A coastal wetland geological carbon sequestration potential evaluation system and method and related equipment

Abstract

This invention discloses a system, method, and related equipment for assessing the geological carbon sequestration potential of coastal wetlands. The system continuously collects in-situ data and remote sensing images of the target coastal wetland and transmits them to a data management module. The data management module receives and stores the in-situ data and remote sensing images. A data preprocessing and fusion module responds to preset periodic nodes, periodically preprocessing the data from the data management module and fusing it to generate high-resolution spatial distribution data. The high-resolution spatial distribution data is used as model-driving parameters in a geological carbon sequestration potential assessment model to obtain the assessment results. A visualization and output module visualizes and outputs the assessment results and their spatial distribution. This invention enables fully automated and intelligent assessment of the geological carbon sequestration potential of coastal wetlands and can be widely applied in the field of geological assessment technology.

Description

Technical Field

[0001] This invention relates to the field of geological assessment technology, and in particular to a system, method and related equipment for assessing the geological carbon sequestration potential of coastal wetlands. Background Technology

[0002] Coastal wetlands, as an important ecological transition zone connecting land and sea, not only provide habitats and breeding grounds for numerous organisms, but also play a crucial role in the global carbon cycle. Their carbon sequestration capacity per unit area far exceeds that of other ecosystems, earning them the figurative term "blue carbon ecosystem." With the increasingly severe global climate change problem, accurate assessment of the carbon sequestration potential of coastal wetlands has become an important foundation for formulating effective carbon reduction strategies and promoting ecological civilization.

[0003] Current technologies primarily employ traditional field measurements and simple data analysis methods. For example, some existing technologies focus solely on measuring vegetation carbon storage, estimating carbon storage through plot surveys and statistical analysis of vegetation biomass, while neglecting soil carbon storage and the impact of geological structure on carbon sequestration. This assessment method uses a single evaluation indicator, focusing only on vegetation as a single factor, and cannot comprehensively encompass the various factors that significantly influence the geological carbon sequestration potential of coastal wetlands, thus failing to fully reflect the geological carbon sequestration potential of coastal wetlands. Summary of the Invention

[0004] The main objective of this invention is to provide a system, method, electronic device, storage medium, and program product for assessing the geological carbon sequestration potential of coastal wetlands, aiming to solve at least one problem of the prior art.

[0005] To achieve the above objectives, one aspect of this invention proposes a system for assessing the geological carbon sequestration potential of coastal wetlands, the system comprising: An in-situ monitoring network is used to continuously collect in-situ data of the target coastal wetlands; The remote sensing image acquisition module is used to acquire multi-temporal, multi-platform remote sensing images of the target coastal wetland. The data acquisition and transmission unit is used to collect in-situ data and remote sensing images, and then transmit them to the data management module. The data management module is used to receive and store in-situ data and remote sensing images; The data preprocessing and fusion module is used to preprocess the data from the data management module at preset periodic nodes, and then fuse them to generate high-resolution spatial distribution data; the high-resolution spatial distribution data includes key parameters of various locations of the target coastal wetland; A geological carbon sequestration potential assessment model is used to take high-resolution spatial distribution data as model driving parameters and process it using a pre-set geological carbon sequestration potential assessment model to obtain assessment results; the assessment results include the spatial distribution of geological carbon sequestration potential in the target coastal wetland. The visualization and output module is used to visualize and output the evaluation results and their spatial distribution.

[0006] In some embodiments, the in-situ monitoring network includes sensors and sedimentation plates, and the in-situ data includes environmental parameters and sedimentation rates. When continuously collecting in-situ data of the target coastal wetland, the in-situ monitoring network specifically performs the following operations: Environmental parameters are continuously collected by various types of sensors pre-deployed throughout the target coastal wetland. Among them, environmental parameters include geological parameters, soil parameters, hydrological parameters, and vegetation parameters; The sedimentation rate is obtained by collecting sedimentation values ​​at various time points through sedimentation plates pre-deployed in different locations of the target coastal wetland, and then combining the differences between time points to quantify the sedimentation rate.

[0007] In some embodiments, when the data preprocessing and fusion module preprocesses the data from the data management module, it specifically performs the following operations: Standardize the in-situ data; Scale transformation of standardized in-situ data based on the spatiotemporal scale of remote sensing images; Wavelet denoising algorithm is used to denoise remote sensing images and scale-transformed in-situ data.

[0008] In some embodiments, before the data preprocessing and fusion module generates high-resolution spatial distribution data, it further performs the following operations: Data matching is performed on the preprocessed in-situ data and remote sensing images to establish correlation parameters for spatiotemporal correspondence. Among them, high-resolution spatial distribution data is generated by fusing correlation parameters of in-situ data and remote sensing images.

[0009] In some embodiments, the in-situ data includes instantaneous data at multiple time points, and the in-situ data is labeled with the coordinates of the in-situ acquisition location. When the data preprocessing and fusion module performs data matching on the preprocessed in-situ data and remote sensing images to establish the correlation parameters of spatiotemporal correspondence, it specifically performs the following operations: Based on the time point corresponding to the instantaneous data and the shooting time corresponding to the remote sensing image, the in-situ data and the remote sensing image are time-aligned, and linear interpolation is used to fill in the missing time period data to obtain the time registration result. Based on the original site coordinates and the corresponding geographic coordinates of the remote sensing image, the in-situ data is associated with the target grid of the remote sensing image to obtain the spatial registration result. Based on the temporal and spatial registration results, the spatiotemporal correspondence between in-situ data and remote sensing images is established, and the correlation parameters between in-situ data and remote sensing images are obtained.

[0010] In some embodiments, when the data preprocessing and fusion module generates high-resolution spatially distributed data, it performs the following operations: Using remote sensing imagery as the prior distribution and in-situ data as the observations, the posterior distribution is quantized through Bayesian assimilation to obtain preliminary estimates of the fusion parameters. Based on the preliminary fusion parameter estimation, the grid pixels of the remote sensing image are used as samples, and the parameter values ​​of the in-situ data corresponding to the grid pixels are used as labels. The key parameters of the entire coastal wetland area are predicted by random forest regression. Key parameters are correlated with remote sensing images to generate continuous spatial distribution data as high-resolution spatial distribution data.

[0011] In some embodiments, the high-resolution spatial distribution data is gridded data, and the geological carbon sequestration potential assessment model includes a carbon input stage, a carbon decomposition and transformation stage, and a carbon sequestration stage. When the geological carbon sequestration potential assessment model uses the high-resolution spatial distribution data as the model driving parameter and processes it using a preset geological carbon sequestration potential assessment model to obtain the assessment results, it specifically performs the following operations: Key parameters corresponding to each grid of the target coastal wetland are extracted from high-resolution spatial distribution data as input vectors; among them, key parameters include geological parameters, soil parameters, hydrological parameters, vegetation parameters, and sedimentation rate; In the carbon input stage, vegetation biomass, vegetation cover and vegetation biophysical parameters are determined based on vegetation parameters, and then organic matter input flux is quantified by combining the preset flux calibration coefficient. In the carbon decomposition and transformation stage, based on the organic matter input flux, the microbial decomposition rate and carbon form transformation are simulated according to soil parameters to obtain simulation results; During the carbon sequestration phase, based on simulation results, the long-term carbon burial amount and stability are quantified by combining sedimentation rate, geological parameters and hydrological parameters to generate an output vector as the evaluation result. The output vector includes the long-term carbon sequestration amount and carbon sequestration rate determined based on the long-term burial amount, and the carbon stability index determined based on stability.

[0012] To achieve the above objectives, another aspect of this invention proposes a method for assessing the geological carbon sequestration potential of coastal wetlands, applied to the aforementioned system. The method includes: Continuously acquire in-situ data and remote sensing images of the target coastal wetlands; In response to preset periodic nodes, the in-situ data and remote sensing images are preprocessed at regular intervals and then fused to generate high-resolution spatial distribution data; among which, the high-resolution spatial distribution data includes key parameters of various locations of the target coastal wetland; High-resolution spatial distribution data is used as the model-driving parameter, and the assessment results are obtained by processing the data using a pre-defined geological carbon sequestration potential assessment model. The assessment results include the spatial distribution of geological carbon sequestration potential in the target coastal wetland. Visualize and output the evaluation results and their spatial distribution; When the sequence reaches the next preset cycle node, return to execute the steps of preprocessing the in-situ data and remote sensing images at the preset cycle node, and then fusing them to generate high-resolution spatial distribution data, and periodically generate evaluation results.

[0013] To achieve the above objectives, another aspect of the present invention provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned method.

[0014] To achieve the above objectives, another aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned method.

[0015] To achieve the above objectives, another aspect of the present invention provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned method.

[0016] The embodiments of the present invention include at least the following beneficial effects: The present invention provides a system, method, electronic device, storage medium, and program product for assessing the geological carbon sequestration potential of coastal wetlands. This scheme continuously collects in-situ data of the target coastal wetland through an in-situ monitoring network; acquires multi-temporal, multi-platform remote sensing images of the target coastal wetland through a remote sensing image acquisition module; collects in-situ data and remote sensing images through a data acquisition and transmission unit, and then transmits them to a data management module; receives and stores in-situ data and remote sensing images through the data management module; and, in response to preset periodic nodes, preprocesses the data from the data management module at regular intervals, and then fuses it to generate high-resolution spatial distribution data. The high-resolution spatial distribution data includes key parameters at various locations of the target coastal wetland. The high-resolution spatial distribution data is used as model-driving parameters by a geological carbon sequestration potential assessment model, and the assessment results are obtained using the preset geological carbon sequestration potential assessment model. The assessment results include the spatial distribution of geological carbon sequestration potential in the target coastal wetland. The assessment results and their spatial distribution are visualized and output through a visualization and output module. This invention integrates five modules—in-situ monitoring, remote sensing, data processing, model calculation, and visualization output—to construct a complete, closed-loop assessment system, achieving full automation and intelligence from data acquisition to result output. Specifically, this invention triggers fusion and assessment through "preset periodic nodes," enabling the system to update assessment results periodically (e.g., monthly, quarterly), dynamically reflecting changes in wetland carbon sequestration potential and effectively overcoming the lag of traditional static assessment methods. Furthermore, the assessment results are presented in a "spatial distribution" format, intuitively demonstrating the spatial heterogeneity of carbon sequestration potential within wetlands (e.g., which areas are carbon sink hotspots), providing direct evidence for precise management (e.g., delineation of priority restoration zones). Attached Figure Description

[0017] Figure 1 This is a schematic diagram of an example structure of a coastal wetland geological carbon sequestration potential assessment system provided in an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the specific process of the in-situ monitoring network execution provided in this embodiment of the invention; Figure 3 This is a schematic diagram illustrating the specific process of the data preprocessing and fusion module provided in this embodiment of the invention; Figure 4 This is a schematic diagram illustrating the specific process of executing the geological carbon sequestration potential assessment model provided in this embodiment of the invention; Figure 5 This is a schematic diagram illustrating an implementation scenario of the method for assessing the geological carbon sequestration potential of coastal wetlands provided in this invention. Figure 6This is a flowchart illustrating a method for assessing the geological carbon sequestration potential of coastal wetlands provided in an embodiment of the present invention; Figure 7 This is a schematic diagram of the system structure for assessing the geological carbon sequestration potential of coastal wetlands provided in an embodiment of the present invention; Figure 8 This is a schematic diagram of the system principle architecture for assessing the geological carbon sequestration potential of coastal wetlands provided in an embodiment of the present invention; Figure 9 This is a schematic diagram illustrating the overall process of the method for assessing the geological carbon sequestration potential of coastal wetlands provided in this embodiment of the invention; Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of this invention; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this invention as detailed in the appended claims.

[0019] It is understood that the terms “first,” “second,” etc., used in this invention may be used herein to describe various concepts, but unless specifically stated otherwise, these concepts are not limited by these terms. These terms are used only to distinguish one concept from another. For example, first information may also be referred to as second information without departing from the scope of embodiments of the invention, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to determination” as used herein may be interpreted as “when…” or “when…” or “in response to determination.”

[0020] The terms “at least one,” “multiple,” “each,” “any,” etc., used in this invention, “at least one” includes one, two, or more than two; “multiple” includes two or more than two; “each” refers to each of the corresponding multiple; and “any” refers to any one of the multiple.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0022] In related technologies, existing techniques mainly employ traditional field measurements and simple data analysis methods. For example, some existing technologies focus solely on measuring vegetation carbon storage, estimating carbon storage through plot surveys and statistical analysis of vegetation biomass, while neglecting soil carbon storage and the impact of geological structure on carbon sequestration. This assessment method uses a single evaluation indicator, focusing only on vegetation as a single factor, and cannot comprehensively cover various factors that significantly influence the geological carbon sequestration potential of coastal wetlands, thus failing to fully reflect the geological carbon sequestration potential of coastal wetlands.

[0023] In view of this, this invention provides a system, method, and related equipment for assessing the geological carbon sequestration potential of coastal wetlands. This scheme continuously collects in-situ data of the target coastal wetland through an in-situ monitoring network; acquires multi-temporal, multi-platform remote sensing images of the target coastal wetland through a remote sensing image acquisition module; collects in-situ data and remote sensing images through a data acquisition and transmission unit, and then transmits them to a data management module; the data management module receives and stores the in-situ data and remote sensing images; the data preprocessing and fusion module responds to preset periodic nodes, periodically preprocessing the data from the data management module, and then fusing it to generate high-resolution spatial distribution data; wherein, the high-resolution spatial distribution data includes key parameters at various locations of the target coastal wetland; the high-resolution spatial distribution data is used as model-driving parameters by a geological carbon sequestration potential assessment model, and the assessment results are obtained using the preset geological carbon sequestration potential assessment model; wherein, the assessment results include the spatial distribution of geological carbon sequestration potential in the target coastal wetland; and the assessment results and their spatial distribution are visualized and output through a visualization and output module. This invention integrates five modules—in-situ monitoring, remote sensing, data processing, model calculation, and visualization output—to construct a complete, closed-loop assessment system, achieving full automation and intelligence from data acquisition to result output. Specifically, this invention triggers fusion and assessment through "preset periodic nodes," enabling the system to update assessment results periodically (e.g., monthly, quarterly), dynamically reflecting changes in wetland carbon sequestration potential and effectively overcoming the lag of traditional static assessment methods. Furthermore, the assessment results are presented in a "spatial distribution" format, intuitively demonstrating the spatial heterogeneity of carbon sequestration potential within wetlands (e.g., which areas are carbon sink hotspots), providing direct evidence for precise management (e.g., delineation of priority restoration zones).

[0024] Reference Figure 1 , Figure 1 This is an optional structural diagram of the coastal wetland geological carbon sequestration potential assessment system provided in this embodiment of the invention. The coastal wetland geological carbon sequestration potential assessment system may include, but is not limited to: In-situ monitoring network 1 is used to continuously collect in-situ data of the target coastal wetland; Remote sensing image acquisition module 2 is used to acquire multi-temporal and multi-platform remote sensing images of the target coastal wetland; The data acquisition and transmission unit 3 is used to collect in-situ data and remote sensing images, and then transmit them to the data management module 4; Data management module 4 is used to receive and store in-situ data and remote sensing images; The data preprocessing and fusion module 5 is used to preprocess the data from the data management module 4 in response to preset periodic nodes, and then fuse them to generate high-resolution spatial distribution data; wherein, the high-resolution spatial distribution data includes key parameters of various locations of the target coastal wetland; Geological carbon sequestration potential assessment model 6 is used to take high-resolution spatial distribution data as model driving parameters and process it using a preset geological carbon sequestration potential assessment model to obtain assessment results; wherein, the assessment results include the spatial distribution of geological carbon sequestration potential in the target coastal wetland. The visualization and output module 7 is used to visualize and output the evaluation results and their spatial distribution.

[0025] For example, in some specific implementations, the weekly geological carbon sequestration potential of a river estuary coastal wetland park is assessed. First, an in-situ monitoring network 1, consisting of various sensors and settlement plates, is deployed according to a preset layout in typical areas of the park, such as tidal flats, salt marshes, and bare beaches, to continuously collect data. Simultaneously, remote sensing images of the area are periodically acquired using a remote sensing data acquisition module 2 via satellite or UAV platforms. A data acquisition and transmission unit 3 (such as an IoT gateway) collects all sensor data and transmits it wirelessly to a cloud-based data management module 4, which also receives and stores the remote sensing images. Weekly (preset cycle node), a data preprocessing and fusion module 5 is triggered to fuse the in-situ data from the previous week with the latest remote sensing images, generating a spatial distribution dataset with a preset grid resolution. This dataset contains key parameters such as soil organic carbon content, vegetation biomass, and sedimentation rate for each grid. Subsequently, the geological carbon sequestration potential assessment model 6 loads the aforementioned dataset, runs its internal algorithm, and simulates the carbon input and sequestration process over a future period. Ultimately, it calculates the long-term carbon sequestration volume, annual carbon sequestration rate, and spatial distribution map of the entire park area, serving as the assessment result. Finally, the visualization and output module 7 displays this result on the management platform in the form of interactive maps and reports, and allows for the development of a data export interface to enable report downloads.

[0026] It should be noted that the in-situ monitoring network includes sensors and settling plates, and the in-situ data includes environmental parameters and sedimentation rates. In some embodiments, such as... Figure 2As shown, when the in-situ monitoring network continuously collects in-situ data of the target coastal wetland, it specifically performs the following operations: S11, continuously collects environmental parameters through various types of sensors pre-deployed in various locations of the target coastal wetland; among which, environmental parameters include geological parameters, soil parameters, hydrological parameters and vegetation parameters; S12, collects settlement values ​​at various time points through settlement plates pre-deployed in various locations of the target coastal wetland, and then combines the differences between time points to quantify and obtain the sedimentation rate.

[0027] For example, in some specific implementations, taking the aforementioned wetland park as an example, the in-situ monitoring network is implemented as follows: geological exploration instruments (such as ground-penetrating radar) can be installed at the edges of tidal channels, mangrove areas, and open mudflats to detect the thickness of sedimentary layers; soil carbon content sensors, humidity sensors, and temperature sensors are installed at each monitoring point to continuously record soil data; in addition, water level sensors, water flow velocity sensors, and water quality sensors are deployed in the tidal channels to monitor tidal hydrological dynamics; and vegetation spectrometers and altimeters are set up in the vegetated areas to periodically scan and obtain vegetation growth status. Simultaneously, settlement plates are buried at representative locations, and the average sedimentation rate (e.g., mm / year) is calculated quarterly by measuring the change in the height of the benchmarks.

[0028] Specifically, by deploying physical sensors and settling plates, this invention can directly and continuously acquire core environmental parameters of various types, including geology, soil, hydrology, and vegetation, as well as the key process parameter of sedimentation rate, providing a solid foundation of measured data for subsequent model processing. The collected parameters directly correspond to key physical, chemical, and biological processes affecting carbon sequestration potential (such as sedimentation rate determining burial opportunity, and temperature and humidity controlling decomposition rate), giving subsequent model simulations clear physical meaning and higher reliability.

[0029] It should be noted that in some embodiments, such as Figure 3 As shown, when the data preprocessing and fusion module preprocesses the data from the data management module, it performs the following operations: S51, standardizes the in-situ data; S52, scales the standardized in-situ data based on the spatiotemporal scale of the remote sensing image; S53, uses a wavelet denoising algorithm to denoise the remote sensing image and the scale-transformed in-situ data.

[0030] For example, in some specific implementations, during the data preprocessing stage, the data preprocessing and fusion module 5 first standardizes all in-situ monitored soil organic carbon content, salinity, biomass, and other in-situ data of different dimensions, converting them into Z-Score values ​​with a mean of 0 and a standard deviation of 1. Then, the single-point, time-discontinuous sensor data is scaled to match the spatiotemporal grid data of the 30-meter resolution, monthly composite remote sensing image. Finally, a wavelet denoising algorithm is used to filter out abnormal fluctuation values ​​of soil moisture sensors caused by instantaneous interference and to remove noise pixels in the remote sensing image caused by thin clouds or solar flares.

[0031] Specifically, this invention eliminates dimensional differences between different parameters through standardization, unifies the spatiotemporal benchmark of data through scale transformation, and removes observation errors through denoising. These three preprocessing steps significantly improve the quality and comparability of multi-source data, which is a prerequisite for subsequent high-precision data fusion. Furthermore, a clean and well-organized data format is essential for the efficient training and accurate prediction of machine learning algorithms (such as random forests). The preprocessing steps in this invention ensure the stability and performance of subsequent fusion algorithms.

[0032] It should be noted that in some embodiments, before the data preprocessing and fusion module fuses and generates high-resolution spatial distribution data, it further performs the following operations: performs data matching on the preprocessed in-situ data and remote sensing images, and then establishes the correlation parameters of spatiotemporal correspondence; wherein, the high-resolution spatial distribution data is generated by fusing the correlation parameters of the in-situ data and remote sensing images.

[0033] It should be noted that in-situ data includes instantaneous data from multiple time points. The in-situ data is labeled with the coordinates of the original acquisition point. In some embodiments, when the data preprocessing and fusion module performs data matching on the preprocessed in-situ data and remote sensing imagery to establish spatiotemporal correspondence parameters, it specifically performs the following operations: Based on the time point corresponding to the instantaneous data and the shooting time corresponding to the remote sensing imagery, the in-situ data and remote sensing imagery are time-aligned, and linear interpolation is used to fill in missing time periods, obtaining a time registration result; Based on the coordinates of the original acquisition point and the geographic coordinates corresponding to the remote sensing imagery, the in-situ data and the target grid of the remote sensing imagery are correlated, obtaining a spatial registration result; Based on the time registration result and the spatial registration result, the spatiotemporal correspondence between the in-situ data and the remote sensing imagery is established, obtaining the correlation parameters between the in-situ data and the remote sensing imagery.

[0034] For example, in some specific implementations, during the data matching stage, the data preprocessing and fusion module 5 may perform the following operations: For a certain monitoring point, for example, the soil temperature (instantaneous data) collected at 10:00 on May 1st is an isolated point. The system finds the remote sensing image taken at 9:50 on May 1st, and "aligns" the sensor data to the image capture time through linear interpolation, completing time registration. At the same time, the GPS coordinates (origin coordinates) of the monitoring point are matched with the corresponding geographic coordinates on the remote sensing image to determine that the data of this point belongs to the Xth row and Yth column grid on the image, completing spatial registration. Through this spatiotemporal matching, a precise correlation parameter is established between the "point-like in-situ data" and the "area-like remote sensing image grid". For example, the correspondence between the measured biomass of this point and the vegetation index (NDVI) of this grid on the image is determined.

[0035] Specifically, the embodiments of the present invention can solve the fundamental problem of the spatiotemporal mismatch between the original site data and the remote sensing surface data through "temporal registration" and "spatial registration", providing technical support for the effective fusion of the two. In addition, the embodiments of the present invention establish "association parameters", which are essentially constructing a "bridge" or "lookup table" for retrieving real ground parameters (such as carbon content) from remote sensing features (such as spectral information), so that sparse point data can be effectively corrected and surface data enriched. This is a key step in generating high-resolution spatial distribution maps.

[0036] It should be noted that in some embodiments, the data preprocessing and fusion module performs the following operations when fusing to generate high-resolution spatial distribution data: using remote sensing images as a prior distribution and in-situ data as observations, the posterior distribution is quantized through Bayesian assimilation to obtain preliminary fusion parameter estimates; based on the preliminary fusion parameter estimates, grid pixels of the remote sensing images are used as samples, and parameter values ​​corresponding to grid pixels in the in-situ data are used as labels, and key parameters of the entire target coastal wetland area are predicted through random forest regression; the key parameters are associated with the remote sensing images to generate continuous spatial distribution data as high-resolution spatial distribution data.

[0037] For example, in some specific implementations, when fusing to generate high-resolution data, the data preprocessing and fusion module 5 adopts a two-step method: First, Bayesian assimilation: Assuming that the initial distribution (prior distribution) of soil organic carbon in the entire area retrieved from remote sensing images is uncertain, the measured soil organic carbon content at each monitoring point is used as a high-confidence observation. The prior distribution is updated using the Bayesian formula to obtain a more accurate preliminary global distribution (posterior distribution) that considers measured evidence. Second, random forest regression: Based on the preliminary estimate of each grid obtained in the previous step, multiple remote sensing features of each grid (such as reflectance and texture features of multiple bands) are used as input features (samples), and the measured values ​​of in-situ monitoring points within or near the grid are used as target values ​​(labels) to train a random forest model. This model is used to predict the soil organic carbon content of each grid without monitoring points, ultimately generating a spatially continuous, high-resolution spatial distribution map with the same resolution as the remote sensing image.

[0038] Specifically, this invention combines the advantages of two advanced algorithms, Bayesian assimilation (using a probabilistic framework to fuse observations and prior knowledge to quantify uncertainty) and random forest regression (powerful nonlinear fitting and spatial prediction capabilities), to form a fusion method that combines statistical rigor with the high performance of machine learning, significantly improving the accuracy of spatial mapping of key parameters. Specifically, this invention cleverly utilizes the "area coverage" advantage of remote sensing data and the "point accuracy" advantage of in-situ data, generating data products with both high spatial resolution and high accuracy through prior-observation fusion and machine learning prediction, effectively compensating for the deficiencies of a single data source.

[0039] It should be noted that the high-resolution spatial distribution data is gridded data, and the geological carbon sequestration potential assessment model includes a carbon input stage, a carbon decomposition and transformation stage, and a carbon sequestration stage. In some embodiments, such as... Figure 4As shown, the geological carbon sequestration potential assessment model, when using high-resolution spatial distribution data as model-driving parameters and processing it using a pre-defined geological carbon sequestration potential assessment model to obtain assessment results, specifically performs the following operations: S61, extracting key parameters corresponding to each grid of the target coastal wetland from the high-resolution spatial distribution data as input vectors; among which, key parameters include geological parameters, soil parameters, hydrological parameters, vegetation parameters, and sedimentation rate; S62, in the carbon input stage, determining vegetation biomass, vegetation cover, and vegetation biophysical parameters based on vegetation parameters, and then quantifying the organic matter input flux by combining it with a pre-defined flux calibration coefficient; S63, in the carbon decomposition and transformation stage, simulating the microbial decomposition rate and carbon form transformation based on the organic matter input flux and according to soil parameters to obtain simulation results; S64, in the carbon sequestration stage, based on the simulation results, combining the sedimentation rate, geological parameters, and hydrological parameters to quantify the long-term carbon burial amount and stability to generate an output vector as the assessment result; among which, the output vector includes the long-term carbon sequestration amount and carbon sequestration rate determined based on the long-term burial amount, and the carbon stability index determined based on stability.

[0040] For example, in some specific implementations, when the geological carbon sequestration potential assessment model 6 is running, for instance, all key parameters can be extracted to form an input vector for each 10-meter grid. During the carbon input phase, formula F is used. in =α1·x1·x6+α2·x7, where x1 is vegetation biomass, x6 is vegetation cover, x7 is vegetation biophysical parameters, and α1 and α2 are input flux calibration coefficients (which can be fitted using historical data). In the carbon decomposition and transformation stage, based on the soil temperature, humidity, and dissolved oxygen concentration of the grid, a preset microbial respiration rate-environmental factor relationship function is invoked to calculate the proportion of organic matter input in the previous step that is decomposed in the current year. In the carbon sequestration stage, combining the grid's deposition rate (determining burial speed), sediment thickness (determining sequestration capacity), and water level flooding frequency (affecting the anaerobic environment), the proportion and stability of undecomposed organic matter that is sequestered long-term (e.g., on a century-long scale) are calculated. Finally, the grid outputs three values: cumulative long-term carbon sequestration, annual carbon sequestration rate, and a carbon stability index reflecting the sequestration environment's resistance to disturbance.

[0041] Specifically, the model training and optimization conditions can be achieved as follows: Training data: historical monitoring data, remote sensing inversion data, and field-measured carbon storage data; Optimization mechanism: A real-measurement-simulation comparison feedback mechanism is adopted. The model output is verified periodically with newly collected in-situ data. If the error exceeds the threshold (e.g., RMSE>10%), the calibration coefficients in the model (e.g., α1, α2) are adjusted or the data fusion algorithm is optimized.

[0042] Iterative updates: For example, each time a new batch of data is added, the closed-loop process of fusion → simulation → verification → optimization is re-executed.

[0043] Furthermore, the application principle of the model can be implemented as follows: Mechanism-driven: Mathematical relationships are pre-established based on the physical, chemical, and biological processes of carbon cycling in coastal wetlands; Data-driven: Relying on high-precision, high-resolution multi-source fusion data as input to improve the spatial representativeness and accuracy of simulations.

[0044] Spatiotemporal scalability: It achieves large-scale coverage through remote sensing data and key point calibration through in-situ data, combining scale applicability with local accuracy.

[0045] Specifically, this invention breaks down the complex carbon sequestration process into three logically clear stages: "input-decomposition-storage." Each stage is quantified based on explicit ecological principles and mathematical relationships, making the model easy to understand, calibrate, and verify. Furthermore, the model outputs not only the total amount of carbon sequestration but also the rate (reflecting efficiency) and stability index (reflecting risk), providing multi-dimensional evaluation indicators. This offers greater decision support value than simply providing a carbon storage value. For example, areas with high storage but low stability may require priority protection measures. Specifically, the model is entirely driven by high-resolution spatial parameters generated through prior fusion, enabling the spatial explicitness of the evaluation results.

[0046] This invention also provides a method for assessing the geological carbon sequestration potential of coastal wetlands, applied to the aforementioned system. It is understood that the content of the method embodiments of this invention is applicable to the aforementioned system embodiments, and the specific functions implemented by the method embodiments of this invention are the same as those achieved by the system embodiments of this invention, and the beneficial effects achieved are also the same as those achieved by the aforementioned system embodiments.

[0047] It is understood that the method for assessing the geological carbon sequestration potential of coastal wetlands provided by this invention can also be applied to any computer device with data processing and computing capabilities, and this computer device can be various types of terminals or servers. When the computer device in the embodiments is a server, the server is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Optionally, the terminal can be a smartphone, tablet, laptop, or desktop computer, but it is not limited to these.

[0048] like Figure 5 The diagram shown is a schematic representation of an implementation environment provided by an embodiment of the present invention. (Refer to...) Figure 5 The implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be connected via a network, either wirelessly or via a wired connection, to complete data transmission and exchange.

[0049] Server 101 can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0050] Additionally, server 101 can also be a node server in a blockchain network. Blockchain is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms.

[0051] Terminal 102 can be a smartphone, tablet computer, laptop computer, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. Terminal 102 and server 101 can be directly or indirectly connected via wired or wireless communication, and this embodiment of the invention does not impose any limitations.

[0052] For example, based on Figure 5 The implementation environment shown in this embodiment of the invention provides a method for assessing the geological carbon sequestration potential of coastal wetlands. The following description uses the application of this method in server 101 as an example. It can be understood that this method can also be applied in terminal 102.

[0053] Reference Figure 6 , Figure 6 This is an optional flowchart of the method for assessing the geological carbon sequestration potential of coastal wetlands provided in the embodiments of the present invention. The subject executing the method for assessing the geological carbon sequestration potential of coastal wetlands can be any of the aforementioned computer devices (including servers or terminals). Figure 6 The method may include, but is not limited to, steps S100 to S500.

[0054] Step S100: Continuously acquire in-situ data and remote sensing images of the target coastal wetland; Step S200: In response to a preset periodic node, preprocess the in-situ data and remote sensing images at regular intervals, and then fuse them to generate high-resolution spatial distribution data; wherein, the high-resolution spatial distribution data includes key parameters of various locations of the target coastal wetland; Step S300: High-resolution spatial distribution data is used as model-driven parameters, and the evaluation results are obtained by processing the data using a preset geological carbon sequestration potential assessment model; wherein, the evaluation results include the spatial distribution of geological carbon sequestration potential in the target coastal wetland. Step S400: Visualize and output the evaluation results and their spatial distribution; Step S500: When the sequence reaches the next preset cycle node, return to the execution of the steps that respond to the preset cycle node, periodically preprocess the in-situ data and remote sensing images, and then fuse them to generate high-resolution spatial distribution data, and periodically generate evaluation results.

[0055] To explain in detail the principle of the technical solution of the present invention, the overall process of the present invention will be described below with reference to some specific embodiments. It is easy to understand that the following is an explanation of the technical principle of the present invention and should not be regarded as a limitation of the present invention.

[0056] To address the shortcomings of existing technologies, such as Figure 7 and Figure 8 As shown, this embodiment of the invention provides a system for assessing the geological carbon sequestration potential of coastal wetlands, which can achieve the following: In-situ monitoring network 1: such as sensors, sedimentation plates, etc., used to continuously collect in-situ data such as environmental parameters and sedimentation rates; Remote sensing data acquisition module 2: Used to acquire multi-temporal, multi-platform remote sensing images of the target area; The correlation logic between the parameters and the carbon sequestration potential assessment is as follows: Geological parameters: The distribution of rock strata and the thickness of sediments determine the physical space capacity for carbon sequestration. The greater the sediment thickness and the worse the permeability, the stronger the stability of long-term carbon sequestration. The sedimentation rate directly affects the efficiency of organic matter burial. The higher the sedimentation rate, the greater the probability that organic matter will be quickly sequestered and decomposed.

[0057] Soil parameters: Soil organic carbon content is the core direct indicator of carbon sequestration potential, directly reflecting the current carbon storage; soil moisture and temperature regulate the rate of organic matter decomposition by affecting microbial activity (e.g., high temperature and high humidity environment accelerates decomposition and reduces carbon sequestration efficiency).

[0058] Hydrological parameters: Water level and flow velocity affect carbon migration (e.g., excessively fast water flow can carry away surface organic matter, reducing sequestration efficiency) and oxidation environment (the higher the water level, the stronger the anaerobic environment in the soil, which inhibits the decomposition of organic matter); dissolved oxygen and salinity indirectly affect the amount of organic matter input and the decomposition rate by influencing vegetation growth and microbial community structure.

[0059] Vegetation parameters: Vegetation species (such as mangroves, salt marshes, etc.) determine organic matter production capacity (the net primary productivity of different vegetation varies significantly); cover, height, and biomass directly reflect the amount of carbon sequestration by vegetation and are the main sources of organic matter input; vegetation biophysical parameters (such as leaf area index) can quantify photosynthetic efficiency and support the accurate calculation of organic matter input.

[0060] Remote sensing parameters: Wetland type determines the basic characteristics of carbon sequestration ecosystems (different wetland types have significantly different carbon sequestration efficiencies); topography affects hydrological conditions and vegetation distribution, indirectly regulating the carbon cycle process; surface inundation frequency affects the rate of organic matter decomposition by altering the anaerobic / aerobic environment of the soil.

[0061] Data acquisition and transmission unit 3: connected to the in-situ monitoring network 1, responsible for acquiring data from each sensor and transmitting the data via wired or wireless means; Data Management Module 4: Receives, stores, and manages data from In-situ Monitoring Network 1, Remote Sensing Data Acquisition Module 2, and possible historical data; Data Preprocessing and Fusion Module 5: Performs preprocessing such as denoising on multi-source data to generate high-resolution spatial distribution maps of key parameters; (Input details: In-situ monitoring data: including all parameters in the above "List of Specific Parameters of In-situ Monitoring Data" (geological, soil, hydrological, vegetation-related parameters and sedimentation rate). Remote sensing data: including all parameters in the "List of Specific Parameters for Remote Sensing Data" above (wetland type, vegetation distribution, topography, etc.). Supporting data: historical and background data (such as regional past carbon storage monitoring data, climate background data, etc.).

[0062] Output details: High-resolution spatial distribution map / dataset of key parameters (covering the target coastal wetland area, containing continuous spatial distribution information of all core parameters, such as "spatial distribution map of soil organic carbon content" and "spatial distribution map of vegetation biomass").

[0063] Interaction logic with Geological Carbon Sequestration Potential Assessment Model 6: The output of Data Preprocessing and Fusion Module 5 is the core driving input of Geological Carbon Sequestration Potential Assessment Model 6. Specific interaction process: The high-resolution spatial dataset generated by Module 5 provides spatiotemporally continuous and accuracy-matched parameter support for Model 6 (solving the problems of sparse in-situ data and insufficient accuracy of remote sensing data). Model 6, based on these high-resolution parameters, simulates the entire process of organic matter input, decomposition, transformation and long-term sequestration in coastal wetland soil / sediments. The spatial continuity and high precision of the parameters directly ensure the accuracy of the simulation process. The simulation results of Model 6 (such as the spatial distribution of carbon sequestration) can be fed back to Module 5 to optimize the data fusion algorithm (such as adjusting the weight allocation in the fusion process when the simulation results deviate significantly from the local measured data). Geological carbon sequestration potential assessment model 6: Utilizes fused high-resolution spatial data to provide model-driven parameters for assessing geological carbon sequestration potential; The core formula of the wetland carbon sequestration model is as follows: Input vector X = {x1, x2, ..., x n}; Output vector Y=[C,R,SI], then perform flux calculation. The formula for calculating the input flux of organic matter is as follows: F in =α1·x1·x6+α2·x7; where x1 is vegetation biomass, x6 is vegetation cover, x7 is vegetation biophysical parameter, and α1 and α2 are input flux calibration coefficients (fitted from historical data).

[0064] Visualization and Output Module 7: This module can visually display the evaluation results and provides a data export interface.

[0065] In some specific application scenarios, the technical solution of this invention can be implemented as follows: A deployed in-situ monitoring network is used to continuously collect in-situ data such as environmental parameters and sedimentation rates; remote sensing image data of the target area is acquired simultaneously; historical and background data are collected; then, using data fusion technology, the high-precision but sparse in-situ data is fused with the wide-coverage but relatively low-precision remote sensing surface data to generate a high-resolution spatial distribution map / dataset of key parameters. Subsequently, based on the input parameters, a model simulates the input, decomposition, transformation, and long-term sequestration process of organic matter in coastal wetland soil / sediments, calculating and outputting the geological carbon sequestration potential of the target area within a specified time period, including long-term carbon sequestration, carbon sequestration rate, carbon stability index, and their spatial distribution. Simultaneously, the geological carbon sequestration potential assessment results are dynamically updated with the continuous input of new in-situ and remote sensing data. The model parameters or fusion algorithm are optimized and calibrated by comparing the model simulation results with subsequent measured data.

[0066] Furthermore, based on the specific process of the aforementioned in-situ monitoring network 1 and remote sensing data acquisition module 2, various types of data are collected by installing multiple sensors distributed in different locations. At the same time, information such as wetland type, vegetation distribution, topography, surface inundation frequency, and vegetation biophysical parameters are extracted from the remote sensing images of the target area.

[0067] Based on the specific process of the data acquisition and transmission unit 3 and the data management module 4, the data acquisition and transmission unit 3 can be connected to the in-situ monitoring network 1 to comprehensively collect relevant data of the coastal wetland, including geological data, soil data, hydrological data and vegetation data. At the same time, the data acquired by the in-situ monitoring network 1 and the remote sensing data acquisition module 2 can be transmitted to the data management module 4. The data management module 4 can organize the massive heterogeneous data collected and establish a spatiotemporal database.

[0068] Based on the specific workflow of the data preprocessing and fusion module 5 described above, multi-source data undergoes preprocessing such as standardization, scale transformation, and denoising. Data assimilation and machine learning methods are then used to fuse the original site data and remote sensing surface data to generate a high-resolution spatial distribution map of key parameters.

[0069] 1. Data preprocessing: Standardization: Convert all parameters to standard values ​​with a mean of 0 and a variance of 1 to eliminate dimensional differences; Scale conversion: unify the spatiotemporal scale of the original site data (without a fixed scale) with that of remote sensing data (such as 30m resolution) (the time scale is unified to a month, and the spatial scale is unified to a 10m grid). Denoising: Wavelet denoising algorithm is used to remove sensor errors (such as random fluctuations in soil moisture sensors) and remote sensing image noise (such as cloud interference). 2. Data Matching: - Time Registration: Aligning instantaneous data from in-situ monitoring (e.g., water level at a certain time point) with the capture time of remote sensing images, and using linear interpolation to supplement missing time periods; - Spatial Registration: Matching the coordinates of in-situ data points with the geographic coordinates of remote sensing images, with each in-situ data point corresponding to several grids in the remote sensing image; - Parameter Correlation: Establishing the correspondence between in-situ parameters and remote sensing parameters (e.g., the correlation between vegetation spectral information and vegetation biomass); 3. Algorithm Fusion: Step 1 (Bayesian Assimilation): (1) Take remote sensing surface data (such as vegetation index at 30m resolution) as the prior distribution P(X), and assume that it follows a normal distribution; (2) Take the original site data (such as measured vegetation biomass) as the observed value Y, and establish the observation equation Y=H(X)+ε (H is the observation operator, ε is the observation error, and follows a normal distribution with a mean of 0). (3) Calculate the posterior distribution using Bayes' formula P(XY)∝P(YX)P(X) to obtain the preliminary parameter estimates of the fusion. Step 2 (Random Forest Regression): ①Use grid pixels of remote sensing data as samples (feature variables are remote sensing parameters), and the parameter values ​​of the original site data as labels; ② Train a random forest model (set the number of decision trees to 100 and the maximum depth to 10), and use the model to predict the parameter values ​​of the entire region to generate continuous spatial distribution data.

[0070] 4. Validation and optimization: Select 20% of the original site data as the validation set, and calculate the RMSE between the fused data and the measured values ​​of the validation set; - If RMSE > 10%, adjust the number of decision trees in the random forest or the prior distribution parameters of Bayesian assimilation, and repeat step 3 (algorithm fusion) until RMSE ≤ 10%; finally, output the optimized high-resolution spatial distribution map.

[0071] Based on the specific process of the geological carbon sequestration potential assessment model 6 and visualization and output module 7, the fused high-resolution spatial data is used to provide model-driven parameters for assessing the potential of geological carbon sequestration.

[0072] Based on the specific process of the visualization and output module 7 mentioned above, the evaluation results, key parameter distribution maps, model diagnostic information, etc. are displayed intuitively in the form of charts, maps, etc., and a data export interface is provided.

[0073] like Figure 9 As shown, this invention also discloses a method for operating a coastal wetland geological carbon sequestration potential assessment system: S1: Monitoring network deployment and data acquisition: Scientifically deploy an in-situ monitoring network in the target coastal wetland area; S2: Multi-source data preprocessing and fusion: Preprocessing the collected in-situ monitoring data and remote sensing data; S3: Geological carbon sequestration potential model calculation: Input the fused high-resolution spatial dataset into the preset geological carbon sequestration potential assessment model; S4: Results Visualization and Output: Visualize the evaluation results and their spatial distribution, and output an evaluation report; S5: Dynamic Updates and Feedback: As new in-situ and remote sensing data continue to be input, repeat steps S2-S4 periodically or in real time.

[0074] In summary, the implementation principle of the coastal wetland geological carbon sequestration potential assessment system and method according to an embodiment of the present invention is as follows: First, various sensors in the in-situ monitoring network 1, including a geological exploration instrument, are used to detect the geological structure of the coastal wetland, such as rock layer distribution and sediment thickness; soil carbon content sensor, soil moisture sensor, and soil temperature sensor are used to measure the organic carbon content, moisture, and temperature in the soil, respectively; water level sensor, water flow velocity sensor, and water quality sensor can acquire water level height, water flow velocity, and water quality parameters such as dissolved oxygen and salinity; vegetation spectrometer and altimeter are also included. This system is used to collect spectral information of vegetation to determine vegetation species and coverage, as well as to measure vegetation height and biomass. It covers multiple factors such as geology, soil, hydrology, and vegetation, and can comprehensively reflect the geological carbon sequestration potential of coastal wetlands. It overcomes the problem of single indicators in existing technologies. Subsequently, data from various sources are collected, transmitted, and fused to generate high-resolution spatial distribution maps of key parameters. Finally, using the fused high-resolution spatial data as driving parameters, an evaluation model is used to evaluate the geological carbon sequestration potential and generate an assessment report. The generated assessment report is then presented intuitively.

[0075] This invention also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described above. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0076] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0077] like Figure 10 As shown, Figure 10 The hardware structure of an electronic device 1000 according to another embodiment is illustrated. The electronic device 1000 includes: The processor 1001 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (aSIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention. The memory 1002 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RaM). The memory 1002 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1002 and is called and executed by the processor 1001. Input / output interface 1003 is used to implement information input and output; The communication interface 1004 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 1005 transmits information between various components of the device (e.g., processor 1001, memory 1002, input / output interface 1003, and communication interface 1004); The processor 1001, memory 1002, input / output interface 1003 and communication interface 1004 are connected to each other within the device via bus 1005.

[0078] The electronic device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0079] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0080] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0081] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0082] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0083] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0084] The coastal wetland geological carbon sequestration potential assessment system, method, electronic device, storage medium, and program products provided in this invention continuously collect in-situ data of the target coastal wetland through an in-situ monitoring network; acquire multi-temporal and multi-platform remote sensing images of the target coastal wetland through a remote sensing image acquisition module; collect in-situ data and remote sensing images through a data acquisition and transmission unit, and then transmit them to a data management module; receive and store in-situ data and remote sensing images through the data management module; and, in response to preset periodic nodes, preprocess the data from the data management module at regular intervals, and then fuse them to generate high-resolution spatial distribution data. The high-resolution spatial distribution data includes key parameters at various locations of the target coastal wetland. The high-resolution spatial distribution data is used as model-driving parameters by a geological carbon sequestration potential assessment model, and the assessment results are obtained using the preset geological carbon sequestration potential assessment model. The assessment results include the spatial distribution of geological carbon sequestration potential in the target coastal wetland. The assessment results and their spatial distribution are visualized and output through a visualization and output module. This invention integrates five modules—in-situ monitoring, remote sensing, data processing, model calculation, and visualization output—to construct a complete, closed-loop assessment system, achieving full automation and intelligence from data acquisition to result output. Specifically, this invention triggers fusion and assessment through "preset periodic nodes," enabling the system to update assessment results periodically (e.g., monthly, quarterly), dynamically reflecting changes in wetland carbon sequestration potential and effectively overcoming the lag of traditional static assessment methods. Furthermore, the assessment results are presented in a "spatial distribution" format, intuitively demonstrating the spatial heterogeneity of carbon sequestration potential within wetlands (e.g., which areas are carbon sink hotspots), providing direct evidence for precise management (e.g., delineation of priority restoration zones).

[0085] The embodiments described in this invention are for the purpose of more clearly illustrating the technical solutions of the embodiments of this invention, and do not constitute a limitation on the technical solutions provided by the embodiments of this invention. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this invention are also applicable to similar technical problems.

[0086] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present invention, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0087] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0088] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0089] The preferred embodiments of the present invention have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and spirit of the present invention should be within the scope of the claims of the present invention.

Claims

1. A system for assessing the geological carbon sequestration potential of coastal wetlands, characterized in that, The system includes: An in-situ monitoring network is used to continuously collect in-situ data of the target coastal wetlands; The remote sensing image acquisition module is used to acquire multi-temporal and multi-platform remote sensing images of the target coastal wetland; The data acquisition and transmission unit is used to collect the in-situ data and the remote sensing images, and then transmit them to the data management module; The data management module is used to receive and store the in-situ data and the remote sensing images; The data preprocessing and fusion module is used to preprocess the data from the data management module at preset periodic nodes, and then fuse it to generate high-resolution spatial distribution data; wherein, the high-resolution spatial distribution data includes key parameters of various locations of the target coastal wetland; A geological carbon sequestration potential assessment model is used to process the high-resolution spatial distribution data as model driving parameters and obtain assessment results using a preset geological carbon sequestration potential assessment model; wherein, the assessment results include the spatial distribution of geological carbon sequestration potential in the target coastal wetland. The visualization and output module is used to visualize and output the evaluation results and their spatial distribution.

2. The system according to claim 1, characterized in that, The in-situ monitoring network includes sensors and sedimentation plates. The in-situ data includes environmental parameters and sedimentation rates. When continuously collecting in-situ data of the target coastal wetland, the in-situ monitoring network specifically performs the following operations: The environmental parameters are continuously collected by various types of sensors pre-deployed throughout the target coastal wetland. The environmental parameters include geological parameters, soil parameters, hydrological parameters, and vegetation parameters; The sedimentation rate is obtained by collecting sedimentation values ​​at various time points through sedimentation plates pre-deployed at various locations in the target coastal wetland, and then combining the differences between the time points to quantify the sedimentation rate.

3. The system according to claim 1, characterized in that, When the data preprocessing and fusion module preprocesses the data from the data management module, it specifically performs the following operations: The in-situ data is standardized. The in-situ data after standardization is scaled based on the spatiotemporal scale of the remote sensing image. The remote sensing image and the scale-transformed in-situ data are denoised using a wavelet denoising algorithm.

4. The system according to claim 1, characterized in that, Before the data preprocessing and fusion module generates high-resolution spatial distribution data, it further performs the following operations: Data matching is performed on the preprocessed in-situ data and the remote sensing image to establish correlation parameters for spatiotemporal correspondence. The high-resolution spatial distribution data is generated by fusing the correlation parameters of the in-situ data and the remote sensing image.

5. The system according to claim 1, characterized in that, The in-situ data includes instantaneous data at multiple time points, and the in-situ data is labeled with the coordinates of the in-situ acquisition location. When the data preprocessing and fusion module performs data matching on the preprocessed in-situ data and the remote sensing image to establish the correlation parameters of spatiotemporal correspondence, it specifically performs the following operations: Based on the time point corresponding to the instantaneous data and the shooting time corresponding to the remote sensing image, the in-situ data and the remote sensing image are time-aligned, and linear interpolation is used to fill in the missing time periods to obtain the time registration result. Based on the original site coordinates and the geographic coordinates corresponding to the remote sensing image, the original site data is associated with the target grid of the remote sensing image to obtain the spatial registration result. Based on the time registration results and the spatial registration results, a spatiotemporal correspondence between the in-situ data and the remote sensing image is established, and the correlation parameters between the in-situ data and the remote sensing image are obtained.

6. The system according to claim 1, characterized in that, When the data preprocessing and fusion module generates high-resolution spatially distributed data, it performs the following operations: Using the remote sensing imagery as a prior distribution and the in-situ data as observations, the posterior distribution is quantized through Bayesian assimilation to obtain preliminary fusion parameter estimates. Based on the preliminary fusion parameter estimation, the grid pixels of the remote sensing image are used as samples, and the parameter values ​​of the in-situ data corresponding to the grid pixels are used as labels. The key parameters of the entire target coastal wetland area are obtained by random forest regression prediction. The key parameters are associated with the remote sensing image to generate continuous spatial distribution data as the high-resolution spatial distribution data.

7. The system according to claim 1, characterized in that, The high-resolution spatial distribution data is gridded data. The geological carbon sequestration potential assessment model includes a carbon input stage, a carbon decomposition and transformation stage, and a carbon sequestration stage. When the geological carbon sequestration potential assessment model uses the high-resolution spatial distribution data as model driving parameters and processes the data using a preset geological carbon sequestration potential assessment model to obtain the assessment results, it specifically performs the following operations: The key parameters corresponding to each grid of the target coastal wetland are extracted from the high-resolution spatial distribution data as input vectors; wherein, the key parameters include geological parameters, soil parameters, hydrological parameters, vegetation parameters and sedimentation rate; In the carbon input stage, vegetation biomass, vegetation cover and vegetation biophysical parameters are determined based on the vegetation parameters, and then the organic matter input flux is quantified by combining the preset flux calibration coefficient. In the carbon decomposition and transformation stage, based on the organic matter input flux, the microbial decomposition rate and carbon form transformation are simulated according to the soil parameters to obtain simulation results; During the carbon sequestration stage, based on the simulation results, and combined with the deposition rate, geological parameters, and hydrological parameters, a long-term carbon burial quantity and stability are quantified to generate an output vector as the evaluation result. The output vector includes the long-term carbon sequestration amount and carbon sequestration rate determined based on the long-term burial amount, and the carbon stability index determined based on the stability.

8. A method for assessing the geological carbon sequestration potential of coastal wetlands, characterized in that, Applied to the system according to any one of claims 1 to 7, the method comprises the following steps: Continuously acquire in-situ data and remote sensing images of the target coastal wetlands; In response to preset periodic nodes, the in-situ data and the remote sensing image are preprocessed at regular intervals, and then fused to generate high-resolution spatial distribution data; wherein, the high-resolution spatial distribution data includes key parameters of various locations of the target coastal wetland; The high-resolution spatial distribution data is used as the model driving parameters, and the evaluation results are obtained by processing the data using a preset geological carbon sequestration potential assessment model; wherein, the evaluation results include the spatial distribution of geological carbon sequestration potential in the target coastal wetland. The evaluation results and their spatial distribution are visualized and output. When the sequence reaches the next preset period node, return to the execution of the step of responding to the preset period node, periodically preprocessing the in-situ data and the remote sensing image, and then fusing them to generate high-resolution spatial distribution data, and periodically generating the evaluation result.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method of claim 8.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of claim 8.

Images