Carbon project credit granting risk assessment method and system, terminal and storage medium

Abstract

The invention discloses a credit granting risk assessment method and system for a carbon project, a terminal and a storage medium. Obtaining the planned carbon elimination amount of the target year and verification data over the years through the project document data of the carbon project; if the verified actual carbon elimination amount of the target year is not included, acquiring remote sensing image data of the target year and a near target year; calculating predicted tree height data of each year according to the remote sensing image data through a tree height prediction model; predicting the carbon elimination amount of the target year through a carbon elimination amount prediction model according to the calculated prediction tree height data and the verified actual carbon elimination amount of the near target year; and determining a carbon project score according to the planned carbon elimination amount and the predicted carbon elimination amount of the target year. According to the method, when the carbon elimination amount is not verified in the target year, the tree height data is obtained through the tree height prediction model based on the remote sensing image data, the carbon elimination amount of the target year is estimated through the carbon elimination amount prediction model based on the tree height data, and then the carbon elimination amount is compared with the corresponding planned carbon elimination amount to complete carbon project rating.

Description

Technical Field

[0001] The present invention relates to the technical field of forestry carbon sinks, and in particular to a credit risk assessment method, system, terminal and storage medium for a carbon project. Background Art

[0002] Forests are not only one of the most spectacular natural landscapes, but also one of the largest carbon sinks on Earth. Through photosynthesis, forests absorb carbon dioxide from the atmosphere and convert it into organic matter, thereby reducing the greenhouse effect and playing a buffering role against global climate change.

[0003] ARR (Afforestation / Reforestation and Reforestation) is part of the VCS (Verified Carbon Standard) and aims to reduce greenhouse gas concentrations by absorbing carbon dioxide from the atmosphere through activities such as afforestation. The amount of carbon removed is an important feature of ARR's carbon project credit rating.

[0004] However, the current method of verifying carbon removal is mainly through field investigation, which estimates carbon removal by selecting sample areas, measuring the tree's diameter at breast height and tree height, and combining the characteristics of the tree species. This has high labor costs and delayed information, which is not conducive to timely rating of projects, nor is it conducive to adjusting the carbon credit market and project optimization.

[0005] Therefore, the existing technology still needs to be improved and developed. Summary of the invention

[0006] The technical problem to be solved by the present invention is that, in view of the above-mentioned defects of the prior art, a credit risk assessment method, system, terminal and storage medium for carbon projects are provided, aiming to solve the problems in the prior art of verifying the carbon elimination amount of carbon projects through field surveys, which have high labor costs and are difficult to achieve timely rating of carbon projects, timely adjustment of the carbon credit market, and timely optimization of carbon projects.

[0007] The technical solution adopted by the present invention to solve the problem is as follows:

[0008] In a first aspect, an embodiment of the present invention provides a credit risk assessment method for a carbon project, the method comprising:

[0009] Obtain project document data of the carbon project, and obtain the planned carbon elimination amount for the target year and historical verification data of the project based on the project document data;

[0010] If the historical verification data of the project does not include the verified actual carbon elimination amount for the target year, then obtain the remote sensing image data corresponding to the target year and the near-target year respectively; wherein the near-target year has the verified actual carbon elimination amount in the historical verification data of the project;

[0011] By using a preset tree height prediction model, according to the remote sensing image data of the target year and the near target year, the predicted tree height data corresponding to the target year and the near target year are calculated;

[0012] Calculate the predicted carbon elimination amount for the target year by using a preset carbon elimination amount prediction model, based on the predicted tree height data for the target year and the near-target year and the verified actual carbon elimination amount for the near-target year;

[0013] A score for the carbon project is determined based on the planned carbon elimination amount and the predicted carbon elimination amount in the target year, and the score is used to reflect the credit risk of the carbon project.

[0014] In one embodiment, the training method of the tree height prediction model includes:

[0015] Obtain remote sensing image data and tree height data for several historical time periods within a preset area;

[0016] The tree height prediction model is trained based on the remote sensing image data and tree height data of each historical time period.

[0017] In one embodiment, the preset area range is determined based on a boundary vector of the carbon project.

[0018] In one embodiment, the carbon removal prediction model is used to:

[0019] Calculate the ratio of the verified actual carbon removal amount in the near-target year to the predicted tree height data in the near-target year;

[0020] The product of the ratio and the predicted tree height data for the target year is calculated to obtain the predicted carbon elimination amount for the target year.

[0021] In one embodiment, the method further comprises:

[0022] If the historical verification data of the project includes the verified actual carbon elimination amount in the target year, the score of the carbon project is determined based on the planned carbon elimination amount and the actual carbon elimination amount in the target year.

[0023] In one embodiment, the method for determining the score of the carbon project includes:

[0024] Determine the score of the carbon project based on the ratio of the actual carbon elimination amount to the planned carbon elimination amount in the target year;

[0025] Alternatively, the score of the carbon project is determined based on the ratio of the predicted carbon elimination amount to the planned carbon elimination amount in the target year.

[0026] In one embodiment, the target year is the most recent year; the carbon project is an ARR project, and the ARR project includes one or more projects of afforestation, reforestation and vegetation restoration.

[0027] In a second aspect, an embodiment of the present invention further provides a credit risk assessment system for a carbon project, the system comprising:

[0028] A document acquisition module, used to acquire project document data of the carbon project, and acquire the planned carbon elimination amount for the target year and the verification data of the project over the years according to the project document data;

[0029] An image acquisition module, for acquiring remote sensing image data corresponding to the target year and the near-target year respectively if the historical verification data of the project do not contain the verified actual carbon elimination amount of the target year; wherein the near-target year has the verified actual carbon elimination amount in the historical verification data of the project;

[0030] A tree height prediction module, used to calculate predicted tree height data corresponding to the target year and the near target year respectively according to the remote sensing image data of the target year and the near target year through a preset tree height prediction model;

[0031] A carbon elimination amount prediction module, used to calculate the predicted carbon elimination amount for the target year according to the predicted tree height data for the target year and the near-target year and the verified actual carbon elimination amount for the near-target year through a preset carbon elimination amount prediction model;

[0032] The project scoring module is used to determine the score of the carbon project based on the planned carbon elimination amount and the predicted carbon elimination amount in the target year, and the score is used to reflect the credit risk of the carbon project.

[0033] In a third aspect, an embodiment of the present invention further provides a terminal, comprising a memory and one or more processors; the memory stores one or more programs; the program comprises instructions for executing a credit risk assessment method for a carbon project as described in any one of the above; and the processor is used to execute the program.

[0034] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium on which a plurality of instructions are stored, wherein the instructions are suitable for being loaded and executed by a processor to implement the steps of the credit risk assessment method for a carbon project as described in any one of the above.

[0035] Beneficial effects of the present invention: In view of the situation where there is no verified actual carbon elimination amount in the target year, the embodiment of the present invention pre-constructs a tree height prediction model and a carbon elimination amount prediction model. The tree height prediction model is used to obtain tree height data based on remote sensing images, and then the carbon elimination amount prediction model is used to estimate the carbon elimination amount in the target year based on the tree height data. Finally, it is compared with the corresponding planned carbon elimination amount to complete the carbon project rating and realize transaction guidance in the carbon credit market. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 It is a schematic diagram of the steps of the credit risk assessment method for a carbon project provided by an embodiment of the present invention.

[0038] Figure 2 It is a process framework diagram of the credit risk assessment method for a carbon project provided in an embodiment of the present invention.

[0039] Figure 3 It is a schematic diagram of the internal modules of the credit risk assessment system for carbon projects provided by an embodiment of the present invention.

[0040] Figure 4 It is a principle block diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The present invention discloses a credit risk assessment method, system, terminal and storage medium for a carbon project. In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0042] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0043] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as generally understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as herein.

[0044] In view of the above-mentioned defects of the prior art, the present invention provides a credit risk assessment method for a carbon project, the method obtaining project document data of the carbon project, and obtaining the planned carbon elimination amount in the target year and the historical verification data of the project according to the project document data; if the historical verification data of the project does not include the verified actual carbon elimination amount in the target year, then obtaining the remote sensing image data corresponding to the target year and the near-target year respectively; wherein the near-target year has a verified actual carbon elimination amount in the historical verification data of the project; through a preset tree height prediction model, according to the remote sensing image data of the target year and the near-target year, calculating the predicted tree height data corresponding to the target year and the near-target year respectively; through a preset carbon elimination amount prediction model, according to the predicted tree height data of the target year and the near-target year and the verified actual carbon elimination amount in the near-target year, calculating the predicted carbon elimination amount in the target year; based on the planned carbon elimination amount and the predicted carbon elimination amount in the target year, determining the score of the carbon project, the score is used to reflect the credit risk of the carbon project. In view of the situation that there is no verified actual carbon elimination amount in the target year, the present invention pre-constructs a tree height prediction model and a carbon elimination amount prediction model. The tree height prediction model is used to obtain tree height data based on remote sensing images, and then the carbon elimination amount prediction model is used to estimate the carbon elimination amount in the target year based on the tree height data. Finally, it is compared with the corresponding planned carbon elimination amount to complete the carbon project rating and realize transaction guidance in the carbon credit market.

[0045] like Figure 1 As shown, the method specifically comprises the following steps:

[0046] Step S100: Acquire project document data of the carbon project, and acquire the planned carbon elimination amount in the target year and historical verification data of the project based on the project document data.

[0047] Specifically, the carbon project in this embodiment can be an ARR project (Afforestation / Reforestation and Reforestation), which mainly includes one or more projects such as afforestation / reforestation and vegetation restoration. Such projects not only help to mitigate climate change, but also can generate tradable carbon credits. Project document data, such as registration documents, can provide planned carbon removal amounts ranging from the start to the end of the project for decades; verification documents can provide verification information on the actual carbon removal amounts from the start of the project to recent years. The project will be verified every few years and the verification data for the past few years will be released. Project document data is an important credential for evaluating ARR projects and carbon issuance transactions. In actual application, for the carbon project that currently needs to be evaluated, the project document data of the carbon project is obtained, and the planned carbon removal amount A for the target year is obtained according to the registration document, where the target year is generally selected as the most recent year to track the recent development status of the carbon project and rate it. According to the registration document or verification document, the actual carbon removal amount verified by the carbon project over the years is obtained.

[0048] Step S200: If the historical verification data of the project does not include the verified actual carbon elimination amount for the target year, then obtain the remote sensing image data corresponding to the target year and the near-target year respectively; wherein the near-target year has a verified actual carbon elimination amount in the historical verification data of the project.

[0049] Specifically, if the project's historical verification data does not contain the verified actual carbon elimination amount for the target year, it is necessary to estimate the carbon elimination amount for the target year through other means. This embodiment chooses to analyze and estimate the carbon elimination amount for the target year through other years close to the target year. First, it is necessary to determine other years that are close to the target year and have verified actual carbon elimination amounts in the project's historical verification data, and use them as near-target years. In other words, the near-target year must be close to the target year, and verification data has been released, with actual carbon elimination amounts. For the target year and near-target year, remote sensing image data of the study area corresponding to the carbon project are obtained respectively. For example, the required remote sensing image data can be obtained from a public remote sensing data platform.

[0050] Step S300: Calculate predicted tree height data corresponding to the target year and the near target year respectively according to the remote sensing image data of the target year and the near target year through a preset tree height prediction model.

[0051] Specifically, this embodiment pre-constructs a tree height prediction model, the input data of the model is remote sensing image data, and the output data is predicted tree height data calculated based on the remote sensing image data. The tree height prediction model pre-uses a large amount of training data and has learned the complex mapping relationship between input and output. In actual application, the remote sensing image data of the target year and the near-target year are respectively input into the trained tree height prediction model, and the tree height prediction model is used for reasoning to obtain the predicted tree height data of the target year and the near-target year.

[0052] For example, Figure 2 As shown, the tree height prediction model (i.e., image-tree height model C) obtains remote sensing image data of the target year and near-target year of the carbon project, and uses model C for reasoning to obtain tree height data of the target year and near-target year.

[0053] In one implementation, after the step of acquiring the remote sensing image data corresponding to the target year and the near target year, the step further includes:

[0054] Data preprocessing is performed on each of the remote sensing image data, and the data preprocessing method includes one or more processing methods of radiation correction processing, atmospheric correction processing, cloud removal processing, and fusion processing.

[0055] Specifically, since the role of remote sensing image data is to predict the amount of carbon removal in the target year, in order to ensure the accuracy and reliability of remote sensing image data, and then ensure the correctness of the prediction results, this embodiment needs to perform data preprocessing on the remote sensing image data after collecting it. Among them, radiation correction processing is to eliminate the influence of the characteristics of the sensor itself and external environmental factors on the remote sensing image data; atmospheric correction processing is to eliminate the influence of interfering gases and aerosols in the atmosphere on remote sensing image data; cloud removal processing is because clouds will block surface information, affecting the quality and analysis results of remote sensing image data; fusion processing is to fuse multi-source remote sensing image data (such as optical images and radar images) or data from different bands of the same sensor to generate data with higher resolution. In actual application, you can choose a suitable processing method or combination according to specific needs and the quality / characteristics of the collected remote sensing image data, and use the selected processing method to preprocess the collected remote sensing image data to ensure the accuracy and reliability of the data.

[0056] In one implementation, the training method of the tree height prediction model includes:

[0057] Obtain remote sensing image data and tree height data for several historical time periods within a preset area;

[0058] The tree height prediction model is trained based on the remote sensing image data and tree height data of each historical time period.

[0059] In one implementation, the preset area range is determined based on a boundary vector of the carbon project.

[0060] Specifically, in order to enable the tree height prediction model to learn the complex mapping relationship between the input remote sensing image data and the output predicted tree height data. This embodiment will first collect historical remote sensing image data of certain time periods within a preset area and historical tree height data (canopy height data) corresponding to each historical remote sensing image data, wherein the preset area is determined by the boundary vector of the carbon project, and the boundary vector can be obtained through the registration information of the carbon project. Then, the training data of the tree height prediction model is constructed based on the collected data. Each training data consists of a training sample and its corresponding true label. The training sample is the historically collected remote sensing image data, and the true label is the corresponding tree height data. During training, the training sample is input into the tree height prediction model, and the prediction accuracy of the tree height prediction model is evaluated by the true label. The model parameters are updated based on the evaluation results until the prediction accuracy of the tree height prediction model meets the standard, and the model training is completed.

[0061] For example, obtain remote sensing image data from April to August of a certain year in the ARR project and perform data preprocessing. Obtain the corresponding tree height data based on GEDI and airborne lidar data. Use machine learning algorithms or deep learning algorithms to build a tree height prediction model, namely, image-tree height model C, through remote sensing image data and tree height data, and complete the model training and verification process.

[0062] Step S400, using a preset carbon elimination prediction model, calculate the predicted carbon elimination amount for the target year according to the predicted tree height data for the target year and the near-target year and the verified actual carbon elimination amount for the near-target year.

[0063] Specifically, this embodiment also pre-constructs a carbon elimination prediction model, the input data of which are the tree height data of a certain year, the tree height data of other years similar to the year, and the actual carbon elimination amount, and the output data is the carbon elimination amount of the year estimated based on the input data, that is, the predicted carbon elimination amount. Figure 2 As shown, this embodiment establishes a carbon elimination prediction model (i.e., carbon elimination-tree height model D) through tree height data and verified carbon elimination. Since tree species, tree growth conditions, etc. are closely related to geographical location, the carbon elimination prediction model established in this embodiment is targeted and can achieve better prediction accuracy within the regional scope / boundary corresponding to the carbon project, but it is not recommended to be extended to projects in other spatial locations.

[0064] In one implementation, the carbon removal prediction model is used to:

[0065] Calculate the ratio of the verified actual carbon removal amount in the near-target year to the predicted tree height data in the near-target year;

[0066] The product of the ratio and the predicted tree height data for the target year is calculated to obtain the predicted carbon elimination amount for the target year.

[0067] Specifically, in the same geographical area, the tree species and tree growth conditions are similar between similar years. In this embodiment, the verified actual carbon removal amount in the near target year is divided by the predicted tree height data in the near target year. The ratio obtained can be regarded as the amount of carbon that can be removed per unit tree height, reflecting the relationship between tree growth and carbon removal. Then, the ratio is multiplied by the predicted tree height data in the target year, and the calculated result can be used as the estimated carbon removal amount in the target year.

[0068] For example, the calculation formula of the carbon removal amount-tree height model D is as follows:

[0069]

[0070] Based on the carbon removal amount-tree height model D, the estimated carbon removal amount B in the target year (i.e. the predicted carbon removal amount in the target year) is obtained.

[0071] Step S500: Determine the score of the carbon project according to the planned carbon elimination amount and the predicted carbon elimination amount in the target year, wherein the score is used to reflect the credit risk of the carbon project.

[0072] Specifically, the planned carbon removal amount in the target year is a set target, which reflects the project party's plan for carbon removal. The predicted carbon removal amount in the target year is the estimated carbon removal amount that can actually be achieved in the target year. By comparing the planned carbon removal amount and the predicted carbon removal amount, the possibility of the project achieving the carbon removal target can be evaluated. This embodiment quantifies the evaluation results into a score, and the overall performance of the project can be reflected by the score. If the predicted carbon removal amount is close to the planned carbon removal amount or the predicted carbon removal amount exceeds the planned carbon removal amount, it means that the project is progressing smoothly and the score will be correspondingly higher; conversely, if the predicted carbon removal amount is much lower than the planned carbon removal amount, it means that the project is progressing slowly and the score will be correspondingly lower. The credit risk of the project can also be determined by the score. Credit risk refers to the risk faced by other institutions when providing credit support to the project.

[0073] In another implementation, the method further includes:

[0074] If the historical verification data of the project includes the verified actual carbon elimination amount in the target year, the score of the carbon project is determined based on the planned carbon elimination amount and the actual carbon elimination amount in the target year.

[0075] Specifically, if the target year has a verified actual carbon elimination amount, for example, the project is at the verification node and has just been verified, there is no need to conduct a carbon elimination forecast process for it. The score can be calculated directly using the planned carbon elimination amount and the actual carbon elimination amount in the target year.

[0076] For example, Figure 2 As shown, the planned carbon elimination amount in the target year is recorded as A, and the verified actual carbon elimination amount in the target year is recorded as B. The score can be determined directly based on A and B.

[0077] In one implementation, the method for determining the score of the carbon project includes:

[0078] Determine the score of the carbon project based on the ratio of the actual carbon elimination amount to the planned carbon elimination amount in the target year;

[0079] Alternatively, the score of the carbon project is determined based on the ratio of the predicted carbon elimination amount to the planned carbon elimination amount in the target year.

[0080] Specifically, the score of carbon projects is B / A, where A is the planned carbon elimination amount in the target year, and B is the verified actual carbon elimination amount or predicted carbon elimination amount in the target year. The higher the score, the higher the actual carbon elimination amount of the project is than the planned carbon elimination amount of the project, and the carbon project will be evaluated better in terms of credit risk accordingly.

[0081] Possible variations of the present invention:

[0082] Data level: Use data from other high-frequency sources, such as canopy height products, to directly obtain tree height and simplify the image-tree height model.

[0083] Application level: The method of the present invention is applied to non-ARR projects, such as other carbon sequestration projects, other engineering designs or rating systems, but the key processes are similar.

[0084] At the model level: the models used were refined, the algorithm steps were partially modified and optimized, and the functions were called. For example, in the construction of the tree height-carbon removal model, a machine learning regression model was used instead of a simple unbiased linear regression equation. For example, in the model for obtaining canopy height, the model input was modified by integrating multiple data sources.

[0085] The advantages of the present invention are:

[0086] 1. The present invention proposes a method for constructing an image-tree height model based on remote sensing images, GEDI, etc., and further constructing a tree height-carbon removal amount model to obtain an estimated carbon removal amount in a target year.

[0087] 2. The present invention constructs a credit risk assessment method based on verified carbon elimination and estimated carbon elimination, supplementing and enriching the evaluation dimensions of ARR projects.

[0088] Based on the above embodiments, the present invention also provides a credit risk assessment system for carbon projects, such as Figure 3 As shown, the system comprises:

[0089] Document acquisition module 01, used to acquire project document data of the carbon project, and acquire the planned carbon elimination amount in the target year and the verification data of the project over the years according to the project document data;

[0090] The image acquisition module 02 is used to acquire the remote sensing image data corresponding to the target year and the near target year respectively if the historical verification data of the project does not contain the verified actual carbon elimination amount of the target year; wherein the near target year has the verified actual carbon elimination amount in the historical verification data of the project;

[0091] The tree height prediction module 03 is used to calculate the predicted tree height data corresponding to the target year and the near target year respectively according to the remote sensing image data of the target year and the near target year through a preset tree height prediction model;

[0092] The carbon elimination amount prediction module 04 is used to calculate the predicted carbon elimination amount for the target year according to the predicted tree height data for the target year and the near-target year and the verified actual carbon elimination amount for the near-target year through a preset carbon elimination amount prediction model;

[0093] The project scoring module 05 is used to determine the score of the carbon project according to the planned carbon elimination amount and the predicted carbon elimination amount in the target year, and the score is used to reflect the credit risk of the carbon project.

[0094] Based on the above embodiment, the present invention further provides a terminal, whose principle block diagram can be shown as follows: Figure 4 As shown. The terminal includes a processor, a memory, a network interface, and a display screen connected through a system bus. Among them, the processor of the terminal is used to provide computing and control capabilities. The memory of the terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the terminal is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the credit risk assessment method of the carbon project is implemented:

[0095] Obtain project document data of the carbon project, and obtain the planned carbon elimination amount for the target year and historical verification data of the project based on the project document data;

[0096] If the historical verification data of the project does not include the verified actual carbon elimination amount for the target year, then obtain the remote sensing image data corresponding to the target year and the near-target year respectively; wherein the near-target year has the verified actual carbon elimination amount in the historical verification data of the project;

[0097] By using a preset tree height prediction model, according to the remote sensing image data of the target year and the near target year, the predicted tree height data corresponding to the target year and the near target year are calculated;

[0098] Calculate the predicted carbon elimination amount for the target year by using a preset carbon elimination amount prediction model, based on the predicted tree height data for the target year and the near-target year and the verified actual carbon elimination amount for the near-target year;

[0099] A score for the carbon project is determined based on the planned carbon elimination amount and the predicted carbon elimination amount in the target year, and the score is used to reflect the credit risk of the carbon project.

[0100] The display screen of the terminal may be a liquid crystal display screen or an electronic ink display screen.

[0101] Those skilled in the art will understand that Figure 4 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the terminal to which the scheme of the present invention is applied. The specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0102] In one implementation, the memory of the terminal stores one or more programs, and is configured to be executed by one or more processors. The one or more programs include instructions for performing a credit risk assessment method for a carbon project:

[0103] Obtain project document data of the carbon project, and obtain the planned carbon elimination amount for the target year and historical verification data of the project based on the project document data;

[0104] If the historical verification data of the project does not include the verified actual carbon elimination amount for the target year, then obtain the remote sensing image data corresponding to the target year and the near-target year respectively; wherein the near-target year has the verified actual carbon elimination amount in the historical verification data of the project;

[0105] By using a preset tree height prediction model, according to the remote sensing image data of the target year and the near target year, the predicted tree height data corresponding to the target year and the near target year are calculated;

[0106] Calculate the predicted carbon elimination amount for the target year by using a preset carbon elimination amount prediction model, based on the predicted tree height data for the target year and the near-target year and the verified actual carbon elimination amount for the near-target year;

[0107] A score for the carbon project is determined based on the planned carbon elimination amount and the predicted carbon elimination amount in the target year, and the score is used to reflect the credit risk of the carbon project.

[0108] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0109] In summary, the present invention discloses a credit risk assessment method, system, terminal and storage medium for carbon projects. The method obtains the project document data of the carbon project, and obtains the planned carbon elimination amount and the historical verification data of the project in the target year according to the project document data; if the historical verification data of the project does not contain the verified actual carbon elimination amount of the target year, the remote sensing image data corresponding to the target year and the near target year are obtained; wherein the near target year has a verified actual carbon elimination amount in the historical verification data of the project; through a preset tree height prediction model, according to the remote sensing image data of the target year and the near target year, the predicted tree height data corresponding to the target year and the near target year are calculated; through a preset carbon elimination amount prediction model, according to the predicted tree height data of the target year and the near target year and the verified actual carbon elimination amount of the near target year, the predicted carbon elimination amount of the target year is calculated; according to the planned carbon elimination amount and the predicted carbon elimination amount of the target year, the score of the carbon project is determined, and the score is used to reflect the credit risk of the carbon project. In view of the situation that there is no verified actual carbon elimination amount in the target year, the present invention pre-constructs a tree height prediction model and a carbon elimination amount prediction model. The tree height prediction model is used to obtain tree height data based on remote sensing images, and then the carbon elimination amount prediction model is used to estimate the carbon elimination amount in the target year based on the tree height data. Finally, it is compared with the corresponding planned carbon elimination amount to complete the carbon project rating and realize transaction guidance in the carbon credit market.

[0110] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A credit risk assessment method for a carbon project, characterized in that: The method comprises: Obtain project document data of the carbon project, and obtain the planned carbon elimination amount for the target year and historical verification data of the project based on the project document data; If the historical verification data of the project does not include the verified actual carbon elimination amount for the target year, then obtain the remote sensing image data corresponding to the target year and the near-target year respectively; wherein the near-target year has the verified actual carbon elimination amount in the historical verification data of the project; By using a preset tree height prediction model, according to the remote sensing image data of the target year and the near target year, the predicted tree height data corresponding to the target year and the near target year are calculated; Calculate the predicted carbon elimination amount for the target year by using a preset carbon elimination amount prediction model, based on the predicted tree height data for the target year and the near-target year and the verified actual carbon elimination amount for the near-target year; A score for the carbon project is determined based on the planned carbon elimination amount and the predicted carbon elimination amount in the target year, and the score is used to reflect the credit risk of the carbon project.

2. The credit risk assessment method for carbon projects according to claim 1 is characterized in that: The training method of the tree height prediction model includes: Obtain remote sensing image data and tree height data for several historical time periods within a preset area; The tree height prediction model is trained based on the remote sensing image data and tree height data of each historical time period.

3. The credit risk assessment method for carbon projects according to claim 2 is characterized in that: The preset area range is determined based on a boundary vector of the carbon project.

4. The credit risk assessment method for carbon projects according to claim 1 is characterized in that: The carbon removal prediction model is used to: Calculate the ratio of the verified actual carbon removal amount in the near-target year to the predicted tree height data in the near-target year; The product of the ratio and the predicted tree height data for the target year is calculated to obtain the predicted carbon elimination amount for the target year.

5. The credit risk assessment method for carbon projects according to claim 1 is characterized in that: The method further comprises: If the historical verification data of the project includes the verified actual carbon elimination amount in the target year, the score of the carbon project is determined based on the planned carbon elimination amount and the actual carbon elimination amount in the target year.

6. The credit risk assessment method for carbon projects according to claim 5 is characterized in that: The method for determining the score of the carbon project includes: Determine the score of the carbon project based on the ratio of the actual carbon elimination amount to the planned carbon elimination amount in the target year; Alternatively, the score of the carbon project is determined based on the ratio of the predicted carbon elimination amount to the planned carbon elimination amount in the target year.

7. The credit risk assessment method for a carbon project according to claim 1, characterized in that: The target year is the most recent year; the carbon project is an ARR project, and the ARR project includes one or more projects of afforestation, reforestation and vegetation restoration.

8. A credit risk assessment system for carbon projects, characterized in that: The system comprises: A document acquisition module, used to acquire project document data of the carbon project, and acquire the planned carbon elimination amount for the target year and the verification data of the project over the years according to the project document data; An image acquisition module, for acquiring remote sensing image data corresponding to the target year and the near-target year respectively if the historical verification data of the project do not contain the verified actual carbon elimination amount of the target year; wherein the near-target year has the verified actual carbon elimination amount in the historical verification data of the project; A tree height prediction module, used to calculate predicted tree height data corresponding to the target year and the near target year respectively according to the remote sensing image data of the target year and the near target year through a preset tree height prediction model; A carbon elimination amount prediction module, used to calculate the predicted carbon elimination amount for the target year according to the predicted tree height data for the target year and the near-target year and the verified actual carbon elimination amount for the near-target year through a preset carbon elimination amount prediction model; The project scoring module is used to determine the score of the carbon project based on the planned carbon elimination amount and the predicted carbon elimination amount in the target year, and the score is used to reflect the credit risk of the carbon project.

9. A terminal, characterized in that: The terminal includes a memory and one or more processors; the memory stores one or more programs; the programs contain instructions for executing the credit risk assessment method for a carbon project as described in any one of claims 1-7; and the processor is used to execute the programs.

10. A computer-readable storage medium having a plurality of instructions stored thereon, characterized in that: The instructions are suitable for being loaded and executed by a processor to implement the steps of the credit risk assessment method for a carbon project as described in any one of claims 1 to 7 above.

Images