm to construct a microenvironmental regulation model for edible fungi cultivation. The cellulose components of discarded mushroom substrate and the mineral components of engineering waste soil were mixed in different volume ratios to form a mushroom residue substrate ratio scheme. This was combined with microbial agents for biochemical activity modification to obtain a special substrate for ecological restoration. The water collection-irrigation synergy index, mushroom residue substrate ratio data, and vegetation restoration effect data were input into the BP neural network for multi-factor economic benefit coupling calculation, outputting the circular agriculture benefit evaluation results.

[0037] In one specific embodiment, the process of performing step S1 may specifically include the following steps:

[0038] Representative quadrats were set up in the rocky desertification area according to the slope difference, and several survey quadrats were set up at each location;

[0039] Multiple equal-length lines are set up for each quadrat, and probes are vertically inserted at fixed intervals along the line direction for detection.

[0040] Numerical labeling was performed on locations where the bare ground was repeatedly hit by probes and where the bare ground surface was continuous between probe points to obtain bare spot identification marks.

[0041] The bare rock coverage rate of the transect is obtained by summing the area ratios of the bare spot identification markers.

[0042] According to the technical regulations for monitoring rocky desertification in the karst region of Southwest China, the bare rock coverage values ​​of the transects were classified into different grades to obtain rocky desertification intensity classification data.

[0043] Specifically, the quadrat setting in the rocky desertification area follows the principle of slope position difference, with representative quadrats set up at three different slope positions: upper, middle, and lower. Three 10m x 10m quadrats are set up at each slope position to ensure that the quadrats represent the typical rocky desertification characteristics of that slope. Quadrat selection needs to consider factors such as the degree of rock exposure, vegetation distribution, and soil thickness, and the precise coordinates of the quadrats are determined using GPS positioning.

[0044] Based on the standardized layout method of the equal-length transects set up in each quadrat, three 50-meter-long transects were set up within each quadrat. The transects were laid out along the direction of the maximum slope to ensure that they could fully reflect the distribution characteristics of rocky desertification on the slope. The transects started from the edge of the quadrat and extended to the opposite corner of the quadrat, with the spacing between the transects remaining uniform. A detection point was set up every 1 meter along the transect direction, and a standard probe was used to penetrate vertically downwards into the ground surface to a depth of 10 centimeters. During the penetration, whether the probe touched the exposed rock surface was recorded.

[0045] Numerical processing for bare rock patch identification and marking employs binary encoding. When the probe strikes the bare ground two or more times consecutively, and the exposed surface between probe points is continuously distributed, the location is marked with a value of 1, indicating the presence of a bare rock patch. Conversely, it is marked with a value of 0, indicating the presence of soil or vegetation cover. The continuity criterion is that the exposed surface between adjacent detection points is uninterrupted, forming a continuous bare rock area. During the numerical marking process, the coordinates, degree of bare rock exposure, and surrounding vegetation cover of each marked point need to be recorded.

[0046] The area ratio calculation employs a grid statistical method. The number of detection points marked as 1 on each transect is counted. When calculating the area ratio of a single bare patch, the number of consecutive detection points marked as 1 is incremented by 1 to represent the length unit of that bare patch. All bare patch length units are then summed to obtain the total bare patch length of the transect. The bare rock coverage rate of the transect is equal to the total bare patch length divided by the total transect length, and the result is expressed as a percentage. The arithmetic mean of the bare rock coverage rates of the three transects is taken to obtain the average bare rock coverage rate of the sample plot.

[0047] The classification process strictly followed the classification standards in the "Technical Regulations for Monitoring Rocky Desertification in Karst Areas of Southwest China," comparing the bare rock coverage values ​​of the transects with standard thresholds. Mild rocky desertification corresponds to a bare rock coverage of less than 30%, moderate rocky desertification to a bare rock coverage between 30% and 60%, and severe rocky desertification to a bare rock coverage greater than 60%. Based on the comparison results, each transect was assigned a corresponding rocky desertification intensity level code: mild, moderate, and severe, corresponding to codes 1, 2, and 3 respectively, forming the rocky desertification intensity grading data.

[0048] In one specific embodiment, the process of performing step S2 may specifically include the following steps:

[0049] In areas with consistent terrain conditions, multiple flexible photovoltaic measurement plots were established, with different combinations of photovoltaic panel height from the ground and panel spacing.

[0050] The height of the flexible photovoltaic panel is gradually adjusted using an adjustable lifting device to obtain a sequence of height change parameters.

[0051] The spacing between photovoltaic panels is controlled and adjusted based on a parallel moving track system, and the spacing change sequence parameters are obtained.

[0052] Handheld weather stations were used to continuously monitor light, temperature, humidity, and wind speed in the area under the panel and between the grid points, in a grid-like manner, to obtain a dataset of microclimate factors.

[0053] Multiple regression analysis was performed on the height variation sequence parameters, spacing variation sequence parameters, and microclimate factor datasets to obtain the subplate microenvironment regulation parameters.

[0054] Specifically, the establishment of representative quadrats in rocky desertification areas requires slope stratification based on the topographic features of karst mountains. Slope position differences refer to the different terrain locations from the mountaintop to the foot of the mountain, including three typical locations: upper slope, middle slope, and lower slope. Each slope position exhibits significant differences in moisture conditions, soil thickness, and degree of rocky desertification. Representative areas are selected at each slope position as quadrats, with each quadrat being a 10m x 10m square area. The coordinates of the four corner points of the quadrat are determined using GPS positioning to ensure the accuracy and reproducibility of the quadrat location.

[0055] The equal-length transects were set up using a standardized layout method. Within each quadrat, three parallel transects were laid out along the direction of the maximum slope. Each transect was 50 meters long, starting at the upper edge of the quadrat and ending at the lower edge, with uniform spacing between them. A detection point was set every 1 meter along the transect direction. A standardized probe, a steel-tipped tool, was used to vertically penetrate the ground surface to detect bare rock. The penetration depth was 10 centimeters, and the insertion angle was kept perpendicular to the ground surface. During the detection process, whether the probe contacted hard, exposed bedrock was recorded. Contact with bedrock was recorded as a positive value, while contact with soil or vegetation roots was recorded as a negative value.

[0056] The numerical processing for bare rock patch identification and marking employs a continuity judgment algorithm. When adjacent detection points all hit exposed bedrock twice or more consecutively, the area is marked as a bare rock patch. The continuity judgment criterion is that there is no discontinuity in soil cover between adjacent detection points, forming a continuous exposed bare rock zone. In the numerical marking process, detection point locations that meet the continuity condition are marked with a value of 1, indicating the presence of bare rock patches; locations that do not meet the condition are marked with a value of 0, indicating the presence of soil or vegetation cover. The marking process needs to consider the spatial relationship of the detection points to ensure that the marking results reflect the true distribution pattern of bare rock.

[0057] The area ratio calculation employs a length statistical method. Each consecutive detection point marked as 1 on a transect forms a bare patch unit. The length of a single bare patch is equal to the number of consecutive detection points marked as 1 multiplied by the detection interval of 1 meter, plus one detection interval as a bare patch boundary correction value. The lengths of all bare patches on the transect are summed to obtain the total bare patch length of the transect. Then, the total bare patch length is divided by the total transect length of 50 meters to calculate the bare rock coverage rate of the transect. The bare rock coverage rates of the three transects are then arithmetically averaged to obtain the average bare rock coverage rate of the sample plot as the final calculation result.

[0058] The grading process strictly follows the quantitative classification standards established in the "Technical Regulations for Monitoring Rocky Desertification in Karst Areas of Southwest China." This standard classifies the degree of rocky desertification into three levels based on the bare rock coverage threshold. When the average bare rock coverage of a sample plot is less than 30%, it is classified as mild rocky desertification, assigned level code 1; when the coverage is between 30% and 60%, it is classified as moderate rocky desertification, assigned level code 2; and when the coverage is greater than 60%, it is classified as severe rocky desertification, assigned level code 3. The level codes, combined with the sample plot coordinates, form rocky desertification intensity grading data. This data includes three key pieces of information: spatial location, rocky desertification intensity level, and quantitative coverage value.

[0059] In one specific embodiment, the process of performing step S3 may specifically include the following steps:

[0060] The location of the water collection trough device at the lower edge of the photovoltaic panel is determined based on the microenvironment control parameters under the panel, and the spatial coordinates of the water collection trough are obtained.

[0061] A hydrophobic guiding water collection surface is obtained by multi-layer coating modification of the water collection tank device with superhydrophobic surface material.

[0062] By geometrically coupling the gradient tilt angle design parameters with the hydrophobic guide water collection surface, a distributed water collection network unit is obtained.

[0063] The rainfall collection volume is continuously monitored and collected using a water collection tank with multiple photovoltaic panels to obtain water collection efficiency data.

[0064] The water collection efficiency data is input into the intelligent water and fertilizer integrated machine control system to perform synergistic optimization calculations for rainy season water storage and dry season irrigation, and the water collection-irrigation synergy index is obtained.

[0065] Specifically, the placement of the rainwater collection trough requires determining the optimal installation coordinates based on the microenvironment control parameters beneath the photovoltaic panels. These parameters include key values ​​such as the height, spacing, and tilt angle of the photovoltaic panels, which directly affect the flow path and collection point of rainwater on the photovoltaic panel surface. The positioning process employs a geometric calculation method, using the lower edge of the photovoltaic panel as the baseline for the collection trough. The lowest point of rainwater convergence is calculated based on the tilt angle of the photovoltaic panels; this location represents the optimal placement coordinates for the collection trough. The spatial coordinates of the collection trough include precise values ​​in three dimensions: the X-axis, Y-axis, and Z-axis. The X-axis represents the position along the length of the photovoltaic panel, the Y-axis represents the horizontal distance perpendicular to the photovoltaic panel, and the Z-axis represents the height relative to the ground.

[0066] The coating modification treatment of superhydrophobic surface materials employs a multi-layer coating process. A superhydrophobic surface refers to a special surface with a water contact angle greater than 150 degrees, exhibiting extremely strong water-repellent properties. The coating modification treatment includes three steps: undercoat treatment, intermediate coating, and surface treatment. The undercoat treatment uses mechanical polishing to increase the surface roughness of the water collection trough. The intermediate coating uses a hydrophobic coating containing nanoparticles for spraying. The surface treatment forms a molecular-level hydrophobic film through chemical vapor deposition. The hydrophobic guiding water collection surface refers to the inner surface of the water collection trough, after modification, which possesses a directional flow guiding function. This surface exhibits gradient hydrophobicity, allowing rainwater to flow rapidly along a predetermined path to the water collection outlet.

[0067] The gradient tilt angle design parameters are coupled with the geometric structure of the drainage and flow-guiding water collection surface using a 3D modeling method. The gradient tilt angle refers to the slope change of the bottom surface of the water collection tank along its length, increasing from the inlet to the outlet. The geometric coupling process uses the gradient tilt angle data as input parameters, and calculates the 3D geometry of the water collection tank using CAD modeling software to determine the tilt angle and surface curvature at each location. A distributed water collection network unit refers to a water collection network formed by multiple water collection tanks arranged in a specific spatial layout. Each unit consists of three parts: a water collection tank, connecting pipes, and a confluence node. Units are connected by pipes to form a complete water collection network.

[0068] Continuous monitoring of rainfall collection volume employs flow meter measurement. Electromagnetic flow meters are installed at the inlet of each collection tank to monitor the water flow entering the tank in real time. Multiple photovoltaic panel configurations refer to a layout of 10 photovoltaic panels per collection tank, with each tank having a standard volume of 3 meters long, 2 meters wide, and 2 meters deep. The monitoring process records the hourly inflow rate and calculates the collection efficiency by combining it with rainfall intensity data. The collection efficiency is calculated as the ratio of actual collected water volume to the theoretical total rainfall. Continuous monitoring covers the entire rainy season to obtain the variation patterns of collection efficiency under different rainfall conditions.

[0069] The intelligent water and fertilizer integrated machine control system employs a dynamic scheduling algorithm for collaborative optimization calculations. It uses water collection efficiency data as input variables, combining it with soil moisture sensor data and weather forecast information for comprehensive analysis. In the rainy season water storage mode, the system predicts the water storage trend in the collection tank based on water collection efficiency data. When the water storage reaches a set threshold, it initiates diversion or overflow control. In the dry season irrigation mode, it calculates irrigation demand based on vegetation water requirements and soil moisture data, and formulates an irrigation plan based on the water storage tank's capacity. The collaborative optimization calculation matches the rainy season water storage with the dry season irrigation demand, calculating water resource utilization efficiency and time allocation ratio. The water collection-irrigation synergy index is equal to the ratio of effective irrigation water volume to total collected water volume.

[0070] In one specific embodiment, the process of performing step S4 may specifically include the following steps:

[0071] Based on the rocky desertification intensity classification data, native plants and high-quality forage grasses were selected for various configuration pattern experiments and layouts.

[0072] In the experimental plot, plant species composition, density, plant height, canopy cover, and biomass indicators were collected regularly to obtain a vegetation restoration index dataset.

[0073] The membership function calculation formula is used to standardize each indicator in the vegetation restoration index dataset to obtain the individual membership degree value.

[0074] The weighted average of the individual membership values ​​is used to obtain the comprehensive membership evaluation value.

[0075] An ecological restoration effect evaluation index was obtained by coupling analysis and processing of rocky desertification intensity classification data and comprehensive membership evaluation value.

[0076] Specifically, the plant selection and configuration pattern experimental layout were differentiated based on the rocky desertification intensity grading data. This data included spatial distribution information for three levels: mild, moderate, and severe, each corresponding to different plant adaptability requirements. Native plants refer to plant species native to the local area and adapted to local climate and soil conditions, including legumes such as *Lotus sibthorpioides*, *Nitraria tangutorum*, and *Indigofera multiflora*. High-quality forage refers to pasture varieties with good nutritional value and palatability, including grasses and legumes such as orchardgrass, alfalfa, sweet clover, and Kentucky bluegrass. Multiple configuration patterns included three basic patterns: monoculture, mixed sowing, and intercropping. Monoculture used a single plant species, mixed sowing used 2-4 plant species, and intercropping used different plants planted alternately in rows or blocks. The experimental layout used a standard 16m × 4m plot as the basic experimental unit, with three replicate plots for each configuration pattern. A 2m wide buffer zone was set between plots to prevent mutual interference.

[0077] Standardized monitoring methods were used for the regular collection of vegetation restoration indicators. Species composition was determined by identifying all plant species within the plot using plant taxonomy methods and recording the number of species. Density was calculated using quadrat counting to count the number of individual plants per unit area. Plant height was measured using measuring tools to record the vertical distance from the ground to the highest point of the plant. Canopy was estimated as the percentage of ground area covered by vegetation using visual inspection or a grid method. Biomass was determined by harvesting and weighing the aboveground parts of the plants. The vegetation restoration indicator dataset contains the measured values ​​of the above five indicators at different time points, with data collection occurring monthly throughout the growing season. The data recording format includes key information such as the collection date, plot number, plant species, indicator values, and environmental conditions, forming a structured data table for subsequent analysis.

[0078] The standardization process for the membership function calculation formula employs numerical normalization, converting indices with different dimensions and numerical ranges into dimensionless values ​​between 0 and 1. The expression for the membership function calculation formula is shown below:

[0079] For positive indicators (plant height, canopy cover, biomass):

[0080]

[0081] For negative indicators:

[0082]

[0083] in, Let be the membership degree value of the j-th indicator in the i-th test area, with a value range of [0,1]. This represents the original measured value of the j-th indicator in the i-th test area; The j-th indicator is the maximum value among all test cells; is the minimum value of the j-th index among all experimental plots; i is the experimental plot number; j is the vegetation restoration index number (1=species composition, 2=density, 3=plant height, 4=coverage, 5=biomass).

[0084] The standardization process first determines the maximum and minimum values ​​for each indicator, then uses a linear transformation formula to convert the original values ​​into membership values. For positive indicators such as plant height, canopy cover, and biomass, the membership value equals the difference between the original value and the minimum value, divided by the difference between the maximum value and the minimum value. For negative indicators, the opposite calculation method is used. Each membership value reflects how close the indicator is to the ideal state; the closer the value is to 1, the better the indicator's performance, and the closer the value is to 0, the worse the indicator's performance.

[0085] The weighted average calculation uses a linear weighting method, summing the membership values ​​of different indicators according to preset weights. The calculation formula is shown below:

[0086]

[0087] Specific weight allocation: The constraints are .

[0088] in, Let be the comprehensive membership evaluation value of the i-th test cell, with a value range of [0,1]. is the weight coefficient of the j-th indicator, reflecting the importance of this indicator in the vegetation restoration evaluation; Let be the membership degree value of the j-th indicator in the i-th test area; The weight of the species composition index is 0.2. The density index weight is 0.15. The weight of the plant height index is 0.2. The weight of the coverage index is 0.25. The biomass index weight is 0.2.

[0089] Weights were assigned based on the importance of each indicator: species composition (0.2), density (0.15), plant height (0.2), canopy cover (0.25), and biomass (0.2), with the sum of all weights equal to 1. The overall membership evaluation value was the sum of the products of each individual membership value and its corresponding weight, comprehensively reflecting the overall status of vegetation restoration. The weighted average calculation considered the contribution of each indicator to the vegetation restoration effect, avoiding the excessive influence of any single indicator on the overall evaluation result.

[0090] The coupling analysis employed correlation analysis to compare and analyze the rocky desertification intensity classification data with the comprehensive membership evaluation value, establishing a quantitative relationship between the two. The rocky desertification intensity classification data served as the background condition variable, while the comprehensive membership evaluation value served as the response variable; the degree of correlation between the two was calculated through correlation analysis. The ecological restoration effect evaluation index is equal to the product of the comprehensive membership evaluation value and the degree of improvement in rocky desertification intensity. The degree of improvement in rocky desertification intensity is quantified by the change in rocky desertification level before and after restoration. The coupling analysis results reflect the adaptability and effectiveness of vegetation restoration measures under different rocky desertification intensities, guiding the optimization and adjustment of plant configuration schemes.

[0091] In one specific embodiment, the process of performing step S5 may specifically include the following steps:

[0092] Based on the water collection-irrigation synergy index, a microenvironment regulation model for edible fungi cultivation under the substrate was constructed using a BP neural network to obtain the suitable environmental parameters for the fungi strains.

[0093] The substrate was prepared by mixing the cellulose components of waste mushroom sticks with the mineral components of engineering waste soil in a multi-gradient volume ratio, resulting in a mushroom residue substrate ratio scheme.

[0094] The substrate formulation of the bacterial residue was modified with microbial agents to obtain a special substrate for ecological restoration.

[0095] Plant seedling growth adaptability tests were conducted based on ecological restoration-specific substrates and microclimate conditions under the board to obtain data on vegetation restoration effects.

[0096] The water collection-irrigation synergy index, the ratio of fungal residue substrate, and the vegetation restoration effect data are input into a BP neural network to perform multi-factor economic benefit coupling calculations, and the results of the circular agriculture benefit assessment are obtained.

[0097] Specifically, the BP neural network used to construct the microenvironment regulation model for under-plate edible fungi cultivation employs a three-layer network structure. The input layer receives the water collection-irrigation synergy index as the main driving variable, which reflects the matching degree between water resource utilization efficiency and irrigation timing. The BP neural network is a multi-layer feedforward neural network based on the backpropagation algorithm, achieving complex nonlinear mapping through hierarchical information processing in the input, hidden, and output layers. During network training, the water collection-irrigation synergy index data is normalized and preprocessed, converting it into standardized values ​​between 0 and 1 as the input layer feature vector. The hidden layer has eight neurons, employing the sigmoid activation function for nonlinear transformation, and establishing the mapping relationship between input and output by adjusting weight and threshold parameters. The optimal range of key environmental factors for the suitable growing environment of the fungi strain, including temperature, humidity, ventilation, and light intensity, is determined by the network output layer, which directly provides the predicted values ​​of these parameters.

[0098] The substrate preparation of waste mushroom substrate and excavated soil adopted a gradient ratio experimental design. The cellulose component of the waste mushroom substrate mainly consists of decomposed lignocellulose and mycelial residues, which has good water retention and air permeability. The mineral component of the excavated soil mainly consists of rock weathering products and clay minerals, which can provide the mineral nutrients required for plant growth. Multiple gradient volume ratios were used, including five ratio schemes: 1:0, 2:1, 1:1, 1:2, and 0:1. Three replicate experimental groups were set up for each ratio scheme for comparative analysis. In the preparation process of the mushroom substrate ratio scheme, the waste mushroom substrate was crushed to a particle size of 2-5 mm, and the excavated soil was screened to remove stones and impurities larger than 10 mm. During the preparation process, the two raw materials were uniformly mixed according to the set volume ratio, and an appropriate amount of water was added to adjust the moisture content to about 60%. The mixture was then composted for 7-10 days for the substrate components to be fully integrated.

[0099] The biochemical activity modification treatment using microbial inoculants employs an inoculation culture method. These inoculants contain a diverse microbial community, including beneficial bacteria, fungi, and actinomycetes, which can promote organic matter decomposition, improve soil structure, and enhance plant disease resistance. During the modification process, the microbial inoculant is inoculated at a ratio of 5 liters per cubic meter of substrate, and mixing is used to ensure uniform distribution within the substrate. The biochemical activity modification reaction is carried out at a temperature of 25-30 degrees Celsius and a humidity of 70-80% for 14-21 days, with mixing every 3 days to ensure sufficient aerobic fermentation. The physicochemical properties of the ecological restoration substrate are tested, including pH value, electrical conductivity, organic matter content, and nitrogen, phosphorus, and potassium nutrient content, to ensure that the substrate properties meet the requirements for plant growth.

[0100] The plant seedling growth adaptability test employed a comparative experimental method, selecting common local flower varieties and native plant seedlings as experimental materials. The experiments were conducted in a special ecological restoration substrate. The microclimate conditions under the photovoltaic panels included diffused light from the shading, relatively stable temperature and humidity, and good wind and ventilation – conditions significantly different from those in open fields. The adaptability test included a control group and a treatment group. The control group was cultivated in ordinary garden soil, while the treatment group was cultivated in the special ecological restoration substrate. The experimental period was three months. Data on vegetation restoration effects included growth indicators such as seedling survival rate, plant height growth, leaf number, and root development. A complete growth dataset was obtained through regular measurement and recording.

[0101] The multi-factor economic benefit coupling calculation employs a multi-input multi-output (MIB) neural network, using the water collection-irrigation synergy index, substrate mix ratio data, and vegetation restoration effect data as input variables for comprehensive analysis. Economic benefit calculation includes multiple components such as substrate production cost, plant cultivation income, and ecosystem service value, quantifying the economic value of circular agriculture through cost-benefit analysis. The network training process utilizes a gradient descent algorithm to optimize weight parameters, with a learning rate set to 0.01 and 1000 training iterations, achieving network convergence by minimizing prediction error. The circular agriculture benefit assessment results are output as a comprehensive benefit index, which comprehensively reflects the synergistic effects of water resource utilization, waste resource recovery, vegetation restoration, and economic benefits.

[0102] In one specific embodiment, the process of constructing a microenvironment regulation model for under-plate edible fungi cultivation using a BP neural network based on the water collection-irrigation synergy index can specifically include the following steps:

[0103] The water collection-irrigation synergy index and soil moisture content data are normalized and preprocessed to obtain the input layer feature vector;

[0104] By setting the number of hidden layer neurons and weight parameters for the input layer feature vectors, the topology of the BP neural network is obtained.

[0105] The backpropagation algorithm is used to iteratively train and optimize the topology of the BP neural network to obtain the converged network weight matrix.

[0106] The environmental requirements for edible fungi growth are input into the converged network weight matrix for forward propagation calculation to obtain the microenvironment prediction output value.

[0107] The predicted microenvironment output values ​​were inversely normalized to obtain the suitable environment parameters for the microbial species.

[0108] Specifically, the normalization preprocessing employs a maximum-minimum standardization method to convert the water harvesting-irrigation synergy index and soil moisture content data into standardized values ​​between 0 and 1. The water harvesting-irrigation synergy index reflects the matching degree between the photovoltaic panel's water harvesting efficiency and the irrigation needs of vegetation, typically ranging from 0.3 to 0.9. Soil moisture content data represents the percentage of water in the soil by its total weight, typically ranging from 8% to 25%. The normalization process first determines the historical maximum and minimum values ​​for each variable, then uses a linear transformation formula to convert the original values ​​into standardized values. The standardized water harvesting-irrigation synergy index and soil moisture content data are combined to form a two-dimensional input layer feature vector. The dimension of the input layer feature vector is fixed at 2, corresponding to the standardized water harvesting-irrigation synergy index and soil moisture content values, respectively. This feature vector serves as the input data for the BP neural network for subsequent processing.

[0109] The BP neural network topology employs a three-layer architecture, comprising an input layer, hidden layers, and an output layer. The input layer has two neurons, corresponding to the dimension of the input feature vector. The hidden layer has six neurons to handle complex nonlinear relationships between input variables. The output layer has four neurons, corresponding to the four suitable environmental parameters for bacterial growth: temperature, humidity, ventilation, and light intensity. Weights are randomly initialized, with values ​​distributed between -0.5 and 0.5. The bias parameter is initially set to 0. The network topology defines the data transmission path and computation method between layers: the input layer receives feature vector data, the hidden layer performs nonlinear transformations, and the output layer generates the prediction result.

[0110] The iterative training optimization of the backpropagation algorithm uses gradient descent to adjust the weight parameters. The training process includes two stages: forward propagation and backpropagation. In the forward propagation stage, the input layer feature vector is passed sequentially through the hidden and output layers for computation. Each neuron undergoes a non-linear transformation using the sigmoid activation function, calculated as the output value equal to 1 divided by 1 plus the negative power of the base of the natural logarithm of the input value. In the backpropagation stage, the error between the predicted and target outputs is calculated. The chain rule is used to calculate the gradient of the error with respect to the weights of each layer, and then the weight parameters are adjusted according to a learning rate of 0.01. The iterative training process repeats the forward and backpropagation calculations until the network error converges to below a preset threshold of 0.001, at which point the converged network weight matrix is ​​obtained.

[0111] The forward propagation calculation of the environmental requirements for edible fungi growth uses a trained network weight matrix for prediction. These environmental requirements include the specific environmental conditions required by different fungal species such as morels, shiitake mushrooms, wood ear mushrooms, and oyster mushrooms. The forward propagation process inputs standardized values ​​of the edible fungi environmental requirements into the network input layer. After weight matrix operations and activation function transformations in the hidden layers, the corresponding microenvironment prediction values ​​are obtained at the output layer. The microenvironment prediction output values ​​are four standardized values, corresponding to the predicted results of optimal temperature, optimal humidity, required ventilation, and light intensity. These values ​​reflect the optimal environmental parameters for edible fungi cultivation under the current water collection-irrigation conditions.

[0112] The inverse normalization process employs the inverse transformation method of normalization to convert the standardized range of the microenvironment prediction output from 0 to 1 back to the actual physical quantity value. The inverse normalization calculation formula is: the actual value equals the standardized value multiplied by the difference between the maximum and minimum values, plus the minimum value. This calculation process restores the true dimensions and numerical range of the prediction results. Specific parameters for the suitable environment for the microbial strain include a temperature range of 18-28 degrees Celsius, a relative humidity range of 70-90%, a ventilation rate range of 0.5-2.0 cubic meters per minute, and a light intensity range of 50-200 lux. These parameters directly guide the cultivation practice of edible fungi in flexible photovoltaic environments in karst mountains.

[0113] The above describes the analysis method for flexible photovoltaic ecological restoration of karst mountains in the embodiments of this application. The following describes the analysis system for flexible photovoltaic ecological restoration of karst mountains in the embodiments of this application. Please refer to [link / reference]. Figure 2 One embodiment of the karst mountain flexible photovoltaic ecological restoration analysis system in this application includes:

[0114] The detection module is used to detect the bare rock ratio in rocky desertification areas using the transect probe method, and obtain rocky desertification intensity classification data.

[0115] The correlation module is used to correlate and analyze the height parameters of flexible photovoltaic panels with microclimate monitoring data to obtain the microenvironment control parameters under the panels;

[0116] The calculation module is used to calculate the water resource efficiency of the water collection tank based on the microenvironment control parameters, and obtain the water collection-irrigation synergy index.

[0117] The evaluation module is used to comprehensively evaluate the rocky desertification intensity classification data and vegetation restoration indicators using the membership function method, and obtain the ecological restoration effect evaluation index.

[0118] The coupling module is used to couple the water collection-irrigation synergy index with the substrate ratio data to obtain the evaluation results of circular agriculture benefits.

[0119] above Figure 2 The flexible photovoltaic ecological restoration analysis system for karst mountains in this embodiment of the invention is described in detail from the perspective of modular functional entities. The flexible photovoltaic ecological restoration analysis equipment for karst mountains in this embodiment of the invention is described in detail from the perspective of hardware processing.

[0120] Reference Figure 3 This invention also provides a flexible photovoltaic ecological restoration analysis device for karst mountains. This device can be a server, and its internal structure can be as follows: Figure 3 As shown, the flexible photovoltaic ecological restoration analysis device for karst mountains includes a processor, memory, display screen, input device, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores the data corresponding to this embodiment. The network interface allows communication with external terminals via a network connection. The computer program is executed by the processor to implement the above-described method.

[0121] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the karst mountain flexible photovoltaic ecological restoration analysis equipment to which the present invention is applied.

[0122] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when the instructions are executed on a computer, cause the computer to perform the steps of the karst mountain flexible photovoltaic ecological restoration analysis method.

[0123] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0124] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a flexible photovoltaic ecological restoration analysis device for karst mountains (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0125] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for analyzing flexible photovoltaic ecological restoration in karst mountains, characterized in that, The method includes: Step S1: Detect the bare rock ratio in the rocky desertification area using the transect probe method to obtain rocky desertification intensity classification data; Step S2: Correlation analysis is performed between the height parameters of the flexible photovoltaic panel and the microclimate monitoring data to obtain the microenvironment control parameters under the panel; Step S3: Calculate the water resource efficiency of the water collection trough based on the microenvironment control parameters to obtain the water collection-irrigation synergy index. This includes: locating the water collection trough device at the lower edge of the photovoltaic panel according to the microenvironment control parameters to obtain the spatial coordinates of the water collection trough; performing multi-layer coating modification treatment on the water collection trough device using superhydrophobic surface materials to obtain a hydrophobic guiding water collection surface; geometrically coupling the gradient tilt angle design parameters with the hydrophobic guiding water collection surface to obtain a distributed water collection network unit; continuously monitoring and collecting rainfall data based on the water collection pools configured with multiple photovoltaic panels to obtain water collection efficiency data; and inputting the water collection efficiency data into the intelligent water and fertilizer integrated machine control system for synergistic optimization calculation of rainy season water storage and dry season irrigation to obtain the water collection-irrigation synergy index. Step S4: The rocky desertification intensity classification data and vegetation restoration indicators are comprehensively evaluated using the membership function method to obtain the ecological restoration effect evaluation index; Step S5: Couple the water collection-irrigation synergy index with the substrate ratio data to obtain the circular agriculture benefit assessment results. This includes: constructing a microenvironment regulation model for under-plate edible fungi cultivation using a BP neural network based on the water collection-irrigation synergy index to obtain suitable environmental parameters for the fungi species. This includes: performing normalization preprocessing on the water collection-irrigation synergy index and soil moisture content data to obtain an input layer feature vector; setting the number of hidden layer neurons and weight parameters on the input layer feature vector to obtain the BP neural network topology; iteratively training and optimizing the BP neural network topology using a backpropagation algorithm to obtain a converged network weight matrix; inputting the edible fungi growth environment requirement parameters into the converged network weight matrix for forward propagation calculation to obtain a microenvironment prediction output value; and performing inverse normalization on the microenvironment prediction output value to obtain the suitable environmental parameters for the fungi species. The cellulose components of waste mushroom substrate and the mineral components of engineering waste soil are mixed in a multi-gradient volume ratio to obtain a substrate ratio scheme for mushroom substrate. The substrate ratio scheme for mushroom substrate is then combined with microbial agents for biochemical activity modification to obtain a special substrate for ecological restoration. Based on the special substrate for ecological restoration and the microclimate conditions under the substrate, a plant seedling growth adaptability test is conducted to obtain vegetation restoration effect data. The water collection-irrigation synergy index, the substrate ratio data for mushroom substrate, and the vegetation restoration effect data are input into a BP neural network for multi-factor economic benefit coupling calculation to obtain the benefit evaluation result of the circular agriculture.

2. The analytical method for flexible photovoltaic ecological restoration of karst mountains according to claim 1, characterized in that, Step S1 includes: Representative quadrats were set up in the rocky desertification area according to the slope difference, and several survey quadrats were set up at each location; Multiple equal-length transects are set up for each quadrat, and probes are vertically inserted at fixed intervals along the transect direction for detection. Numerical labeling was performed on locations where the bare ground was repeatedly hit by probes and where the bare ground surface was continuous between probe points to obtain bare spot identification marks. The area ratio of the bare rock identification marks is accumulated to obtain the bare rock coverage value of the transect; According to the technical regulations for monitoring rocky desertification in karst areas of Southwest China, the bare rock coverage values ​​of the transects are classified into grades to obtain the rocky desertification intensity classification data.

3. The analytical method for flexible photovoltaic ecological restoration of karst mountains according to claim 1, characterized in that, Step S2 includes: In areas with consistent terrain conditions, multiple flexible photovoltaic measurement plots were established, with different combinations of photovoltaic panel height from the ground and panel spacing. The height of the flexible photovoltaic panel is gradually adjusted using an adjustable lifting device to obtain a sequence of height change parameters. The spacing between photovoltaic panels is controlled and adjusted based on a parallel moving track system, and the spacing change sequence parameters are obtained. Handheld weather stations were used to continuously monitor light, temperature, humidity, and wind speed in the area under the panel and between the grid points, in a grid-like manner, to obtain a dataset of microclimate factors. Multiple regression analysis was performed on the height variation sequence parameters, spacing variation sequence parameters, and the microclimate factor dataset to obtain the subplate microenvironment regulation parameters.

4. The analytical method for flexible photovoltaic ecological restoration of karst mountains according to claim 1, characterized in that, Step S4 includes: Based on the aforementioned rocky desertification intensity classification data, native plants and superior forage grasses were selected for various configuration pattern experiments. In the experimental plot, plant species composition, density, plant height, canopy cover, and biomass indicators were collected regularly to obtain a vegetation restoration index dataset. The membership function calculation formula is used to standardize each indicator in the vegetation restoration index dataset to obtain the individual membership degree value. The weighted average of the individual membership values ​​is used to obtain the comprehensive membership evaluation value. The ecological restoration effect evaluation index is obtained by coupling analysis and processing the rocky desertification intensity classification data and the comprehensive membership evaluation value.

5. A flexible photovoltaic ecological restoration analysis system for karst mountains, characterized in that, For implementing the karst mountain flexible photovoltaic ecological restoration analysis method as described in any one of claims 1-4, the karst mountain flexible photovoltaic ecological restoration analysis system comprises: The detection module is used to detect the bare rock ratio in rocky desertification areas using the transect probe method, and obtain rocky desertification intensity classification data. The correlation module is used to correlate and analyze the height parameters of flexible photovoltaic panels with microclimate monitoring data to obtain the microenvironment control parameters under the panels; The calculation module is used to calculate the water resource efficiency of the water collection tank based on the microenvironment control parameters, and obtain the water collection-irrigation synergy index. The evaluation module is used to comprehensively evaluate the rocky desertification intensity classification data and vegetation restoration indicators using the membership function method, and obtain the ecological restoration effect evaluation index. The coupling module is used to couple the water collection-irrigation synergy index with the substrate ratio data to obtain the evaluation results of circular agriculture benefits.

6. A flexible photovoltaic ecological restoration analysis device for karst mountains, characterized in that, The method includes a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the computer program to implement the karst mountain flexible photovoltaic ecological restoration analysis method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is run by the processor, it causes the processor to execute the karst mountain flexible photovoltaic ecological restoration analysis method as described in any one of claims 1 to 4.

Images