A Soil Carbon Sequestration and Emission Reduction Detection Method Combining Isotope Tracing Technology

Abstract

This invention discloses a method for detecting soil carbon sequestration and emission reduction using isotope tracing technology, relating to the fields of environmental science and agricultural technology. It establishes an online coupled system comprising a front-end column chromatography separation module, a mid-end isotope ratio mass spectrometer, and a back-end AI algorithm. Front-end sampling and column chromatography separation are performed in the target area to obtain classified gas components. This online coupled system, combining isotope tracing technology, enables real-time reception and processing of monitoring data through the collaborative work of the front-end column chromatography separation module, the mid-end isotope ratio mass spectrometer, and the back-end AI algorithm. It rapidly generates emission source contribution heatmaps, significantly shortening data acquisition and processing time. This ensures that managers can obtain accurate emission information in a timely manner, enabling rapid response and effective control measures. It avoids missing the optimal intervention window due to data lag, significantly improving the efficiency and timeliness of soil carbon sequestration and emission reduction monitoring.

Description

Technical Field

[0001] This invention relates to the fields of environmental science and agricultural technology, specifically to a method for detecting soil carbon sequestration and emission reduction using isotope tracing technology. Background Technology

[0002] Soil is one of the largest carbon sinks in terrestrial ecosystems, possessing enormous carbon sequestration potential. Agriculture is a significant source of greenhouse gas emissions, with emissions of gases such as carbon dioxide, methane, and nitrous oxide from soil making a substantial contribution to the greenhouse effect. By monitoring soil carbon sequestration and emission reduction, we can clarify the emission characteristics and dynamic changes of greenhouse gases during wheat and corn cultivation, providing a basis for formulating scientific and reasonable emission reduction measures, thereby effectively reducing the impact of agricultural activities on climate change.

[0003] In existing technologies, soil carbon sequestration and emission reduction detection relies heavily on offline sampling and laboratory analysis processes. This results in long data acquisition cycles and makes it difficult to capture short-term emission pulses and diurnal / seasonal fluctuations. Consequently, subsequent management measures may miss the optimal intervention window due to data lag. Therefore, the problem this invention aims to solve is how to build an online coupled system that includes column chromatography, isotope tracing, and real-time AI algorithm analysis to generate emission source contribution heat maps and realize an integrated soil carbon sequestration and emission reduction detection process that combines separation, detection, and source tracing. To this end, a soil carbon sequestration and emission reduction detection method combining isotope tracing technology is proposed. Summary of the Invention

[0004] The purpose of this invention is to provide a soil carbon sequestration and emission reduction detection method that combines isotope tracing technology to solve the problems mentioned in the background art.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0006] A method for detecting soil carbon sequestration and emission reduction using isotope tracing technology includes the following steps:

[0007] Step 1: Build an online coupled system that includes a front-end column chromatography separation module, a mid-end isotope ratio mass spectrometer, and a back-end AI algorithm;

[0008] Step 2: Perform front-end sampling and column chromatography separation in the target area to obtain classified gas components, and perform mid-range isotope ratio mass spectrometry to obtain gas isotope characteristic data.

[0009] Step 3: Receive mass spectrometer data in real time through backend AI algorithms, analyze gas concentration and isotopic fingerprint characteristics, and identify emission source types and contribution ratios.

[0010] Step 4: Based on the analysis results, the AI ​​algorithm generates a soil greenhouse gas emission source contribution heat map, showing the distribution and intensity of emission sources in different regions;

[0011] Step 5: Combine heat maps and isotope data to trace the sources of greenhouse gas emissions, continuously monitor them dynamically, and capture short-term emission pulses and daily / seasonal scale fluctuations.

[0012] Step 6: The system automatically matches the preset early warning threshold, triggers the early warning signal, and adjusts agricultural management measures to carry out control and intervention, thereby improving the carbon sequestration and emission reduction effect.

[0013] A further improvement to the technical solution of the present invention is that step 1 includes:

[0014] Wheat and corn planting plots that need to be tested for soil carbon sequestration and emission reduction are selected as target areas, and monitoring targets are set. Then, column chromatography separation module, isotope ratio mass spectrometer and AI algorithm are selected as needed.

[0015] Based on the selected column chromatography separation module, isotope ratio mass spectrometer, and AI algorithm, an online coupling system suitable for the target region was built. This system includes a front-end column chromatography separation module, a mid-end isotope ratio mass spectrometer, and a back-end AI algorithm. The hardware connections of each module were ensured to be correct, the data transmission lines were unobstructed, the column chromatography separation conditions were optimized, and the isotope ratio mass spectrometer parameters were adjusted to achieve the best detection sensitivity. At the same time, the back-end AI algorithm was initialized and configured to ensure that it could receive and process data in real time.

[0016] A further improvement to the technical solution of the present invention is that step 2 includes:

[0017] Gas sampling devices are deployed in a grid layout of 10m×10m in the target area. The sampling devices introduce gas samples into the column chromatography separation module through the gas path system, ensuring that the sampling devices and column chromatography modules are tightly connected and the gas path is unobstructed to avoid gas leakage or contamination.

[0018] After receiving the gas sample, the column chromatography separation module separates the gas based on its physicochemical properties. By optimizing the column temperature and carrier gas flow rate, different greenhouse gas components are effectively separated. The separated gas components are then sequentially sent to the isotope ratio mass spectrometer to provide pure gas samples for subsequent detection and ensure the accuracy of the detection results.

[0019] The isotope ratio mass spectrometer receives the separated gas components and uses a dual-inlet method to simultaneously detect isotope characteristic data. The conventional inlet is used to introduce sample gas, while the high-concentration inlet is used to inject standard gas with known isotope ratios for mass discrimination correction. At the same time, the chromatographic separation time axis is aligned through a dynamic time warping algorithm to generate a concentration-isotope data stream, which is then pushed to the back-end AI algorithm in real time.

[0020] A further improvement to the technical solution of the present invention is that step 3 includes:

[0021] The backend AI algorithm receives the concentration-isotope data stream pushed by the mass spectrometer in real time via the MQTT protocol, analyzes the timestamp, gas composition and isotope ratio, segments the data using the sliding window method with a window length of 15 minutes, applies Kalman filtering to smooth noise, fills missing values ​​using the KNN algorithm to ensure the spatiotemporal continuity of the data, and standardizes the data to convert it into a unified format.

[0022] The backend AI algorithm uses a pre-trained LSTM-random forest hybrid model to analyze the standardized data, extract the dynamic features and isotopic fingerprint features of the gas concentration time series, and then compare them with known isotopic feature databases to identify the emission source types of different greenhouse gases.

[0023] Based on the identified emission source types, the contribution ratio of each emission source to greenhouse gas concentration is further analyzed, and the relative contribution of each emission source is quantified.

[0024] A further improvement to the technical solution of this invention lies in the following: the analysis process for the emission source type and contribution ratio is as follows:

[0025] The pre-trained LSTM model was used to analyze the standardized gas concentration time series data, capture the dynamic features in the time series data, extract the pattern of gas concentration change over time, and extract isotope fingerprint features, that is, the features of the ratio of different isotopes in the gas.

[0026] The extracted isotopic fingerprint features are compared with a known isotopic feature database, which stores typical isotopic features of different emission sources. The feature identifier of each emission source is determined by comparison, that is, the unique isotopic fingerprint of each emission source. Based on the comparison results, the emission source type is classified and identified using a random forest model, and the identification results are output to clarify the greenhouse gas emission source type of each sampling point.

[0027] Based on the identified emission source types, we further analyzed the contribution ratio of each emission source to greenhouse gas concentration. Using the output probability of the random forest model, we quantified the relative contribution of each emission source. Combined with gas concentration time series data, we analyzed the changes in the contribution of different emission sources in different time periods.

[0028] A further improvement to the technical solution of the present invention is that step 4 includes:

[0029] The AI ​​algorithm aggregates the emission source contribution data after analysis into a 10m×10m grid, calculates the average contribution ratio of each emission source in each grid, and uses the Kriging interpolation algorithm combined with spatial autocorrelation characteristics to convert the discrete grid data into a continuous spatial distribution field, generating a basic contribution density map covering the entire target area to ensure spatial continuity.

[0030] Based on the interpolation results, thematic contribution maps are generated according to emission source type, and then merged into a comprehensive heat map through a weighted overlay algorithm. The contribution intensity is divided into five levels: low / low-medium / medium / high-medium / high using the natural breakpoint method. The contribution intensity is visualized using different color gradients from blue to yellow to red. At the same time, the dominant emission source type in each region is marked to enhance the readability of the information.

[0031] The system receives new data every 15 minutes and triggers incremental updates, recalculating only the grid areas affected by the new data, refreshing the heatmap through GPU-accelerated rendering, and finally outputting a visual interface that supports interactive operation.

[0032] A further improvement to the technical solution of this invention lies in the following: the generation process of the basic contribution density map is as follows:

[0033] The emission source contribution data parsed by the AI ​​algorithm is aggregated into a 10m×10m grid. All sampling point data in each grid are summarized to ensure the data integrity in each grid. For each grid, the average contribution ratio of each emission source is calculated. The average emission source contribution ratio calculated in each grid is stored as grid contribution data. Each grid corresponds to a set of average emission source contribution ratios, forming a discrete grid dataset.

[0034] The Kriging interpolation algorithm is used to spatially interpolate the grid contribution data in a discrete grid dataset. The values ​​of unknown points are estimated based on the values ​​of known points, and the spatial autocorrelation of the grid contribution data is analyzed to determine the parameters of the Kriging interpolation.

[0035] Based on the Kriging interpolation results, discrete grid data is converted into a continuous spatial distribution field. The continuous spatial distribution field generated by Kriging interpolation is then plotted as a basic contribution density map covering the entire target area. The generated basic contribution density map is verified by comparing it with known emission source distribution information to ensure its rationality and accuracy. Based on the verification results, the Kriging interpolation parameters or AI algorithm are optimized to further improve the accuracy of the basic contribution density map.

[0036] A further improvement to the technical solution of the present invention is that step 5 includes:

[0037] The generated heat map is combined with isotope data for analysis. The heat map provides spatial distribution information, while the isotope data provides emission source characteristic identification. The isotope fingerprint characteristics are associated with emission source types. The spatial resolution of the heat map and the density of isotope sampling points are calibrated simultaneously to ensure spatiotemporal matching of the data and form a multi-dimensional emission source characteristic database.

[0038] A Bayesian mixture model is used to fuse the contribution ratio of heat map and isotope concentration data in real time, and the instantaneous contribution intensity of each emission source is calculated in reverse. High-frequency pulses and low-frequency periods in the time series are extracted by wavelet analysis to obtain emission pulse characteristics and mark the spatiotemporal coordinates of abnormal emission events. When an abnormal emission event is detected, a high-precision resampling verification mechanism is triggered.

[0039] Based on historical emission pulse characteristics, the update frequency of the heat map and the isotope sampling strategy are dynamically adjusted, and the emission trend of the next 24 hours is predicted using an LSTM neural network.

[0040] A further improvement to the technical solution of this invention lies in the following: the process of predicting the emission trend in the next 24 hours using an LSTM neural network is as follows:

[0041] Historical emission data is collected, including the contribution ratio of emission sources in the heat map, isotope concentration data, and time series data. The data is organized, historical emission pulse features are extracted, and wavelet analysis is used to extract high-frequency pulse features and low-frequency periodic features from the historical emission data. The emission pulse features of different regions are analyzed to identify regions and time periods with frequent emission activities. The extracted emission pulse features are then stored in a feature database, including the spatiotemporal coordinates of each sampling point and pulse feature parameters.

[0042] Based on the characteristics of historical emission pulses, the target area is divided into sub-regions with different priorities. High-priority areas are those with frequent and large emission pulses, while low-priority areas are those with less emission activity. The update frequency of the heat map is dynamically adjusted according to the regional priority, and the isotope sampling strategy is also adjusted. This dynamic adjustment strategy is implemented, and the heat map update and isotope sampling process are monitored in real time. Based on real-time data feedback, the adjustment strategy is further optimized to ensure the effective use of resources and the accuracy of data.

[0043] The LSTM neural network model is trained using historical emission data, and the model parameters are optimized to ensure that the model can accurately capture the dynamic features in the time series. The latest emission data is then input into the trained LSTM neural network model to predict the emission trend for the next 24 hours. The prediction results include the emission concentration and emission source contribution ratio for each sampling point. The prediction results are then visualized to generate a heat map of the emission trend for the next 24 hours.

[0044] A further improvement to the technical solution of the present invention is that step 6 includes:

[0045] The system monitors emission data in real time and automatically compares the current emission indicators of each emission source with the preset warning thresholds. When the monitored value exceeds the warning threshold range, an warning signal is immediately triggered, and management personnel are notified through a visual interface, SMS or email to ensure timely response.

[0046] Based on the early warning signals, the causes of exceeding the standards are analyzed and corresponding control strategies are matched from the knowledge base to generate targeted management measures and suggestions, which managers can then adjust agricultural activities accordingly.

[0047] Managers implement control interventions according to the adjusted measures, continuously monitor the intervention effects, compare data before and after the intervention, evaluate the effectiveness of the measures, provide a reference for subsequent management, and ensure that agricultural activities meet the carbon sequestration and emission reduction targets.

[0048] Due to the adoption of the above technical solution, the technical progress achieved by this invention compared to the prior art is as follows:

[0049] 1. This invention provides a soil carbon sequestration and emission reduction detection method combining isotope tracing technology. The online coupling system combining isotope tracing technology, through the collaborative work of the front-end column chromatography separation module, the mid-end isotope ratio mass spectrometer, and the back-end AI algorithm, can receive and process monitoring data in real time, and quickly generate emission source contribution heat maps. This greatly shortens the time for data acquisition and processing, ensuring that managers can obtain accurate emission information in a timely manner, thereby responding quickly and taking effective control measures, avoiding missing the best intervention window due to data lag, and significantly improving the efficiency and timeliness of soil carbon sequestration and emission reduction monitoring.

[0050] 2. This invention provides a soil carbon sequestration and emission reduction detection method combining isotope tracing technology. By utilizing the correlation between isotope fingerprint characteristics and emission source types, and analyzing gas concentration and isotope characteristics through AI algorithms, it can accurately identify different emission source types and their contribution ratios. It can not only distinguish different emission sources such as soil organic matter decomposition, microbial activity, and fertilizer application, but also quantify the relative contribution of each emission source to greenhouse gas concentration. By dynamically monitoring and analyzing the spatiotemporal changes of emission sources, managers can identify high-emission areas and major emission sources, thereby formulating targeted emission reduction strategies, optimizing agricultural management measures, effectively reducing greenhouse gas emission risks, and improving carbon sequestration and emission reduction effects. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0052] Figure 1 This is a schematic diagram of the workflow of the present invention;

[0053] Figure 2 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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 some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] Example 1, as Figure 1 , Figure 2 As shown, this invention provides a method for detecting soil carbon sequestration and emission reduction using isotope tracing technology, comprising the following steps:

[0056] Step 1: Construct an online coupling system comprising a front-end column chromatography separation module, a mid-end isotope ratio mass spectrometer, and a back-end AI algorithm. Select wheat and corn planting plots that require soil carbon sequestration and emission reduction monitoring as target areas and set monitoring targets. Then, select the column chromatography separation module, isotope ratio mass spectrometer, and AI algorithm as needed. Based on the selected column chromatography separation module, isotope ratio mass spectrometer, and AI algorithm, construct an online coupling system suitable for the target area, comprising a front-end column chromatography separation module, a mid-end isotope ratio mass spectrometer, and a back-end AI algorithm. Ensure that the hardware connections of each module are correct, the data transmission lines are unobstructed, and optimize the column chromatography separation conditions. Adjust the isotope ratio mass spectrometer parameters to achieve the best detection sensitivity. At the same time, initialize and configure the back-end AI algorithm to ensure that it can receive and process data in real time.

[0057] The specific workflow for step 1 is as follows:

[0058] Select plots of land that have been continuously planted with wheat-corn rotation for more than 3 years, covering different soil types and topography, ensuring that the plots have a stable power supply, 4G / 5G signal coverage, and irrigation systems, and set monitoring targets, with the core indicators being: , , Emission flux and its isotopic characteristics , , For spatiotemporal resolution, the spatial resolution is 10 m × 10 m, and the temporal resolution is 15 minutes, with nighttime resolution reduced to 5 minutes. The selection of the front-end column chromatography separation module is based on the requirement to complete the separation within 5 minutes. , , Baseline separation is required, and the instrument is suitable for high humidity and dusty gas environments. The selection criteria for a mid-range isotope ratio mass spectrometer are multi-isotope detection capabilities: simultaneous measurement is necessary. , , With an accuracy of ≤0.3‰, adaptable to gas concentration fluctuations, the selection criteria for the backend AI algorithm were based on the requirement to complete data analysis and heat map generation for 10 monitoring points within 1 minute. An online coupling system was built. Based on the selected column chromatography separation module, isotope ratio mass spectrometer, and AI algorithm, the outlet of the column chromatography separation module was connected to the inlet of the isotope ratio mass spectrometer via a 1 / 8-inch stainless steel capillary tube (2m in length), with a three-way valve installed for standard gas calibration. The mass spectrometer pushed the concentration-isotope data stream to the AI ​​algorithm server in real time via TCP / IP protocol. Data transmission tests were conducted to ensure that the column chromatography separation module could transmit the separated gas component data to the isotope ratio mass spectrometer, and that the isotope ratio mass spectrometer could transmit the detected isotope characteristic data to the AI ​​algorithm in real time. The column chromatography separation conditions were optimized to ensure effective separation of greenhouse gas components, meeting standard requirements. Gas samples were tested, separation conditions were optimized to ensure the best separation effect, and the parameters of the isotope ratio mass spectrometer were adjusted according to the isotopic characteristics of the target gas. Calibration was performed using standard isotope gases to ensure optimal detection sensitivity and accuracy. The AI ​​algorithm was initialized and configured, including the data receiving interface, data processing model, and warning threshold settings, to ensure that the AI ​​algorithm could receive and process data transmitted from the mass spectrometer in real time and generate heat maps and source tracing results. Actual sampling tests were conducted in the target area, and the entire online coupling system was run to check its normal operation, including sampling, separation, detection, data transmission, and analysis. The system's detection results were compared with known emission source characteristics to ensure the system's accuracy and reliability. The results of offline sampling and laboratory analysis were compared to verify the performance advantages of the online coupling system.

[0059] Step 2: Front-end sampling and column chromatography separation are performed in the target area to obtain classified gas components. Mid-range isotope ratio mass spectrometry is then used to acquire isotopic characteristic data of the gases. Gas sampling devices are deployed in a 10m × 10m grid layout in the target area. The sampling devices introduce gas samples into the column chromatography separation module through a gas path system, ensuring a tight connection between the sampling devices and the column chromatography module, unobstructed gas flow, and preventing gas leakage or contamination. This ensures that the collected gas samples accurately reflect the emissions in the target area. After receiving the gas samples, the column chromatography separation module separates the gases based on their physicochemical properties. By optimizing column temperature and carrier gas flow rate, different greenhouse gas components are effectively separated. The separated gas components are then sequentially sent to an isotope ratio mass spectrometer to provide pure gas samples for subsequent detection, ensuring the accuracy of the detection results. The isotope ratio mass spectrometer receives the separated gas components and uses a dual-inlet method to simultaneously detect isotope characteristic data. The conventional inlet is used to introduce sample gas, while the high-concentration inlet is injected with standard gas of known isotope ratios for mass discrimination correction. At the same time, the chromatographic separation time axis is aligned through a dynamic time warping algorithm to generate a concentration-isotope data stream, which is then pushed to the back-end AI algorithm in real time.

[0060] The specific workflow for step 2 is as follows:

[0061] Sampling points were divided into a 10m × 10m grid pattern in the target area (wheat or corn planting plots), and the location of each sampling point was marked to ensure uniform distribution and comprehensive coverage of the target area. A gas sampling device, such as a soil gas diffuser, gas chromatograph injector, or other suitable equipment for soil gas collection, was installed at each sampling point. The sampling device was ensured to be securely installed to prevent loosening or damage due to external factors (such as wind, animals, etc.). The sampling device was connected to the column chromatography separation module via the gas path system. The gas path connection was checked for tightness to ensure unobstructed flow and prevent gas leakage or contamination. A leak test was performed on the gas path system, using soapy water to check for air bubbles at the connections to ensure the gas sample accurately reflects the emissions of the target area. The gas sampling device was activated to collect soil gas samples from the target area, ensuring the sampling frequency and time met the detection requirements. Sampling was set to once per hour to capture short-term emission pulses. The collected gas samples were then introduced into the column chromatography separation module via the gas path system. The column chromatography separation module optimized the separation conditions based on the physicochemical properties of the gas and set an appropriate column temperature according to the boiling point and polarity of the target gas. , , The column temperature is set between 40℃ and 60℃, and a suitable carrier gas, such as helium or nitrogen, is selected. The flow rate is adjusted to ensure effective separation of gas components, with the carrier gas flow rate set between 1.0 mL / min and 2.0 mL / min. Through optimized column chromatography conditions, different greenhouse gas components are effectively separated, ensuring the purity of the separated gas components. The gas components separated by column chromatography are then sequentially sent to an isotope ratio mass spectrometer. The isotope ratio mass spectrometer uses a dual-inlet method to simultaneously detect isotope characteristic data. The sample gas is introduced through the conventional inlet for isotope ratio measurement, while the high-concentration inlet is injected with standard gas with known isotope ratios for mass discrimination correction. The chromatographic separation time axis is aligned using a dynamic time warping algorithm to ensure data accuracy, generating a concentration-isotope data stream, including gas concentration and isotope ratio information. This concentration-isotope data stream is then pushed to the backend AI algorithm in real time.

[0062] Step 3: The backend AI algorithm receives mass spectrometer data in real time, analyzes gas concentration and isotopic fingerprint characteristics, identifies emission source types and contribution ratios. The backend AI algorithm receives the concentration-isotope data stream pushed by the mass spectrometer in real time via the MQTT protocol, parses the timestamp, gas components and isotope ratios, segments the data using the sliding window method with a window length of 15 minutes, applies Kalman filtering to smooth noise, fills missing values ​​using the KNN algorithm to ensure the spatiotemporal continuity of the data, standardizes the data and converts it into a unified format, and uses a pre-trained LSTM-random forest hybrid model to analyze the standardized data, extracts the dynamic characteristics and isotopic fingerprint characteristics of the gas concentration time series, and then compares them with known isotopic feature databases to identify different greenhouse gas emission source types. Based on the identified emission source types, the contribution ratio of each emission source to the greenhouse gas concentration is further analyzed, and the relative contribution of each emission source is quantified.

[0063] Furthermore, the analysis process for emission source types and contribution ratios is as follows:

[0064] A pre-trained LSTM model was used to analyze standardized gas concentration time series data, capturing dynamic features and extracting patterns of gas concentration changes over time. Simultaneously, isotopic fingerprint features—characteristics of the ratios of different isotopes in the gas—were extracted and compared with a known isotopic feature database containing typical isotopic features of different emission sources. The comparison determined the characteristic identifiers of each emission source, i.e., the unique isotopic fingerprints of each source. Based on the comparison results, a random forest model was used to classify and identify emission source types, outputting the identification results and clarifying the greenhouse gas emission source type for each sampling point. Based on the identified emission source types, the contribution ratio of each emission source to greenhouse gas concentration was further analyzed. The output probability of the random forest model was used to quantify the relative contribution of each emission source. Combined with the gas concentration time series data, the changes in the contribution of different emission sources over different time periods were analyzed.

[0065] The formula for calculating the output probability of a random forest model is as follows:

[0066] ;

[0067] In the formula, Indicates input sample Type of emission source The probability, This represents the number of decision trees in the random forest model. Indicates the first A decision tree for input samples The prediction results For indicator functions, if ,but ;otherwise The output probability of the random forest model is determined by the voting results of each decision tree. For a given input sample, each decision tree in the random forest model will give a prediction result. The final output probability of the random forest model is the average of the prediction results of all decision trees.

[0068] The formulas for calculating the contribution ratio of each emission source to greenhouse gas concentration are as follows:

[0069] ;

[0070] In the formula, Indicates emission source type The proportion of contribution to greenhouse gas concentration, Indicates the number of sampling points. Indicates the first The gas at each sampling point belongs to the emission source type. The probability, Indicates the first Gas concentration at each sampling point This indicates the total number of emission source types. This represents the total weighted contribution of all emission source types to the gas concentration at all sampling points;

[0071] The formulas for calculating the changes in the contributions of different emission sources over different time periods are as follows:

[0072] ;

[0073] In the formula, Indicates within the time window Internal, emission source types The proportion of contribution to greenhouse gas concentration, This represents a time window, containing all sampling points within that window.

[0074] The specific workflow for step 3 is as follows:

[0075] The backend AI algorithm receives concentration-isotope data streams from the isotope ratio mass spectrometer in real time via the MQTT protocol, ensuring the stability and real-time nature of data transmission, avoiding data loss or delay, and analyzing the timestamps, gas components, and isotope ratios in the data stream. Gas components include... , , Isotope ratios such as , The parsed data is stored in a temporary data buffer. A sliding window method is used to segment the data, with a window length of 15 minutes. Data within each window is treated as an independent segment for subsequent analysis. A Kalman filter is applied to smooth the data within each segment, removing noise. The KNN algorithm is used to fill in missing values ​​in the data segments to ensure the spatiotemporal continuity of the data. The processed data is then standardized to a uniform format. A pre-trained LSTM (Long Short-Term Memory) model is used to analyze the standardized gas concentration time series data. The LSTM model captures dynamic features in the time series data, extracting patterns of gas concentration changes over time and extracting features of different isotope ratios in the gas, i.e., isotope fingerprint features, to distinguish different emission sources. The extracted isotope fingerprint features are compared with a known isotope feature database. The isotopic feature database stores typical isotopic features of different emission sources, such as soil organic matter decomposition, microbial activity, and fertilizer application. Through comparison, a unique isotopic fingerprint is determined for each emission source. Based on the comparison results, a random forest model is used to classify and identify emission source types. The random forest model outputs the greenhouse gas emission source type for each sampling point based on the isotopic fingerprint features and known emission source features. The output clearly identifies the emission source type for each sampling point, such as soil organic matter decomposition, microbial activity, or fertilizer application. Based on the identified emission source types, the contribution ratio of each emission source to greenhouse gas concentration is further analyzed. The output probability of the random forest model is used to quantify the relative contribution of each emission source. Then, combined with gas concentration time series data, the changes in the contribution of different emission sources over different time periods are analyzed, generating a time series graph of the emission source contribution ratio, which visually displays the dynamic changes of each emission source.

[0076] Step 4: Based on the analysis results, the AI ​​algorithm generates a soil greenhouse gas emission source contribution heat map, showing the distribution and intensity of emission sources in different regions;

[0077] Step 5: Combine heat maps and isotope data to trace the sources of greenhouse gas emissions, continuously monitor them dynamically, and capture short-term emission pulses and daily / seasonal scale fluctuations.

[0078] Step 6: The system automatically matches the preset early warning threshold, triggers the early warning signal, and adjusts agricultural management measures to carry out control and intervention, thereby improving the carbon sequestration and emission reduction effect.

[0079] Example 2, as Figure 1 , Figure 2 As shown, based on Embodiment 1, the present invention provides a technical solution: Preferably, step 4 includes:

[0080] The AI ​​algorithm aggregates and analyzes the emission source contribution data in a 10m×10m grid, calculates the average contribution ratio of each emission source within each grid, and uses the Kriging interpolation algorithm, combined with spatial autocorrelation characteristics, to transform the discrete grid data into a continuous spatial distribution field, generating a basic contribution density map covering the entire target area to ensure spatial continuity. Based on the interpolation results, thematic contribution maps are generated according to emission source type, and then merged into a comprehensive heat map using a weighted overlay algorithm. The contribution intensity is divided into five levels: low / low-medium / medium / high-medium / high, using the natural breakpoint method, and visualized with different color gradients from blue to yellow to red. At the same time, the dominant emission source type in each area is marked to enhance information readability. The system receives new data every 15 minutes and triggers incremental updates, only recalculating the grid areas affected by the new data. The heat map is refreshed through GPU-accelerated rendering, and finally outputs a visualization interface that supports interactive operation. Users can zoom, pan, or switch time dimensions to view the spatiotemporal evolution trend of emission source contributions.

[0081] Furthermore, the process for generating the basic contribution density map is as follows:

[0082] The emission source contribution data parsed by the AI ​​algorithm is aggregated into a 10m×10m grid. All sampling point data within each grid are summarized to ensure the data integrity of each grid. For each grid, the average contribution ratio of each emission source is calculated. The calculated average emission source contribution ratio within each grid is stored as grid contribution data. Each grid corresponds to a set of average emission source contribution ratios, forming a discrete grid dataset. The Kriging interpolation algorithm is used to spatially interpolate the grid contribution data in the discrete grid dataset. The values ​​of unknown points are estimated based on the values ​​of known points, and the spatial autocorrelation of the grid contribution data is analyzed to determine the parameters of the Kriging interpolation. Based on the Kriging interpolation results, the discrete grid data is converted into a continuous spatial distribution field. The continuous spatial distribution field generated by Kriging interpolation is plotted as a basic contribution density map covering the entire target area. The generated basic contribution density map is verified by comparing it with known emission source distribution information to ensure its rationality and accuracy. Based on the verification results, the Kriging interpolation parameters or AI algorithm are optimized to further improve the accuracy of the basic contribution density map.

[0083] The formula for calculating the average contribution ratio of each emission source is as follows:

[0084] ;

[0085] In the formula, Indicates the first The average contribution ratio of each emission source within the current grid. This indicates the number of sampling points within the current grid. Indicates the first The first grid sampling point The contribution ratio of each emission source;

[0086] The formula for calculating Kriging interpolation is as follows:

[0087] ;

[0088] In the formula, Indicates the target point The estimated value, Represents a known point The actual value, The weighting coefficients are calculated based on spatial autocorrelation. Indicates the number of known points;

[0089] The specific workflow for step 4 is as follows:

[0090] A quadtree structure is used to spatially partition the target area, aggregating discrete sampling point data into 10m×10m grid cells. Each grid cell is defined with a unique ID. The grid cell to which a sampling point belongs is calculated based on its coordinates. For sampling points located at the grid boundary (i.e., those less than 1m from the boundary), nearest neighbor assignment is used to avoid duplicate assignments. Then, the data from all sampling points within each grid are summarized, and the average contribution ratio of each emission source is calculated. Simultaneously, the calculated average contribution ratio of emission sources within each grid is stored as grid contribution data, forming a discrete grid dataset. Based on the grid contribution data, the experimental variability function is calculated, where coverage is set... The maximum lag distance of the grid range is determined, and the number of range bands is determined by setting the lag interval. For each emission source type, the semivariogram of each range band is calculated, and then the theoretical variogram is fitted. Using the semivariogram model, the least squares method is used to fit the parameters, and evaluation indicators including the sum of squared residuals and the coefficient of determination are calculated. Cross-validation optimization is then performed, excluding one grid data point at a time, and using the remaining grids to interpolate and predict the value of that grid. The root mean square error is calculated, and if the root mean square error is >15%, the variogram parameters are adjusted. Based on the Kriging interpolation results, the discrete grid data is converted into a continuous spatial distribution field, and a basic contribution density map covering the entire target area is drawn. The contribution density is represented by color gradients. The generated baseline contribution density map is validated by comparing it with known emission source distribution information to ensure its rationality and accuracy. Based on the validation results, the Kriging interpolation parameters or AI algorithms are optimized to further improve the accuracy of the baseline contribution density map. Based on the interpolation results, thematic contribution maps are generated for each emission source type, showing its contribution distribution within the target area. A weighted overlay algorithm is used to merge the thematic contribution maps of different emission source types into a comprehensive heat map, assigning different weights based on the importance or contribution ratio of each emission source. The system uses a row overlay method and natural breakpoint method to divide the contribution intensity into five levels: low / low-medium / medium / high-medium / high. It uses different color gradients from blue to yellow to red for visualization. The dominant emission source type in each region is marked on the comprehensive heat map. The system receives new data every 15 minutes and triggers incremental updates. Only the grid areas affected by the new data are recalculated to avoid recalculating the entire dataset. GPU-accelerated rendering is used to refresh the heat map to ensure the smoothness of the visualization interface. The output visualization interface supports interactive operation. Users can zoom, pan, or switch time dimensions to view the spatiotemporal evolution trend of emission source contribution.

[0091] Step 5 includes:

[0092] The generated heatmaps are combined with isotopic data for analysis. The heatmaps provide spatial distribution information, while the isotopic data provides emission source characteristic identification. The isotopic fingerprint characteristics are correlated with emission source types. The spatial resolution of the heatmaps and the density of isotopic sampling points are calibrated simultaneously to ensure spatiotemporal matching of the data, forming a multi-dimensional emission source characteristic database. A Bayesian mixture model is used to fuse the contribution ratio of the heatmaps and isotopic concentration data in real time, and the instantaneous contribution intensity of each emission source is calculated in reverse. Wavelet analysis is used to extract high-frequency pulses and low-frequency periods in the time series to obtain emission pulse characteristics. The spatiotemporal coordinates of abnormal emission events are marked. When an abnormal emission event is detected, a high-precision resampling verification mechanism is triggered. Based on historical emission pulse characteristics, the heatmap update frequency and isotopic sampling strategy are dynamically adjusted. An LSTM neural network is used to predict the emission trend for the next 24 hours.

[0093] The process of using an LSTM neural network to predict emissions trends over the next 24 hours is as follows:

[0094] Historical emission data was collected, including the contribution ratio of emission sources in the heat map, isotope concentration data, and time series data. The data was processed, and historical emission pulse characteristics were extracted. Wavelet analysis was used to extract high-frequency pulse characteristics and low-frequency periodic characteristics from the historical emission data. The emission pulse characteristics of different regions were analyzed to identify areas and time periods with frequent emission activity. The extracted emission pulse characteristics were then stored in a feature database, including the spatiotemporal coordinates and pulse characteristic parameters of each sampling point. Based on the historical emission pulse characteristics, the target area was divided into sub-regions of different priorities. High-priority regions were those with frequent and large-amplitude emission pulses; low-priority regions were those with less emission activity. The update frequency of the heat map was dynamically adjusted according to the region priority. In high-priority regions, the update frequency was increased to once every 15 minutes; in low-priority regions, the update frequency was decreased to once every hour. Next, the isotope sampling strategy is adjusted simultaneously. In high-priority areas, the isotope sampling density is increased, the number of sampling points is increased, or the sampling interval is shortened. In low-priority areas, the original sampling density is maintained or the number of sampling points is appropriately reduced. This dynamic adjustment strategy is implemented, and the heat map update and isotope sampling process are monitored in real time. Based on real-time data feedback, the adjustment strategy is further optimized to ensure the effective use of resources and the accuracy of data. Historical emission data, including time series data, heat map contribution ratio, and isotope concentration, are used to train the LSTM neural network model. The model parameters are optimized to ensure that the model can accurately capture the dynamic features in the time series. The latest emission data is input into the trained LSTM neural network model to predict the emission trend in the next 24 hours. The prediction results include the emission concentration and emission source contribution ratio of each sampling point. The prediction results are then visualized to generate an emission trend heat map for the next 24 hours.

[0095] The specific workflow for step 5 is as follows:

[0096] The generated heatmap (providing spatial distribution information) is combined with isotopic data (providing emission source characteristic identifiers) for analysis. This ensures that the spatial resolution of the heatmap matches the density of isotopic sampling points, allowing for accurate spatiotemporal correspondence of the data. Based on the fingerprint characteristics in the isotopic data, the characteristic identifiers of each emission source are clearly defined. The isotopic fingerprint characteristics are associated with the emission source type, forming a one-to-one correspondence. The spatial distribution information of the heatmap and the emission source characteristic identifiers in the isotopic data are integrated into a database containing multi-dimensional information such as the geographical location of each sampling point, emission source type, isotopic fingerprint characteristics, and contribution ratio. A Bayesian mixture model is used to fuse the contribution ratio data and isotopic concentration data from the heatmap in real time, and to reverse-engineer the emission sources. The instantaneous contribution intensity is determined, and wavelet analysis is performed on the time series data of emission sources to extract high-frequency pulse and low-frequency periodic features, obtain emission pulse characteristics, and mark the spatiotemporal coordinates of abnormal emission events. When an abnormal emission event is detected, a high-precision resampling verification mechanism is triggered to perform high-precision sampling of the spatiotemporal coordinates of the abnormal event to verify its authenticity. Based on historical emission pulse characteristics, the update frequency of the heat map and the isotope sampling strategy are dynamically adjusted. The time series data of emission sources is analyzed using an LSTM neural network to predict the emission trend in the next 24 hours. The prediction results are visualized to show the spatial distribution of the emission trend in the next 24 hours, and the time dimension switching function is provided in the visualization interface to facilitate users to view the prediction results for different time periods.

[0097] Step 6 includes:

[0098] The system monitors emission data in real time and automatically compares the current emission indicators of each emission source with preset warning thresholds. When the monitored value exceeds the warning threshold, an early warning signal is immediately triggered, and managers are notified through a visual interface, SMS, or email to ensure timely response. Based on the warning signal, the system analyzes the reasons for exceeding the standard and matches corresponding control strategies from the knowledge base to generate targeted management measures. Managers adjust agricultural activities accordingly, such as optimizing fertilizer application, changing irrigation methods, or adjusting planting patterns, to reduce emission risks and improve carbon sequestration and emission reduction effects. Managers implement control interventions according to the adjusted measures and continuously monitor the intervention effects, compare data before and after the intervention, evaluate the effectiveness of the measures, and provide a reference for subsequent management to ensure that agricultural activities meet carbon sequestration and emission reduction targets.

[0099] The specific workflow for step 6 is as follows:

[0100] The system receives and processes emission monitoring data in real time, including greenhouse gas concentrations and the contribution ratio of emission sources. Data sources include online monitoring equipment and AI algorithm analysis results. It compares the current emission indicators of each emission source with preset warning thresholds in real time. These preset warning thresholds are set according to emission standards and management objectives. When a monitored value exceeds the warning threshold, a warning signal is immediately triggered. The warning signal is notified to management personnel through multiple methods, including a visual interface, SMS notifications, and email notifications. For the visual interface, the warning information is displayed on the system interface, highlighting the areas and indicators exceeding the standard. For SMS notifications, a text message is sent to management personnel, including the warning information, the exceeding indicator, and recommended measures. For email notifications, an email is sent to management personnel, detailing the warning situation and recommended measures. Detailed information for each warning is recorded, generating a warning log. Based on the warning signals, the specific causes of exceeding the standard are analyzed, including excessive fertilization, improper irrigation, or improper soil management. Excessive fertilization easily leads to… Increased emissions and improper irrigation can easily lead to Increased emissions and improper soil management can easily lead to Increased emissions trigger the matching of control strategies corresponding to the causes of exceedances from a knowledge base. The knowledge base stores response measures and suggestions for different causes of exceedances. Based on the matching results, targeted management measures are generated, such as optimizing fertilizer application (reducing nitrogen fertilizer application, increasing the proportion of organic fertilizer), changing irrigation methods (using drip or sprinkler irrigation to reduce flooding time), adjusting planting patterns (using crop rotation or intercropping to improve soil structure), and notifying managers of these management measures through visual interfaces, SMS, or email. Managers adjust agricultural activities according to the recommendations, continuously monitor emission data after intervention, record the intervention effects, compare data before and after intervention, and evaluate the effectiveness of the measures. For example, a decrease in emission concentration indicates the measures are effective; no change or an increase in emission concentration indicates the measures are ineffective and require further adjustment. The evaluation results are fed back to the knowledge base to optimize future control strategies. The intervention effect evaluation results serve as a reference for subsequent management, continuously optimizing agricultural activities to ensure they meet carbon sequestration and emission reduction targets and reduce greenhouse gas emissions.

[0101] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for detecting soil carbon sequestration and emission reduction using isotope tracing technology, characterized in that, Includes the following steps: Step 1: Build an online coupled system that includes a front-end column chromatography separation module, a mid-end isotope ratio mass spectrometer, and a back-end AI algorithm; Step 2: Perform front-end sampling and column chromatography separation in the target area to obtain classified gas components, and perform mid-range isotope ratio mass spectrometry to obtain gas isotope characteristic data. Step 3: Receive mass spectrometer data in real time through backend AI algorithms, analyze gas concentration and isotopic fingerprint characteristics, and identify emission source types and contribution ratios. Step 4: Based on the analysis results, the AI ​​algorithm generates a soil greenhouse gas emission source contribution heat map, showing the distribution and intensity of emission sources in different regions; Step 5: Combine heat maps and isotope data to trace the sources of greenhouse gas emissions, continuously monitor them dynamically, and capture short-term emission pulses and daily / seasonal scale fluctuations. Step 6: The system automatically matches the preset early warning threshold, triggers the early warning signal, and adjusts agricultural management measures to carry out control and intervention. Step 2 includes: Gas sampling devices are deployed in a grid layout of 10m×10m in the target area. The sampling devices introduce gas samples into the column chromatography separation module through the gas path system. After receiving the gas sample, the column chromatography separation module separates the gas according to its physicochemical properties. By optimizing the column temperature and carrier gas flow rate, different greenhouse gas components are effectively separated, and then the separated gas components are sequentially sent to the isotope ratio mass spectrometer. The isotope ratio mass spectrometer receives the separated gas components and uses a dual-inlet method to simultaneously detect isotope characteristic data. The conventional inlet is used to introduce sample gas, while the high-concentration inlet is used to inject standard gas with known isotope ratios for mass discrimination correction. At the same time, the chromatographic separation time axis is aligned through a dynamic time warping algorithm to generate a concentration-isotope data stream, which is then pushed to the back-end AI algorithm in real time. Step 4 includes: The AI ​​algorithm aggregates the emission source contribution data after analysis into a 10m×10m grid, calculates the average contribution ratio of each emission source in each grid, and uses the Kriging interpolation algorithm, combined with spatial autocorrelation characteristics, to convert the discrete grid data into a continuous spatial distribution field, generating a basic contribution density map covering the entire target area. Based on the interpolation results, thematic contribution maps are generated according to emission source type, and then merged into a comprehensive heat map through a weighted overlay algorithm. The contribution intensity is divided into five levels: low / low-medium / medium / high-medium / high using the natural breakpoint method, and visualized using different color gradients from blue to yellow to red. At the same time, the dominant emission source type in each region is marked. The system receives new data every 15 minutes and triggers incremental updates, recalculating only the grid areas affected by the new data, refreshing the heatmap through GPU-accelerated rendering, and finally outputting a visual interface that supports interactive operation.

2. The method for detecting soil carbon sequestration and emission reduction using isotope tracing technology according to claim 1, characterized in that: Step 1 includes: Wheat and corn planting plots that need to be tested for soil carbon sequestration and emission reduction are selected as target areas, and monitoring targets are set. Then, column chromatography separation module, isotope ratio mass spectrometer and AI algorithm are selected as needed. Based on the selected column chromatography separation module, isotope ratio mass spectrometer, and AI algorithm, an online coupling system suitable for the target region is built, including a front-end column chromatography separation module, a mid-end isotope ratio mass spectrometer, and a back-end AI algorithm. The column chromatography separation conditions are optimized, the isotope ratio mass spectrometer parameters are adjusted to achieve the best detection sensitivity, and the back-end AI algorithm is initialized and configured.

3. The method for detecting soil carbon sequestration and emission reduction using isotope tracing technology according to claim 1, characterized in that: Step 3 includes: The backend AI algorithm receives the concentration-isotope data stream pushed by the mass spectrometer in real time via the MQTT protocol, analyzes the timestamp, gas composition and isotope ratio, segments the data using the sliding window method with a window length of 15 minutes, applies Kalman filtering to smooth noise, fills in missing values ​​using the KNN algorithm, and standardizes the data to convert it into a unified format. The backend AI algorithm uses a pre-trained LSTM-random forest hybrid model to analyze the standardized data, extract the dynamic features and isotopic fingerprint features of the gas concentration time series, and then compare them with known isotopic feature databases to identify the emission source types of different greenhouse gases. Based on the identified emission source types, the contribution ratio of each emission source to greenhouse gas concentration is further analyzed, and the relative contribution of each emission source is quantified.

4. The method for detecting soil carbon sequestration and emission reduction using isotope tracing technology according to claim 3, characterized in that: The analysis process for the emission source types and contribution ratios is as follows: The pre-trained LSTM model was used to analyze the standardized gas concentration time series data, capture the dynamic features in the time series data, extract the pattern of gas concentration change over time, and extract isotope fingerprint features, that is, the features of the ratio of different isotopes in the gas. The extracted isotopic fingerprint features are compared with a known isotopic feature database. The feature identifier of each emission source is determined by the comparison, that is, the unique isotopic fingerprint of each emission source. Based on the comparison results, the emission source type is classified and identified using a random forest model, and the identification results are output to clarify the greenhouse gas emission source type of each sampling point. Based on the identified emission source types, we further analyzed the contribution ratio of each emission source to greenhouse gas concentration. Using the output probability of the random forest model, we quantified the relative contribution of each emission source. Combined with gas concentration time series data, we analyzed the changes in the contribution of different emission sources in different time periods.

5. The method for detecting soil carbon sequestration and emission reduction using isotope tracing technology according to claim 1, characterized in that: The process of generating the basic contribution density map is as follows: The emission source contribution data parsed by the AI ​​algorithm is aggregated into a 10m×10m grid. All sampling point data in each grid are summarized. For each grid, the average contribution ratio of each emission source is calculated. The average emission source contribution ratio calculated in each grid is stored as grid contribution data. Each grid corresponds to a set of average emission source contribution ratios, forming a discrete grid dataset. The Kriging interpolation algorithm is used to spatially interpolate the grid contribution data in a discrete grid dataset. The values ​​of unknown points are estimated based on the values ​​of known points, and the spatial autocorrelation of the grid contribution data is analyzed to determine the parameters of the Kriging interpolation. Based on the Kriging interpolation results, discrete grid data is converted into a continuous spatial distribution field. The continuous spatial distribution field generated by Kriging interpolation is plotted as a basic contribution density map covering the entire target area. The generated basic contribution density map is verified by comparing it with known emission source distribution information. Based on the verification results, the Kriging interpolation parameters or AI algorithm are optimized.

6. The method for detecting soil carbon sequestration and emission reduction using isotope tracing technology according to claim 1, characterized in that: Step 5 includes: The generated heat map is combined with isotope data for analysis. The heat map provides spatial distribution information, while the isotope data provides emission source characteristic identification. The isotope fingerprint characteristics are associated with emission source types, and the spatial resolution of the heat map and the density of isotope sampling points are calibrated simultaneously to form a multi-dimensional emission source characteristic database. A Bayesian mixture model is used to fuse the contribution ratio of heat map and isotope concentration data in real time, and the instantaneous contribution intensity of each emission source is calculated in reverse. High-frequency pulses and low-frequency periods in the time series are extracted by wavelet analysis to obtain emission pulse characteristics and mark the spatiotemporal coordinates of abnormal emission events. When an abnormal emission event is detected, a high-precision resampling verification mechanism is triggered. Based on historical emission pulse characteristics, the update frequency of the heat map and the isotope sampling strategy are dynamically adjusted, and the emission trend of the next 24 hours is predicted using an LSTM neural network.

7. The method for detecting soil carbon sequestration and emission reduction using isotope tracing technology according to claim 6, characterized in that: The process of using an LSTM neural network to predict emission trends for the next 24 hours is as follows: Historical emission data is collected, including the contribution ratio of emission sources in the heat map, isotope concentration data, and time series data. The data is organized, historical emission pulse features are extracted, and wavelet analysis is used to extract high-frequency pulse features and low-frequency periodic features from the historical emission data. The emission pulse features of different regions are analyzed to identify regions and time periods with frequent emission activities. The extracted emission pulse features are then stored in a feature database. Based on the characteristics of historical emission pulses, the target area is divided into sub-regions with different priorities. High-priority areas are those with frequent and large emission pulses, while low-priority areas are those with less emission activity. The update frequency of the heat map is dynamically adjusted according to the regional priority, and the isotope sampling strategy is also adjusted. The dynamic adjustment strategy is implemented, and the heat map update and isotope sampling process are monitored in real time. The adjustment strategy is further optimized based on real-time data feedback. The LSTM neural network model is trained using historical emission data, and the model parameters are optimized. The latest emission data is then input into the trained LSTM neural network model to predict the emission trend for the next 24 hours. The prediction results include the emission concentration and emission source contribution ratio for each sampling point. The prediction results are then visualized to generate a heat map of the emission trend for the next 24 hours.

8. The method for detecting soil carbon sequestration and emission reduction using isotope tracing technology according to claim 7, characterized in that: Step 6 includes: The system monitors emission data in real time and automatically compares the current emission indicators of each emission source with the preset warning thresholds. When the monitored value exceeds the range of the warning threshold, an warning signal is immediately triggered, and the management personnel are notified through a visual interface, SMS or email. Based on the early warning signals, the causes of exceeding the standards are analyzed and corresponding control strategies are matched from the knowledge base to generate targeted management measures and suggestions, which managers can then adjust agricultural activities accordingly. Managers implement control interventions according to the adjusted measures, continuously monitor the intervention effects, compare data before and after the intervention, evaluate the effectiveness of the measures, and provide a reference for subsequent management.

Images