Karst mountain flexible photovoltaic ecological restoration analysis method and system

Abstract

The invention relates to the technical field of data analysis, and discloses a karst mountain flexible photovoltaic ecological restoration analysis method and system. The method comprises the following steps: carrying out bare rock rate detection on a stony desertification area through a line transect probe method to obtain stony desertification intensity grading data, and carrying out association analysis on a flexible photovoltaic panel height parameter and microclimate monitoring data to obtain an under-panel microenvironment regulation and control parameter; performing water resource efficiency calculation on the collection amount of the water collection tank according to the microenvironment regulation and control parameters to obtain a water collection-irrigation cooperation index, and performing comprehensive evaluation on stony desertification intensity grading data and a vegetation restoration index through a membership function method to obtain an ecological restoration effect evaluation index. And performing coupling processing on the water collection-irrigation cooperation index and the mushroom dreg matrix ratio data to obtain a circular agricultural benefit evaluation result. The integrated development efficiency of the photovoltaic industry and ecological restoration in the karst mountain stony desertification area and the utilization efficiency of water resources are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data analysis, in particular to a karst mountain flexible photovoltaic ecological restoration analysis method and system. BACKGROUND

[0002] At present, the main method for treating rocky desertification in karst mountainous areas is traditional vegetation restoration technology, including artificial afforestation, forest enclosure and engineering treatment. These technologies can improve the rocky desertification condition to a certain extent. At the same time, photovoltaic power generation technology is widely used in flat and gentle slope areas, which converts solar radiation into electric energy through solar panels, contributing to the development of clean energy. Traditional rocky desertification treatment methods usually combine soil and water conservation engineering and vegetation planting technology to control soil erosion by improving soil conditions and increasing vegetation coverage.

[0003] However, the existing technology has significant shortcomings. Traditional rocky desertification treatment methods rely solely on vegetation restoration, lack economic benefits, and are difficult to form a sustainable treatment model. At the same time, in the complex topographic conditions of karst mountainous areas, land use efficiency is low and water resources utilization is insufficient. Photovoltaic power generation projects have good economic benefits, but when applied in karst mountainous areas, they face problems such as poor topographic adaptability, insufficient ecological impact assessment, and lack of organic combination with ecological restoration. Existing rocky desertification monitoring methods mainly rely on manual investigation and remote sensing monitoring, lacking accurate analysis methods for rocky desertification degree under photovoltaic environment.

[0004] Based on the above analysis, the existing technology cannot solve the key technical problems in the integrated development of photovoltaic construction and rocky desertification treatment. Due to the lack of quantitative analysis methods for the relationship between the microenvironment under photovoltaic panels and vegetation restoration, it is difficult to scientifically determine the optimal photovoltaic system configuration parameters; due to the lack of water resource efficiency evaluation technology based on photovoltaic water collection and rocky desertification characteristics, it is difficult to fully utilize the water collection potential of photovoltaic panels for ecological restoration; due to the lack of system evaluation methods considering rocky desertification degree, vegetation restoration effect and circular agriculture benefit, it is difficult to establish a sustainable "photovoltaic + ecological restoration" integrated development model. SUMMARY

[0005] The present application provides a karst mountain flexible photovoltaic ecological restoration analysis method and system for improving the integrated development efficiency of photovoltaic industry and ecological restoration in rocky desertification areas in karst mountainous areas and water resource utilization efficiency.

[0006] In a first aspect, the present application provides a karst mountain flexible photovoltaic ecological restoration analysis method, which comprises:

[0007] Step S1: detecting the bare rock rate of the rocky desertification area by the line probe method to obtain rocky desertification intensity grading data;

[0008] Step S2: Correlate the flexible photovoltaic panel height parameter with the microclimate monitoring data to obtain the microenvironment regulation parameter under the panel;

[0009] Step S3: Perform water resource efficiency calculation on the water collection amount according to the microenvironment regulation parameter to obtain a water collection-irrigation synergy index;

[0010] Step S4: Perform comprehensive evaluation on the stone desertification intensity grading data and the vegetation restoration index by the membership function method to obtain an ecological restoration effect evaluation index;

[0011] Step S5: Perform coupling processing on the water collection-irrigation synergy index and the mushroom residue substrate ratio data to obtain a circular agriculture benefit evaluation result.

[0012] In a second aspect, the present application provides a karst mountain flexible photovoltaic ecological restoration analysis system, which comprises:

[0013] A detection module is configured to detect the bare rock rate of the stone desertification area by the sample line probe method to obtain stone desertification intensity grading data.

[0014] An association module is configured to correlate the flexible photovoltaic panel height parameter with the microclimate monitoring data to obtain the microenvironment regulation parameter under the panel.

[0015] A calculation module is configured to perform water resource efficiency calculation on the water collection amount according to the microenvironment regulation parameter to obtain a water collection-irrigation synergy index.

[0016] An evaluation module is configured to perform comprehensive evaluation on the stone desertification intensity grading data and the vegetation restoration index by the membership function method to obtain an ecological restoration effect evaluation index.

[0017] A coupling module is configured to perform coupling processing on the water collection-irrigation synergy index and the mushroom residue substrate ratio data to obtain a circular agriculture benefit evaluation result.

[0018] In a third aspect, a karst mountain flexible photovoltaic ecological restoration analysis device is provided, which comprises a memory and at least one processor, and the memory stores instructions; the at least one processor invokes the instructions in the memory to enable the karst mountain flexible photovoltaic ecological restoration analysis device to perform the above-mentioned karst mountain flexible photovoltaic ecological restoration analysis method.

[0019] In a fourth aspect, a computer readable storage medium is provided, which stores instructions, and when the instructions are run on a computer, the computer performs the above-mentioned karst mountain flexible photovoltaic ecological restoration analysis method.

[0020] In the technical solution provided by this application, the present application uses the sample line probe method to detect the bare rock rate in the desertified area and generate desertification intensity classification data, which solves the problem of insufficient accuracy of traditional desertification assessment methods under complex terrain conditions in karst mountains. This method can accurately identify the distribution of bare rocks and quantify the degree of desertification through standardized probe penetration detection and continuity judgment algorithm, providing reliable geological environment basic data for the scientific layout of subsequent flexible photovoltaic systems. The height parameters of the flexible photovoltaic panels are correlated with the microclimate monitoring data to obtain the microenvironment control parameters under the panels, breaking through the technical bottleneck of traditional photovoltaic system design that ignores microenvironment control. The quantitative relationship between photovoltaic panel configuration parameters and microclimate factors is established through multivariate regression analysis, realizing the active control of the ecological environment under the panels by the photovoltaic system. The water resource efficiency of the water collection tank is calculated according to the microenvironment control parameters to obtain the water collection-irrigation synergy index, innovatively converting the photovoltaic panel into a water collection device. Through super-hydrophobic surface modification and gradient diversion design, the water resource utilization efficiency of karst mountains is significantly improved, solving the key problem of seasonal water shortage restricting ecological restoration in desertified areas.

[0021] Using the membership function method, a comprehensive evaluation of desertification intensity classification data and vegetation restoration indicators was conducted to obtain an ecological restoration effect evaluation index. This led to the establishment of a multi-index vegetation restoration evaluation system. The membership function algorithm, through standardization and weighted average calculation, eliminated the impact of dimensional differences between different indicators, improving the objectivity and comparability of the evaluation results and providing a scientific method for the quantitative assessment of desertification control effects. The water collection-irrigation synergy index was coupled with the mushroom residue matrix 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 mountainous areas. Through multi-layer nonlinear mapping and backpropagation optimization, the algorithm was able to handle the complex coupling relationships between multiple factors, such as water collection efficiency, matrix ratio, and vegetation restoration, achieving accurate prediction and optimal configuration of circular agriculture benefits. The entire plan forms a complete technical chain of "desertification assessment - photovoltaic microenvironment regulation - efficient use of water resources - vegetation restoration evaluation - circular agricultural development", providing a systematic solution for the coordinated development of photovoltaic industry and ecological restoration in karst mountainous areas, with significant ecological, economic and social benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1It is an embodiment schematic diagram of the karst mountain flexible photovoltaic ecological restoration analysis method in the embodiment of the application.

[0024] Figure 2 It is an embodiment schematic diagram of the karst mountain flexible photovoltaic ecological restoration analysis system in the embodiment of the application.

[0025] Figure 3 It is a structural schematic diagram of the karst mountain flexible photovoltaic ecological restoration analysis equipment in the embodiment of the application. DETAILED DESCRIPTION

[0026] The embodiment of the application provides a karst mountain flexible photovoltaic ecological restoration analysis method and system. The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the application and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" or "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, product or device.

[0027] For the convenience of understanding, the specific process of the embodiment of the application is described below, please refer to Figure 1 One embodiment of the karst mountain flexible photovoltaic ecological restoration analysis method in the embodiment of the application includes:

[0028] Step S1: detecting the bare rock rate of the rocky desertification area by the sample line probe method to obtain rocky desertification intensity grading data;

[0029] Step S2: associating and analyzing the flexible photovoltaic panel height parameter and the microclimate monitoring data to obtain the microenvironment regulation parameter under the panel;

[0030] Step S3: calculating the water resource efficiency of the water collection tank according to the microenvironment regulation parameter to obtain a water collection-irrigation synergy index;

[0031] Step S4: comprehensively evaluating the rocky desertification intensity grading data and the vegetation restoration index by the membership function method to obtain an ecological restoration effect evaluation index;

[0032] Step S5: coupling the water collection-irrigation synergy index and the compost substrate ratio data to obtain a circular agriculture benefit evaluation result.

[0033] It can be understood that the execution subject of the present application can be a karst mountain flexible photovoltaic ecological restoration analysis system, and can also be a terminal or a server, and the specific implementation is not limited herein. The server is taken as an example for description in the embodiments of the present application.

[0034] Specifically, the sample line probe method is a basic data collection method for rock desertification intensity evaluation. Representative sample plots are set at different slope positions of rock desertification areas, such as on-slope, middle-slope and off-slope. Three 50-meter-long sample lines are arranged in each sample plot, and a probe is vertically inserted every 1 meter along the sample line for detection. When the probe continuously penetrates the exposed ground for 2 times or more and the exposed ground between the probe points is continuous, it is recorded as 1, otherwise it is recorded as 0. The number of times recorded as 1 is added to obtain the single bare spot area ratio, and the bare rock coverage rate value of the sample line is obtained by adding all the bare spot area ratios. According to the “Southwest Karst Region Rock Desertification Monitoring Technical Regulations”, the bare rock coverage rate value is divided into three rock desertification intensity grades, i.e. mild, moderate and severe, to form rock desertification intensity grading data. The flexible photovoltaic panel height parameter and microclimate correlation analysis adopts a multiple regression analysis method. A 16m x 16m measurement plot is established in an area with consistent topographic conditions. The height and spacing of the photovoltaic panel are adjusted by an adjustable lifting device and a parallel moving track system, respectively, to obtain height variation sequence parameters and spacing variation sequence parameters. A handheld weather station is arranged in a grid at the panel and spacing areas to continuously monitor the light intensity, temperature, humidity and wind speed, forming a microclimate factor data set. The multiple regression analysis takes the height parameter and spacing parameter as the independent variable and the microclimate factor as the dependent variable to establish a regression equation to determine the optimal panel microenvironment regulation parameter.

[0035] The water resource efficiency calculation is based on the panel microenvironment regulation parameter to determine the optimal layout position of the water collection tank device. The water collection tank is modified by multi-level coating with super-hydrophobic surface material, and a distributed water collection network unit is formed by designing a gradient inclination angle. The water collection efficiency data is obtained by monitoring the collection amount of the water collection tank under different rainfall intensities. The water collection efficiency data is input into the intelligent water and fertilizer integrated machine control system for collaborative optimization calculation of rainwater storage in the rainy season and irrigation in the dry season, and finally the water collection-irrigation collaborative index is obtained.

[0036] The method of membership function is used for comprehensive evaluation. Firstly, according to the data of rock desertification intensity classification, the appropriate native plants and excellent forage grasses are selected for configuration test. The vegetation restoration indexes such as plant species composition, density, height, coverage and biomass are collected regularly in the test plots. The membership function calculation uses the standardization formula to process each index, converts the index value into the membership degree value between 0 and 1, and then calculates the comprehensive membership evaluation value by weighted average. The data of rock desertification intensity classification and the comprehensive membership evaluation value are coupled to form the evaluation index of ecological restoration effect. The water-collecting and irrigation synergy index is used as the input layer data to train the network weight matrix through the back propagation algorithm, and the edible fungus cultivation microenvironment regulation model is constructed. The cellulose components of waste mushroom sticks and the mineral components of engineering spoil are mixed in different volume ratios to form the mushroom residue matrix matching scheme, which is modified by microbial agents to obtain the ecological restoration special matrix. The water-collecting and irrigation synergy index, mushroom residue matrix matching data and vegetation restoration effect data are input into the BP neural network for multi-factor economic benefit coupling calculation, and the cycle agricultural benefit evaluation result is output.

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

[0038] Representative quadrats are set according to slope position differences in the rock desertification area, and several investigation quadrats are arranged at each place;

[0039] Based on each quadrat, a plurality of equal-length sample lines are set, and a probe is vertically inserted at a fixed interval position along the sample line direction for detection;

[0040] The positions where the probe is continuously inserted into the exposed ground for multiple times and the exposed ground surface is continuous are numerically marked and processed to obtain bare spot identification marks;

[0041] The area proportion of the bare spot identification marks is accumulated to obtain the sample line bare rock coverage value;

[0042] According to the rock desertification monitoring technology regulation in the karst area of southwest China, the sample line bare rock coverage value is graded and processed to obtain the rock desertification intensity classification data.

[0043] Specifically, the quadrat setting in the rock desertification area follows the principle of slope position difference, and representative quadrats are arranged at three different slope positions, i.e. upper slope, middle slope and lower slope. Three 10m x 10m investigation quadrats are set at each slope position to ensure that the quadrats can represent the typical rock desertification characteristics of the slope position. The selection of the quadrats needs to consider the degree of rock exposure, vegetation distribution and soil thickness, and the accurate coordinate position of the quadrat is determined by GPS positioning.

[0044] The standardized layout method is used for each sample plot. Three 50-meter-long sample lines are set in each sample plot, and the direction of the sample line is along the maximum slope direction of the slope surface to ensure that the sample line can fully reflect the distribution characteristics of the rocky desertification of the slope surface. The starting point of the sample line is from the edge of the sample plot, and the end point is extended to the opposite corner of the sample plot. The sample lines are uniformly distributed. A detection point is set every 1 meter along the direction of the sample line. A standard probe is vertically downwardly inserted into the ground surface, and the insertion depth of the probe is 10 cm. Whether the exposed rock surface is contacted during the insertion process is recorded.

[0045] The numerical processing of the bare spot identification mark adopts a binary encoding mode. When the probe continuously penetrates the exposed ground surface for 2 times or more and the exposed ground surface between the detection points is continuously distributed, the position is marked as a value of 1, indicating that there is a bare rock patch. Otherwise, it is marked as a value of 0, indicating that there is soil coverage or vegetation coverage at the position. The continuity judgment standard is that the exposed ground surface between adjacent detection points is not discontinuously distributed, forming a coherent bare rock area. During the numerical marking process, the coordinate position, bare rock exposure degree and surrounding vegetation coverage of each marked point need to be recorded.

[0046] The area proportion cumulative calculation adopts a grid statistical method. The number of detection points marked as 1 on each sample line is counted. When calculating the area proportion of a single bare spot, the number of detection points continuously marked as 1 is added by 1 as the length unit of the bare spot, and then the total bare spot length of the sample line is obtained by adding the length units of all bare spots. The value of the bare rock coverage rate of the sample line is equal to the total bare spot length divided by the total length of the sample line, and the calculation result is expressed in percentage. The bare rock coverage rate values of the three sample lines are arithmetically averaged to obtain the average bare rock coverage rate of the sample plot.

[0047] The grade division processing strictly follows the classification standard in the “Southwest Karst Region Rocky Desertification Monitoring Technical Regulations”. The value of the bare rock coverage rate of the sample line is compared with the standard threshold value to determine the rocky desertification intensity grade. The corresponding code is assigned to each sample plot according to the comparison result. The codes of the light, medium and heavy grades are 1, 2 and 3 respectively, and the rocky desertification intensity grading data is formed.

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

[0049] A plurality of flexible photovoltaic measurement plots are established in a region with consistent topographic conditions, and different combinations of photovoltaic panel height from the ground and panel spacing are set;

[0050] The height of the flexible photovoltaic panel is adjusted by the adjustable lifting device to obtain a height variation sequence parameter;

[0051] The spacing between photovoltaic panels is controlled and adjusted based on the parallel moving track system to obtain spacing variation sequence parameters.

[0052] The handheld weather station is arranged in a grid pattern under the board and in the spacing area to continuously monitor the light, temperature, humidity, and wind speed to obtain a microclimate factor dataset.

[0053] Multivariate regression analysis is performed on the height variation sequence parameters, spacing variation sequence parameters, and microclimate factor dataset to obtain board microenvironment regulation parameters.

[0054] Specifically, the representative quadrat setting in the stone desertification area needs to be stratified according to the slope position of the karst mountain terrain. The slope position difference refers to the different terrain positions of the mountain slope from the top to the foot, including the upper slope, middle slope, and lower slope. The water condition, soil thickness, and stone desertification degree of each slope position differ significantly. A representative area is selected as a quadrat layout point at each slope position. The quadrat specification is a square area of 10 meters x 10 meters. The coordinates of the four corner points of the quadrat are determined by GPS positioning to ensure the accuracy and reproducibility of the quadrat position.

[0055] The standardized layout method is used to set equal-length sample lines. Three parallel sample lines are laid along the maximum slope direction in each quadrat, with a uniform length of 50 meters. The starting point of the sample line is located at the upper edge of the quadrat, and the ending point extends to the lower edge of the quadrat. The sample line spacing is uniformly distributed. A detection point is set every 1 meter along the sample line direction. A standardized probe is used to vertically penetrate the ground surface for bare rock detection. The probe is a steel-tipped tool with a penetration depth of 10 centimeters and a penetration angle perpendicular to the ground surface. During the detection process, it is recorded whether the probe contacts the hard exposed bedrock or not. If it contacts the bedrock, it is recorded as a positive value. If it contacts soil or vegetation roots, it is recorded as a negative value.

[0056] The numerical processing of the bare spot identification marker uses a continuity judgment algorithm. When the adjacent detection points all penetrate the exposed bedrock and the number of consecutive penetrations reaches 2 or more, the area is marked as a bare spot area. The continuity judgment standard is that there is no soil coverage interruption between adjacent detection points, forming a continuous bare rock exposure zone. In the numerical marker processing, the detection point positions that meet the continuity condition are marked as value 1, indicating the existence of bare rock patches. Positions that do not meet the condition are marked as value 0, indicating the existence of soil or vegetation coverage. The marking process needs to consider the spatial position relationship of the detection points to ensure that the marking result reflects the true bare rock distribution pattern.

[0057] The length statistical method is used for area proportion accumulation calculation. A bare spot unit is formed by the continuous detection points marked as 1 on each sample line. The length of a single bare spot is equal to the number of continuous detection points marked as 1 multiplied by the detection interval of 1 meter, plus 1 detection interval as a bare spot boundary correction value. The total bare spot length of the sample line is obtained by accumulating the lengths of all bare spots on the sample line, and then the average bare rock coverage of the sample plot is obtained by dividing the total bare spot length by the total length of the sample line of 50 meters.

[0058] The grade division process strictly follows the quantitative classification standard formulated in the “Southwest Karst Region Stone Desertification Monitoring Technology Regulations”. The standard divides the stone desertification degree into three levels according to the bare rock coverage threshold. When the average bare rock coverage of the sample plot is less than 30%, it is determined to be light stone desertification, and the grade code 1 is assigned; when the coverage is between 30% and 60%, it is determined to be moderate stone desertification, and the grade code 2 is assigned; when the coverage is greater than 60%, it is determined to be severe stone desertification, and the grade code 3 is assigned. The grade code is combined with the sample plot coordinate information to form the stone desertification intensity grading data, which contains three key information: spatial position, stone desertification intensity grade and quantitative coverage value.

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

[0060] According to the micro-environment regulation parameters under the panel, the position of the water collection groove device under the lower edge of the photovoltaic panel is positioned, and the spatial coordinates of the water collection groove are obtained;

[0061] The water collection groove device is modified by multi-level coating with super-hydrophobic surface material to obtain a hydrophobic flow guide water collection surface;

[0062] The gradient inclination angle design parameter is geometrically coupled with the hydrophobic flow guide water collection surface to obtain a distributed water collection network unit;

[0063] Based on the water collection pool configured by multiple groups of photovoltaic panels, the rainfall collection amount is continuously monitored and collected to obtain water collection efficiency data;

[0064] The water collection efficiency data is input into the intelligent water and fertilizer integrated machine control system for collaborative optimization calculation of rainwater storage in the rainy season and irrigation in the dry season to obtain a water collection-irrigation collaboration index.

[0065] Specifically, the positioning of the layout position of the water collecting tank device needs to determine the optimal installation coordinates according to the micro-environment regulation parameters under the panel, including the key values such as the height, spacing and inclination angle of the photovoltaic panel, which directly affect the flow path and collection position of the rainwater on the surface of the photovoltaic panel. The positioning process adopts a geometric calculation method, taking the lower edge boundary of the photovoltaic panel as the reference line of the water collecting tank, and calculating the lowest point position of the rainwater confluence according to the inclination angle of the photovoltaic panel. The position is the optimal layout coordinate of the water collecting tank. The spatial coordinates of the water collecting tank include accurate numerical values of three dimensions of X-axis, Y-axis and Z-axis. The X-axis represents the position along the length direction of the photovoltaic panel, the Y-axis represents the horizontal distance perpendicular to the photovoltaic panel, and the Z-axis represents the height position relative to the ground.

[0066] The coating modification treatment of the super-hydrophobic surface material adopts a multi-layer coating process. The super-hydrophobic surface refers to a special surface with a water contact angle greater than 150 degrees, which has strong water-repellent performance. The coating modification treatment includes three process steps of bottom treatment, intermediate layer coating and surface layer treatment. The bottom treatment adopts mechanical polishing method to increase the roughness of the surface of the water collecting tank. The intermediate layer coating uses a hydrophobic coating containing nanoparticles for spraying. The surface layer treatment forms a molecular-level hydrophobic film by chemical vapor deposition method. The hydrophobic flow-guiding water collecting surface refers to the inner surface of the water collecting tank after modification, which has a directional flow-guiding function. The surface has gradient hydrophobicity, so that the rainwater flows quickly along the preset path to the water collecting outlet.

[0067] The coupling of the gradient inclination angle design parameter and the geometric structure of the hydrophobic flow-guiding water collecting surface adopts a three-dimensional modeling method. The gradient inclination angle refers to the slope change of the bottom surface of the water collecting tank along the length direction, which presents an increasing inclination angle from the water inlet end to the water outlet end. In the geometric structure coupling process, the gradient inclination angle data is taken as the input parameter, and the three-dimensional geometry of the water collecting tank is calculated by CAD modeling software to determine the inclination angle and surface curvature of each position point. The distributed water collecting network unit refers to a water collecting network formed by a plurality of water collecting tanks according to a certain spatial layout. Each unit includes a water collecting tank, a connecting pipeline and a confluence node. The units are connected by pipelines to form a complete water collecting network.

[0068] The continuous monitoring of the rainfall collection amount adopts a flow meter measurement method. An electromagnetic flow meter is installed at the water inlet of each water collecting tank to monitor the water flow entering the water collecting tank in real time. The multi-group photovoltaic panel configuration refers to a layout mode in which one water collecting tank is provided for 10 groups of photovoltaic panels. The volume of each water collecting tank is 3 meters long, 2 meters wide and 2 meters deep according to the standard specification. The monitoring and collection process records the water inflow value every hour, and calculates the water collecting efficiency in combination with the rainfall intensity data. The water collecting efficiency data is equal to the ratio of the actual collected water amount to the theoretical total rainfall amount. The continuous monitoring period covers the entire rainy season, and the variation law of the water collecting efficiency under different rainfall conditions is obtained.

[0069] The collaborative optimization calculation of the intelligent water and fertilizer integrated machine control system uses a dynamic scheduling algorithm, takes the water collection efficiency data as an input variable, and comprehensively analyzes the soil humidity sensor data and weather forecast information. In the rainy season, the water storage mode predicts the water storage trend of the water storage tank according to the water collection efficiency data, and starts the shunt or overflow control when the water storage reaches the set threshold. In the dry season, the irrigation mode calculates the irrigation demand according to the vegetation water demand and soil moisture data, and formulates the irrigation plan combined with the water storage capacity of the water storage tank. The collaborative optimization calculation matches the water storage in the rainy season and the irrigation demand in the dry season, calculates the water resource utilization efficiency and the time distribution ratio, and the collection-irrigation collaborative index is equal to the ratio of the effective irrigation water volume to the total collected water volume.

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

[0071] According to the stone desertification intensity classification data, select native plants and excellent forage grasses to carry out multiple configuration mode test layout;

[0072] In the test plot, collect plant species composition, density, height, coverage, and biomass indicators regularly to obtain a set of vegetation restoration index data;

[0073] Standardize each index in the set of vegetation restoration index data through a membership function calculation formula to obtain a single membership value;

[0074] Calculate the single membership values by weighted average to obtain a comprehensive membership evaluation value;

[0075] Based on the stone desertification intensity classification data and the comprehensive membership evaluation value, perform coupling analysis and processing to obtain an ecological restoration effect evaluation index.

[0076] Specifically, the plant selection and configuration mode test layout is designed differently according to the stone desertification intensity classification data, which contains spatial distribution information of three levels of mild, moderate, and severe stone desertification intensity. Each level corresponds to different plant adaptability requirements. Native plants refer to plant species that are native to the local area and can adapt to local climate and soil conditions, including legume plants such as Lotus japonicus, Forsythia viridissima, and Indigofera. Excellent forage grasses refer to forage grass varieties with good nutritional value and palatability, including Dactylis glomerata, Medicago sativa, Melilotus officinalis, and Poaceae and Leguminous forage grasses. Multiple configuration modes include three basic modes of monoculture, mixed sowing, and intercropping. Monoculture mode uses a single plant species for planting, mixed sowing mode uses 2-4 plants for mixed planting, and intercropping mode uses different plants for planting in rows or blocks alternately. The test layout process uses a 16m x 4m standard plot as the basic test unit, sets up 3 repeated plots for each configuration mode, and sets up a 2m wide buffer zone between plots to prevent mutual interference.

[0077] Vegetation restoration indicators were collected periodically using standardized monitoring methods. Species composition was identified by botanical methods, counting the number of species in each plot. Density was calculated by counting the number of individuals per unit area using quadrat methods. Height was measured from the ground to the highest point of the plant. Coverage was estimated by visual observation or grid methods. Biomass was measured by harvesting and weighing the aboveground dry mass. The vegetation restoration indicator dataset included the values of the five indicators at different time points. Data were collected monthly and monitored throughout the growing season. The data record format included the collection date, plot number, plant species, indicator values, and environmental conditions, forming a structured data table for subsequent analysis.

[0078] The standardization of the membership function calculation formula used numerical normalization to convert indicators with different dimensions and numerical ranges to dimensionless values between 0 and 1. The expression of the membership function calculation formula is as follows:

[0079] For positive indicators (height, coverage, biomass):

[0080]

[0081] For negative indicators:

[0082]

[0083] where, is the membership value of the jth indicator in the ith test plot, with a value range of [0, 1]; is the original measured value of the jth indicator in the ith test plot; is the maximum value of the jth indicator in all test plots; is the minimum value of the jth indicator in all test plots; i is the test plot number; j is the vegetation restoration indicator number (1 = species composition, 2 = density, 3 = height, 4 = coverage, 5 = biomass).

[0084] The standardization process first determines the maximum and minimum values of each indicator, then uses a linear transformation formula to convert the original values to membership values. For positive indicators such as height, coverage, and biomass, the membership value is equal to 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 calculation method is reversed. Single membership values reflect the closeness of each indicator to the ideal state, with values closer to 1 indicating better performance and values closer to 0 indicating worse performance.

[0085] The weighted average calculation adopts a linear weighting method, and the single membership value of different indexes is weighted and summed according to the preset weight. The calculation formula is as follows:

[0086]

[0087] Specific weight distribution: , the constraint condition is .

[0088] Wherein, is the comprehensive membership evaluation value of the ith test plot, the value range is [0, 1]; is the weight coefficient of the jth index, reflecting the importance of the index in the vegetation restoration evaluation; is the single membership value of the jth index of the ith test plot; is the weight of the species composition index (0.2); is the weight of the density index (0.15); is the weight of the plant height index (0.2); is the weight of the coverage index (0.25); is the weight of the biomass index (0.2).

[0089] The weight distribution is set according to the importance of the index. The weight of the species composition is 0.2, the weight of the density is 0.15, the weight of the plant height is 0.2, the weight of the coverage is 0.25, and the weight of the biomass is 0.2. The sum of each weight is equal to 1. The comprehensive membership evaluation value is equal to the cumulative sum of the product of each single membership value and the corresponding weight, which comprehensively reflects the overall situation of vegetation restoration. The weighted average calculation process considers the contribution of each index to the vegetation restoration effect, and avoids the excessive influence of a single index on the comprehensive evaluation result.

[0090] The coupling analysis process adopts the correlation degree analysis method to compare and analyze the stone desertification intensity classification data and the comprehensive membership evaluation value, and establishes the quantitative relationship between the two. The stone desertification intensity classification data is used as the background condition variable, and the comprehensive membership evaluation value is used as the response variable. The correlation analysis is used to calculate the correlation degree of the two. The ecological restoration effect evaluation index is equal to the product of the comprehensive membership evaluation value and the improvement degree of the stone desertification intensity. The improvement degree of the stone desertification intensity is quantified by the change of the stone desertification grade before and after the restoration. The coupling analysis result reflects the adaptability and effectiveness of the vegetation restoration measures under different stone desertification intensity conditions, and guides the optimization and adjustment of the plant configuration scheme.

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

[0092] According to the water-collecting-irrigation coordination index, a plate-under edible fungus cultivation microenvironment regulation model is constructed by a BP neural network to obtain fungus suitable environment parameters;

[0093] The waste mushroom stick cellulose component and the engineering spoil mineral component are subjected to matrix preparation according to multiple gradient volume ratios to obtain a mushroom residue matrix matching scheme;

[0094] The mushroom residue matrix matching scheme is subjected to biochemical activity modification treatment in combination with a microbial agent to obtain an ecological restoration special matrix;

[0095] Plant seedling growth adaptability tests are carried out based on the ecological restoration special matrix and the under-plate microclimate conditions to obtain vegetation restoration effect data;

[0096] The water-collecting-irrigation synergy index, the mushroom residue matrix matching data and the vegetation restoration effect data are input into a BP neural network for multi-factor economic benefit coupling calculation to obtain a circular agriculture benefit evaluation result.

[0097] Specifically, the BP neural network for constructing the under-plate edible mushroom cultivation microenvironment regulation and control model adopts a three-layer network structure, and the input layer receives the water-collecting-irrigation synergy index as the main driving variable, which reflects the matching degree of water resource utilization efficiency and irrigation timing. The BP neural network is a multi-layer feedforward neural network based on the error backpropagation algorithm, and realizes complex nonlinear mapping through hierarchical information processing of the input layer, the hidden layer and the output layer. The network training process carries out normalization preprocessing on the water-collecting-irrigation synergy index data, converts it into standardized numerical values between 0 and 1 as the input layer feature vector. The hidden layer is provided with 8 neuron nodes, and a sigmoid activation function is used for nonlinear transformation to establish the mapping relationship between the input and the output by adjusting the weight parameters and the threshold parameters. The optimal value range of the strain suitable environment parameters including temperature, humidity, ventilation volume, light intensity and other key environmental factors is directly given by the network output layer.

[0098] The matrix preparation of the waste mushroom stick and the engineering spoil adopts gradient matching experimental design. The waste mushroom stick cellulose component mainly includes decomposed wood fiber and mycelium residues, which have good water retention and air permeability. The engineering spoil mineral component mainly includes rock weathering products and clay minerals, which can provide mineral nutrient elements required for plant growth. The multiple gradient volume ratios include 1:0, 2:1, 1:1, 1:2 and 0:1 five matching schemes, and three repeated test groups are set for each matching scheme for comparative analysis. The preparation process of the mushroom residue matrix matching scheme crushes the waste mushroom stick, and the particle size is controlled within 2-5 millimeters. The engineering spoil is subjected to screening treatment to remove stones and impurities larger than 10 millimeters. During the preparation process, the two raw materials are uniformly mixed according to the set volume ratio, an appropriate amount of water is added to adjust the moisture content to about 60%, and the matrix components are fully integrated after stacking and fermentation for 7-10 days.

[0099] The biochemical activity modification treatment of the microbial inoculant adopts inoculation culture method. The microbial inoculant contains various microbial communities such as beneficial bacteria, fungi and actinomycetes, and can promote the decomposition of organic matter, improve soil structure and enhance the disease resistance of plants. During the modification process, the microbial inoculant is inoculated at a ratio of 5 liters per cubic meter of substrate, and the uniform distribution of the inoculant in the substrate is ensured through mixing. The biochemical activity modification reaction is carried out under the conditions of temperature 25-30 degrees Celsius and humidity 70-80%, and the duration is 14-21 days. During this period, the substrate is turned over every 3 days to ensure sufficient aerobic fermentation. The physicochemical property detection of the ecological restoration special substrate includes pH value, electrical conductivity, organic matter content, nitrogen, phosphorus and potassium nutrient content and other indicators to ensure that the substrate properties meet the requirements of plant growth.

[0100] The plant seedling growth adaptability test adopts a comparative test method, selects local common flower varieties and native plant seedlings as test materials, and carries out cultivation test in the ecological restoration special substrate. The microclimate conditions under the board include scattered light environment formed by photovoltaic board shading, relatively stable temperature and humidity conditions and good wind ventilation environment, which are significantly different from the open field environment. The adaptability test sets up a control group and a treatment group. The control group adopts ordinary garden soil cultivation, and the treatment group adopts ecological restoration special substrate cultivation, and the test period is 3 months. The vegetation restoration effect data include growth indexes such as seedling survival rate, plant height increment, leaf number and root development status, and complete growth data set is obtained through regular measurement and recording.

[0101] The multi-factor economic benefit coupling calculation adopts the multi-input and multi-output mode of BP neural network, and takes the catchment-irrigation synergy index, microbial residue substrate ratio data and vegetation restoration effect data as input variables for comprehensive analysis. The economic benefit calculation includes substrate production cost, plant cultivation income, ecological service value and other components, and the economic value of circular agriculture is quantified through cost-benefit analysis method. The network training process adopts gradient descent algorithm to optimize weight parameters, the learning rate is set to 0.01, the training rounds are set to 1000 times, and the network convergence is realized by minimizing the prediction error. The circular agriculture benefit evaluation result is output in the form of comprehensive benefit index, which comprehensively reflects the synergistic effect of water resource utilization, waste resourceization, vegetation restoration and economic benefit.

[0102] In a specific embodiment, the execution step of constructing a photovoltaic board microenvironment regulation model for edible mushroom cultivation under the board through BP neural network according to the catchment-irrigation synergy index can specifically include the following steps:

[0103] The catchment-irrigation synergy index and the soil moisture content data are normalized and pretreated to obtain an input layer feature vector;

[0104] The number of hidden layer neuron nodes and weight parameters are set for the input layer feature vector to obtain a BP neural network topology structure;

[0105] The BP neural network topology structure is iteratively trained and optimized by a back propagation algorithm to obtain a converged network weight matrix;

[0106] The edible fungus growth environment requirement parameters are input into the converged network weight matrix for forward propagation calculation to obtain microenvironment prediction output values;

[0107] The microenvironment prediction output values are subjected to inverse normalization processing to obtain fungus suitable environment parameters.

[0108] Specifically, the normalization preprocessing adopts a maximum and minimum value standardization method to convert the catchment-irrigation synergy index and soil moisture content data into standardized values between 0 and 1. The catchment-irrigation synergy index reflects the matching degree of the photovoltaic panel catchment efficiency and the vegetation irrigation demand, and the numerical range is usually between 0.3 and 0.9. The soil moisture content data represent the percentage of water in the soil to the total weight of the soil, and the numerical range is usually between 8% and 25%. The normalization processing process first determines the historical maximum and minimum values of each variable, and then uses a linear transformation formula to convert the original values into standardized values. The standardized catchment-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 catchment-irrigation synergy index and soil moisture content values, respectively. The feature vector is used as the input data of the BP neural network for subsequent processing.

[0109] The BP neural network topology structure setting adopts a three-layer network architecture, including an input layer, a hidden layer and an output layer. The number of input layer neuron nodes is set to 2, corresponding to the dimension of the input layer feature vector. The number of hidden layer neuron nodes is set to 6, which can handle complex nonlinear relationships between input variables. The number of output layer neuron nodes is set to 4, corresponding to the temperature, humidity, ventilation volume and light intensity four fungus suitable environment parameters. The weight parameters are set by a random initialization method, with weight values randomly distributed between -0.5 and 0.5. The initial value of the bias parameter is set to 0. The network topology structure determines the data transmission path and calculation method between layers. The input layer receives the feature vector data, the hidden layer performs nonlinear transformation processing, and the output layer generates prediction results.

[0110] The iterative training optimization of the back propagation algorithm adopts the gradient descent method to adjust the weight parameters, and the training process includes two stages of forward propagation and back propagation. In the forward propagation stage, the input layer feature vector is calculated through the hidden layer and the output layer in turn, each neuron adopts the sigmoid activation function for nonlinear transformation, and the calculation formula is that the output value is equal to 1 divided by 1 plus the negative input value raised to the power of the natural logarithm base. In the back propagation stage, the error between the predicted output and the target output 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 weights are adjusted according to the learning rate of 0.01. The iterative training process repeatedly performs forward propagation and back propagation calculations until the network error converges to below the preset threshold of 0.001, at which time the converged network weight matrix is obtained.

[0111] The forward propagation calculation of the edible fungus growth environment requirement parameter adopts the trained network weight matrix for prediction, and the edible fungus growth environment requirement parameter includes the specific requirements of different fungi such as Morchella, Lentinula edodes, Auricularia auricular, and Pleurotus ostreatus for environmental conditions. In the forward propagation calculation process, the standardized values of the edible fungus environment requirements are input into the network input layer, and the weight matrix operation and activation function transformation of the hidden layer are performed, and finally the corresponding microenvironment prediction values are obtained in the output layer. The microenvironment prediction output value is four standardized values, which correspond to the prediction results of the optimal temperature, optimal humidity, required ventilation volume and light intensity, respectively. These values reflect the best environment parameters for edible fungus cultivation under the current water collection-irrigation conditions.

[0112] The reverse normalization processing adopts the inverse transformation method of normalization to convert the microenvironment prediction output value from the standardized range of 0 to 1 back to the actual physical quantity value. The reverse normalization calculation formula is that the actual value is equal to the standardized value multiplied by the difference between the maximum value and the minimum value, and then the minimum value is added. This calculation process restores the true dimension and value range of the prediction results. The fungus growth environment parameters include specific values such as temperature range 18-28 degrees Celsius, relative humidity range 70-90%, ventilation volume range 0.5-2.0 cubic meters per minute, and light intensity range 50-200 lux, which directly guide the edible fungus cultivation practice in the karst mountain flexible photovoltaic environment.

[0113] The above describes the karst mountain flexible photovoltaic ecological restoration analysis method in the embodiments of the present application, and the karst mountain flexible photovoltaic ecological restoration analysis system in the embodiments of the present application is described below. Please refer to Figure 2 An embodiment of the karst mountain flexible photovoltaic ecological restoration analysis system in the embodiments of the present application includes:

[0114] The detection module is configured to detect the bare rock rate of the rocky desertification area by the line probe method to obtain the rocky desertification intensity classification data.

[0115] The association module is configured to associate and analyze the flexible photovoltaic panel height parameter and the microclimate monitoring data to obtain a panel-under microenvironment regulation parameter.

[0116] The calculation module is configured to calculate water resource efficiency of the water collection tank collection amount according to the microenvironment regulation parameter to obtain a water collection-irrigation synergy index.

[0117] The evaluation module is configured to comprehensively evaluate the rock desertification intensity grading data and the vegetation restoration index by using a membership function method to obtain an ecological restoration effect evaluation index.

[0118] The coupling module is configured to couple the water collection-irrigation synergy index and the mushroom residue substrate ratio data to obtain a circular agriculture benefit evaluation result.

[0119] The above Figure 2 The karst mountain flexible photovoltaic ecological restoration analysis system in the embodiment of the present application is described in detail from the perspective of a modular functional entity, and the karst mountain flexible photovoltaic ecological restoration analysis device in the embodiment of the present application is described in detail from the perspective of hardware processing.

[0120] Referring to Figure 3 , the embodiment of the present application also provides a karst mountain flexible photovoltaic ecological restoration analysis device, which can be a server, and the internal structure thereof can be as shown in Figure 3 . The karst mountain flexible photovoltaic ecological restoration analysis device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. The processor of the computer is designed to provide calculation and control capabilities. The memory of the karst mountain flexible photovoltaic ecological restoration analysis device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the karst mountain flexible photovoltaic ecological restoration analysis device is used to store the corresponding data in the embodiment. The network interface of the karst mountain flexible photovoltaic ecological restoration analysis device is used to communicate with the external terminal through the network connection. The computer program is executed by the processor to implement the above method.

[0121] Those skilled in the art can understand Figure 3 the structure shown in the embodiment of the present application, which is only a block diagram of part of the structure related to the present application scheme, and does not constitute a limitation on the karst mountain flexible photovoltaic ecological restoration analysis device to which the present application scheme is applied.

[0122] The application further provides a computer readable storage medium, which can be a nonvolatile computer readable storage medium or a volatile computer readable storage medium, and the computer readable storage medium stores instructions, and the instructions make a computer execute the steps of the karst mountain flexible photovoltaic ecological restoration analysis method when the instructions are run on the computer.

[0123] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, system and unit can refer to the corresponding processes in the foregoing method embodiments, and will not be described here.

[0124] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the application or the whole or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for making a karst mountain flexible photovoltaic ecological restoration analysis device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the application. The foregoing storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0125] The above embodiments are only used to illustrate the technical solutions of the application, rather than limit them; although the application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the application.

Claims

1. A karst mountain flexible photovoltaic ecological restoration analysis method, characterized in that: The method comprises: Step S1: Using the transect probe method, the bare rock ratio of the rocky desertification area is detected to obtain rocky desertification intensity classification data; Step S2: Correlation analysis is performed on the flexible photovoltaic panel height parameters and the microclimate monitoring data to obtain the microenvironment control parameters under the panel; Step S3: calculating the water resource efficiency of the water collection tank according to the microenvironment control parameters to obtain a water collection-irrigation synergy index; Step S4: Comprehensively evaluating the rocky desertification intensity classification data and vegetation restoration indicators using a membership function method to obtain an ecological restoration effect evaluation index; Step S5: coupling the water collection-irrigation synergy index with the mushroom residue matrix ratio data to obtain a circular agriculture benefit evaluation result.

2. The karst mountain flexible photovoltaic ecological restoration analysis method according to claim 1 is characterized in that: Step S1 includes: In the rocky desertification area, representative sample plots are set up according to the differences in slope positions, with several survey sample plots arranged in each location; Multiple sample lines of equal length are set up for each sample plot, and probes are vertically inserted into the sample lines at fixed intervals along the sample lines for detection. Numerical marking is performed on the locations where the exposed ground is continuously pierced multiple times and the exposed ground between the probe points is continuous to obtain the bare spot identification mark; Accumulate the area ratio of the bare spot identification marks to obtain the bare rock coverage value of the sample line; According to the technical regulations for monitoring desertification in the karst areas of Southwest China, the bare rock coverage ratio values ​​of the sample lines are graded to obtain the desertification intensity classification data.

3. The karst mountain flexible photovoltaic ecological restoration analysis method according to claim 1 is characterized in that: Step S2 includes: Establish multiple flexible photovoltaic measurement cells in areas with consistent terrain conditions, setting different combinations of photovoltaic panel heights from the ground and panel spacing; The height of the flexible photovoltaic panel is adjusted gradually by an adjustable lifting device to obtain height change sequence parameters; The photovoltaic panel spacing is controlled and adjusted based on the parallel moving track system to obtain the spacing change sequence parameters; Handheld weather stations were distributed in a grid pattern under the boards and in the spacing areas to continuously monitor light, temperature, humidity, and wind speed, and a microclimate factor dataset was obtained. A multiple regression analysis is performed on the height change sequence parameters, the spacing change sequence parameters and the microclimate factor data set to obtain the sub-plate microenvironment control parameters.

4. The karst mountain flexible photovoltaic ecological restoration analysis method according to claim 1 is characterized in that: Step S3 includes: Positioning the water collection tank device at the lower edge of the photovoltaic panel according to the micro-environment control parameters under the panel to obtain the spatial coordinates of the water collection tank; The water collection tank device is subjected to multi-layer coating modification treatment by using a super-hydrophobic surface material to obtain a hydrophobic diversion and water collection surface; The gradient tilt angle design parameter is geometrically coupled with the drainage diversion and water collection surface to obtain a distributed water collection network unit; The water collection pool based on multiple groups of photovoltaic panels continuously monitors and collects rainfall to obtain water collection efficiency data; The water collection efficiency data is input into the intelligent water-fertilizer integrated machine control system to perform coordinated optimization calculation of water storage in the rainy season and irrigation in the dry season to obtain the water collection-irrigation coordination index.

5. The karst mountain flexible photovoltaic ecological restoration analysis method according to claim 1 is characterized in that: Step S4 includes: According to the rocky desertification intensity classification data, native plants and excellent forage grasses are selected to conduct experimental layout of various configuration modes; Plant species composition, density, plant height, cover, and biomass were collected regularly in the experimental plots to obtain a vegetation restoration index dataset; Standardizing each indicator in the vegetation restoration indicator data set using a membership function calculation formula to obtain a single item membership value; Perform weighted average calculation on the individual membership values ​​to obtain a 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.

6. The karst mountain flexible photovoltaic ecological restoration analysis method according to claim 1 is characterized in that: Step S5 includes: According to the water collection-irrigation synergy index, a microenvironment control model for edible fungi cultivation under the plate is constructed through a BP neural network to obtain the suitable environment parameters for the fungi; The cellulose components of the discarded mushroom sticks and the mineral components of the engineering waste soil are prepared into a matrix according to a multi-gradient volume ratio to obtain a mushroom residue matrix ratio scheme; The mushroom residue matrix ratio scheme is combined with microbial agents to perform biochemical activity modification treatment to obtain a matrix specifically for ecological restoration; Conducting plant seedling growth adaptability tests based on the ecological restoration-specific matrix and the microclimate conditions under the slabs to obtain vegetation restoration effect data; The water collection-irrigation synergy index, the mushroom residue matrix ratio data and the vegetation restoration effect data are input into the BP neural network to perform multi-factor economic benefit coupling calculation to obtain the circular agriculture benefit evaluation result.

7. The karst mountain flexible photovoltaic ecological restoration analysis method according to claim 6 is characterized in that: The water collection-irrigation synergy index is used to construct a microenvironment control model for edible fungi cultivation under the plate through a BP neural network to obtain the suitable environment parameters for the fungus species, including: Normalizing and preprocessing the water collection-irrigation synergy index and soil moisture data to obtain an input layer feature vector; Setting the number of hidden layer neuron nodes and weight parameters for the input layer feature vector to obtain a BP neural network topology structure; Performing iterative training and optimization on the BP neural network topology structure by back propagation algorithm to obtain a converged network weight matrix; Inputting the edible fungus growth environment requirement parameters into the converged network weight matrix for forward propagation calculation to obtain a microenvironment prediction output value; The microenvironment prediction output value is subjected to denormalization processing to obtain the suitable environment parameters of the bacterial species.

8. A karst mountain flexible photovoltaic ecological restoration analysis system, characterized in that: Used to implement the karst mountain flexible photovoltaic ecological restoration analysis method according to any one of claims 1 to 7, the karst mountain flexible photovoltaic ecological restoration analysis system comprises: The detection module is used to detect the bare rock ratio in the desertification area through the transect probe method to obtain desertification intensity classification data; The correlation module is used to correlate and analyze the height parameters of the flexible photovoltaic panels with the microclimate monitoring data to obtain the microenvironment control parameters under the panels; a calculation module, configured to calculate the water resource efficiency of the water collection tank based on the microenvironment control parameters to obtain a water collection-irrigation synergy index; An evaluation module is used to comprehensively evaluate the rocky desertification intensity classification data and vegetation restoration indicators through a membership function method to obtain an ecological restoration effect evaluation index; The coupling module is used to couple the water collection-irrigation synergy index with the mushroom residue matrix ratio data to obtain the circular agriculture benefit evaluation result.

9. A karst mountain flexible photovoltaic ecological restoration analysis device, characterized in that: It includes a memory and a processor, the memory stores a computer program that can be run on the processor, and the processor implements the karst mountain flexible photovoltaic ecological restoration analysis method described in any one of claims 1 to 7 when executing the computer program.

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

Images