Carbon sink potential prediction method and device fusing remote sensing and model technology

Abstract

The application provides a carbon sink potential prediction method and device fusing remote sensing and model technology. The carbon sink potential prediction method fusing remote sensing and model technology comprises the following steps: inputting multi-temporal remote sensing data into a vegetation type identification model based on historical remote sensing data and historical vegetation type labels to obtain vegetation structure dynamic distribution data; inputting the vegetation structure dynamic distribution data into a regional carbon-nitrogen cycle model based on historical crop distribution data and vegetation and soil dynamic data to obtain a regional carbon-nitrogen cycle dynamic simulation result; and determining carbon sink data according to the regional carbon-nitrogen cycle dynamic simulation result. The application can break through the bottleneck of insufficient regional scale carbon accounting data and high uncertainty, and realize carbon sink maximization.

Description

Technical Field

[0001] This invention relates to the field of smart agricultural management technology, specifically to a method and apparatus for predicting carbon sequestration potential that integrates remote sensing and modeling technologies. Background Technology

[0002] The carbon budget of agricultural systems is a crucial component of the Earth's carbon cycle. Farmland is one of the land types with the highest net primary productivity, absorbing and releasing CO2 at rapid rates. The primary pathway for carbon sequestration in agriculture is increasing soil carbon sequestration capacity; 90% of agricultural emission reductions are achieved through increasing soil organic carbon. Due to the significant human intervention in agricultural systems, the factors influencing farmland carbon emissions and soil organic carbon sequestration are highly complex. Nitrogen and water management have a particularly significant impact on farmland carbon exchange. The emissions of the three greenhouse gases (CO2, N2O, CH4) from farmland systems are mainly products of microbial activity within a carbon-nitrogen-water coupling mechanism. Therefore, factors such as soil composition, fertilization, irrigation, plant type, organic fertilizer use, and straw management all significantly affect changes in soil organic carbon. Thus, strengthening research on the changes and responses of CO2, N2O, and CH4 emissions from farmland soil under human agricultural activities is of great importance for understanding and estimating carbon emissions from agricultural systems.

[0003] Currently, satellite remote sensing imagery can effectively observe specific spectra of above-ground crops and underground soil in farmland with extremely high spatiotemporal resolution. This allows for the inversion of spatiotemporal dynamics of key variables such as crop type, growth status, and soil organic matter content. It is widely used in agricultural planting structure identification, agricultural disaster yield monitoring, and farmland greenhouse gas and carbon sequestration assessment at different regional scales, offering significant advantages in data convenience and timeliness at the regional scale.

[0004] Agriculture is a significant source of greenhouse gas emissions, and there is an urgent need to accurately assess the dynamics of greenhouse gas emissions and carbon sequestration potential of agricultural ecosystems in order to achieve green and sustainable upgrading of agriculture by improving agricultural management.

[0005] Current regional-scale simulation technologies suffer from spatial variability, leading to problems such as untimely model-driven databases (e.g., crop planting distribution) and inaccurate regional validation observations (e.g., crop growth status), resulting in significant uncertainties in regional simulation assessments.

[0006] Satellite remote sensing technology is an important tool for regional data acquisition and key variable retrieval. However, the grid resolution of current mainstream satellite platforms is only 10-100m, which is not suitable for the characteristics of typical rural areas with small, interspersed plots and complex planting structures in regional-scale crop species identification and variable retrieval applications. Furthermore, current satellite data is rarely used in agricultural carbon-nitrogen-water processes, and there is still a gap in understanding how to use appropriate remote sensing classification and retrieval algorithms. Summary of the Invention

[0007] The main objective of this invention is to provide a method and apparatus for predicting carbon sink potential by integrating remote sensing and modeling technologies, so as to overcome the bottleneck of insufficient regional-scale carbon accounting data and high uncertainty, and to maximize carbon sink potential.

[0008] To achieve the above objectives, embodiments of the present invention provide a method for predicting carbon sink potential that integrates remote sensing and modeling technologies, including:

[0009] The dynamic distribution data of the vegetation structure is input into the regional carbon and nitrogen cycle model to obtain the regional carbon and nitrogen cycle dynamic simulation results; wherein, the regional carbon and nitrogen cycle model is trained by soil distribution data and vegetation and soil dynamic data; the dynamic distribution data of the vegetation structure is input into the regional carbon and nitrogen cycle model created based on historical crop distribution data and vegetation and soil dynamic data to obtain the regional carbon and nitrogen cycle dynamic simulation results.

[0010] Carbon sink data are determined based on the dynamic simulation results of the carbon and nitrogen cycle in the region.

[0011] In one embodiment, it further includes:

[0012] Satellite spectral data is input into a vegetation and soil inversion model created based on historical vegetation and soil characteristics and historical satellite spectral data to obtain the vegetation and soil dynamic data.

[0013] In one embodiment, the step of creating a vegetation and soil inversion model includes:

[0014] Sensitivity data are determined based on the correlation coefficient between the historical vegetation and soil characteristics and the historical satellite spectral data.

[0015] The historical satellite spectral data is updated based on the sensitivity data, and a vegetation and soil inversion dataset is constructed based on the updated historical satellite spectral data and the historical vegetation and soil characteristics.

[0016] The initial inversion model is trained based on the vegetation and soil inversion dataset to obtain the vegetation and soil inversion model.

[0017] In one embodiment, it further includes:

[0018] Vegetation index is calculated based on reflectivity and wavelength parameters from historical satellite data;

[0019] The historical satellite spectral data is generated based on the vegetation index and satellite spectral band data.

[0020] This invention also provides a carbon sink potential prediction device that integrates remote sensing and modeling technologies, comprising:

[0021] The vegetation structure dynamic distribution module is used to input the vegetation structure dynamic distribution data into the regional carbon and nitrogen cycle model to obtain the regional carbon and nitrogen cycle dynamic simulation results; wherein, the regional carbon and nitrogen cycle model is trained by soil distribution data and vegetation and soil dynamic data;

[0022] The regional carbon and nitrogen cycle dynamic simulation result module is used to input the dynamic distribution data of the vegetation structure into the regional carbon and nitrogen cycle model created based on historical crop distribution data and vegetation and soil dynamic data to obtain the regional carbon and nitrogen cycle dynamic simulation results.

[0023] The carbon sink data module is used to determine carbon sink data based on the dynamic simulation results of the carbon and nitrogen cycle in the region.

[0024] In one embodiment, it further includes:

[0025] The vegetation and soil dynamics data module is used to input satellite spectral data into a vegetation and soil inversion model created based on historical vegetation and soil characteristics and historical satellite spectral data to obtain the vegetation and soil dynamics data.

[0026] In one embodiment, it further includes:

[0027] The sensitivity data module is used to determine sensitivity data based on the correlation coefficient between the historical vegetation and soil characteristics and the historical satellite spectral data.

[0028] The vegetation and soil inversion dataset module is used to update the historical satellite spectral data based on the sensitivity data, and to construct a vegetation and soil inversion dataset based on the updated historical satellite spectral data and the historical vegetation and soil characteristics.

[0029] The vegetation and soil inversion model module is used to train an initial inversion model based on the vegetation and soil inversion dataset to obtain the vegetation and soil inversion model.

[0030] In one embodiment, it further includes:

[0031] The vegetation index module is used to calculate the vegetation index based on the reflectance and wavelength parameters of historical satellite data.

[0032] The historical satellite spectral data module is used to generate the historical satellite spectral data based on the vegetation index and satellite spectral band data.

[0033] This invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of the carbon sink potential prediction method that integrates remote sensing and modeling technologies.

[0034] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the carbon sequestration potential prediction method that integrates remote sensing and modeling technologies.

[0035] This invention also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the carbon sequestration potential prediction method that integrates remote sensing and modeling technologies.

[0036] The carbon sink potential prediction method and device that integrates remote sensing and modeling technologies in this invention inputs multi-temporal remote sensing data into a vegetation type identification model to obtain dynamic distribution data of vegetation structure. This data is then further used to obtain dynamic simulation results of regional carbon and nitrogen cycles based on a regional carbon and nitrogen cycle model. The carbon sink data is then determined based on the regional carbon and nitrogen cycle dynamic simulation results. This approach can overcome the current bottleneck of insufficient regional-scale carbon accounting data and high uncertainty, thereby maximizing carbon sinks. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a flowchart of the carbon sink potential prediction method that integrates remote sensing and modeling technologies in an embodiment of the present invention;

[0039] Figure 2 This is a flowchart of a carbon sink potential prediction method that integrates remote sensing and modeling technologies in another embodiment of the present invention;

[0040] Figure 3 This is a flowchart of creating a vegetation and soil inversion model in an embodiment of the present invention;

[0041] Figure 4 This is a flowchart illustrating the generation of historical satellite spectral data in an embodiment of the present invention;

[0042] Figure 5 This is a structural block diagram of the carbon sequestration potential prediction device that integrates remote sensing and modeling technologies in an embodiment of the present invention;

[0043] Figure 6 This is a schematic block diagram illustrating the system configuration of an electronic device 9600 according to an embodiment of this application. Detailed Implementation

[0044] 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, and 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.

[0045] Those skilled in the art will recognize that embodiments of the present invention can be implemented as a system, apparatus, device, method, or computer program product. Therefore, this disclosure can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0046] The acquisition, storage, use, and processing of data in the technical solution of this invention all comply with relevant national laws and regulations. The user information in the embodiments of this application was obtained through legal and compliant means, and the acquisition, storage, use, and processing of user information have all been authorized and agreed upon by the client.

[0047] To address the technical challenges of high uncertainty in existing regional-scale farmland carbon cycle assessments and the limited utilization of satellite remote sensing imagery, this invention quantifies regional farmland greenhouse gas emissions and soil carbon storage based on a carbon-nitrogen-water coupling mechanism. It constructs an efficient model-remote sensing data fusion method to achieve regional-scale carbon accounting and carbon sink potential assessment, and can be extended from farmland to other land uses. The invention is described in detail below with reference to the accompanying drawings.

[0048] Figure 1 This is a flowchart of the carbon sink potential prediction method that integrates remote sensing and modeling technologies in an embodiment of the present invention. Figure 2 This is a flowchart of a carbon sink potential prediction method integrating remote sensing and modeling technologies, as described in another embodiment of the present invention. Figures 1-2 As shown, methods for predicting carbon sink potential that integrate remote sensing and modeling technologies include:

[0049] S101: Input multi-temporal remote sensing data into a vegetation type identification model created based on historical remote sensing data and historical vegetation type labels to obtain dynamic distribution data of vegetation structure.

[0050] In practice, land cover category labels (historical vegetation type labels) are established for multi-temporal remote sensing data (historical remote sensing data). Major crop planting areas within the image range are marked, and data from different crop types (such as corn, wheat, and cabbage) are selected as the training set. A subset of data from the training set is selected as the validation set. A deep learning convolutional neural network model is constructed using DeepLabV3, with ResNet-34 selected as the backbone model for training. The trained model is then used to perform pixel classification on the test set. Accuracy evaluation metrics are selected to assess the accuracy of the remote sensing classification results, and information on crop distribution and historical evolution (dynamic distribution data of vegetation structure) is obtained.

[0051] S102: Input the dynamic distribution data of the vegetation structure into the regional carbon and nitrogen cycle model to obtain the dynamic simulation results of the regional carbon and nitrogen cycle.

[0052] The regional carbon and nitrogen cycle model is trained using soil distribution data and vegetation and soil dynamics data.

[0053] The steps to create a regional carbon and nitrogen cycle model are as follows:

[0054] 1. Set the initial parameters of the optimization algorithm, including the population size and the number of generations to optimize the search; use binary crossover and polynomial mutation, and set the crossover rate and mutation rate.

[0055] 2. Combining the regional farmland dynamic data obtained from the inversion with the point observation results (vegetation and soil dynamic data), set the objective function of the optimization algorithm (including minimizing the calculation error of greenhouse gas emissions, crop yield, and soil carbon, nitrogen and water content) and physical constraints.

[0056] 3. Based on the distribution of farmland crops (historical crop distribution data), a regional database is constructed to drive the DNDC model (Denitrification-Decomposition model) to perform crop-carbon cycle simulation calculations. The simulation results within the time step are then input into the NSGA-Ⅱ multi-objective optimization algorithm.

[0057] 4. The algorithm calculates and generates a new offspring population. Then, based on non-dominance relationships and individual crowding, suitable individuals are selected to form a new parent population. This new offspring population (i.e., model parameters) is then generated through basic operations of the particle swarm optimization algorithm. The optimized model parameters are then fed back into the model for calculation, repeating this process until the loop termination condition is met, at which point the algorithm stops. Ultimately, a Pareto solution set composed of multiple solutions is obtained, thus creating a regional carbon-nitrogen cycle model. There is no inherent good or bad among the optimal solutions; all solutions are optimal, and the choice depends on the decision-maker's priorities.

[0058] Before executing S102, the following is also included:

[0059] Satellite spectral data is input into a vegetation and soil inversion model created based on historical vegetation and soil characteristics and historical satellite spectral data to obtain the vegetation and soil dynamic data.

[0060] In practice, satellite spectral data is used as input, and key crop characteristic parameters are simulated for each grid based on the trained vegetation and soil inversion model. The results are then aggregated into a set of key crop characteristic parameters for the region (vegetation and soil dynamic data).

[0061] Figure 3 This is a flowchart illustrating the creation of a vegetation and soil inversion model in an embodiment of the present invention. For example... Figure 3 As shown, the steps for creating a vegetation and soil inversion model include:

[0062] S201: Determine the sensitivity data based on the correlation coefficient between the historical vegetation and soil characteristics and the historical satellite spectral data.

[0063] In practice, typical research sites are first selected to obtain measured values ​​of key crop characteristic parameters such as long-term leaf area index, harvest index, and surface biomass (historical vegetation and soil characteristics). Sensitivity data are obtained by calculating the Pearson correlation coefficient between historical satellite spectral data and one of the historical vegetation and soil characteristics (such as long-term leaf area index).

[0064] Figure 4 This is a flowchart illustrating the generation of historical satellite spectral data in an embodiment of the present invention. For example... Figure 4 As shown, methods for predicting carbon sink potential that integrate remote sensing and modeling technologies also include:

[0065] S301: Calculate the vegetation index based on the reflectivity and wavelength parameters of historical satellite data.

[0066] In practice, a series of vegetation indices, such as the Normalized Interpolated Vegetation Index (NDVI) and the Water Stress Index (MSI), are calculated for typical locations using the reflectance and wavelength parameters of historical satellite data.

[0067] S302: Generate the historical satellite spectral data based on the vegetation index and satellite spectral band data.

[0068] S202: Update the historical satellite spectral data according to the sensitivity data, and construct a vegetation and soil inversion dataset based on the updated historical satellite spectral data and the historical vegetation and soil characteristics.

[0069] In practice, historical satellite spectral data with low sensitivity are removed. T-tests and correlation tests are performed on the correlation between spectral features and historical vegetation and soil characteristics, and historical satellite spectral data that are not significant at the 0.01 confidence level are removed. Partial least squares (PLSR) is used to calculate the importance of each historical satellite spectral data set, and features with low importance are removed. The remaining historical satellite spectral data and historical vegetation and soil characteristics are used to construct corresponding vegetation and soil inversion datasets (e.g., long-sequence leaf area index inversion datasets).

[0070] S203: Train an initial inversion model based on the vegetation and soil inversion dataset to obtain the vegetation and soil inversion model.

[0071] For example, using the long-sequence leaf area index as the output variable, the training set and the test set are divided in a 7:3 ratio, and the coefficient of determination R2 and root mean square error (RMSE) are used as evaluation parameters. The LSTM algorithm is used to train the long-sequence leaf area index inversion dataset and obtain the optimal set of hyperparameters, thereby constructing a long-sequence leaf area index growth inversion model.

[0072] S103: Determine carbon sink data based on the dynamic simulation results of the carbon and nitrogen cycle in the region.

[0073] For example, to optimize farmland planting structure, different scenarios combining crop types and crop areas are generated to drive the DNDC model for simulation. Based on the simulation results, the yield and carbon sequestration results (carbon sequestration data) under different combinations are calculated. The corresponding benefits are calculated based on the yield, and the benefits and carbon sequestration results are normalized by maximum and minimum respectively. The sum of benefits and carbon sequestration results under different combinations is calculated, and the farmland planting structure combination corresponding to the optimal result is selected as the optimal planting structure that balances benefits and carbon sequestration.

[0074] To optimize farmland management, different scenarios involving irrigation and fertilization amounts are generated to drive the DNDC model for simulation. Based on the simulation results, the benefits and carbon sequestration results under different combinations are calculated. The irrigation amount, fertilization amount, benefits, and carbon sequestration results are then normalized to their maximum and minimum values. The sum of the benefits and carbon sequestration results under different combinations is calculated. Under the condition that the effect is not lower than the actual water and fertilizer combination results, the combination with the smallest sum of irrigation and fertilization amounts is selected as the optimal farmland management mode.

[0075] To optimize organic agriculture, different scenarios of organic fertilizer return to the field and chemical fertilizer application are generated to drive the DNDC model for simulation. Based on the simulation results, the benefits and carbon sequestration results under different combinations are calculated. The organic fertilizer return to the field, chemical fertilizer application, benefits and carbon sequestration results are normalized by maximum and minimum, respectively. The sum of yield benefits and carbon sequestration results under different combinations is calculated. Under the condition that the effect is not lower than the actual organic fertilizer and chemical fertilizer combination results, the combination with the largest ratio of organic fertilizer to chemical fertilizer is selected as the optimal organic agriculture model.

[0076] Figure 1 The carbon sequestration potential prediction method shown, which integrates remote sensing and modeling technologies, is executed by a computer. Figure 1 As shown in the process, the carbon sink potential prediction method that integrates remote sensing and modeling technologies in this embodiment of the invention inputs multi-temporal remote sensing data into a vegetation type identification model to obtain dynamic distribution data of vegetation structure. This data is then used to obtain dynamic simulation results of regional carbon and nitrogen cycles based on a regional carbon and nitrogen cycle model. In turn, carbon sink data is determined based on the dynamic simulation results of regional carbon and nitrogen cycles. This method can overcome the current bottleneck of insufficient regional-scale carbon accounting data and high uncertainty, and maximize carbon sinks.

[0077] In summary, the carbon sequestration potential prediction method integrating remote sensing and model technologies provided in this invention effectively achieves multi-dimensional fusion of regional-scale remote sensing data and farmland carbon and nitrogen models, significantly improving the accuracy of regional-scale carbon accounting and carbon sequestration potential assessment. Current assessment methods primarily driven by remote sensing data or model simulation have varying degrees of deficiencies in predictive capabilities under changing environments, spatiotemporal assessment scales, and result accuracy, failing to form an effective complementary system. This invention addresses these issues by constructing a prediction and assessment system that integrates remote sensing data and models based on machine learning and numerical optimization algorithms. It utilizes remote sensing images to generate vegetation distribution and vegetation and soil data, simultaneously improving accuracy from both the input and parameter optimization perspectives of the model. This approach overcomes the current bottlenecks of insufficient regional-scale accounting data and high uncertainty.

[0078] Specifically, this invention innovates a regional-scale farmland carbon cycle simulation and prediction system based on machine learning and numerical optimization algorithms. It effectively integrates high-resolution remote sensing data with farmland carbon-nitrogen cycle models, thereby improving the prediction accuracy of regional carbon sink assessment and management measure optimization. The specific approach is as follows:

[0079] (1) Based on the dynamic image of farmland remote sensing, the CNN algorithm is used to identify information such as the distribution of different crops and the sowing and harvesting time, so as to construct a regional farmland annual and seasonal dynamic database and drive the DNDC model to simulate.

[0080] (2) Based on dynamic images of farmland remote sensing, LSTM is used to invert the time series of key crop variables such as crop yield and ground biomass during the growing season. The model is then optimized and corrected in real time using this real-time data to improve the accuracy of crop and carbon cycle simulation.

[0081] (3) Drive the DNDC model to perform crop-carbon cycle calculations based on different meteorological scenarios and fertilization and irrigation management methods. Based on the accurate simulation of the model, assess the regional agricultural carbon sink potential under different management methods, and optimize relevant management measures (such as fertilizer application and irrigation water) to maximize the actual comprehensive carbon sink.

[0082] Based on the same inventive concept, this invention also provides a carbon sequestration potential prediction device that integrates remote sensing and modeling technologies. Since the principle of this device in solving the problem is similar to that of the carbon sequestration potential prediction method that integrates remote sensing and modeling technologies, the implementation of this device can refer to the implementation of the method, and the repeated parts will not be described again.

[0083] Figure 5 This is a structural block diagram of a carbon sequestration potential prediction device integrating remote sensing and modeling technologies, as described in an embodiment of the present invention. Figure 5 As shown, the carbon sequestration potential prediction device integrating remote sensing and modeling technologies includes:

[0084] The vegetation structure dynamic distribution module is used to input multi-temporal remote sensing data into a vegetation type identification model created based on historical remote sensing data and historical vegetation type labels to obtain vegetation structure dynamic distribution data.

[0085] The regional carbon and nitrogen cycle dynamic simulation result module is used to input the dynamic distribution data of the vegetation structure into the regional carbon and nitrogen cycle model to obtain the regional carbon and nitrogen cycle dynamic simulation results; wherein, the regional carbon and nitrogen cycle model is trained by soil distribution data and vegetation and soil dynamic data;

[0086] The carbon sink data module is used to determine carbon sink data based on the dynamic simulation results of the carbon and nitrogen cycle in the region.

[0087] In one embodiment, it further includes:

[0088] The vegetation and soil dynamics data module is used to input satellite spectral data into a vegetation and soil inversion model created based on historical vegetation and soil characteristics and historical satellite spectral data to obtain the vegetation and soil dynamics data.

[0089] In one embodiment, the sensitivity data module is used to determine sensitivity data based on the correlation coefficient between the historical vegetation and soil characteristics and the historical satellite spectral data;

[0090] The vegetation and soil inversion dataset module is used to update the historical satellite spectral data based on the sensitivity data, and to construct a vegetation and soil inversion dataset based on the updated historical satellite spectral data and the historical vegetation and soil characteristics.

[0091] The vegetation and soil inversion model module is used to train an initial inversion model based on the vegetation and soil inversion dataset to obtain the vegetation and soil inversion model.

[0092] In one embodiment, the vegetation index module is used to calculate the vegetation index based on the reflectance and wavelength parameters of historical satellite data;

[0093] The historical satellite spectral data module is used to generate the historical satellite spectral data based on the vegetation index and satellite spectral band data.

[0094] In summary, the carbon sink potential prediction device that integrates remote sensing and modeling technologies in this embodiment of the invention inputs multi-temporal remote sensing data into a vegetation type identification model to obtain dynamic distribution data of vegetation structure. This data is then used to obtain dynamic simulation results of regional carbon and nitrogen cycles based on a regional carbon and nitrogen cycle model. In turn, carbon sink data is determined based on the regional carbon and nitrogen cycle dynamic simulation results. This approach can overcome the current bottleneck of insufficient regional-scale carbon accounting data and high uncertainty, thereby maximizing carbon sinks.

[0095] Figure 6 This is a schematic block diagram illustrating the system configuration of the electronic device 9600 according to an embodiment of this application. Figure 6 As shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It is worth noting that... Figure 6 This is an example; other types of structures can also be used to supplement or replace this structure to achieve telecommunications functions or other functions.

[0096] In one embodiment, the carbon sequestration potential prediction method integrating remote sensing and modeling technologies can be integrated into the central processing unit 9100. The central processing unit 9100 can be configured to perform the following controls:

[0097] Multi-temporal remote sensing data is input into a vegetation type identification model created based on historical remote sensing data and historical vegetation type labels to obtain dynamic distribution data of vegetation structure.

[0098] The dynamic distribution data of the vegetation structure is input into the regional carbon and nitrogen cycle model to obtain the dynamic simulation results of the regional carbon and nitrogen cycle; wherein, the regional carbon and nitrogen cycle model is trained by soil distribution data and vegetation and soil dynamic data;

[0099] Carbon sink data are determined based on the dynamic simulation results of the carbon and nitrogen cycle in the region.

[0100] As can be seen from the above description, the carbon sink potential prediction method that integrates remote sensing and modeling technologies provided in this application inputs multi-temporal remote sensing data into a vegetation type identification model to obtain dynamic distribution data of vegetation structure, and further obtains regional carbon and nitrogen cycle dynamic simulation results based on a regional carbon and nitrogen cycle model. Thus, carbon sink data is determined based on the regional carbon and nitrogen cycle dynamic simulation results, which can overcome the current bottleneck of insufficient regional-scale carbon accounting data and high uncertainty, and maximize carbon sink.

[0101] In another embodiment, the carbon sequestration potential prediction device that integrates remote sensing and modeling technologies can be configured separately from the central processing unit 9100. For example, the carbon sequestration potential prediction device that integrates remote sensing and modeling technologies can be configured as a chip connected to the central processing unit 9100, and the function of the carbon sequestration potential prediction method that integrates remote sensing and modeling technologies can be realized through the control of the central processing unit.

[0102] like Figure 6 As shown, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily need to include these components. Figure 6 All components shown; in addition, the electronic device 9600 may also include Figure 6 For components not shown, please refer to existing technologies.

[0103] like Figure 6 As shown, the central processing unit 9100, sometimes also referred to as a controller or operating control, may include a microprocessor or other processor device and / or logic device, which receives inputs and controls the operation of various components of the electronic device 9600.

[0104] The memory 9140 may be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It may store the aforementioned failure-related information, and also store a program for executing that information. The central processing unit 9100 may execute the program stored in the memory 9140 to perform information storage or processing, etc.

[0105] Input unit 9120 provides input to central processing unit 9100. Input unit 9120 may be, for example, a keypad or touch input device. Power supply 9170 provides power to electronic device 9600. Display 9160 displays images and text. Display may be, for example, an LCD display, but is not limited thereto.

[0106] The memory 9140 can be a solid-state memory, such as a read-only memory (ROM), random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and contains more data; examples of this type of memory are sometimes referred to as EPROMs. The memory 9140 can also be some other type of device. The memory 9140 includes a buffer 9141 (sometimes referred to as a buffer memory). The memory 9140 may include an application / function storage unit 9142 for storing application programs and function programs or processes for executing the operation of the electronic device 9600 via the central processing unit 9100.

[0107] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for the electronic device's communication functions and / or for performing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0108] The communication module 9110 is a transmitter / receiver 9110 that transmits and receives signals via the antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processing unit 9100 to provide input signals and receive output signals, which can be the same as in a conventional mobile communication terminal.

[0109] Based on different communication technologies, multiple communication modules 9110 can be configured in the same electronic device, such as cellular network modules, Bluetooth modules, and / or wireless LAN modules. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby realizing typical telecommunications functions. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. Additionally, the audio processor 9130 is coupled to a central processing unit 9100, enabling on-device recording via the microphone 9132 and on-device playback of stored sound via the speaker 9131.

[0110] This invention also provides a computer-readable storage medium capable of implementing all steps of the carbon sequestration potential prediction method fused with remote sensing and modeling technologies, where the execution subject is a server or client, as described in the above embodiments. The computer-readable storage medium stores a computer program that, when executed by a processor, implements all steps of the carbon sequestration potential prediction method fused with remote sensing and modeling technologies as described in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0111] Multi-temporal remote sensing data is input into a vegetation type identification model created based on historical remote sensing data and historical vegetation type labels to obtain dynamic distribution data of vegetation structure.

[0112] The dynamic distribution data of the vegetation structure is input into the regional carbon and nitrogen cycle model to obtain the dynamic simulation results of the regional carbon and nitrogen cycle; wherein, the regional carbon and nitrogen cycle model is trained by soil distribution data and vegetation and soil dynamic data;

[0113] Carbon sink data are determined based on the dynamic simulation results of the carbon and nitrogen cycle in the region.

[0114] In summary, the computer-readable storage medium of this invention inputs multi-temporal remote sensing data into a vegetation type identification model to obtain dynamic distribution data of vegetation structure, and further obtains regional carbon and nitrogen cycle dynamic simulation results based on a regional carbon and nitrogen cycle model. Thus, carbon sink data is determined based on the regional carbon and nitrogen cycle dynamic simulation results, which can overcome the current bottleneck of insufficient regional-scale carbon accounting data and high uncertainty, and maximize carbon sink.

[0115] This invention also provides a computer program product capable of implementing all steps in the carbon sequestration potential prediction method fused with remote sensing and modeling technologies, where the execution subject is a server or client, as described in the above embodiments. The computer program product includes a computer program / instruction that, when executed by a processor, implements all steps of the carbon sequestration potential prediction method fused with remote sensing and modeling technologies as described in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0116] Multi-temporal remote sensing data is input into a vegetation type identification model created based on historical remote sensing data and historical vegetation type labels to obtain dynamic distribution data of vegetation structure.

[0117] The dynamic distribution data of the vegetation structure is input into the regional carbon and nitrogen cycle model to obtain the dynamic simulation results of the regional carbon and nitrogen cycle; wherein, the regional carbon and nitrogen cycle model is trained by soil distribution data and vegetation and soil dynamic data;

[0118] Carbon sink data are determined based on the dynamic simulation results of the carbon and nitrogen cycle in the region.

[0119] In summary, the computer program product of this invention inputs multi-temporal remote sensing data into a vegetation type identification model to obtain dynamic distribution data of vegetation structure, and further obtains regional carbon and nitrogen cycle dynamic simulation results based on a regional carbon and nitrogen cycle model. Thus, carbon sink data is determined based on the regional carbon and nitrogen cycle dynamic simulation results, which can overcome the bottleneck of insufficient regional-scale carbon accounting data and high uncertainty, and maximize carbon sink.

[0120] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, hardware + program embodiments are relatively simple in description because they are fundamentally similar to method embodiments; relevant parts can be referred to the descriptions in the method embodiments.

[0121] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0122] While this application provides the method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual device or client product execution, the methods shown in the embodiments or drawings can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0123] While this specification provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive means. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual device or end product execution, the methods shown in the embodiments or drawings may be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed data processing environment). The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, product, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, product, or apparatus. Without further limitations, the presence of other identical or equivalent elements in the process, method, product, or apparatus that includes said elements is not excluded.

[0124] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing the embodiments of this specification, the functions of each module can be implemented in one or more software and / or hardware components, or a module that performs the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0125] Those skilled in the art will also know that, besides implementing the controller using purely computer-readable program code, the same functions can be achieved by logically programming the method steps, making the controller function as logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers (PLCs), and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the devices within it used to implement various functions can also be considered structures within that hardware component. Alternatively, the devices used to implement various functions can be considered as both software modules implementing the method and structures within a hardware component.

[0126] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0127] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0128] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0129] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0130] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0131] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0132] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of computer program products implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0133] The embodiments described in this specification can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. The embodiments of this specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0134] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the embodiments of this specification. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0135] The above description is merely an embodiment of the present specification and is not intended to limit the embodiments of the present specification. For those skilled in the art, various modifications and variations can be made to the embodiments of the present specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the embodiments of the present specification should be included within the scope of the claims of the embodiments of the present specification.

Claims

1. A method for predicting carbon sequestration potential that integrates remote sensing and modeling technologies, characterized in that, include: Multi-temporal remote sensing data is input into a vegetation type identification model created based on historical remote sensing data and historical vegetation type labels to obtain dynamic distribution data of vegetation structure. The dynamic distribution data of the vegetation structure is input into a regional carbon and nitrogen cycle model created based on historical crop distribution data and vegetation and soil dynamic data to obtain the regional carbon and nitrogen cycle dynamic simulation results. Carbon sink data is determined based on the dynamic simulation results of the carbon and nitrogen cycles in the region, specifically including: To optimize farmland planting structure, different scenarios of crop types and crop area are generated to drive the DNDC model for simulation. Based on the simulation results, yield and carbon sequestration data under different combinations are calculated. To optimize farmland management, different scenarios with varying irrigation and fertilization rates are generated to drive the DNDC model for simulation. Based on the simulation results, the benefits and carbon sequestration data under different combinations are calculated. To optimize organic agriculture, different scenarios of organic fertilizer return to the field and chemical fertilizer application are generated to drive the DNDC model for simulation. The benefits and carbon sink data under different combinations are calculated based on the simulation results. The steps to create a regional carbon and nitrogen cycle model are as follows: Set the initial parameters for the optimization algorithm, including the population size and the number of generations to optimize the search; use binary crossover and polynomial mutation, and set the crossover rate and mutation rate; Based on the vegetation and soil dynamic data obtained by inversion, an optimization algorithm objective function and physical constraints are set. The optimization algorithm objective function includes minimizing the calculation error of greenhouse gas emissions, minimizing the calculation error of crop yield, and minimizing the calculation error of soil carbon, nitrogen and water content. The vegetation and soil dynamic data are regional farmland dynamic data and point observation results. A regional database is constructed based on historical crop distribution data, which drives the DNDC model to perform crop-carbon cycle simulation calculations. The simulation results within the time step are then input into the NSGA-Ⅱ multi-objective optimization algorithm. The algorithm calculates and generates a child population. Based on the non-dominance relationship and the crowding of individuals, suitable individuals are selected to form a new parent population. Then, a new child population is generated through the basic operations of the particle swarm optimization algorithm. The new child population serves as the model parameters. The model parameters obtained by the algorithm optimization are then fed back into the model for calculation. This process is repeated until the loop termination condition is met, at which point the operation stops. Finally, a Pareto solution set composed of multiple solutions is obtained, creating a regional carbon and nitrogen cycle model. The method further includes: Based on dynamic imagery of farmland remote sensing, LSTM is used to invert the time series of key crop variables. The model parameters are optimized and corrected in real time using real-time data. The key crop variables include crop yield during the growing season and ground biomass.

2. The carbon sink potential prediction method integrating remote sensing and modeling technologies according to claim 1, characterized in that, Also includes: Satellite spectral data is input into a vegetation and soil inversion model created based on historical vegetation and soil characteristics and historical satellite spectral data to obtain the vegetation and soil dynamic data.

3. The carbon sink potential prediction method integrating remote sensing and modeling technologies according to claim 2, characterized in that, The steps to create a vegetation and soil inversion model include: Sensitivity data are determined based on the correlation coefficient between the historical vegetation and soil characteristics and the historical satellite spectral data. The historical satellite spectral data is updated based on the sensitivity data, and a vegetation and soil inversion dataset is constructed based on the updated historical satellite spectral data and the historical vegetation and soil characteristics. The initial inversion model is trained based on the vegetation and soil inversion dataset to obtain the vegetation and soil inversion model.

4. The carbon sink potential prediction method integrating remote sensing and modeling technologies according to claim 2, characterized in that, Also includes: Vegetation index is calculated based on reflectivity and wavelength parameters from historical satellite data; The historical satellite spectral data is generated based on the vegetation index and satellite spectral band data.

5. A carbon sequestration potential prediction device integrating remote sensing and modeling technologies, characterized in that, include: The vegetation structure dynamic distribution module is used to input multi-temporal remote sensing data into a vegetation type identification model created based on historical remote sensing data and historical vegetation type labels to obtain vegetation structure dynamic distribution data. The carbon and nitrogen cycle simulation module is used to input the dynamic distribution data of the vegetation structure into a regional carbon and nitrogen cycle model created based on historical crop distribution data and vegetation and soil dynamic data, and obtain the regional carbon and nitrogen cycle dynamic simulation results. The carbon sink data module is used to determine carbon sink data based on the dynamic simulation results of the carbon and nitrogen cycle in the region. The carbon sequestration data module is specifically used to optimize the farmland planting structure, generate different combinations of farmland crop types and crop area scenarios, drive the DNDC model to simulate, and calculate the yield and carbon sequestration data under different combinations based on the simulation results. For farmland management optimization, different scenarios with varying irrigation and fertilization rates are generated to drive the DNDC model for simulation. Based on the simulation results, the benefits and carbon sequestration data under different combinations are calculated. For organic agriculture optimization, different scenarios with varying amounts of organic fertilizer returned to the field and chemical fertilizer applied are generated to drive the DNDC model for simulation. Based on the simulation results, the benefits and carbon sequestration data under different combinations are calculated. Also includes: The regional carbon and nitrogen cycle model creation module is used to set initial parameters for the optimization algorithm, including population size and number of generations; to set the crossover and mutation rates using binary crossover and polynomial mutation; and to set the objective function and physical constraints of the optimization algorithm based on the inverted vegetation and soil dynamic data. The objective function includes minimizing the errors in greenhouse gas emission calculations, crop yield calculations, and soil carbon, nitrogen, and water content calculations. The vegetation and soil dynamic data consists of regional farmland dynamic data and point observation results. Regional data is constructed based on historical crop distribution data. The library drives the DNDC model to perform crop-carbon cycle simulation calculations. The simulation results within the time step are input into the NSGA-II multi-objective optimization algorithm. The algorithm calculates and generates offspring populations. Based on non-dominance relationships and individual crowding, suitable individuals are selected to form a new parent population. Then, a new offspring population is generated through the basic operations of the particle swarm optimization algorithm. The new offspring population serves as the model parameters. The model parameters obtained by the algorithm optimization are then input back into the model for calculation. This process is repeated until the loop termination condition is met, at which point the operation stops. Finally, a Pareto solution set composed of multiple solutions is obtained, creating a regional carbon and nitrogen cycle model. The model calibration module is used to invert the time series of key crop variables based on farmland remote sensing dynamic images using LSTM, and to optimize and calibrate the model parameters in real time using real-time data. The key crop variables include growing season crop yield and ground biomass.

6. The carbon sequestration potential prediction device integrating remote sensing and modeling technologies according to claim 5, characterized in that, Also includes: The vegetation and soil dynamics data module is used to input satellite spectral data into a vegetation and soil inversion model created based on historical vegetation and soil characteristics and historical satellite spectral data to obtain the vegetation and soil dynamics data.

7. The carbon sequestration potential prediction device integrating remote sensing and modeling technologies according to claim 6, characterized in that, Also includes: The sensitivity data module is used to determine sensitivity data based on the correlation coefficient between the historical vegetation and soil characteristics and the historical satellite spectral data. The vegetation and soil inversion dataset module is used to update the historical satellite spectral data based on the sensitivity data, and to construct a vegetation and soil inversion dataset based on the updated historical satellite spectral data and the historical vegetation and soil characteristics. The vegetation and soil inversion model module is used to train an initial inversion model based on the vegetation and soil inversion dataset to obtain the vegetation and soil inversion model.

8. The carbon sequestration potential prediction device integrating remote sensing and modeling technologies according to claim 6, characterized in that, Also includes: The vegetation index module is used to calculate the vegetation index based on the reflectance and wavelength parameters of historical satellite data. The historical satellite spectral data module is used to generate the historical satellite spectral data based on the vegetation index and satellite spectral band data.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the carbon sink potential prediction method that integrates remote sensing and modeling technologies as described in any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the carbon sink potential prediction method that integrates remote sensing and modeling technologies as described in any one of claims 1 to 4.

11. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the carbon sink potential prediction method that integrates remote sensing and modeling technologies as described in any one of claims 1 to 4.

Images