Ecological environment effect evaluation system for photovoltaic base

Abstract

The invention discloses a photovoltaic base ecological environment effect evaluation system, and relates to the technical field of effect evaluation, the photovoltaic base ecological environment effect evaluation system comprises a data acquisition module, a data processing module, an effect analysis module and a decision management module, and the effect analysis module comprises an ecological sensitive submodule, an environment bearing submodule and an effect synthesis submodule. According to the invention, multiple factors are integrated through the ecological sensitivity sub-module to quantify ecological sensitivity, surface soil crust shear strength is introduced to fill the blank of traditional evaluation, multi-dimensional evaluation is realized, the collaborative level of ecological protection and energy efficiency is quantified through the output result, and the environment bearing sub-module is used to introduce the overground wind direction and underground hydrology, so that the comprehensive evaluation of the ecological protection and energy efficiency is realized. According to the method, the influence of ecological sensitivity and installed capacity can be accurately adjusted to improve the matching degree of photovoltaic development and ecological capacity, calculation results and factors of multiple sub-modules are integrated through the effect integration sub-module, the problem that existing evaluation is inaccurate is solved, and the whole system is based on the artificial intelligence technology and has an excellent intelligent effect.

Description

Technical Field

[0001] The present invention relates to the technical field of effect evaluation, and in particular to an ecological environment effect evaluation system for a photovoltaic base. Background Art

[0002] As the global energy structure transitions to clean energy, the photovoltaic industry, as an important component of renewable energy, is developing rapidly. The scale of photovoltaic base construction in China is expanding year by year. However, large-scale photovoltaic development may cause disturbances to the ecological environment, such as soil erosion, vegetation destruction, and carbon sink loss. In recent years, with the gradual application of artificial intelligence technology in environmental assessment, there is a need for an intelligent assessment system for the ecological and environmental effects of photovoltaic bases.

[0003] Currently, existing photovoltaic base ecological and environmental impact assessment systems are mostly based on the ecological and environmental impact assessment of the already operating photovoltaic power station after its construction, but may lack the ecological and environmental impact assessment of the photovoltaic base before its construction.

[0004] Furthermore, existing assessment systems may rely heavily on static ecological factors, such as the weighted superposition of vegetation coverage or soil pH, to conduct a brief assessment of the ecological and environmental effects of photovoltaic bases. These systems tend to focus on the one-way impact of photovoltaic construction on the ecology, such as vegetation destruction rates, while ignoring some ecological factors, such as surface albedo and the counter-effects of dust deposition on power generation efficiency. Consequently, these systems may fail to provide a basis for collaborative decision-making on optimizing ecological protection measures and improving power generation efficiency.

[0005] Moreover, existing evaluation systems may rely more on manual experience for the preprocessing of multi-source data, lacking a unified algorithm framework combination and normalized and unified parameter processing, which may result in a larger fluctuation range in the evaluation results. Summary of the Invention

[0006] The purpose of the present invention is to provide a photovoltaic base ecological environment effect assessment system to solve the problems raised in the above background technology.

[0007] To achieve the above objectives, the present invention provides a photovoltaic base ecological environment effect assessment system, comprising:

[0008] Data acquisition module: used to collect slope data, biomass data, annual precipitation data, soil organic carbon content, microbial biomass carbon content, topsoil crust shear strength, groundwater depth, annual groundwater level fluctuation range, dominant wind direction angle in the proposed area, sand and dust deposition rate and albedo data at the proposed construction area of ​​the photovoltaic base;

[0009] Data processing module: used to input the data collected by the data acquisition module, remove outliers from the input data, and perform normalized data processing to input the processed data into the effect analysis module;

[0010] Effect analysis module:

[0011] First, a weighted summation of slope data, biomass data, groundwater depth, and annual precipitation data was used to analyze the values ​​of multiple sensitivity factors. The soil carbon sink potential was analyzed by combining soil organic carbon content and microbial biomass carbon content. The shear strength of the topsoil crust was then introduced to generate an ecological sensitivity index.

[0012] Second, based on the installed capacity information of photovoltaic bases in the proposed area and combined with the dominant wind direction angle in the proposed area, the coupling relationship between the inclination angle and wind direction was analyzed. The annual fluctuation amplitude of the groundwater level was then introduced, and the ecological sensitivity index was converted into development potential to generate a dynamic environmental carrying capacity index.

[0013] Third, based on albedo data, we analyze the rate of change of surface albedo by measuring the albedo of photovoltaic-covered and uncovered areas. We also introduce the dust deposition rate to analyze the impact of dust on the efficiency of photovoltaic panels. This is combined with the ecological sensitivity index and the dynamic environmental carrying capacity index to generate a comprehensive effect index.

[0014] Decision-making management module: used to analyze the ecological sensitivity index, dynamic environmental carrying capacity index and comprehensive effect index, and evaluate the ecological sensitivity level, environmental carrying capacity level and effect level, and take corresponding measures based on the level.

[0015] Optionally, the effect analysis module includes an ecological sensitivity submodule, an environmental carrying submodule and an effect synthesis submodule.

[0016] Optionally, the specific processing flow of the ecologically sensitive submodule is as follows:

[0017] S1. Calculate the values ​​of various sensitivity factors using slope data, biomass data, groundwater depth, and annual precipitation data. Standardize the data using the maximum value of each sensitive factor. Then, use the AI-based random forest algorithm to train and determine the weight of each sensitive factor. Fusion is performed using a summation function.

[0018] S2. By combining soil organic carbon content and microbial biomass carbon content, the soil carbon sequestration potential index is evaluated, and the impact of soil carbon sequestration capacity on ecological function restoration is analyzed;

[0019] S3. By introducing the shear strength of the topsoil crust, the ability of the topsoil crust to resist mechanical damage is quantified, and the ecological sensitivity index is finally output.

[0020] Optionally, the specific processing flow of the environment bearing submodule is as follows:

[0021] S1. Analyze the remaining proportion of the proposed photovoltaic base construction capacity to the theoretical maximum capacity in the proposed area by comparing the installed capacity of the proposed photovoltaic base to the theoretical maximum capacity in the proposed area;

[0022] S2. Quantify the matching degree between the tilt angle of the photovoltaic panel and the dominant wind direction of the region through the absolute value of the difference between the dominant wind direction angle of the proposed region and the tilt angle of the photovoltaic panel;

[0023] S3. The impact of groundwater level fluctuations on the stability of the support foundation is quantified by the annual fluctuation amplitude of the groundwater level, and the ecological sensitivity index is converted into development potential to generate a dynamic environmental carrying capacity index.

[0024] Optionally, the specific processing flow of the effect synthesis submodule is as follows:

[0025] S1. Introduce the ecological sensitivity index and dynamic environmental carrying capacity index into the comprehensive submodule of this effect;

[0026] S2. Evaluate the surface albedo change rate by analyzing the surface albedo of the PV-covered area and the albedo of the uncovered area;

[0027] S3. Quantify the impact of dust settling rate on the photovoltaic panel surface on power generation efficiency through dust settling rate, and finally output the comprehensive effect index.

[0028] Optionally, the assessment process of the decision management module based on the ecological sensitivity index is:

[0029] Ecological sensitivity index > 0.7, indicating a highly sensitive area;

[0030] 0.5<ecological sensitivity index≤0.7, indicating a moderately sensitive area;

[0031] Ecological sensitivity index ≤ 0.5, indicating low sensitivity areas;

[0032] When located in a highly sensitive area, the response measures are: prohibiting the construction of photovoltaic bases, prioritizing the demarcation of ecological buffer zones, and planting local sand-fixing vegetation;

[0033] When located in a moderately sensitive area, the response measures are: limiting the scale of photovoltaic base construction;

[0034] When in a low-sensitivity area, the response measures are: build the photovoltaic base normally.

[0035] Optionally, the evaluation process of the decision management module based on the dynamic environmental carrying capacity index is:

[0036] Dynamic environmental bearing capacity index > 0.6, indicating high bearing capacity;

[0037] 0.4<dynamic environmental bearing capacity index≤0.6, indicating medium bearing capacity;

[0038] The dynamic environmental bearing capacity index is less than 0.4, indicating low bearing capacity;

[0039] When the load capacity is high, the response measures are: implementation according to the planned construction scale of the photovoltaic base;

[0040] When the capacity is medium, the response measures are: to reduce the scale of photovoltaic bases by 25%;

[0041] When the bearing capacity is low, the response measure is to replace the photovoltaic frame to avoid the risk of subsidence.

[0042] Optionally, the evaluation process of the decision management module based on the comprehensive effect index is:

[0043] The comprehensive effect index is >0.7, indicating an excellent grade;

[0044] 0.6<comprehensive effect index≤0.7, indicating a medium level;

[0045] The comprehensive effect index is ≤0.6, indicating a low level;

[0046] When it is at the excellent level, the response measures are: implementation according to the planned construction scale of the photovoltaic base;

[0047] When it is at the medium level, the response measures are: to optimize the construction of photovoltaic bases, to optimize albedo and control dust;

[0048] When at a low level, the response measures are: prohibiting the construction of photovoltaic bases.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] 1. The present invention outputs the ecological sensitivity index through the ecological sensitivity submodule. This submodule integrates core influencing factors such as terrain slope, vegetation biomass, soil carbon sequestration potential index, and climate sensitivity factors of annual precipitation variability, based on the integration of multiple factors to comprehensively quantify the ecological sensitivity of the proposed area. Based on the introduction of the shear strength of the topsoil crust, it accurately identifies the risk of damage to the topsoil structure caused by photovoltaic construction in arid areas, thereby filling the gap in traditional assessments of insufficient attention to soil microecology. This system is upgraded from a single ecological impact assessment to a multi-dimensional assessment of ecological vulnerability, environmental carrying capacity and two-way effects, covering the entire life cycle of photovoltaic bases, pre-construction site selection, construction optimization and post-operation monitoring environmental management needs. The ecological sensitivity index is used as a comprehensive output to directly quantify the synergy level of ecological protection and energy efficiency, providing planners with operational site optimization, scale adjustment and measure formulation plans, thereby improving the conversion efficiency from assessment to decision-making.

[0051] 2. The present invention outputs a dynamic environmental carrying capacity index through the environmental carrying submodule. This submodule introduces the inclination wind direction coupling coefficient and the groundwater level fluctuation coefficient, and incorporates the design parameters of the photovoltaic construction and the geological and hydrological dynamic factors into the carrying capacity calculation. To a certain extent, it can dynamically adjust the impact of ecological sensitivity and installed capacity according to the protection of the regional ecology. The calculation of the dynamic environmental carrying capacity index can support the dynamic adjustment of the scale of photovoltaic base construction, improve the matching degree between photovoltaic development and ecological capacity, and reduce the risk of project rework.

[0052] 3. The present invention outputs a comprehensive effect index through the effect synthesis sub-module. This sub-module integrates the ecological sensitivity index and the dynamic environmental carrying capacity index with factors related to power generation efficiency such as the surface albedo change rate and the dust deposition rate to construct a quantitative logic for the counter-effect of ecology on efficiency, thereby solving the unidirectional problem of traditional evaluation. The comprehensive effect index can directly support the site selection optimization of photovoltaic bases and the formulation of ecological protection measures based on the user's intuitive evaluation suggestions, thereby improving the ecological and economic benefits of the photovoltaic base throughout its life cycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a flow chart of the method steps of the photovoltaic base ecological environment effect assessment system;

[0054] Figure 2 This is a schematic diagram of the structural composition of the photovoltaic base ecological environment effect assessment system. DETAILED DESCRIPTION

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0056] See also Figure 1 and Figure 2 This implementation provides a photovoltaic base ecological environment effect assessment system, including:

[0057] Data acquisition module: used to collect slope data, biomass data, annual precipitation data, soil organic carbon content, microbial biomass carbon content, topsoil crust shear strength, groundwater depth, annual groundwater level fluctuation range, dominant wind direction angle in the proposed area, sand and dust deposition rate and albedo data at the proposed construction area of ​​the photovoltaic base;

[0058] Data processing module: used to input the data collected by the data acquisition module, remove outliers from the input data, and perform normalized data processing to input the processed data into the effect analysis module;

[0059] Effect analysis module:

[0060] First, a weighted summation of slope data, biomass data, groundwater depth, and annual precipitation data was used to analyze the values ​​of multiple sensitivity factors. The soil carbon sink potential was analyzed by combining soil organic carbon content and microbial biomass carbon content. The shear strength of the topsoil crust was then introduced to generate an ecological sensitivity index.

[0061] Among them, the ecological sensitivity index > 0.7 refers to a highly sensitive area. When in a highly sensitive area, the response measures are: prohibiting the construction of photovoltaic bases, prioritizing the demarcation of ecological buffer zones, and planting local sand-fixing vegetation;

[0062] Among them, 0.5<ecological sensitivity index≤0.7 refers to the medium sensitive area. When in the medium sensitive area, the response measures are: limit the construction scale of photovoltaic bases;

[0063] Among them, the ecological sensitivity index ≤ 0.5 refers to a low-sensitivity area. When in a low-sensitivity area, the response measures are: build a photovoltaic base normally;

[0064] Second, based on the installed capacity information of photovoltaic bases in the proposed area and combined with the dominant wind direction angle in the proposed area, the coupling relationship between the inclination angle and wind direction was analyzed. The annual fluctuation amplitude of the groundwater level was then introduced, and the ecological sensitivity index was converted into development potential to generate a dynamic environmental carrying capacity index.

[0065] Among them, the dynamic environmental carrying capacity index is greater than 0.6, indicating high carrying capacity. When it is at high carrying capacity, the response measures are: implement according to the planned construction scale of the photovoltaic base;

[0066] Among them, 0.4<dynamic environmental carrying capacity index≤0.6 refers to medium carrying capacity. When it is at medium carrying capacity, the response measures are: to reduce the scale of photovoltaic bases by 25%;

[0067] Among them, the dynamic environmental bearing capacity index is less than 0.4, which refers to low bearing capacity. When it is at low bearing capacity, the response measures are: replace the photovoltaic support to avoid the risk of settlement;

[0068] Third, based on albedo data, we analyze the rate of change of surface albedo by measuring the albedo of photovoltaic-covered and uncovered areas. We also introduce the dust deposition rate to analyze the impact of dust on the efficiency of photovoltaic panels. This is combined with the ecological sensitivity index and the dynamic environmental carrying capacity index to generate a comprehensive effect index.

[0069] Among them, the comprehensive effect index is greater than 0.7, which indicates an excellent level. When it is at the excellent level, the response measures are: implement according to the planned construction scale of the photovoltaic base;

[0070] Among them, 0.6<comprehensive effect index≤0.7 refers to the medium level. When it is at the medium level, the response measures are: to optimize the construction of photovoltaic bases, to optimize albedo and control dust;

[0071] Among them, the comprehensive effect index ≤ 0.6 refers to a low level. When it is at a low level, the response measures are: prohibiting the construction of photovoltaic bases;

[0072] Decision-making management module: used to analyze the ecological sensitivity index, dynamic environmental carrying capacity index and comprehensive effect index, and evaluate the ecological sensitivity level, environmental carrying capacity level and effect level, and take corresponding measures based on the level;

[0073] The effect analysis module includes an ecological sensitivity submodule, an environmental carrying submodule and an effect synthesis submodule.

[0074] It should be noted that this system implements a comprehensive assessment of the ecosystem, from aboveground vegetation to underground soil carbon sinks and topsoil crust, from the inclination angle in engineering design to the groundwater level in the geological environment, from albedo in microclimate factors to the dust factor that attenuates efficiency. Furthermore, this system uses random forests and reinforcement learning in artificial intelligence to optimize parameter weights and balance coefficients, allowing the assessment results to dynamically adjust with regional characteristics, such as geology and climate, to adapt to the construction needs of different scenarios. It not only assesses the ecological disturbance caused by photovoltaics, such as the soil carbon sink potential index (EMD) and the shear strength of the soil crust (EMF), but also evaluates the ecological response to power generation, such as the surface albedo change rate (BVB) and the dust deposition rate (BVC), thereby supporting coordinated decision-making between ecology and energy.

[0075] The calculation of the ecological sensitivity index (EM) introduces the soil carbon sink potential index (EMD). Compared with traditional assessments, this index may ignore the long-term impact of soil carbon sink loss on ecological functions. For example, carbon sink loss leads to increased greenhouse gas emissions. The soil carbon sink potential index (EMD) quantifies this impact by combining organic carbon with microbial biomass carbon, identifying high carbon sink sensitive areas in advance and avoiding the irreversibility of carbon sink loss after construction. By introducing the topsoil crust shear strength (EMF), the topsoil crust in arid areas is a natural anti-erosion barrier. Traditional assessments may only use soil type descriptions, while the topsoil crust shear strength (EMF) uses laboratory shear strength tests to accurately quantify the wind erosion risk after crust destruction. For example, in areas with low crust shear strength, the wind erosion rate may increase to a certain extent after construction.

[0076] The calculation of the dynamic environmental bearing capacity index DQ introduces the inclination angle and wind direction coupling coefficient DQA. Compared with the traditional bearing capacity, which only considers the matching of installed capacity and land area, the inclination angle and wind direction coupling coefficient DQA associates the inclination angle in the design parameters with wind erosion in the environmental disturbance factors. For example, when the angle between the inclination angle and the dominant wind direction is too large, the ground disturbance caused by wind resistance may reduce the bearing capacity, thereby promoting the pre-construction optimization of design and environmental adaptation. By introducing the groundwater level fluctuation coefficient DQD, compared with the traditional assessment, which only focuses on the groundwater level depth, the groundwater level fluctuation coefficient DQD predicts the support foundation settlement risk through the annual fluctuation amplitude. For example, when the fluctuation amplitude is 2m, the groundwater level fluctuation coefficient DQD may be 0.6, thereby limiting the construction scale and avoiding additional repair costs caused by foundation settlement after construction;

[0077] The calculation of the comprehensive effect index (BV) introduces the surface albedo variation (BVB), which changes the surface albedo based on the photovoltaic panels. For example, the grassland albedo is 0.2, and the photovoltaic panel albedo is 0.1. Traditional assessments may ignore the impact of this change on the microclimate. For example, the reduced albedo leads to local warming, accelerated soil evaporation, and inhibited vegetation recovery. The surface albedo variation (BVB) quantifies this feedback and thus predicts the risk of vegetation coverage decline after construction in advance.

[0078] The three sets of formulas in this system implement a full-chain and multi-dimensional ecological and environmental impact assessment before the construction of a photovoltaic base through the progressive logic of sensitivity assessment, carrying capacity adaptation, and comprehensive effect output. Through sensitivity assessment, ecological vulnerabilities in the proposed area can be identified, such as high-carbon sink soils and fragile topsoil crusts, allowing users to determine whether the target area is susceptible to damage due to construction. Through carrying capacity adaptation analysis, combined with sensitivity results and design parameters such as inclination and groundwater level, users can determine the maximum scale of photovoltaic bases that can be built in the target area and how to adjust design parameters to reduce environmental disturbances. Through the comprehensive effect output, the results of the first two steps are integrated to simultaneously assess the impact of photovoltaics on the ecology, such as albedo changes leading to vegetation decline and ecological countermeasures to power generation, such as dust adhesion leading to efficiency degradation, thus allowing users to determine the overall effect of the photovoltaic base after construction.

[0079] This system reflects the effect evaluation as follows:

[0080] Prospective: Traditional assessments may only summarize impacts that have already occurred. However, this system uses three submodules to simulate the causal chain of sensitivity, load, and effect before construction, predicting possible impacts in advance. For example, after construction, the destruction of the topsoil crust will lead to increased wind erosion rate, which in turn will reduce power generation efficiency due to dust adhesion on the panel surface.

[0081] Bidirectionality: The effect synthesis submodule clarifies the mutual influence between photovoltaics and ecology. For example, photovoltaic panels change the albedo and affect vegetation, and vegetation decline exacerbates dust deposition and counteracts power generation efficiency. This breaks through the limitations of traditional assessment of one-way cause and effect.

[0082] Operability: The parameters of the formulas in this submodule are based on monitorable and calculable indicators, such as soil carbon sinks, groundwater level fluctuations, and surface albedo. The evaluation results directly guide site selection adjustments to avoid areas with high ecological sensitivity index EM, design optimization to adjust the inclination to reduce the inclination-wind direction coupling coefficient DQA, and scale control to determine the installed capacity DQC of the proposed photovoltaic base in the proposed area based on the dynamic environmental carrying capacity index DQ, thus realizing a closed loop of evaluation, decision-making, and optimization.

[0083] In this example, see Figures 1 to 2 , the ecologically sensitive submodules are as follows:

[0084] S1. Calculate the values ​​of various sensitivity factors using slope data, biomass data, groundwater depth, and annual precipitation data. Standardize the data using the maximum value of each sensitive factor. Then, use the AI-based random forest algorithm to train and determine the weight of each sensitive factor. Fusion is performed using a summation function.

[0085] S2. By combining soil organic carbon content and microbial biomass carbon content, the soil carbon sequestration potential index is evaluated, and the impact of soil carbon sequestration capacity on ecological function restoration is analyzed;

[0086] S3. By introducing the shear strength of the topsoil crust, the ability of the topsoil crust to resist mechanical damage is quantified, and the ecological sensitivity index is finally output.

[0087] In this example, see Figures 1 to 2 , the calculation formula of the ecological sensitive submodule is as follows:

[0088]

[0089] in:

[0090] EM refers to the ecological sensitivity index;

[0091] n refers to the total number of sensitive factors;

[0092] i refers to the index of the sensitive factor;

[0093] EMA i Refers to the weight of the i-th sensitive factor, which can be determined by training the random forest algorithm of artificial intelligence, with a weight range of 0-1, and Based on the random forest algorithm, the historical data on ecological restoration costs after disturbances caused by photovoltaic projects are input, and the contribution of each factor to the restoration cost is output as the weight;

[0094] EMB i Refers to the sensitivity factor value of category i;

[0095] The following four categories of sensitive factors are selected, covering topography, vegetation, hydrology and climate. The original data can be obtained through remote sensing monitoring, and the maximum and minimum value standardization method is used to normalize each type of sensitive factor;

[0096] 1. Terrain sensitivity factor, expressed in slope, ranges from 0-60°, which is the upper limit of the slope for photovoltaic construction. The calculation formula is as follows;

[0097] EMB1 = actual slope / 60;

[0098] Among them: the steeper the slope, the higher the risk of soil erosion after construction;

[0099] 2. Vegetation sensitivity factor, the unit is biomass t / ha, ranging from 0-300t / ha, which is the maximum biomass of the forest. The calculation formula is as follows;

[0100] EMB2 = actual biomass / 300;

[0101] Among them: the higher the biomass, the denser the vegetation, and the longer the recovery period after disturbance;

[0102] 3. Hydrological sensitivity factor refers to the groundwater depth, with a unit of m and a range of 0-20 m. It indicates that shallow groundwater is susceptible to disturbance. The calculation formula is as follows;

[0103] EMB3 = (1 - actual burial depth / 20);

[0104] Among them: the shallower the groundwater, the higher the risk of water level drop after construction, such as water seepage from the support foundation;

[0105] 4. Climate sensitivity factor refers to the annual precipitation variability, with a unit of %, ranging from 0-50%, indicating that it can reach more than 50% in extreme areas. The calculation formula is as follows;

[0106] EMB4 = actual rate of change / 50;

[0107] Among them: the greater the precipitation variability, the more frequent the fluctuations of drought and flood, and the worse the ecosystem stability;

[0108] EMC refers to the soil carbon sequestration coefficient, which ranges from 0 to 1. It is trained through soil sample test data and reflects the positive correlation between soil carbon sequestration capacity and vegetation restoration. The stronger the carbon sequestration capacity, the larger the soil carbon sequestration coefficient (EMC), and the more significant the impact of carbon sequestration loss on ecological function after disturbance.

[0109] EMD refers to the soil carbon sequestration potential index, which reflects the impact of soil carbon sequestration capacity on ecological function recovery. The stronger the carbon sequestration capacity, the greater the carbon sequestration loss after disturbance. The calculation formula is as follows:

[0110] EMD = (T1 × M1) / (TT1 × MM1);

[0111] Where: T1 refers to soil organic carbon content, M1 refers to microbial biomass carbon content, and the units of the two are normalized to the same range for processing, such as g / kg, TT1 and MM1 refer to the maximum soil organic carbon content and the maximum microbial biomass carbon content in the proposed area, respectively;

[0112] Unlike existing technologies, traditional assessments may ignore the long-term ecological value of soil carbon sequestration. This parameter reveals the potential impact of photovoltaic construction on carbon peak and carbon neutrality goals;

[0113] EME refers to the shear strength coefficient of the soil crust, ranging from 0 to 1. It is measured in the laboratory by the ring knife method and reflects the ability of the topsoil crust, which is formed by fine particles and cementing materials, to resist mechanical damage. The weaker the crust, the greater the shear strength coefficient EME of the topsoil crust.

[0114] EMF refers to the shear strength of the soil crust, with the unit of kPa. It is measured by measuring the destructive strength of the crust under shear force. The higher the shear strength, the greater the EMF of the topsoil crust. The EMF of loose sandy soil crust is 0, and the EMF of dense clay crust is 1. The value is normalized to between 0 and 1.

[0115] Quantify the ability of topsoil crust to resist mechanical damage. The weaker the crust, the higher the risk of soil erosion after construction. Unlike traditional assessments that only focus on aboveground factors such as slope and vegetation, this parameter supplements the coupling of underground and surface factors. For example, topsoil crust in arid areas acts as an ecological barrier.

[0116] (1+EMC×EMD) refers to the amplification factor of the soil carbon sequestration potential index EMD on sensitivity. When the soil carbon sequestration potential index EMD increases, the overall sensitivity is amplified. By amplifying its sensitivity through (1+EMC×EMD), for example, the actual sensitivity of wetlands with high soil carbon sequestration potential index EMD is higher than the result calculated using only traditional factors. This is the coupled sensitivity of underground and surface areas that is not covered by existing technologies.

[0117] (1-EME×EMF) refers to the suppression coefficient of the soil crust shear strength EMF on sensitivity. When the soil crust shear strength EMF increases, the sensitivity is suppressed.

[0118] Topsoil crusts in arid and semi-arid regions are key to curbing wind erosion. For example, if the shear strength of a biocrust is high, it indicates a high EMF. Even if traditional sensitivity factors, such as slope and windy days, are high, the risk of wind erosion after construction disturbance will be weakened by the crust. Therefore, the sensitivity needs to be reduced by (1-EME×EMF). For example, in desert areas with dense crusts, the actual sensitivity is lower than that calculated using traditional factors alone. This is an innovative correction for the disturbance resistance of arid regions, different from traditional assessments that ignore the role of crusts.

[0119] Refers to the weighted summation of sensitive factors such as terrain, vegetation, hydrology, climate, such as slope, biomass, etc., and the weight EMA of the i-th sensitive factor i , reflecting the actual contribution of each factor to the ecological recovery cycle, which is the basis for evaluating ecological sensitivity. By weighted summation, the multi-dimensional discrete sensitivity factors are converted into a single quantitative indicator, which solves the problem of independent analysis of multiple factors and lack of comprehensive conclusions in traditional assessments. Existing technologies may often evaluate slope, vegetation, etc. separately, and cannot directly compare the comprehensive sensitivity of different areas.

[0120] It should be noted that the larger the ecological sensitivity index (EM) value calculated in this submodule, the more sensitive the ecosystem is to disturbances caused by photovoltaic construction. This means that before the construction of the photovoltaic base, the ecosystem in the proposed area is at risk of damage due to construction activities such as land leveling and support installation, as well as the difficulty of recovery after damage. This submodule is the starting point for the subsequent environmental carrying capacity submodule and the comprehensive effect submodule, and determines the calculation logic of the subsequent carrying capacity and comprehensive effect. By quantifying soil carbon sinks and topsoil crust, this submodule converts abstract ecological vulnerability into a calculable indicator, which meets the core requirements of ecological and environmental effect assessment. Based on the ecological sensitivity index (EM), ecological risks can be predicted before the construction of the photovoltaic base, making up for the defect that traditional post-construction assessment cannot avoid damage in advance.

[0121] This submodule introduces the soil carbon sink potential index EMD and the shear strength of topsoil crust EMF. The former quantifies the impact of disturbance on the long-term carbon cycle of the ecosystem from the perspective of soil carbon sequestration function, while traditional assessments may only focus on vegetation destruction and ignore the implicit ecological asset of soil carbon sink. The latter reflects the risk of wind erosion and water erosion after construction in arid and semi-arid areas through the shear strength of topsoil crust. Traditional assessments only use soil types for general descriptions without detailing the crust's anti-destruction ability, and the i-th category sensitivity factor value EMB iBy training historical recovery cycle data with the random forest algorithm, the subjectivity of the traditional AHP method is avoided and the scientific nature of weight distribution is improved. This sub-module extends the assessment of the ecological environment from surface vegetation to underground soil functions, and combines artificial intelligence, that is, in the form of machine learning weight optimization, to achieve accurate quantification of ecological sensitivity. It is an interdisciplinary integration of ecological environment and artificial intelligence. Based on this sub-module, before the construction of the photovoltaic base, the ecological vulnerability of the selected area is assessed through the ecological sensitivity index EM, such as high-carbon sink soil or fragile crust area, to identify sensitive areas that may be difficult to recover after construction in advance, avoiding the passive mode of remediation after traditional construction.

[0122] In this example, see Figures 1 to 2 , the environment bearing submodule is specifically:

[0123] S1. Analyze the remaining proportion of the proposed photovoltaic base construction capacity to the theoretical maximum capacity in the proposed area by comparing the installed capacity of the proposed photovoltaic base to the theoretical maximum capacity in the proposed area;

[0124] S2. Quantify the matching degree between the tilt angle of the photovoltaic panel and the dominant wind direction of the region through the absolute value of the difference between the dominant wind direction angle of the proposed region and the tilt angle of the photovoltaic panel;

[0125] S3. The impact of groundwater level fluctuations on the stability of the support foundation is quantified by the annual fluctuation amplitude of the groundwater level, and the ecological sensitivity index is converted into development potential to generate a dynamic environmental carrying capacity index.

[0126] In this example, see Figures 1 to 2 , the calculation formula of the environmental bearing submodule is as follows:

[0127]

[0128] in:

[0129] DQ refers to the dynamic environmental carrying capacity index;

[0130] The dynamic environmental carrying capacity index (DQ) is a dimensionless value ranging from 0 to 1. The larger the DQ value, the larger the scale of photovoltaic construction that the region can withstand. It indicates the upper limit of the photovoltaic construction scale that the proposed region can bear, taking into account the ecological sensitivity index (EM) and photovoltaic design parameters, inclination angle, and support foundation.

[0131] For pre-construction assessment: DQ predicts the scale, design and environmental adaptability before construction to avoid ecological damage or efficiency loss caused by insufficient carrying capacity after construction;

[0132] DQA refers to the dip-wind direction coupling coefficient, which is 0-1 and is calculated as follows:

[0133] DQA=1-(∣D1-D2∣ / 90°);

[0134] in:

[0135] D1 refers to the tilt angle of the photovoltaic panels, and D2 refers to the dominant wind direction angle in the proposed area;

[0136] The larger the angle between the inclination angle and the wind direction, the stronger the ground disturbance caused by wind resistance, such as dust, and the smaller the inclination-wind direction coupling coefficient DAQ, the lower the carrying capacity. It is used to quantify the degree of matching between the inclination angle of the photovoltaic panel and the dominant wind direction in the area. The smaller the angle, the smaller the ground disturbance caused by wind resistance;

[0137] Different from traditional assessments that only focus on maximizing power generation efficiency, such as assuming the inclination angle is equal to the local latitude, this parameter reveals the trade-off between efficiency and ecology, as excessive inclination angles may exacerbate wind erosion;

[0138] The introduction of the inclination-wind direction coupling coefficient (DQA) is different from existing technologies. Traditional bearing capacity assessments may only consider scale matching, while ignoring the adaptability of inclination design parameters to ambient wind direction. If the angle between the inclination and the prevailing wind direction is too large, that is, the inclination-wind direction coupling coefficient (DQA) is small, wind resistance will aggravate ground disturbances such as dust, resulting in a decrease in actual bearing capacity. For example, when the inclination angle is 30° and the prevailing wind direction is 60°, the inclination-wind direction coupling coefficient (DQA) is 0.7, and the bearing capacity needs to be reduced by 30%. This is an innovation in the dynamic coupling of engineering design and environmental effects.

[0139] DQB refers to the theoretical maximum installed photovoltaic capacity of the proposed area, which is determined by the solar resources, that is, the annual radiation, and the land area, that is, the available area after excluding ecologically sensitive areas. The calculation formula is as follows;

[0140] DQB = land area × installed capacity density per unit area × solar energy resource correction factor;

[0141] in:

[0142] DQC refers to the installed capacity of the proposed PV base in the proposed area;

[0143] DQD refers to the groundwater level fluctuation coefficient, which ranges from 0 to 1 and is calculated as follows;

[0144] DQD=e -k×HS ;

[0145] in:

[0146] HS refers to the annual fluctuation amplitude of groundwater level in the proposed construction area, in m, and k refers to the geological sensitivity parameter, such as k = 0.5 for clay layer and k = 1 for sand layer;

[0147] When the groundwater level fluctuates greatly, the photovoltaic support foundation is prone to settlement. The groundwater level fluctuation coefficient DQD decreases, limiting the construction scale. This parameter is used to quantify the impact of groundwater level fluctuations on the stability of the support foundation. The greater the fluctuation, the higher the risk of foundation settlement.

[0148] Traditional assessments ignore the impact of geological stability on long-term ecology. For example, foundation settlement can cause plate tilt, which in turn leads to soil erosion. This parameter can provide early warning of geological risks.

[0149] The introduction of the groundwater level fluctuation coefficient (DQD) differs from existing technologies. Traditional assessments may ignore the impact of groundwater level fluctuations on support foundation stability. For example, large water level fluctuations in sandy strata can easily lead to settlement. The groundwater level fluctuation coefficient (DQD) converts geological risks into a bearing capacity correction factor. For example, when the water level fluctuates by 2 meters per year and k = 1, the groundwater level fluctuation coefficient (DQD) = 0.135, indicating a significant reduction in bearing capacity. This demonstrates the dynamic correlation between geological stability and engineering safety.

[0150] A1 refers to the weight factor of sensitive factors;

[0151] A2 refers to the capacity factor weight factor;

[0152] A1×(1-EM)×DQA refers to the coupling relationship between ecological sensitivity and design adaptability. 1-EM converts ecological sensitivity (EM) into development potential. The smaller the EM, the higher the development potential. The introduction of 1-EM converts sensitivity into development feasibility, avoiding focusing only on sensitivity while ignoring development value. For example, areas with medium sensitivity may still have high development potential.

[0153] Refers to the coupling of remaining capacity and geological stability, where It indicates the remaining ratio of the planned construction capacity to the theoretical maximum capacity of the proposed area. The larger the value, the higher the remaining capacity and the stronger the carrying capacity.

[0154] It should be noted that this submodule is used to evaluate the effects of photovoltaics on the ecological environment and the impact of the ecological environment on power generation efficiency, and thus has an excellent two-way effect evaluation effect. The ecological sensitivity index EM of this submodule, based on the ecological sensitivity submodule, is the core input of the environmental carrying capacity submodule. 1-EM directly converts ecological sensitivity into development potential, so that the carrying capacity calculation is no longer a simple scale matching, but a comprehensive result of ecological sensitivity, design adaptability and geological stability. If the ecological sensitivity index EM of a region is 0.8, indicating high sensitivity, then 1-EM = 0.2. Even if the theoretical remaining capacity is high, that is, the latter term in this submodule is large, the low potential of the former term in this submodule will still lower the overall dynamic environmental carrying capacity index DQ, avoiding ignoring ecological risks for development;

[0155] This submodule is based on the introduction of the inclination-wind direction coupling coefficient (DQA) and the groundwater level fluctuation coefficient (DQD). It directly links the photovoltaic design parameter inclination with environmental disturbances, such as wind erosion and foundation settlement. For example, the inclination-wind direction coupling coefficient (DQA) quantifies the ground disturbance risk caused by wind resistance through the angle between the inclination and the dominant wind direction. Traditional bearing capacity only considers land area and solar energy resources, and does not consider the indirect impact of design parameters on the environment. The groundwater level fluctuation coefficient (DQD) predicts the support foundation settlement risk through the annual fluctuation amplitude of the groundwater level. This is different from the traditional assessment in existing technologies, which may only focus on the depth of the groundwater level and do not consider the impact of dynamic fluctuations on project stability.

[0156] The sensitive factor weight factor A1 and capacity factor weight factor A2 in this sub-module can be dynamically adjusted through reinforcement learning, and the ecological protection priority and energy demand are input to achieve a dynamic balance between ecological protection and energy development. This sub-module combines artificial intelligence, that is, the reinforcement learning optimization coefficient, with the adaptability of the engineering environment. It is a technical innovation of artificial intelligence plus effect evaluation, which solves the defect of traditional carrying capacity assessment that focuses on resources and neglects design. Based on this sub-module, the dynamic environmental carrying capacity index DQ is used to calculate the maximum tolerable construction scale before the construction of the photovoltaic base, and the influence of design parameters such as inclination angle on the carrying capacity during the construction of the photovoltaic base is clarified, providing a basis for the site selection, design and scale integration decision-making of the photovoltaic base.

[0157] In this example, see Figures 1 to 2 , the effect synthesis submodule is specifically:

[0158] S1. Introduce the ecological sensitivity index and dynamic environmental carrying capacity index into the comprehensive submodule of this effect;

[0159] S2. Evaluate the surface albedo change rate by analyzing the surface albedo of the PV-covered area and the albedo of the uncovered area;

[0160] S3. Quantify the impact of dust settling rate on the photovoltaic panel surface on power generation efficiency through dust settling rate, and finally output the comprehensive effect index.

[0161] In this example, see Figures 1 to 2 , the calculation formula of the effect synthesis submodule is as follows:

[0162] BV=B1×DQ+(1-B1)×[BVA×(1-B2×EM)]×(1-B3×BVB)×(1-B4×BVC);

[0163] in:

[0164] BV refers to the combined effect index;

[0165] BV is a dimensionless value ranging from 0 to 1. The larger the value, the higher the comprehensive benefit of photovoltaic construction. It represents the combined effect of the positive and negative effects of photovoltaics on the ecology and the counter-effect of the ecology on power generation efficiency.

[0166] The comprehensive effect index (BV) directly outputs the conclusion on whether the construction is suitable, and locates the main risk sources through parameter decomposition, such as the surface albedo change rate (BVB) and the dust deposition rate (BVC), such as excessive albedo change or rapid dust deposition.

[0167] If the comprehensive effect index BV is too low, targeted adjustments can be made, such as replacing low-albedo panels to reduce the surface albedo change rate BVB, or increasing the cleaning frequency to reduce the dust deposition rate BVC;

[0168] By integrating the ecological effect B1×DQ and the efficiency effect (1-B1)×[BVA×(1-B2×EM)], a quantitative evaluation of the two-way effect is achieved, which meets the core goal of effect evaluation;

[0169] BV predicts the long-term dynamic relationship of the photovoltaic ecosystem before construction to avoid efficiency degradation caused by ecological counteraction after construction, such as vegetation degradation exacerbating soil erosion and further affecting power generation;

[0170] BVA refers to the theoretical photovoltaic power generation efficiency without ecological interference, which is determined by the panel conversion efficiency and annual sunshine hours.

[0171] BVB refers to the rate of change of surface albedo, 0-1, standardized value. The calculation formula of BVB is as follows:

[0172] BVB=|P1-P2| / P2;

[0173] in:

[0174] P1 refers to the surface albedo of the photovoltaic coverage area;

[0175] P2 refers to the albedo of uncovered area;

[0176] When the albedo changes too much, it will change the local temperature, affect vegetation growth, and indirectly counter the power generation efficiency. The impact of the surface albedo change on the microclimate after the installation of photovoltaic panels is quantified. The greater the albedo change, the higher the local temperature, which inhibits vegetation growth.

[0177] Unlike traditional assessments, which may ignore the indirect ecological impacts of photovoltaic panel albedo, such as changes in local climate and impacts on vegetation recovery, this parameter reveals the chain reaction between photovoltaics, climate, and vegetation;

[0178] BVC refers to the dust deposition rate, the unit is g / m 2Monthly is a standardized value, measured by a sand collector on the board surface. The higher the sedimentation rate, such as in spring in arid areas, the greater the sand and dust sedimentation rate (BVC), the lower the board surface transmittance, and the lower the efficiency;

[0179] Quantify the impact of dust settling rate on the panel surface on power generation efficiency. The faster the settling, the lower the panel surface transmittance and the lower the efficiency.

[0180] Unlike traditional assessments, which may only focus on theoretical values ​​of power generation efficiency, this parameter takes into account the actual situation in arid and semi-arid regions, where dust is the main cause of efficiency degradation, to improve the regional adaptability of the assessment.

[0181] B1 refers to the eco-efficiency trade-off coefficient, which ranges from 0 to 1 and can be adjusted by policy objectives. For example, if ecology is given priority, B1 = 0.8;

[0182] B2 refers to the attenuation coefficient of the ecological sensitivity coefficient to the efficiency, ranging from 0 to 1. It is fitted through historical data. When the ecological sensitivity index EM increases by 0.1, the attenuation coefficient of the ecological sensitivity coefficient to the efficiency is B2×0.1;

[0183] B3 refers to the surface albedo change coefficient, which ranges from 0 to 1. It is trained through satellite remote sensing data and reflects the impact of surface albedo changes on microclimate after photovoltaic panels are installed. The greater the albedo change, the greater the surface albedo change coefficient B3;

[0184] B4 refers to the dust settling rate attenuation coefficient, which ranges from 0 to 1. It is trained through dust monitoring data from meteorological stations and reflects the dust settling rate on the board surface. The faster the rate, the larger the dust settling rate attenuation coefficient B4.

[0185] B1×DQ represents the weighted expression of ecological engineering carrying capacity. By allocating the weight of the eco-efficiency trade-off coefficient B1, policy goals, such as ecological priority or energy priority, are directly mapped to the comprehensive effect assessment. For example, when B1 = 0.8, the comprehensive effect index BV is mainly driven by the dynamic environmental carrying capacity index DQ, which focuses more on ecological sustainability. When B1 = 0.3, the comprehensive effect index BV focuses more on power generation efficiency. This is an innovative point that directly links policy goals and assessment results.

[0186] [BVA×(1-B2×EM)]×(1-B3×BVB)×(1-B4×BVC) refers to the multi-factor attenuation of power generation efficiency;

[0187] (1-B2×EM) is the attenuation of efficiency by ecological sensitivity. The higher the ecological sensitivity index EM, the lower the efficiency.

[0188] (1-B3×BVB) is the attenuation of efficiency due to changes in surface albedo. The greater the albedo change, the more significant the local temperature anomaly, which hinders vegetation growth and indirectly affects the cleanliness of the panel.

[0189] (1-B4×BVC) is the attenuation of efficiency due to dust settling. The higher the settling rate, the lower the panel transmittance.

[0190] This submodule involves the introduction of multiple 1-terms. The multiplication relationship between the multiple terms in this submodule quantifies the cumulative impact of multi-dimensional factors such as ecological sensitivity, albedo change, and dust deposition on power generation efficiency.

[0191] It should be noted that this submodule differs from existing assessment systems. Traditional assessments may only focus on one-way evaluation of post-construction efficiency or ecological impact. The comprehensive effect index (BV) quantifies the counter-effect of ecology on efficiency through multiplication. For example, albedo changes lead to vegetation degradation, which in turn exacerbates dust deposition and ultimately reduces power generation efficiency, forming a two-way feedback loop between ecology and efficiency.

[0192] This submodule uses the Ecological Sensitivity Index (EM) from the Ecological Sensitivity submodule to directly use ecological sensitivity as the core factor of efficiency attenuation, reflecting the causal relationship that the more sensitive the ecology, the more susceptible the power generation efficiency is to interference. For example, soil erosion in highly sensitive areas can cause the support to tilt, the panel to deviate from the sun, and efficiency to decrease. This module also uses the Dynamic Environmental Carrying Capacity Index (DQ) from the Environmental Carrying Capacity submodule to use ecological and engineering carrying capacity as weighted items for the combined effect, ensuring that the assessment results also reflect the purpose of whether construction is feasible.

[0193] This submodule introduces the surface albedo change rate (BVB) and the dust deposition rate (BVC). The former quantifies the impact of surface albedo changes on microclimate after photovoltaic panel installation, such as increased albedo leading to local cooling and inhibiting vegetation growth. The latter reflects the trade-off between photovoltaic efficiency and maintenance costs in arid areas through the dust deposition rate on the panel surface. Traditional assessments only focus on power generation efficiency and do not consider the long-term maintenance needs caused by dust adhesion. This submodule simultaneously assesses the effects of photovoltaics on the ecology, represented by the dynamic environmental carrying capacity index (DQ), and the counter-effect of ecology on power generation, represented by [BVA×(1-B2×EM)]×(1-B3×BVB)×(1-B4×BVC). This breaks through the limitations of traditional assessments of unidirectional causality. This submodule achieves a deep integration of ecological and environmental coordination effect assessments, combined with artificial intelligence, that is, remote sensing data training of albedo and dust parameters, to improve the real-time and accuracy of the assessment.

[0194] Based on this sub-module, the comprehensive effect index BV is used to output the quantitative value of the two-way impact of the photovoltaic ecosystem before construction. For example, after construction, the change in albedo causes the vegetation coverage rate to decrease by 5%, which in turn causes the power generation efficiency to decrease by 3%. This supports the final decision on whether the construction is feasible and how to optimize the design.

[0195] Furthermore, the comprehensive effect index BV is used to influence the soil carbon sequestration correlation coefficient EMC in the ecologically sensitive submodule, and then the influence of the soil carbon sequestration potential index EMD in the ecologically sensitive submodule is adjusted by adjusting the soil carbon sequestration correlation coefficient EMC. This iterative process is in line with the machine learning based on artificial intelligence to automatically adjust the parameters for the purpose of automatic adjustment and automatic convergence, and has excellent intelligent effects. The specific processing process is as follows:

[0196] S1, EMC t+1 =EMC t +α×(BVS-BV t / BVS);

[0197] S2. Set the iterative convergence condition. When any of the following two conditions is met, the iteration is terminated.

[0198] 1: The number of iterations is 50;

[0199] 2: |BVS-BV t |<0.001;

[0200] in:

[0201] EMC t+1 refers to the soil carbon sink correlation coefficient after the t+1th iteration;

[0202] EMC t refers to the soil carbon sink correlation coefficient after the tth iteration;

[0203] BV t Refers to the comprehensive effect index after the tth iteration;

[0204] α refers to the adjustment coefficient, which ranges from 0 to 1 and is used to control the adjustment range of the soil carbon sequestration correlation coefficient EMC in each iteration;

[0205] BVS refers to the ideal value of the comprehensive effect index;

[0206] If BV t <BVS, reflecting insufficient ecological effects, indicating EMC t If it is too small, it means that the carbon sequestration impact is underestimated and the EMC needs to be increased;

[0207] If BV t >BVS, reflecting excessive ecological effects, indicating EMC t If it is too large, it means that the carbon sequestration impact is overestimated and the EMC needs to be reduced;

[0208] It should be noted that the EMC in the ecological sensitivity submodule quantifies the amplifying effect of soil carbon sink potential on ecological sensitivity. The larger the soil carbon sink correlation coefficient EMC, the more significant the impact of carbon sink loss on ecological sensitivity. The core of the effect synthesis submodule is the two-way effect assessment, in which the dynamic environmental carrying capacity index DQ directly depends on the ecological sensitivity index EM, and the soil carbon sink correlation coefficient EMC in the ecological sensitivity index EM determines the weight of carbon sink loss on ecological sensitivity. If the comprehensive effect index BV result shows that the ecological effect is lower than expected, such as the actual carbon sink loss leads to an extension of the ecological recovery period, it is necessary to adjust the soil carbon sink correlation coefficient EMC through the comprehensive effect index BV feedback to make the ecological sensitivity index EM more accurately reflect the real impact of carbon sink on ecological sensitivity.

[0209] This iterative form reversely optimizes the ecological sensitivity index EM through the results of the comprehensive effect index BV, upgrading the assessment from a one-way calculation to a closed-loop iteration, which is closer to the nonlinear response of the actual ecosystem. The soil carbon sink correlation coefficient EMC is dynamically adjusted through the comprehensive effect index BV to avoid reliance on subjective experience. For example, the initial soil carbon sink correlation coefficient EMC = 0.5 may lead to deviations due to regional differences. In high carbon sink areas, such as grasslands, the soil carbon sink correlation coefficient EMC can be increased from 0.5 to 0.8 after iteration, significantly increasing the weight of carbon sink loss on ecological sensitivity and avoiding underestimation of ecological risks.

[0210] Through the iterative optimization of the ecological sensitivity submodule EMC using the comprehensive effect index BV of the effect synthesis submodule, the system realizes a dynamic closed loop of ecological sensitivity, environmental carrying capacity and comprehensive effects, significantly improving the accuracy of pre-construction assessments. The iterative logic is based on the strong correlation between carbon sinks and two-way effects, avoiding deviations in subjective parameter settings, and providing a more scientific decision-making basis for ecological risk prevention and control and efficiency optimization of photovoltaic bases.

[0211] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A photovoltaic base ecological environment effect assessment system, characterized in that: include: Data acquisition module: used to collect slope data, biomass data, annual precipitation data, soil organic carbon content, microbial biomass carbon content, topsoil crust shear strength, groundwater depth, annual groundwater level fluctuation range, dominant wind direction angle in the proposed area, sand and dust deposition rate and albedo data at the proposed construction area of ​​the photovoltaic base; Data processing module: used to input the data collected by the data acquisition module, remove outliers from the input data, and perform normalized data processing to input the processed data into the effect analysis module; Effect analysis module: First, a weighted summation of slope data, biomass data, groundwater depth, and annual precipitation data was used to analyze the values ​​of multiple sensitivity factors. The soil carbon sink potential was analyzed by combining soil organic carbon content and microbial biomass carbon content. The shear strength of the topsoil crust was then introduced to generate an ecological sensitivity index. Second, based on the installed capacity information of photovoltaic bases in the proposed area and combined with the dominant wind direction angle in the proposed area, the coupling relationship between the inclination angle and wind direction was analyzed. The annual fluctuation amplitude of the groundwater level was then introduced, and the ecological sensitivity index was converted into development potential to generate a dynamic environmental carrying capacity index. Third, based on albedo data, we analyze the rate of change of surface albedo by measuring the albedo of photovoltaic-covered and uncovered areas. We also introduce the dust deposition rate to analyze the impact of dust on the efficiency of photovoltaic panels. This is combined with the ecological sensitivity index and the dynamic environmental carrying capacity index to generate a comprehensive effect index. Decision-making management module: used to analyze the ecological sensitivity index, dynamic environmental carrying capacity index and comprehensive effect index, and evaluate the ecological sensitivity level, environmental carrying capacity level and effect level, and take corresponding measures based on the level.

2. The photovoltaic base ecological environment effect assessment system according to claim 1, characterized in that: The effect analysis module includes an ecological sensitivity submodule, an environmental carrying submodule and an effect synthesis submodule.

3. The photovoltaic base ecological environment effect assessment system according to claim 2, characterized in that: The specific processing flow of the ecologically sensitive submodule is as follows: S1. Calculate the values ​​of various sensitivity factors using slope data, biomass data, groundwater depth, and annual precipitation data. Standardize the data using the maximum value of each sensitive factor. Then, use the AI-based random forest algorithm to train and determine the weight of each sensitive factor. Fusion is performed using a summation function. S2. By combining soil organic carbon content and microbial biomass carbon content, the soil carbon sequestration potential index is evaluated, and the impact of soil carbon sequestration capacity on ecological function restoration is analyzed; S3. By introducing the shear strength of the topsoil crust, the ability of the topsoil crust to resist mechanical damage is quantified, and the ecological sensitivity index is finally output.

4. The photovoltaic base ecological environment effect assessment system according to claim 3 is characterized by: The specific processing flow of the environment bearing submodule is as follows: S1. Analyze the remaining proportion of the proposed photovoltaic base construction capacity to the theoretical maximum capacity in the proposed area by comparing the installed capacity of the proposed photovoltaic base to the theoretical maximum capacity in the proposed area; S2. Quantify the matching degree between the tilt angle of the photovoltaic panel and the dominant wind direction of the region through the absolute value of the difference between the dominant wind direction angle of the proposed region and the tilt angle of the photovoltaic panel; S3. The impact of groundwater level fluctuations on the stability of the support foundation is quantified by the annual fluctuation amplitude of the groundwater level, and the ecological sensitivity index is converted into development potential to generate a dynamic environmental carrying capacity index.

5. The photovoltaic base ecological environment effect assessment system according to claim 4 is characterized by: The specific processing flow of the effect synthesis submodule is as follows: S1. Introduce the ecological sensitivity index and dynamic environmental carrying capacity index into the comprehensive submodule of this effect; S2. Evaluate the surface albedo change rate by analyzing the surface albedo of the PV-covered area and the albedo of the uncovered area; S3. Quantify the impact of dust settling rate on the photovoltaic panel surface on power generation efficiency through dust settling rate, and finally output the comprehensive effect index.

6. The photovoltaic base ecological environment effect assessment system according to claim 3 is characterized by: The assessment process of the decision management module based on the ecological sensitivity index is as follows: Ecological sensitivity index > 0.7, indicating a highly sensitive area; 0.5<ecological sensitivity index≤0.7, indicating a moderately sensitive area; Ecological sensitivity index ≤ 0.5, indicating low sensitivity areas; When located in a highly sensitive area, the response measures are: prohibiting the construction of photovoltaic bases, prioritizing the demarcation of ecological buffer zones, and planting local sand-fixing vegetation; When located in a moderately sensitive area, the response measures are: limiting the scale of photovoltaic base construction; When in a low-sensitivity area, the response measures are: build the photovoltaic base normally.

7. The photovoltaic base ecological environment effect assessment system according to claim 4, characterized in that: The evaluation process of the decision management module based on the dynamic environmental carrying capacity index is as follows: Dynamic environmental bearing capacity index > 0.6, indicating high bearing capacity; 0.4<dynamic environmental bearing capacity index≤0.6, indicating medium bearing capacity; The dynamic environmental bearing capacity index is less than 0.4, indicating low bearing capacity; When the load capacity is high, the response measures are: implementation according to the planned construction scale of the photovoltaic base; When the capacity is medium, the response measures are: to reduce the scale of photovoltaic bases by 25%; When the bearing capacity is low, the response measure is to replace the photovoltaic frame to avoid the risk of subsidence.

8. The photovoltaic base ecological environment effect assessment system according to claim 5, characterized in that: The evaluation process of the decision management module based on the comprehensive effect index is as follows: The comprehensive effect index is >0.7, indicating an excellent grade; 0.6<comprehensive effect index≤0.7, indicating a medium level; The comprehensive effect index is ≤0.6, indicating a low level; When it is at the excellent level, the response measures are: implementation according to the planned construction scale of the photovoltaic base; When it is at the medium level, the response measures are: to optimize the construction of photovoltaic bases, to optimize albedo and control dust; When at a low level, the response measures are: prohibiting the construction of photovoltaic bases.

Images