Wetland carbon sequestration capacity improving method based on intelligent regulation and ecological restoration

Abstract

The invention relates to the technical field of wetland ecological restoration. The invention discloses a wetland carbon sink capacity improving method and system based on intelligent regulation and ecological restoration, and the method comprises the steps: laying a multi-parameter sensing network, and monitoring the water level, vegetation growth and soil wetland carbon reserve parameters in real time; obtaining a vegetation NDVI index and surface temperature data, and analyzing the vegetation NDVI index and the surface temperature data to obtain an ecological restoration strategy; according to an ecological restoration strategy, carbon sink dominant plants are combined, and emergent aquatic plants, submerged plants and floating-leaved plants are matched; strengthening the microorganisms, and inoculating a carbon sequestration fungicide; establishing a carbon sink-environmental parameter response model according to the historical intelligent regulation and control data; and inputting the ecological restoration strategy into the carbon sink-environmental parameter response model for analysis, and adjusting ecological restoration data according to an analysis result of the carbon sink-environmental parameter response model. According to the invention, intelligent response to environment change is realized, and the carbon sink efficiency is dynamically optimized.

Description

Technical Field

[0001] This invention relates to the field of wetland ecological restoration technology, and in particular to a method for enhancing wetland carbon sequestration capacity based on intelligent regulation and ecological restoration. Background Technology

[0002] Carbon sequestration capacity refers to the ability of an ecosystem to absorb and store carbon dioxide. Natural ecosystems such as forests, grasslands, and wetlands absorb carbon dioxide from the atmosphere through processes such as photosynthesis and fix it in vegetation and soil, thereby reducing the concentration of greenhouse gases in the atmosphere and playing a vital role in combating global climate change. Wetlands are important carbon sequestration ecosystems with significant carbon storage and fixation capabilities. Protecting and restoring wetlands and other ecosystems can enhance their carbon sequestration capacity.

[0003] However, due to the impact of human activities and climate change, the global wetland area continues to decrease, and its carbon sink function is seriously threatened. The current methods for enhancing the carbon sink capacity of wetlands are conventional protection and restoration measures, which mainly include (1) halting development (prohibiting wetland drainage, landfilling and over-exploitation to prevent the release of carbon pools); (2) restoring wetlands to their original state (restoring wetland hydrological conditions through engineering measures to promote vegetation restoration and carbon accumulation); (3) monitoring and accounting of wetland carbon sinks (carbon sink baseline survey and model prediction); (4) research and development of carbon sequestration technologies (studying the carbon sink regulation mechanism in the process of wetland restoration, such as peatland management and sustainable grazing; optimizing wetland vegetation structure, such as planting high carbon sequestration plants to increase soil organic carbon storage).

[0004] Existing technology 1, Chinese patent, patent number: 202510315909.4, discloses a method and system for carbon sink data analysis in coal mining subsidence areas, relating to the field of carbon sink data processing. It includes: analyzing the carbon sink impact trend based on subsidence characteristic information to obtain carbon sink impact coefficients for soil, vegetation, and water; collecting the main carbon sink characteristic information to conduct auxiliary carbon sink trend impact analysis on the main carbon sink mode, obtaining auxiliary carbon sink impact coefficients; and combining the carbon sink impact coefficients for soil, vegetation, and water to correct the impact on the basic carbon sink parameters of the main carbon sink mode and the two secondary carbon sink modes, obtaining carbon sink parameters for soil, vegetation, and water. This method can solve the technical problem that traditional methods fail to fully consider the special geographical environment of coal mining subsidence areas and the mutual influence between carbon sink modes, resulting in insufficient accuracy and comprehensiveness of carbon sink data analysis. Although it can improve the scientific rigor, accuracy, and comprehensiveness of carbon sink data analysis, achieving the effect of accurately assessing the carbon sink capacity of coal mining subsidence areas under different geographical conditions, it suffers from insufficient market liquidity.

[0005] Prior art two, Chinese patent, patent number: 202510315909.4, discloses a method and system for carbon sink data analysis in coal mining subsidence areas, relating to the field of carbon sink data processing. The method includes: analyzing the carbon sink impact trend based on subsidence characteristic information to obtain carbon sink impact coefficients for soil, vegetation, and water; collecting the main carbon sink characteristic information to conduct auxiliary carbon sink trend impact analysis on the main carbon sink mode, obtaining auxiliary carbon sink impact coefficients; and combining the carbon sink impact coefficients for soil, vegetation, and water to correct the impact on the basic carbon sink parameters of the main carbon sink mode and two secondary carbon sink modes, obtaining carbon sink parameters for soil, vegetation, and water. This invention can solve the technical problem that traditional methods fail to fully consider the special geographical environment of coal mining subsidence areas and the mutual influence between carbon sink modes, resulting in insufficient accuracy and comprehensiveness in carbon sink data analysis. It can improve the scientific rigor, accuracy, and comprehensiveness of carbon sink data analysis, achieving the effect of accurately assessing the carbon sink capacity of coal mining subsidence areas under different geographical conditions. However, it suffers from an incomplete wetland carbon sink monitoring system.

[0006] Existing technology three, Chinese patent, patent number: 202510096242.3, describes a method for monitoring and measuring carbon sequestration in mangrove vegetation based on UAV and AI technology. This method utilizes UAV AI technology to construct a mangrove identification model based on an improved U-Net model within the PyTorch deep learning framework. This model enables intelligent identification and differentiation of various types of mangrove vegetation and their area and quantity, achieving an accuracy rate of over 90%. Through regular aerial photography monitoring using UAVs, combined with growth parameters measured in the field and variable parameters derived from UAV aerial data, an optimal fitting model is constructed for mangrove tree height and crown width, aboveground biomass, and leaf area per unit area based on UAV aerial surveys. This model accurately calculates the carbon storage and carbon sequestration of mangrove vegetation, providing a comprehensive assessment of the carbon sequestration capacity of mangroves within the monitored area. While this method achieves intelligent, digital, and comprehensive monitoring and assessment of the carbon sequestration capacity of mangrove wetland vegetation, the promotion of carbon sequestration technologies remains insufficient.

[0007] Currently, existing technologies 1, 2, and 3 suffer from problems such as an imperfect wetland carbon sequestration accounting system, insufficient market liquidity, inadequate promotion of carbon sequestration technologies, and an incomplete wetland carbon sequestration monitoring system. To address these issues, this invention provides a method for enhancing wetland carbon sequestration capacity based on intelligent regulation and ecological restoration. Summary of the Invention

[0008] The main objective of this invention is to provide a method for enhancing wetland carbon sequestration capacity based on intelligent regulation and ecological restoration. This addresses the problems in existing wetland restoration methods, which often focus on single technical means, such as vegetation restoration or hydrological regulation, resulting in large fluctuations in carbon sequestration efficiency, a lack of systematicness, intelligence, and sustainability, and difficulty in maximizing carbon sequestration capacity. Furthermore, traditional wetland ecological restoration and carbon sequestration function enhancement are disconnected, and restoration projects do not specifically optimize carbon sequestration pathways. Existing monitoring methods are also lagging behind, making it difficult to provide timely feedback on regulation effects.

[0009] To achieve the above objectives, the present invention provides the following technical solution: A method for enhancing wetland carbon sequestration capacity through intelligent regulation and ecological restoration, the process of which includes the following steps: real-time monitoring of key wetland carbon sequestration indicators through a multi-parameter sensor network, formulating an ecological restoration plan based on NDVI and surface temperature data analysis, and adopting a synergistic restoration strategy of using a golden ratio of superior plants and inoculation with compound carbon-fixing bacteria. A carbon sink-environmental parameter response model is established based on historical intelligent regulation data; ecological restoration strategies are input into the carbon sink-environmental parameter response model for analysis, and ecological restoration data is adjusted based on the analysis results of the carbon sink-environmental parameter response model.

[0010] As a further improvement of the present invention, the process of establishing a carbon sink-environmental parameter response model includes the following steps: Collect historical intelligent remote control data and corresponding carbon sink index data; cover historical intelligent remote control data and corresponding carbon sink index data with different time scales and spatial distributions; The relationship between environmental parameters and carbon sink indicators was fitted, and the linear relationship was transformed into a nonlinear relationship. A carbon sink-environmental parameter response model was constructed by introducing the ratio vegetation index, normalized vegetation index and meteorological variables. The variable combination was optimized and redundant parameters were removed. The carbon sink-environmental parameter response model is calibrated to correct prediction biases; ecological restoration strategies are input into the carbon sink-environmental parameter response model for analysis, and ecological restoration data are adjusted based on the analysis results.

[0011] As a further improvement of the present invention, the process of intelligent remote control data and corresponding carbon sink index data covering different time scales and spatial distributions includes the following steps: By using historical remote control data from mobile phones, covering different time granularities, and integrating spatial data of different resolutions, radiometric positioning and atmospheric correction are performed on the raw data to convert it into the actual reflectance of ground objects; and standardization processing is performed on multi-source data to match time and spatial scales. Vegetation indices and environmental parameters were extracted from remote sensing data; NDVI was calculated using near-infrared and red bands to retrieve biomass; and enhanced vegetation index, land surface temperature, and precipitation carbon sink data were obtained. Land use types are classified according to unified rules, and spatially differentiated carbon storage is calculated by combining vegetation carbon content. Multi-source data are fused to form a spatiotemporal distribution pattern by combining ground-based observation data to verify and calibrate remote sensing results.

[0012] As a further improvement of the present invention, the process of constructing a carbon sink-environmental parameter response model by introducing ratio vegetation index, normalized vegetation index and meteorological variables includes the following steps: The vegetation biomass and coverage were calculated by the ratio of the near-infrared band to the red band; the intensity of vegetation photosynthesis and growth status were calculated by the normalized difference between the near-infrared and red bands. Introduce real-time or historical meteorological data variables to achieve spatiotemporal consistency with vegetation indices; fit the relationship between vegetation indices, meteorological variables, and carbon sink indices to capture the complex interactions between variables. Variables that contribute more than a preset contribution threshold to the explanation of carbon sinks are prioritized for retention; the carbon sink-environmental parameter response model is calibrated based on ground-based measured data; and the parameters of the carbon sink-environmental parameter response model are adjusted based on regional characteristics.

[0013] As a further improvement of the present invention, the process of capturing the complex interactions between vegetation index, meteorological variables and carbon sink index includes the following steps: The relationship between vegetation index, meteorological variables and carbon sink index was fitted. The physiological and ecological processes of photosynthesis and respiration were used to quantify the impact of meteorological changes on vegetation photosynthetic efficiency and to correlate carbon sink dynamics. The index data, meteorological data, and background CO2 flux are input into the carbon sink-environmental parameter response model to capture the nonlinear interaction between variables; vegetation index, light energy utilization rate, and photosynthetically active radiation are analyzed to obtain vegetation productivity. The data of leaf area index and chlorophyll content in vegetation indices were nonlinearly fitted with the interaction of meteorological factors; the fitted data were then subjected to sensitivity analysis to identify the marginal impact of meteorological variables on carbon sinks and to quantify the impact of soil organic carbon on climate factors.

[0014] As a further improvement of the present invention, the process of performing sensitivity analysis on the fitted data includes the following steps: Select a set of baseline meteorological data from historical standard year climate data as the starting point for simulation, input the fitted vegetation index into the carbon sink-environmental parameter response model, and initialize the parameters of the carbon sink-environmental parameter response model. Simulate different climate scenarios by changing one or more meteorological variables while keeping other variables constant; after each change, rerun the carbon sink-environmental parameter response model simulation and calculate the output variables. The output variables include carbon sink index, net ecosystem productivity, and soil organic carbon content; The simulation results under different scenarios are compared to quantify the changes in output variables; the marginal impact is calculated, the soil organic carbon response is quantified, and the sensitivity index is calculated; by quantifying the changes in output variables, the meteorological variables with the greatest impact on carbon sinks are identified, and the carbon sink-environmental parameter response model is evaluated.

[0015] As a further improvement of the present invention, the process of calculating the output variable includes the following steps: The baseline scenario is solidified, and the historical meteorological baseline set is transformed by the response model to generate a baseline output set, which includes carbon sink index, net productivity, and soil carbon value; Directional variable perturbation involves selecting a target meteorological factor and replacing the data sequence of that factor in the historical meteorological baseline set to form a perturbation group; the perturbation group is then transformed by the model to generate a new output set. Response gap extraction: The new output set is compared with the baseline output set item by item to derive the absolute response gap, including the gap values ​​of carbon sink index and soil carbon content; directional perturbation, model transformation and gap extraction are performed iteratively to cover all target factors and accumulate the gap set. Sensitivity spectrum construction, range standardization is performed on the gap set; the gap set is transformed into relative sensitivity using the maximum gap value of each factor as the reference base; Arrange them in descending order of relative sensitivity values ​​to generate a sensitivity spectrum; To verify the coupling effect, the top k most sensitive factors in the sensitivity spectrum were extracted to construct a composite perturbation set. The composite perturbation set was transformed by the model to obtain the output variables, and the comprehensive gap between it and the benchmark output set was derived. The superimposed estimate of the comprehensive gap and the single-factor gap was compared to generate the coupling bias, which was used to evaluate the multi-factor interaction effect.

[0016] As a further improvement to the present invention, the process of evaluating the carbon sink-environmental parameter response model includes the following steps: By fitting curves or response surface analysis, the partial derivatives of meteorological variables with respect to the carbon sink index are determined, and the marginal impact is calculated. By comparing the dynamics of soil organic carbon content under different climatic conditions, the relationship between soil organic carbon and climatic factors is established, and the quantitative soil organic carbon response results are obtained. Sensitivity was eliminated, and meteorological variables were arranged according to their magnitude of influence. The nonlinear interaction method was tested, and the interaction effect between variables was analyzed using the fitted carbon sink-environmental parameter response model. Uncertainty was quantified by considering parameter variations through multiple simulations and calculating the confidence region. A sensitivity report is generated based on the results of excluding sensitivity, nonlinear interaction, and uncertainty quantification, and then the sensitivity report is output.

[0017] As a further improvement of the present invention, it also includes deploying a multi-parameter sensor network to monitor key wetland carbon sink parameters such as water level, vegetation growth, and soil carbon storage in real time; acquiring vegetation NDVI index and surface temperature data; analyzing the vegetation NDVI index and surface temperature data; and deriving ecological restoration strategies. Based on ecological restoration strategies, a combination of carbon sequestration-advantageous plants is used, with an optimal ratio of emergent, submerged, and floating-leaved plants; and microorganisms are enhanced by inoculating with carbon-fixing bacteria.

[0018] To achieve the above objectives, the present invention also provides the following technical solution: A wetland carbon sequestration capacity enhancement system based on intelligent remote control and ecological restoration includes: The intelligent sensing module is used to deploy a multi-parameter sensor network to monitor key wetland carbon sink parameters such as water level, vegetation growth, and soil carbon storage in real time; acquire vegetation NDVI index and surface temperature data, analyze the vegetation NDVI index and surface temperature data, and derive ecological restoration strategies. The ecological restoration module is used to combine carbon sequestration-advantageous plants according to ecological restoration strategies, with a golden ratio of emergent plants, submerged plants, and floating-leaved plants; and to enhance microorganisms by inoculating carbon-fixing bacteria; the carbon-fixing bacteria include nitrogen-fixing bacteria and methanogenic bacteria; The intelligent remote control module is used to establish a carbon sink-environmental parameter response model based on historical intelligent control data; ecological restoration strategies are input into the carbon sink-environmental parameter response model for analysis, and ecological restoration data are adjusted based on the analysis results of the carbon sink-environmental parameter response model.

[0019] This invention utilizes IoT sensors (such as water level, soil carbon flux, and vegetation growth monitoring equipment) and remote sensing technology to achieve high-frequency dynamic monitoring of key wetland carbon sink parameters (CO2 / CH4 flux, soil organic carbon, and vegetation biomass), compensating for the sparse data of traditional manual sampling. Machine learning is used to integrate multi-source data (meteorological, hydrological, etc.) to construct wetland type-specific carbon sink accounting models, reducing human estimation errors. Intelligent systems dynamically adjust restoration measures (such as water level control, vegetation replanting, and introduction of microbial communities) to match optimal restoration schemes for different degraded wetlands (peatlands, salt marshes, etc.). Based on climate change (such as drought and flood), wetland hydrological conditions are automatically adjusted (such as intelligent gate water control) to maintain a high carbon sink state, avoiding the inefficiency of traditional static management. Attached Figure Description

[0020] Figure 1This is a schematic diagram of the steps in an embodiment of the wetland carbon sequestration capacity enhancement method based on remote control and ecological restoration of the present invention. Figure 2 This is a schematic diagram illustrating the steps of an embodiment of the wetland carbon sequestration capacity enhancement method based on remote control and ecological restoration of the present invention. Figure 3 This is a schematic diagram of the steps in an embodiment of the wetland carbon sequestration capacity enhancement method based on remote control and ecological restoration of the present invention, which combines carbon sequestration dominant plants according to an ecological restoration strategy. Figure 4 This is a schematic diagram of the steps involved in establishing a carbon sink-environmental parameter response model in one embodiment of the wetland carbon sequestration capacity enhancement method based on remote control and ecological restoration of the present invention. Figure 5 This is a schematic diagram of a module of an embodiment of the wetland carbon sequestration capacity enhancement system based on remote control and ecological restoration of the present invention. Figure 6 This is a schematic diagram of the module flow of an embodiment of the wetland carbon sequestration capacity enhancement system based on remote control and ecological restoration of the present invention. Figure 7 This is a schematic diagram of the structure of an embodiment of the electronic device of the present invention; Figure 8 This is a schematic diagram of the structure of one embodiment of the storage medium of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0022] The terms "first," "second," and "third" used in this invention are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified. All directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this invention are only used to explain the relative positional relationships and movements between components in a specific orientation (as shown in the figures). If the specific orientation changes, the directional indications also change accordingly. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0023] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0024] like Figure 1 As shown, this embodiment provides an example of a method for enhancing wetland carbon sequestration capacity through intelligent regulation and ecological restoration. In this embodiment, the method for enhancing wetland carbon sequestration capacity through intelligent regulation and ecological restoration specifically includes the following steps: Step S1: Deploy a multi-parameter sensor network to monitor key wetland carbon sink parameters such as water level, vegetation growth, and soil carbon storage in real time; acquire vegetation NDVI index and surface temperature data, analyze the vegetation NDVI index and surface temperature data, and derive ecological restoration strategies. Step S2: Based on the ecological restoration strategy, combine plants with carbon sequestration advantages, using a golden ratio of emergent plants, submerged plants, and floating-leaved plants; and strengthen the microorganisms by inoculating with carbon-fixing bacteria; the carbon-fixing bacteria include nitrogen-fixing bacteria and methanogenic bacteria; Step S3: Establish a carbon sink-environmental parameter response model based on historical intelligent regulation data; input the ecological restoration strategy into the carbon sink-environmental parameter response model for analysis, and adjust the ecological restoration data based on the analysis results of the carbon sink-environmental parameter response model.

[0025] Preferably, this embodiment utilizes a multi-parameter sensor network to monitor key parameters such as water level, vegetation growth, and soil carbon storage in real time. Combined with NDVI index and surface temperature data, it achieves dynamic analysis of vegetation status. Based on the monitoring data, the relationship between vegetation NDVI and surface temperature is analyzed, and ecological restoration strategies are proposed, including a golden ratio of emergent, submerged, and floating-leaved plants. Microbial enhancement measures are introduced, such as inoculation with nitrogen-fixing and methanogenic bacteria, to improve carbon fixation capacity. A carbon sink-environmental parameter response model is established using historical intelligent regulation data. The ecological restoration strategies are input into the model for analysis, and the restoration strategies are adjusted based on model feedback to achieve dynamic optimization of carbon sink function. Inoculation with nitrogen-fixing and methanogenic bacteria enhances microbial carbon fixation capacity, improves soil organic carbon storage and burial efficiency, thereby enhancing wetland carbon sink function. Hydrological regulation and vegetation restoration provide favorable habitats for microorganisms, promoting carbon deposition and burial, and improving the overall carbon sink capacity of the wetland. By optimizing vegetation structure and enhancing microorganisms, the carbon absorption and sequestration capacity of wetlands can be significantly improved, enhancing their function as the main carbon sink. Based on real-time monitoring data and model analysis, dynamic adjustments to ecological restoration strategies can be achieved, improving restoration efficiency and carbon sink effectiveness. Through vegetation restoration and hydrological regulation, the structure of wetland ecosystems can be improved, biodiversity can be enhanced, and the stability and resilience of the ecosystem can be strengthened. Intelligent management of wetland ecosystems can be realized, providing efficient and accurate technical means for carbon sink monitoring and assessment.

[0026] Furthermore, such as Figure 2 As shown, the process of deriving the ecological restoration strategy in step S1 specifically includes the following steps: Step S11: Obtain vegetation NDVI index and land surface temperature data, and assess vegetation cover, biomass and carbon sequestration capacity; when the NDVI index value is less than the preset NDVI threshold, it is judged as a low NDVI value; combine historical NDVI index to judge the degree of degradation of the low NDVI index value. Step S12: Conduct surface temperature analysis, and combine it with soil content and water level to determine the main causes of carbon sequestration capacity degradation; select dominant species with high carbon sequestration capacity and optimize their ratio based on the vegetation type degradation indicated by NDVI. Step S13: Based on the optimized ratio, select a hydrological regulation strategy. If soil carbon data indicates insufficient microbial activity, introduce nitrogen-fixing bacteria and methanogenic bacteria. These nitrogen-fixing bacteria and methanogenic bacteria are commercially available products.

[0027] Preferably, this embodiment utilizes the Normalized Difference Vegetation Index (NDVI) to assess vegetation cover and biomass, and determines the degree of degradation through historical NDVI data. NDVI is calculated using near-infrared and red light reflectance to reflect vegetation health; its value ranges from -1 to +1, with high values ​​indicating dense and healthy vegetation, and low values ​​indicating sparse or degraded vegetation. Combining NDVI with LST (Land Surface Temperature) analysis can identify the main causes of carbon sequestration degradation, such as soil moisture content and water level changes. Based on the vegetation type degradation indicated by NDVI, high carbon-sequestration dominant species are selected and their proportions optimized. Based on the optimized vegetation proportions, hydrological control strategies are formulated, such as adjusting irrigation frequency and volume to meet the needs of different vegetation types. Furthermore, soil structure is improved through amendments such as biochar, promoting the optimization of microbial community structure and increasing soil carbon mineralization rate and carbon sequestration capacity.

[0028] Furthermore, such as Figure 3 As shown, step S2, which involves combining carbon sequestration-advantageous plants according to ecological restoration strategies, specifically includes the following steps: Step S21: Based on the site conditions and restoration goals of the wetland degradation area, screen the dominant species with high carbon sequestration capacity, and combine them with the ecological functions of emergent plants, submerged plants and floating-leaved plants to make a golden ratio. Step S22: Combine trees, shrubs and grasses in multiple layers to construct a vegetation community structure; and analyze the development of vegetation towards the high carbon sink succession stage, and control the vegetation towards the high carbon sink succession stage at the preset vegetation towards the high carbon sink succession stage state. Step S23: Inoculate with carbon-fixing bacteria to form soil aggregates through microbial activity; use drones and satellite remote sensing to monitor vegetation NDVI index and carbon sink dynamics.

[0029] Preferably, this embodiment selects dominant species with high carbon sequestration capacity and combines them with emergent, submerged, and floating-leaved plants in a golden ratio to form a multi-layered and multifunctional vegetation community structure. A multi-layered combination of trees, shrubs, and herbaceous plants is used to construct a stable and diverse vegetation community, promoting vegetation succession to a high carbon sink stage. Inoculation with carbon-fixing microbial agents promotes the formation of soil aggregates through microbial activity, thereby enhancing the stability and sequestration capacity of soil organic carbon. The formation of soil aggregates helps protect organic carbon from decomposition, improving soil carbon sink capacity. Using UAVs and satellite remote sensing technology, the NDVI index of vegetation and dynamic changes in carbon sink are monitored, providing data support for vegetation restoration and carbon sink enhancement. Remote sensing technology can quickly acquire information on large areas of vegetation, and combined with model inversion, it enables accurate assessment of carbon sink volume. By regularly monitoring indicators such as plant carbon sequestration and soil carbon storage, the effectiveness of vegetation restoration and carbon sink enhancement is evaluated, and management measures are adjusted based on the monitoring results to achieve continuous optimization of carbon sink capacity.

[0030] Furthermore, such as Figure 4 As shown, the process of establishing the carbon sink-environmental parameter response model in step S3 specifically includes the following steps: Step S31: Collect historical intelligent remote control data and corresponding carbon sink index data; cover different time scales and spatial distributions of historical intelligent remote control data and corresponding carbon sink index data; among which, intelligent remote control data includes water level, soil carbon content, vegetation NDVI index and surface temperature, etc. Step S32: Fit the relationship between environmental parameters and carbon sink indicators, and convert the linear relationship into a nonlinear relationship; construct a carbon sink-environmental parameter response model by introducing variables such as ratio vegetation index, normalized vegetation index and meteorology; and optimize the variable combination and remove redundant parameters. Step S33: Correct the carbon sink-environmental parameter response model to rectify its prediction bias; input the ecological restoration strategy into the carbon sink-environmental parameter response model for analysis, and adjust the ecological restoration data based on the analysis results of the carbon sink-environmental parameter response model.

[0031] Preferably, this embodiment achieves coverage of different time scales and spatial distributions by collecting historical intelligent remote control data on water level, soil carbon content, vegetation NDVI index, surface temperature and corresponding carbon sink index data. This indicates that the system relies on the fusion of multi-source heterogeneous data, including multi-dimensional data from sensors, remote sensing, and meteorology; it introduces ratio vegetation index, normalized difference vegetation index, and meteorological variables to construct a carbon sink-environmental parameter response model, and eliminates redundant parameters by optimizing variable combinations, transforming linear relationships into nonlinear relationships; it corrects model prediction bias, inputs ecological restoration strategies into the model for analysis, and adjusts ecological restoration data based on the analysis results; through multi-source data fusion and nonlinear modeling, the system can more accurately reflect the complex relationship between carbon sinks and environmental parameters, thereby improving the accuracy and reliability of carbon sink assessment; the correction and ecological restoration feedback mechanism enables ecological restoration strategies to be dynamically adjusted based on actual carbon sink changes, improving the scientific nature and pertinence of ecological restoration; the system has time series monitoring capabilities, which can dynamically reflect the changing trend of carbon sinks over time, providing decision support for the long-term management and optimization of carbon sink projects; through the combination of remote sensing and big data technologies, the system is applicable to carbon sink monitoring and assessment at different scales and in different regions, providing technical support for the realization of the "dual carbon" goal.

[0032] Furthermore, such as Figure 5 As shown, step S31, which involves intelligent remote control data and corresponding carbon sequestration index data covering different time scales and spatial distributions, specifically includes the following steps: Step S311: Using historical remote control data from mobile phones, covering different time granularities, and integrating spatial data of different resolutions; performing radiometric positioning and atmospheric correction on the raw data, converting it into the actual reflectance of ground objects; and performing standardization processing on multi-source data to match time and spatial scales. Step S312: Extract vegetation index and environmental parameters from remote sensing data; calculate NDVI using near-infrared and red bands to retrieve biomass; and obtain carbon sink evidence data such as enhanced vegetation index, surface temperature, and rainfall. Step S313: Classify land use types according to unified rules, calculate spatially differentiated carbon storage based on vegetation carbon content, verify and calibrate remote sensing results using ground-based observation data, and fuse multi-source data to form a spatiotemporal distribution pattern.

[0033] Specifically, NDVI is calculated using near-infrared and red bands. By utilizing the difference in reflectance between near-infrared bands or vegetation with strong reflectance and red bands or vegetation with strong absorption in remote sensing images, a normalized vegetation index (NDVI) is constructed to quantitatively characterize vegetation cover and growth vitality. Spatially differentiated carbon storage is calculated by combining vegetation carbon content data: based on biomass data retrieved from NDVI, the unit carbon content of different vegetation types, such as the carbon density coefficient of trees / shrubs / herbs, is matched, and gridded and accurate estimation of carbon storage is achieved through spatial overlay analysis.

[0034] Preferably, this embodiment integrates remote sensing data with different temporal and spatial resolutions to achieve coverage and standardization of the original data; it eliminates sensor noise through radiometric correction and eliminates the effects of atmospheric scattering and absorption through atmospheric correction, ultimately converting the remote sensing data into the actual reflectance of ground objects to ensure the physical authenticity of the data; based on vegetation indices such as NDVI, combined with red band and near-infrared band data, it inverts vegetation biomass and health status; it classifies land use types using unified rules and calculates spatially differentiated carbon storage based on vegetation carbon content. Simultaneously, it combines ground-based observation data for verification and calibration to improve the reliability of the remote sensing results. Through multi-source data fusion and classification, it forms a spatiotemporal distribution pattern of carbon sinks, providing a scientific basis for carbon sink monitoring and the achievement of carbon neutrality goals.

[0035] Furthermore, step S32, which involves constructing a carbon sink-environmental parameter response model by introducing variables such as ratio vegetation index, normalized difference vegetation index, and meteorological conditions, specifically includes the following steps: Step S321: Calculate the vegetation biomass and coverage by the ratio of near-infrared band to red band; calculate the intensity of vegetation photosynthesis and growth status by the normalized difference between near-infrared and red bands. Specifically, vegetation biomass and cover are calculated by the ratio of near-infrared to red light bands; vegetation biomass density and canopy cover ratio per unit area are directly quantified by the ratio of high reflectance in the near-infrared band to high absorption in the red light band (e.g., RVI); the intensity of photosynthesis and growth status of vegetation are determined by the normalized difference between the near-infrared and red light bands; and the normalized difference vegetation index (NDVI) is used to eliminate light interference, and the leaf chlorophyll activity and photosynthetic efficiency are dynamically reflected by the standardized calculation of near-infrared-red light / near-infrared+red light. Step S322: Introduce real-time or historical meteorological data variables and make them consistent with the vegetation index in time and space; fit the relationship between the vegetation index, meteorological variables and carbon sink index, and capture the complex interaction between the variables in the relationship between the vegetation index, meteorological variables and carbon sink index. Step S323: Prioritize retaining variables whose contribution to the carbon sink explanation is greater than the preset contribution threshold; calibrate the carbon sink-environmental parameter response model based on ground-based measured data; adjust the parameters of the carbon sink-environmental parameter response model based on regional characteristics.

[0036] Preferably, this embodiment calculates vegetation biomass and cover by the ratio of near-infrared and red light bands, and uses normalized difference in light (NDVI) to reflect the photosynthetic intensity and growth status of vegetation. Real-time or historical meteorological data such as temperature, precipitation, and solar radiation are incorporated and spatiotemporally consistent with vegetation indices to capture the complex interaction between vegetation indices and meteorological variables. Variables contributing more than a preset threshold to carbon sink explanation are preferentially retained, and model parameters are corrected using ground-measured data to ensure the model's applicability in different regions and environments. Model parameters are adjusted according to regional vegetation types, climate conditions, and other characteristics to make the model more closely match the actual environment. The accuracy of the model is verified by comparison with ground-measured data, and the model structure and parameter settings are continuously optimized.

[0037] Furthermore, step S322, which involves capturing the complex interactions between vegetation indices, meteorological variables, and carbon sink indices, specifically includes the following steps: Step S3221: Fit the relationship between vegetation index, meteorological variables and carbon sink index, and use physiological and ecological processes such as photosynthesis and respiration to quantify the impact of meteorological changes on vegetation photosynthetic efficiency and correlate carbon sink dynamics. Step S3222: Input index data, meteorological data, and background CO2 flux into the carbon sink-environmental parameter response model to capture the nonlinear interaction between variables; analyze vegetation index, light energy utilization rate, and photosynthetically active radiation to obtain vegetation productivity; Step S3223: Perform nonlinear fitting on the interaction between the leaf area index and chlorophyll content data in the vegetation index and meteorological factors; perform sensitivity analysis on the fitted data to identify and test the marginal impact of meteorological variables on carbon sinks, and quantify the impact of soil organic carbon on climate factors.

[0038] Preferably, this embodiment utilizes the nonlinear interaction between vegetation indices (leaf area index, normalized difference vegetation index) and meteorological variables such as photosynthetically active radiation, temperature, and precipitation; it introduces physiological mechanisms such as photosynthesis and respiration to quantify the impact of meteorological changes on vegetation photosynthetic efficiency; and it performs sensitivity analysis on the fitted data to identify the marginal impact of meteorological variables on carbon sinks and assess the response of soil organic carbon to climate factors. A model is established using remotely sensed vegetation indices (NDVI, LAI) and ground-measured data to improve the accuracy of vegetation parameter inversion. Nonlinear fitting of vegetation indices with meteorological variables allows for more accurate estimation of vegetation productivity, thereby improving the simulation accuracy of carbon sink dynamics; combining parameters such as light energy utilization rate and photosynthetically active radiation effectively assesses vegetation carbon sink capacity, providing data support for carbon neutrality goals; identifying the impact of key meteorological variables on carbon sinks provides a scientific basis for agricultural and forestry management; and sensitivity analysis helps identify key driving factors in the model, improving its robustness and interpretability.

[0039] Furthermore, step S3223, which involves performing sensitivity analysis on the fitted data, specifically includes the following steps: Step S32231: Select a set of benchmark meteorological data from the climate data of historical standard years as the starting point of the simulation, input the fitted vegetation index into the carbon sink-environmental parameter response model, and initialize the parameters of the carbon sink-environmental parameter response model. Step S32232: Change one or more meteorological variables while keeping other variables constant, and simulate different climate scenarios; after each change, rerun the carbon sink-environmental parameter response model simulation and calculate the output variables; The process of calculating the output variable specifically includes the following steps: The baseline scenario is solidified, and the historical meteorological baseline set is transformed by the response model to generate a baseline output set, which includes carbon sink index, net productivity, and soil carbon value; Directional variable perturbation involves selecting a target meteorological factor and replacing the data sequence of that factor in the historical meteorological baseline set to form a perturbation group; the perturbation group is then transformed by the model to generate a new output set. Response gap extraction: The new output set is compared with the baseline output set item by item to derive the absolute response gap, including the gap values ​​of carbon sink index and soil carbon content; directional perturbation, model transformation and gap extraction are performed iteratively to cover all target factors and accumulate the gap set. Sensitivity spectrum construction, range standardization is performed on the gap set; the gap set is transformed into relative sensitivity using the maximum gap value of each factor as the reference base; Arrange them in descending order of relative sensitivity values ​​to generate a sensitivity spectrum; Coupling effect verification: The top k highly sensitive factors in the sensitivity spectrum are extracted to construct a composite perturbation group; the composite perturbation group is transformed by the model to obtain the output variables, and the comprehensive gap between it and the benchmark output set is derived; the superimposed value of the comprehensive gap and the single factor gap is compared to generate the coupling bias, which is used to evaluate the multi-factor interaction effect; The output variables include carbon sink index, net ecosystem productivity, and soil organic carbon content; Step S32233: Compare the simulation results under different scenarios and quantify the changes in output variables; calculate the marginal impact, quantify the soil organic carbon response, and calculate the sensitivity indicators; identify the meteorological variables that have the greatest impact on carbon sinks by quantifying the changes in output variables, and evaluate the carbon sink-environmental parameter response model.

[0040] Preferably, this embodiment selects benchmark meteorological data from historical standard years as the starting point for simulation, ensuring the accuracy and representativeness of model initialization. The fitted vegetation index is input into the carbon sink-environmental parameter response model, and the model parameters are initialized to provide a foundation for subsequent simulations. By changing one or more meteorological variables, such as temperature, precipitation, and CO2 concentration, while keeping other variables constant, the carbon sink response under different climate scenarios is simulated. The output includes the carbon sink index, net ecosystem productivity (NEP), and soil organic carbon content, used to assess carbon sink changes under different climate conditions. By comparing the simulation results under different scenarios, the changes in output variables are quantified, and the model is identified. This study focuses on identifying the meteorological variables that have the greatest impact on carbon sinks and assessing the predictive power of models. By combining historical data with model simulations, it aims to more accurately predict carbon sink changes under different climate scenarios, providing a scientific basis for policy-making and carbon emission reduction. Quantifying the impact of different meteorological variables on carbon sinks allows for the identification of the factors with the greatest influence, such as temperature, precipitation, or CO2 concentration, thereby optimizing carbon sink management strategies. Model validation and parameter calibration improve the predictive accuracy and stability of models, making them applicable to carbon sink assessments at different scales and regions. Furthermore, it supports simulations of different climate scenarios and management measures, providing predictions of future carbon sink dynamics under climate change and contributing to the development of adaptive strategies.

[0041] Furthermore, the process of evaluating the carbon sink-environmental parameter response model in step S32233 specifically includes the following steps: Step S322331: By fitting curves or response surface analysis, determine the partial derivatives of meteorological variables with respect to the carbon sink index and obtain the results of calculating the marginal impact; by comparing the dynamics of soil organic carbon content under different climatic conditions, establish the relationship between soil organic carbon and climatic factors and obtain the quantitative results of soil organic carbon response. Step S322332: Eliminate sensitivity by arranging meteorological variables according to their magnitude of influence; test the nonlinear interaction method by using the fitted carbon sink-environmental parameter response model to analyze the interaction effects between variables; quantify uncertainty by considering parameter variations through multiple simulations and calculating the confidence region. By using Monte Carlo simulation or Bayesian statistical methods, the random variation of model parameters is calculated iteratively multiple times to finally generate the probability distribution range of carbon sink prediction values ​​and quantify the reliability range of the model output. Step S322333: Generate a sensitivity report based on the results of excluding sensitivity, nonlinear interaction, and uncertainty quantification, and output the sensitivity report.

[0042] Preferably, this embodiment determines the partial derivatives of meteorological variables with respect to the carbon sink index through curve fitting or response surface analysis, thus deriving the marginal impact results. Excluding sensitive variables and ranking meteorological variables by their magnitude of influence helps identify key driving factors, reduces model complexity, and improves computational efficiency. Simultaneously, testing for nonlinear interaction effects shows that the model not only focuses on linear relationships but also considers complex interactions between variables, enhancing its explanatory power. Multiple simulations considering parameter variations and calculating confidence regions demonstrate a systematic approach to model uncertainty. This method combines Monte Carlo simulation and probability distribution fitting, enabling a more accurate assessment of the reliability of model predictions. Finally, the results of sensitivity analysis, nonlinear interaction effects, and uncertainty quantification are integrated into a sensitivity report, providing a scientific basis for decision-making. Through response surface analysis and sensitivity analysis, the model can more accurately identify key variables and reduce redundant parameters, thereby improving prediction accuracy. Testing for nonlinear interaction effects allows the model to more comprehensively reflect the complex relationships between variables, enhancing its explanatory power. By quantifying uncertainty and calculating confidence regions, the model can provide policymakers with a scientific basis. It offers a systematic process for carbon sink assessment, which helps promote the standardization of carbon sink measurement and monitoring.

[0043] Furthermore, step S33, which involves inputting the ecological restoration strategy into the carbon sink-environmental parameter response model for analysis, specifically includes the following steps: Step S331: Input the ecological restoration strategy into the carbon sink-environmental parameter response model for analysis, run the carbon sink-environmental parameter response model to simulate the carbon sink potential under different ecological restoration strategies; obtain the vegetation carbon sequestration effect, microbial enhancement effect and hydrological regulation effect based on the simulation results; Step S332: Based on the carbon sink-environmental parameter response curve output by the carbon sink-environmental parameter response model, identify the optimal control node, and output adjustment suggestions for data on carbon sink anomalies in characteristic areas and methane emissions exceeding the threshold. Step S333: Compare the analysis results of the carbon sink-environmental parameter response model with real-time monitoring data to evaluate the short-term and long-term carbon sink effectiveness of the remediation strategy; establish a dynamic feedback mechanism to update the parameters of the carbon sink-environmental parameter response model based on monitored data such as vegetation carbon sequestration and soil carbon density.

[0044] Preferably, this embodiment inputs ecological restoration strategies into a carbon sink-environmental parameter response model to simulate carbon sink potential under different strategies and identify the effects of vegetation carbon sequestration, microbial enhancement, and hydrological regulation. This model combines the coupling relationship between environmental factors such as temperature, precipitation, and soil type with ecological processes such as photosynthesis and microbial carbon sequestration to achieve dynamic simulation of the carbon sink mechanism. Based on the carbon sink-environmental parameter response curve output by the model, it identifies optimal regulation nodes and proposes adjustment suggestions for areas with abnormal carbon sinks or methane emissions exceeding the threshold, reflecting refined management of the ecosystem. The simulation results are compared with real-time monitoring data on vegetation carbon sequestration and soil carbon density to establish a dynamic feedback mechanism, continuously updating model parameters and improving the model's prediction accuracy and adaptability. Through measures such as vegetation restoration, soil improvement, and microbial enhancement, the carbon sink capacity of the ecosystem is significantly enhanced, especially in key ecosystems such as forests, wetlands, and mangroves. Identifying optimal regulation nodes provides customized restoration suggestions for different regions, avoiding resource waste and carbon leakage, and improving restoration efficiency. Through the dynamic feedback mechanism, the continuous improvement of ecological restoration and carbon sink capacity is achieved, providing scientific support for the "dual carbon" goal.

[0045] Furthermore, the process of proposing adjustments in step S332 specifically includes the following steps: Step S3221: Run the carbon sink-environmental parameter response model to simulate the carbon sink potential under different ecological restoration strategies, analyze the impact of plant combinations on biomass carbon density and soil organic carbon accumulation, and evaluate the synergistic effect of carbon-fixing agents on soil carbon fixation and methane emission reduction. Step S3222: Simulate the effect of water level changes on the organic matter sorting rate and the balance of CO2 and CH4 emissions; output key indicators such as changes in carbon storage, net carbon sink increment, carbon flux, and greenhouse gas emission intensity. Step S3223: For data on abnormal carbon sequestration and methane emissions exceeding the threshold in specific areas, adjust vegetation management, hydrological optimization, and microbial disturbance based on vegetation carbon sequestration effect, microbial enhancement effect, and hydrological regulation effect.

[0046] Preferably, this embodiment assesses the effects of different ecological restoration strategies, vegetation combinations, and the application of carbon-fixing agents on carbon sequestration potential, thereby evaluating the effectiveness of plant biomass carbon density and soil organic carbon accumulation. By simulating the impact of water level changes on organic matter sorting rates and the CO2 and CH4 emission balance, the effect of hydrological regulation on carbon flux and greenhouse gas emission intensity is evaluated. For areas with abnormal carbon sequestration or methane emissions exceeding thresholds, carbon sequestration capacity is enhanced and greenhouse gas emissions are reduced by adjusting vegetation management, selecting high-carbon-sequestration plants, optimizing hydrology, controlling irrigation, drainage, and microbial intervention, and introducing carbon-fixing agents. For example, vegetation restoration can significantly increase soil organic carbon density, while soil and water conservation measures can enhance the stability of the soil carbon pool.

[0047] like Figure 5 As shown, this embodiment also provides an embodiment of a wetland carbon sequestration capacity enhancement system based on intelligent remote control and ecological restoration. In this embodiment, the wetland carbon sequestration capacity enhancement method based on remote control and ecological restoration, the wetland carbon sequestration capacity enhancement system based on remote control and ecological restoration, includes: The intelligent sensing module 1 is used to deploy a multi-parameter sensor network to monitor key wetland carbon sink parameters such as water level, vegetation growth, and soil carbon storage in real time; acquire vegetation NDVI index and surface temperature data, analyze the vegetation NDVI index and surface temperature data, and derive ecological restoration strategies. Ecological restoration module 2 is used to combine carbon sequestration-advantageous plants according to ecological restoration strategies, with a golden ratio of emergent plants, submerged plants, and floating-leaved plants; and to enhance microorganisms by inoculating carbon-fixing bacteria; the carbon-fixing bacteria include nitrogen-fixing bacteria and methanogenic bacteria; The intelligent remote control module 3 is used to establish a carbon sink-environmental parameter response model based on historical intelligent control data; the ecological restoration strategy is input into the carbon sink-environmental parameter response model for analysis, and the ecological restoration data is adjusted according to the analysis results of the carbon sink-environmental parameter response model.

[0048] Preferably, the intelligent sensing module 1 is equipped with a multi-parameter sensor network (water level sensor, CO2 / CH4 flux tower, soil carbon content detector); UAV remote sensing periodically acquires vegetation NDVI index and surface temperature data; the ecological restoration module 2 uses a golden ratio of emergent plants, submerged plants, and floating-leaved plants to form a carbon sink-advantageous plant combination; the microbial enhancement module inoculates carbon-fixing bacteria (including nitrogen-fixing bacteria and methanogenic bacteria); the intelligent remote control module 3 uses a hybrid modeling method of multiple nonlinear regression and machine learning correction to establish a carbon sink-environmental parameter response model; by deploying a multi-parameter sensor network, key parameters such as water level, vegetation growth, and soil carbon storage are monitored in real time, and combined with NDVI index and surface temperature data, dynamic analysis of vegetation status is achieved; based on monitoring... Data was collected and the relationship between vegetation NDVI and land surface temperature was analyzed. Ecological restoration strategies were proposed, including a golden ratio of emergent, submerged, and floating-leaved plants, and microbial enhancement measures, such as inoculation with nitrogen-fixing and methanogenic bacteria, to improve carbon fixation capacity. A carbon sink-environmental parameter response model was established using historical intelligent regulation data. The ecological restoration strategies were input into the model for analysis, and the strategies were adjusted based on model feedback to achieve dynamic optimization of carbon sink function. Specifically, inoculating with nitrogen-fixing and methanogenic bacteria enhances microbial carbon fixation capacity, improves soil organic carbon storage and burial efficiency, and thus enhances wetland carbon sink function. Hydrological regulation and vegetation restoration provide favorable habitats for microorganisms, promoting carbon deposition and burial, and improving the overall carbon sink capacity of wetlands. By optimizing vegetation structure and enhancing microbial activity, the carbon absorption and sequestration capacity of wetlands is significantly improved, enhancing their function as primary carbon sinks. Based on real-time monitoring data and model analysis, dynamic adjustments to ecological restoration strategies are achieved, improving restoration efficiency and carbon sequestration effectiveness. Through vegetation restoration and hydrological regulation, the structure of wetland ecosystems is improved, biodiversity is enhanced, and the stability and resilience of the ecosystem are strengthened. This enables intelligent management of wetland ecosystems, providing efficient and precise technical means for carbon sequestration monitoring and assessment (see appendix for specific principles). Figure 6 ).

[0049] like Figure 7 As shown, this embodiment provides an embodiment of an electronic device 4, which includes a processor 41 and a memory 42 coupled to the processor 41.

[0050] The memory 42 stores program instructions for implementing the layout method of the wetland carbon sequestration capacity enhancement method based on remote control and ecological restoration in any of the above embodiments.

[0051] The processor 41 is used to execute program instructions stored in the memory 42 to deploy a method for enhancing wetland carbon sequestration capacity based on remote control and ecological restoration.

[0052] The processor 41 can also be referred to as a CPU (Central Processing Unit). The processor 41 may be an integrated circuit chip with signal processing capabilities. The processor 41 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor.

[0053] Furthermore, Figure 8 This is a schematic diagram of the structure of a storage medium according to an embodiment of this application. The storage medium 5 of this embodiment stores program instructions 51 capable of implementing all the methods described above. These program instructions 51 can be stored in the storage medium in the form of a software product, including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, or terminal devices such as computers, servers, mobile phones, and tablets.

[0054] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0055] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units. The above are merely embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

[0056] The specific embodiments of the invention have been described in detail above, but these are merely examples, and the invention is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modifications or substitutions to the invention are also within the scope of this invention. Therefore, all equivalent transformations, modifications, and improvements made without departing from the spirit and principles of this invention should be included within the scope of this invention.

Claims

1. A method for enhancing wetland carbon sequestration capacity through intelligent regulation and ecological restoration, characterized in that, The process of the intelligent regulation and ecological restoration method for enhancing wetland carbon sequestration capacity includes the following steps: real-time monitoring of key wetland carbon sequestration indicators through a multi-parameter sensor network, development of an ecological restoration plan based on NDVI and surface temperature data analysis, and adoption of a synergistic restoration strategy of using a golden ratio of superior plants and inoculation with compound carbon-fixing bacteria. A carbon sink-environmental parameter response model is established based on historical intelligent regulation data; ecological restoration strategies are input into the carbon sink-environmental parameter response model for analysis, and ecological restoration data is adjusted based on the analysis results of the carbon sink-environmental parameter response model.

2. The method for enhancing wetland carbon sequestration capacity through intelligent regulation and ecological restoration according to claim 1, characterized in that, The process of establishing a carbon sink-environmental parameter response model includes the following steps: Collect historical intelligent remote control data and corresponding carbon sink index data; cover historical intelligent remote control data and corresponding carbon sink index data with different time scales and spatial distributions; The relationship between environmental parameters and carbon sink indicators was fitted, and the linear relationship was transformed into a nonlinear relationship. A carbon sink-environmental parameter response model was constructed by introducing the ratio vegetation index, normalized vegetation index and meteorological variables. The variable combination was optimized and redundant parameters were removed. The carbon sink-environmental parameter response model is calibrated to correct prediction biases; ecological restoration strategies are input into the carbon sink-environmental parameter response model for analysis, and ecological restoration data are adjusted based on the analysis results.

3. The method for enhancing wetland carbon sequestration capacity through intelligent regulation and ecological restoration according to claim 2, characterized in that, The intelligent remote control data and corresponding carbon sequestration index data cover processes with different time scales and spatial distributions, including the following steps: By using historical remote control data from mobile phones, covering different time granularities, and integrating spatial data of different resolutions, radiometric positioning and atmospheric correction are performed on the raw data to convert it into the actual reflectance of ground objects; and standardization processing is performed on multi-source data to match time and spatial scales. Vegetation indices and environmental parameters were extracted from remote sensing data; NDVI was calculated using near-infrared and red bands to retrieve biomass; and enhanced vegetation index, land surface temperature, and precipitation carbon sink data were obtained. Land use types are classified according to unified rules, and spatially differentiated carbon storage is calculated by combining vegetation carbon content. Multi-source data are fused to form a spatiotemporal distribution pattern by combining ground-based observation data to verify and calibrate remote sensing results.

4. The method for enhancing wetland carbon sequestration capacity through intelligent regulation and ecological restoration according to claim 2, characterized in that, The process of constructing a carbon sink-environmental parameter response model by introducing ratio vegetation index, normalized vegetation index and meteorological variables includes the following steps: The vegetation biomass and coverage were calculated by the ratio of the near-infrared band to the red band; the intensity of vegetation photosynthesis and growth status were calculated by the normalized difference between the near-infrared and red bands. Introduce real-time or historical meteorological data variables to achieve spatiotemporal consistency with vegetation indices; fit the relationship between vegetation indices, meteorological variables, and carbon sink indices to capture the complex interactions between variables. Variables that contribute more than a preset contribution threshold to the explanation of carbon sinks are prioritized for retention; the carbon sink-environmental parameter response model is calibrated based on ground-based measured data; and the parameters of the carbon sink-environmental parameter response model are adjusted based on regional characteristics.

5. The method for enhancing wetland carbon sequestration capacity through intelligent regulation and ecological restoration according to claim 4, characterized in that, The process of capturing the complex interactions between vegetation indices, meteorological variables, and carbon sink indices includes the following steps: The relationship between vegetation index, meteorological variables and carbon sink index was fitted. The physiological and ecological processes of photosynthesis and respiration were used to quantify the impact of meteorological changes on vegetation photosynthetic efficiency and to correlate carbon sink dynamics. The index data, meteorological data, and background CO2 flux are input into the carbon sink-environmental parameter response model to capture the nonlinear interaction between variables; vegetation index, light energy utilization rate, and photosynthetically active radiation are analyzed to obtain vegetation productivity. The data of leaf area index and chlorophyll content in vegetation indices were nonlinearly fitted with the interaction of meteorological factors; the fitted data were then subjected to sensitivity analysis to identify the marginal impact of meteorological variables on carbon sinks and to quantify the impact of soil organic carbon on climate factors.

6. The method for enhancing wetland carbon sequestration capacity through intelligent regulation and ecological restoration according to claim 5, characterized in that, The process of performing sensitivity analysis on the fitted data includes the following steps: Select a set of baseline meteorological data from historical standard year climate data as the starting point for simulation, input the fitted vegetation index into the carbon sink-environmental parameter response model, and initialize the parameters of the carbon sink-environmental parameter response model. Simulate different climate scenarios by changing one or more meteorological variables while keeping other variables constant; after each change, rerun the carbon sink-environmental parameter response model simulation and calculate the output variables. The output variables include carbon sink index, net ecosystem productivity, and soil organic carbon content; The simulation results under different scenarios are compared to quantify the changes in output variables; the marginal impact is calculated, the soil organic carbon response is quantified, and the sensitivity index is calculated; by quantifying the changes in output variables, the meteorological variables with the greatest impact on carbon sinks are identified, and the carbon sink-environmental parameter response model is evaluated.

7. The method for enhancing wetland carbon sequestration capacity through intelligent regulation and ecological restoration according to claim 6, characterized in that, in, The process of calculating the output variable includes the following steps: The baseline scenario is solidified, and the historical meteorological baseline set is transformed by the response model to generate a baseline output set, which includes carbon sink index, net productivity, and soil carbon value; Directional variable perturbation involves selecting a target meteorological factor and replacing the data sequence of that factor in the historical meteorological baseline set to form a perturbation group; the perturbation group is then transformed by the model to generate a new output set. Response gap extraction: The new output set is compared with the baseline output set item by item to derive the absolute response gap, including the gap values ​​of carbon sink index and soil carbon content; directional perturbation, model transformation and gap extraction are performed iteratively to cover all target factors and accumulate the gap set. Sensitivity spectrum construction, range standardization is performed on the gap set; the gap set is transformed into relative sensitivity using the maximum gap value of each factor as the reference base; Arrange them in descending order of relative sensitivity values ​​to generate a sensitivity spectrum; To verify the coupling effect, the top k most sensitive factors in the sensitivity spectrum were extracted to construct a composite perturbation set. The composite perturbation set was transformed by the model to obtain the output variables, and the comprehensive gap between it and the benchmark output set was derived. The superimposed estimate of the comprehensive gap and the single-factor gap was compared to generate the coupling bias, which was used to evaluate the multi-factor interaction effect.

8. The method for enhancing wetland carbon sequestration capacity through intelligent regulation and ecological restoration according to claim 6, characterized in that, The process of evaluating the carbon sink-environmental parameter response model includes the following steps: By fitting curves or response surface analysis, the partial derivatives of meteorological variables with respect to the carbon sink index are determined, and the marginal impact is calculated. By comparing the dynamics of soil organic carbon content under different climatic conditions, the relationship between soil organic carbon and climatic factors is established, and the quantitative soil organic carbon response results are obtained. Sensitivity was eliminated, and meteorological variables were arranged according to their magnitude of influence. The nonlinear interaction method was tested, and the interaction effect between variables was analyzed using the fitted carbon sink-environmental parameter response model. Uncertainty was quantified by considering parameter variations through multiple simulations and calculating the confidence region. A sensitivity report is generated based on the results of excluding sensitivity, nonlinear interaction, and uncertainty quantification, and then the sensitivity report is output.

9. The method for enhancing wetland carbon sequestration capacity through intelligent regulation and ecological restoration according to claim 1, characterized in that, It also includes deploying a multi-parameter sensor network to monitor key wetland carbon sink parameters such as water level, vegetation growth, and soil carbon storage in real time; acquiring vegetation NDVI index and surface temperature data; analyzing the vegetation NDVI index and surface temperature data; and deriving ecological restoration strategies. Based on ecological restoration strategies, a combination of carbon sequestration-advantageous plants is used, with an optimal ratio of emergent, submerged, and floating-leaved plants; and microorganisms are enhanced by inoculating with carbon-fixing bacteria.

10. A wetland carbon sequestration capacity enhancement system based on intelligent remote control and ecological restoration, applied to the wetland carbon sequestration capacity enhancement method based on remote control and ecological restoration as described in any one of claims 1 to 9, characterized in that, The wetland carbon sequestration capacity enhancement system based on intelligent remote control and ecological restoration includes: The intelligent sensing module is used to deploy a multi-parameter sensor network to monitor key wetland carbon sink parameters such as water level, vegetation growth, and soil carbon storage in real time; acquire vegetation NDVI index and surface temperature data, analyze the vegetation NDVI index and surface temperature data, and derive ecological restoration strategies. The ecological restoration module is used to combine carbon sequestration-advantageous plants according to ecological restoration strategies, with a golden ratio of emergent plants, submerged plants, and floating-leaved plants; and to enhance microorganisms by inoculating carbon-fixing bacteria; the carbon-fixing bacteria include nitrogen-fixing bacteria and methanogenic bacteria; The intelligent remote control module is used to establish a carbon sink-environmental parameter response model based on historical intelligent control data; ecological restoration strategies are input into the carbon sink-environmental parameter response model for analysis, and ecological restoration data are adjusted based on the analysis results of the carbon sink-environmental parameter response model.

Images