Quantification method for the impact of climate change and human activities on vegetation and related device

Abstract

The present invention discloses a method and related device for quantifying the impact of climate change and human activities on vegetation. The present invention uses the residual trend method to determine the sub-regions / time periods where climate change and human activities jointly affect vegetation growth, inputs the corresponding climate data and detrended climate data into a deep learning model, obtains the remote sensing vegetation index Pre1 and the remote sensing vegetation index Pre2, so as to obtain the quantification result of the impact of climate change and human activities on vegetation, and improves the quantification accuracy compared with the traditional statistical regression model.

Description

Technical Field

[0001] The present invention relates to a method and related device for quantifying the impact of climate change and human activities on vegetation, belonging to the field of data statistics and quantification. Background Art

[0002] With the intensification of climate change and the extensive development of human activities, the dynamic changes of vegetation are affected by various factors. Generally, the factors affecting vegetation dynamics are divided into climate factors and human activity factors. For example, in arid areas, the increase in precipitation promotes vegetation growth, while the increase in temperature may inhibit the growth of regional vegetation; over-reclamation may lead to vegetation degradation. Therefore, accurately quantifying the impact of climate change and human activities on vegetation growth can deepen the understanding of the impact of climate change and human activities on regional vegetation ecology, which is the premise of the vegetation protection plan in the region. The existing quantification methods mainly rely on traditional statistical regression models. Although they can quantify the impact of climate and human activities to a certain extent, the quantification accuracy is poor. Summary of the Invention

[0003] The present invention provides a method and related device for quantifying the impact of climate change and human activities on vegetation, which solves the problems disclosed in the background art.

[0004] According to one aspect of the present application, a method for quantifying the impact of climate change and human activities on vegetation is provided, including:

[0005] Obtaining the remote sensing vegetation index and climate data of the area to be quantified;

[0006] According to the remote sensing vegetation index and climate data of the area to be quantified, using the residual trend method, determining the first sub-region / time period A1; wherein, the first sub-region / time period A1 is the sub-region or time period in the area to be quantified where climate change and human activities jointly affect vegetation growth;

[0007] Inputting the climate data corresponding to the first sub-region / time period A1 into a deep learning model to obtain the remote sensing vegetation index Pre1 corresponding to the first sub-region / time period A1, and inputting the detrended climate data corresponding to the first sub-region / time period A1 into the deep learning model to obtain the remote sensing vegetation index Pre2 corresponding to the first sub-region / time period A1; wherein, the detrended climate data is the climate data after removing the climate change trend data;

[0008] Calculating the quantification result of the impact of climate change on vegetation according to the remote sensing vegetation index Pre1 and the remote sensing vegetation index Pre2;

[0009] Calculating the quantification result of the impact of human activities on vegetation according to the remote sensing vegetation index Pre1 and the remote sensing vegetation index corresponding to the first sub-region / time period A1.

[0010] Further, the deep learning model is pre-trained, and the pre-training process includes:

[0011] Obtain the remote sensing vegetation index and climate data of the training area; among them, the climate of the training area is similar to that of the area to be quantified;

[0012] According to the remote sensing vegetation index and climate data of the training area, use the residual trend method to determine the second sub-region / time period A2; where the second sub-region / time period A2 is the sub-region or time period in the training area where only climate change affects vegetation growth;

[0013] Use the remote sensing vegetation index and climate data corresponding to the second sub-region / time period A2 to train the deep learning model.

[0014] Further, the process of determining the sub-region / time period according to the remote sensing vegetation index and climate data by using the residual trend method includes:

[0015] According to the climate data, use the pre-constructed regression model to predict the remote sensing vegetation index; where the remote sensing vegetation index is used as the dependent variable and the climate data is used as the independent variable in the regression model;

[0016] Calculate the residual between the obtained remote sensing vegetation index and the predicted remote sensing vegetation index;

[0017] If the trend of the residual is not significant, it is considered that the sub-region / time period corresponding to the residual is the sub-region or time period where only climate change affects vegetation growth;

[0018] If the trend of the residual is significant, it is considered that the sub-region / time period corresponding to the residual is the sub-region or time period where both climate change and human activities affect vegetation growth.

[0019] Further, when training the deep learning model, in addition to obtaining the remote sensing vegetation index and climate data of the training area, also obtain the underlying surface factors and / or human activity data of the training area, and use the remote sensing vegetation index, climate data, and underlying surface factors and / or human activity data corresponding to the second sub-region / time period A2 for training;

[0020] During quantification, in addition to obtaining the remote sensing vegetation index and climate data of the area to be quantified, also obtain the underlying surface factors and / or human activity data of the area to be quantified, and input the climate data corresponding to the first sub-region / time period A1, as well as the underlying surface factors and / or human activity data into the deep learning model.

[0021] Further, according to the remote sensing vegetation index Pre1 and the remote sensing vegetation index Pre2, calculating the quantification result of the impact of climate change on vegetation includes:

[0022] Calculate the difference between the remote sensing vegetation index Pre1 and the remote sensing vegetation index Pre2, and use the difference as the quantification result of the impact of climate change on vegetation.

[0023] Further, according to the remote sensing vegetation index Pre1 and the remote sensing vegetation index corresponding to the first sub-region / time period A1, calculate the quantification result of the impact of human activities on vegetation, including:

[0024] Calculate the difference between the remote sensing vegetation index corresponding to the first sub-region / time period A1 and the remote sensing vegetation index Pre1, and use the difference as the quantification result of the impact of human activities on vegetation.

[0025] Further, the deep learning model is a ConvLSTM model. A convolution operation is introduced into the gating mechanism of the ConvLSTM model, and the weights and biases of the gating are calculated through convolutional kernels.

[0026] According to another aspect of the present application, there is provided a quantification device for the impact of climate change and human activities on vegetation, including:

[0027] An acquisition module that acquires the remote sensing vegetation index and climate data of the area to be quantified;

[0028] A residual trend module that determines the first sub-region / time period A1 according to the climate data of the area to be quantified by using the residual trend method; wherein, the first sub-region / time period A1 is the sub-region or time period where climate change and human activities jointly affect vegetation growth, and the first sub-region is a sub-region of the area to be quantified;

[0029] A prediction module that inputs the climate data corresponding to the first sub-region / time period A1 into the deep learning model to obtain the remote sensing vegetation index Pre1 corresponding to the first sub-region / time period A1, and inputs the detrended climate data corresponding to the first sub-region / time period A1 into the deep learning model to obtain the remote sensing vegetation index Pre2 corresponding to the first sub-region / time period A1; wherein, the detrended climate data is the climate data after removing the climate change trend data;

[0030] A first quantification module that calculates the quantification result of the impact of climate change on vegetation according to the remote sensing vegetation index Pre1 and the remote sensing vegetation index Pre2;

[0031] A second quantification module that calculates the quantification result of the impact of human activities on vegetation according to the remote sensing vegetation index Pre1 and the remote sensing vegetation index corresponding to the first sub-region / time period A1.

[0032] According to another aspect of the present application, there is provided a computer-readable storage medium. The computer-readable storage medium stores one or more programs, and the one or more programs include instructions that, when executed by a computing device, cause the computing device to execute the quantification method for the impact of climate change and human activities on vegetation.

[0033] According to another aspect of the present application, there is provided a computer device, including one or more processors and one or more memories. One or more programs are stored in the one or more memories and configured to be executed by the one or more processors. The one or more programs include instructions for executing a method for quantifying the impact of climate change and human activities on vegetation.

[0034] Beneficial effects achieved by the present invention: The present invention uses the residual trend method to determine the sub-regions / time periods jointly affected by climate change and human activities on vegetation growth, inputs the corresponding climate data and detrended climate data into a deep learning model to obtain the remote sensing vegetation index Pre1 and the remote sensing vegetation index Pre2, thereby obtaining the quantification result of the impact of climate change and human activities on vegetation. Compared with the traditional statistical regression model, the quantification accuracy is improved. Description of the Drawings

[0035] Figure 1 It is a flowchart of a method for quantifying the impact of climate change and human activities on vegetation;

[0036] Figure 2 It is a schematic structural diagram of a ConvLSTM model;

[0037] Figure 3 It is a block diagram of a device for quantifying the impact of climate change and human activities on vegetation. Detailed Embodiments

[0038] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and in no way limits the present application and its application or use. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0039] Unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions and values set forth in these embodiments do not limit the scope of the present application.

[0040] At the same time, it should be understood that, for the sake of convenience of description, the sizes of the various parts shown in the drawings are not drawn in actual proportional relationships.

[0041] For technologies, methods and devices known to those of ordinary skill in the relevant art, they may not be discussed in detail, but should be regarded as part of the specification when appropriate.

[0042] In all the examples shown and discussed here, any specific values should be construed as merely exemplary and not as a limitation. Thus, other examples of the exemplary embodiments may have different values.

[0043] It should be noted that like reference signs and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.

[0044] Deep learning is a machine learning method that mimics the structure and function of the human brain's neural network. By constructing a multi-layer neural network model, it automatically extracts complex features from large-scale data and achieves end-to-end learning. Its core lies in hierarchical feature extraction. Through multi-layer non-linear transformations, high-level semantic features are gradually abstracted from the original data. Common deep learning models include LSTM (Long Short-Term Memory), CNN (Convolutional Neural Networks), GAN (Generative Adversarial Network), ConvLSTM (Convolutional Long Short-Term Memory, a deep learning model that combines convolutional neural networks and long short-term memory networks), etc. Deep learning models are widely used in image recognition, natural language processing, weather prediction, etc.

[0045] The residual trend method is a statistical method for analyzing the relationship between variables by separating the trend component and the residual component in the data. Its core steps include constructing a basic model, calculating the residuals, and trend analysis. This method is mainly applied in ecological and environmental sciences (such as quantifying the contribution ratio of climate change and human activities to vegetation cover), economic forecasting (such as analyzing time series data of economic indicators and detecting potential influencing factors not captured by the model), medicine and engineering (testing whether the assumptions of time series models hold and identifying the sources of abnormal fluctuations), etc.

[0046] The embodiment of the present application provides a method for quantifying the impact of climate change and human activities on vegetation based on deep learning technology and the residual trend method. This quantification method can be executed by a quantification device, which can be a terminal device or a server. Among them, the terminal device can include, but is not limited to, mobile phones, computers, smart wearable devices, etc., and the embodiment of the present application does not make restrictions; the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, big data, and artificial intelligence platforms, etc., and the embodiment of the present application does not make restrictions. Optionally, this quantification method can also be executed collaboratively by multiple electronic devices with computing power. For the convenience of description, the subsequent embodiments will be described with the quantification device executing.

[0047] See Figure 1 , Figure 1 is a flowchart of a method for quantifying the impact of climate change and human activities on vegetation provided by the embodiment of the present application. This quantification method can be executed by a quantification device, and this quantification method can at least include the following steps:

[0048] Step 1, obtain the remote sensing vegetation index (Normalized Difference Vegetation Index, NDVI) and climate data of the area to be quantified.

[0049] It should be noted that the remote sensing vegetation index: such as vegetation index data of different time series and different resolutions like GIMMS NDVI3g (Global Inventory Modeling and Mapping Studies Normalized Difference Vegetation Index version 1 of the third generation), MODIS (Moderate Resolution Imaging Spectroradiometer); climate data: including temperature (highest, lowest, average), precipitation, radiation, wind speed, air pressure, etc., or extended to other factors according to actual needs (such as soil moisture, evapotranspiration, etc.). The obtained data are time series data of spatial data, and the spatial resolution and time range of each factor should be consistent in the end.

[0050] It should be noted that, in order to improve the recognition ability of the subsequent model, in some embodiments, the underlying surface factors and / or human activity data will be further obtained; among them, the underlying surface factors: such as land use, terrain (elevation, slope, etc.) and other static or semi-static information that may affect vegetation growth; human activity data: such as land use change intensity, socio-economic indicators, etc.

[0051] For the convenience of subsequent processing, the obtained data will be further preprocessed, such as interpolation, cropping, alignment, and unification of time and space resolutions.

[0052] Step 2: According to the remote sensing vegetation index and climate data of the area to be quantified, the residual trend method is used to determine the first sub-region / time period A1; among them, the first sub-region / time period A1 is the sub-region or time period in the area to be quantified where climate change and human activities jointly affect vegetation growth.

[0053] In some embodiments, the specific process of Step 2 can be as follows:

[0054] 21) According to the climate data, a pre-constructed regression model is used to predict the remote sensing vegetation index; among them, in the regression model, the remote sensing vegetation index is used as the dependent variable and the climate data is used as the independent variable.

[0055] It should be noted that a multiple linear or other suitable regression form (linear regression, non-linear regression, etc.) can be used, with the remote sensing vegetation index as the dependent variable and the climate data as the independent variable, to construct a regression model, so as to obtain the theoretical trend of the impact of climate change on NDVI, which can be expressed by the formula:

[0056] NDVI 预测 = f(temperature, precipitation, radiation,...);

[0057] Among them, NDVI 预测 represents the predicted remote sensing vegetation index, and f is the regression function.

[0058] 22) Calculate the residual between the obtained remote sensing vegetation index and the predicted remote sensing vegetation index.

[0059] The residual can be expressed by the formula ΔNDVI 预测 = NDVI 获取 - NDVI 预测 ; among them, NDVI 获取 is the obtained remote sensing vegetation index, that is, the actual remote sensing vegetation index.

[0060] 23) Conduct a significance test on the trend of the residuals. If the trend of the residuals is not significant, it is considered that the sub-region / time period corresponding to the residuals is the sub-region or time period where only climate change affects vegetation growth. If the trend of the residuals is significant, it is considered that the sub-region / time period corresponding to the residuals is the sub-region or time period where both climate change and human activities affect vegetation growth.

[0061] It should be noted that the significance test can be carried out using the Mann-Kendall test or the t-test, etc., to screen out the regions / time periods where the influence of human activities is significant at a significance level of α = 0.05. If the residual trend is not significant (i.e., not less than α) or close to zero, it is considered that climate change can explain most of the vegetation changes, that is, only climate change affects vegetation growth. If it is significant (i.e., below α), it indicates that human activities have a greater influence in this region / time period, that is, both climate change and human activities affect vegetation growth. Specifically, if the residuals show a significant positive trend in time or space, it usually indicates that human activities in this region / time period promote vegetation growth. If it shows a significant negative trend, it indicates that human activities may have an inhibitory or destructive effect on vegetation growth.

[0062] Step 3: Input the climate data corresponding to the first sub-region / time period A1 into the deep learning model to obtain the remote sensing vegetation index Pre1 corresponding to the first sub-region / time period A1. Input the detrended climate data corresponding to the first sub-region / time period A1 into the deep learning model to obtain the remote sensing vegetation index Pre2 corresponding to the first sub-region / time period A1; where the detrended climate data is the climate data after removing the climate change trend data.

[0063] It should be noted that the deep learning model needs to be pre-trained. First, obtain the remote sensing vegetation index and climate data of the training region. The climate of the training region is similar to that of the region to be quantified. According to the remote sensing vegetation index and climate data of the training region, use the residual trend method to determine the second sub-region / time period A2. The second sub-region / time period A2 is the sub-region or time period in the training region where only climate change affects vegetation growth. Then, use the remote sensing vegetation index and climate data corresponding to the second sub-region / time period A2 to train the deep learning model.

[0064] It should be noted that the deep learning model here can use LSTM or CNN. However, in some embodiments, the ConvLSTM model is used. The ConvLSTM model is a deep learning model that combines the spatial feature extraction ability of the convolutional neural network (CNN) with the time series learning ability of LSTM. Adaptive modifications are made based on the ConvLSTM model as follows:

[0065] See Figure 2, in order to make full use of the spatial feature extraction ability of the convolutional network, here the regional grid data (i.e., the climate data and remote sensing vegetation index of the input data) are input into the ConvLSTM network (specifically a two-layer network) in the form of "multi-channel images" and "temporal image sequences", that is, each time step (such as Figure 2 one month in Figure 2 , or a quarter) corresponds to a "two-dimensional map", where the pixel values can correspond to climate data (multi-channel) such as NDVI, temperature, precipitation, radiation, etc., and then stacked over time to form a four-dimensional data structure (height, width, channel, time).

[0066] In the ConvLSTM network, convolution operations are introduced into the gating mechanisms such as the input gate, forget gate, and output gate of the traditional LSTM, so that the weights and biases of the gating are calculated through convolutional kernels instead of fully connected layers, thus retaining spatial information.

[0067] For the multi-dimensional time, space, and feature dimension variables output by the ConvLSTM network, first add a pooling layer to reduce the spatial dimension to one dimension, then reduce the feature dimension to one dimension through a fully connected layer, and finally splice them to obtain the predicted vegetation index for the target time period.

[0068] The output layer of the ConvLSTM model can be set to the regression mode as needed for predicting the value of NDVI. For each time step, the ConvLSTM will output the predicted spatial distribution of NDVI. Through the convolutional gating operation on the input sequences of multiple time periods, the network can capture the complex spatio-temporal correlation relationship and potential time lag effect between vegetation and climate data.

[0069] Comparing the prediction results of the above ConvLSTM model with the output of the random forest has superiority in capturing spatio-temporal dependence and non-linear relationships.

[0070] In order to improve the model's ability to identify the impact of human activities, during training, underlying surface factors and / or human activity data can be added to the input channels of the ConvLSTM model, and these data enter the model together with the climate data for model training.

[0071] Correspondingly, during quantification, in addition to obtaining remote sensing vegetation index and climate data, underlying surface factors and / or human activity data are also obtained, and the climate data corresponding to the first sub-region / time period A1, as well as the underlying surface factors and / or human activity data, are input into the ConvLSTM model to obtain the remote sensing vegetation index.

[0072] It should be noted that the climate change trend data is the straight line that best represents the time series trend obtained by fitting through a linear regression model. Then, subtracting the climate change trend data from the actual climate data can obtain the detrended climate data. For example, subtracting the climate change trend data at time k from the climate data at time k can obtain the detrended climate data at time k.

[0073] Step 4: Calculate the quantitative result of the impact of climate change on vegetation based on the remote sensing vegetation index Pre1 and the remote sensing vegetation index Pre2.

[0074] Specifically, Step 4 is to calculate the difference between the remote sensing vegetation index Pre1 and the remote sensing vegetation index Pre2, and use the difference as the quantitative result of the impact of climate change on vegetation. It can be expressed by the formula C = Pre1 - Pre2, and the corresponding relative contribution value can be expressed as R C = C / Pre1.

[0075] Step 5: Calculate the quantitative result of the impact of human activities on vegetation based on the remote sensing vegetation index Pre1 and the remote sensing vegetation index corresponding to the first sub-region / time period A1.

[0076] Specifically, Step 5 is to calculate the difference between the remote sensing vegetation index corresponding to the first sub-region / time period A1 and the remote sensing vegetation index Pre1, and use the difference as the quantitative result of the impact of human activities on vegetation. It can be expressed by the formula H = Obs - Pre1, where Obs is the remote sensing vegetation index corresponding to the first sub-region / time period A1, and the corresponding relative contribution value can be expressed as R H = H / Pre1.

[0077] The results obtained by the above method can be visually displayed in combination with the spatio-temporal distribution map of land use changes to help decision-makers or researchers understand the regional situation.

[0078] In the above method, the ConvLSTM model can comprehensively consider spatio-temporal characteristics, learn spatio-temporal features through the convolution process of data in different spatial ranges at different time periods, and at the same time utilize the time-lag correlation of vegetation to different climate data to determine the climate data with the optimal memory time limit as the input of the deep learning model, improving the accuracy of quantification.

[0079] The above method uses the residual trend method to determine the sub-regions / time periods jointly affected by climate change and human activities on vegetation growth, inputs the corresponding climate data and detrended climate data into the deep learning model to obtain the remote sensing vegetation index Pre1 and the remote sensing vegetation index Pre2, so as to obtain the quantitative results of the impact of climate change and human activities on vegetation. Compared with the traditional statistical regression model, the accuracy of quantification is improved.

[0080] See Figure 3 , Figure 3It is a block diagram of a device for quantifying the impact of climate change and human activities on vegetation provided by an embodiment of the present application. Figure 3 The embodiment of is a virtual device that can be loaded and executed by a computer device, which may include the above-mentioned quantification device. Figure 3 The device of may include an acquisition module, a residual trend module, a prediction module, a first quantification module, and a second quantification module. When used to execute the above-mentioned quantification method, it can:

[0081] The acquisition module acquires the remote sensing vegetation index and climate data of the area to be quantified.

[0082] The residual trend module determines the first sub-region / time period A1 using the residual trend method based on the remote sensing vegetation index and climate data of the area to be quantified; wherein, the first sub-region / time period A1 is the sub-region or time period in the area to be quantified where climate change and human activities jointly affect vegetation growth.

[0083] The prediction module inputs the climate data corresponding to the first sub-region / time period A1 into the deep learning model to obtain the remote sensing vegetation index Pre1 corresponding to the first sub-region / time period A1, and inputs the detrended climate data corresponding to the first sub-region / time period A1 into the deep learning model to obtain the remote sensing vegetation index Pre2 corresponding to the first sub-region / time period A1; wherein, the detrended climate data is the climate data after removing the climate change trend data.

[0084] The first quantification module calculates the quantification result of the impact of climate change on vegetation based on the remote sensing vegetation index Pre1 and the remote sensing vegetation index Pre2.

[0085] The second quantification module calculates the quantification result of the impact of human activities on vegetation based on the remote sensing vegetation index Pre1 and the remote sensing vegetation index corresponding to the first sub-region / time period A1.

[0086] The above-mentioned device uses the residual trend method to determine the sub-region / time period where climate change and human activities jointly affect vegetation growth, inputs the corresponding climate data and detrended climate data into the deep learning model to obtain the remote sensing vegetation index Pre1 and the remote sensing vegetation index Pre2, thereby obtaining the quantification results of the impacts of climate change and human activities on vegetation, improving the quantification accuracy compared with the traditional statistical regression model.

[0087] The present application also relates to a computer-readable storage medium storing one or more programs, and the one or more programs include instructions that, when executed by a computing device, cause the computing device to execute the method for quantifying the impact of climate change and human activities on vegetation.

[0088] The present application also relates to a computer device, including one or more processors and one or more memories. One or more programs are stored in one or more memories and configured to be executed by one or more processors. The one or more programs include instructions for executing a method for quantifying the impact of climate change and human activities on vegetation.

[0089] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0090] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0091] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0092] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0093] The above are only embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention are included within the scope of the claims of the present invention awaiting approval of the application.

Claims

1. A method for quantifying the impact of climate change and human activities on vegetation, characterized in that, Including: Obtain the remote sensing vegetation index and climate data of the area to be quantified; According to the remote sensing vegetation index and climate data of the area to be quantified, adopt the residual trend method to determine the first sub-region / time period A1; wherein, the first sub-region / time period A1 is the sub-region or time period in the area to be quantified where climate change and human activities jointly affect vegetation growth; Input the climate data corresponding to the first sub-region / time period A1 into the deep learning model to obtain the remote sensing vegetation index Pre1 corresponding to the first sub-region / time period A1, and input the detrended climate data corresponding to the first sub-region / time period A1 into the deep learning model to obtain the remote sensing vegetation index Pre2 corresponding to the first sub-region / time period A1; wherein, the detrended climate data is the climate data after removing the climate change trend data; Calculate the quantification result of the impact of climate change on vegetation according to the remote sensing vegetation index Pre1 and the remote sensing vegetation index Pre2; Calculate the quantification result of the impact of human activities on vegetation according to the remote sensing vegetation index Pre1 and the remote sensing vegetation index corresponding to the first sub-region / time period A1; The process of determining the sub-region / time period by adopting the residual trend method according to the remote sensing vegetation index and climate data includes: Predict the remote sensing vegetation index according to the climate data by using a pre-constructed regression model; wherein, in the regression model, the remote sensing vegetation index is used as the dependent variable and the climate data is used as the independent variable; Calculate the residual between the obtained remote sensing vegetation index and the predicted remote sensing vegetation index; If the trend of the residual is not significant, it is considered that the sub-region / time period corresponding to the residual is the sub-region or time period where only climate change affects vegetation growth; If the trend of the residual is significant, it is considered that the sub-region / time period corresponding to the residual is the sub-region or time period where climate change and human activities jointly affect vegetation growth.

2. The method according to claim 1, wherein The deep learning model is pre-trained, and the pre-training process includes: Obtain the remote sensing vegetation index and climate data of the training area; wherein, the climate of the training area is similar to that of the area to be quantified; According to the remote sensing vegetation index and climate data of the training area, adopt the residual trend method to determine the second sub-region / time period A2; wherein, the second sub-region / time period A2 is the sub-region or time period in the training area where only climate change affects vegetation growth; Use the remote sensing vegetation index and climate data corresponding to the second sub-region / time period A2 to train the deep learning model.

3. The method according to claim 2, characterized in that, When training the deep learning model, in addition to obtaining the remote sensing vegetation index and climate data of the training area, also obtain the underlying surface factors and / or human activity data of the training area, and use the remote sensing vegetation index, climate data, and underlying surface factors and / or human activity data corresponding to the second sub-region / time period A2 for training; During quantification, in addition to obtaining the remote sensing vegetation index and climate data of the area to be quantified, also obtain the underlying surface factors and / or human activity data of the area to be quantified, and input the climate data corresponding to the first sub-region / time period A1, as well as the underlying surface factors and / or human activity data, into the deep learning model.

4. The method according to claim 1, wherein Calculating the quantification result of the impact of climate change on vegetation according to the remote sensing vegetation index Pre1 and the remote sensing vegetation index Pre2 includes: Calculate the difference between the remote sensing vegetation index Pre1 and the remote sensing vegetation index Pre2, and use the difference as the quantification result of the impact of climate change on vegetation.

5. The method according to claim 1, wherein According to the remote sensing vegetation index Pre1 and the remote sensing vegetation index corresponding to the first sub-region / time period A1, calculate the quantification result of the impact of human activities on vegetation, including: Calculate the difference between the remote sensing vegetation index corresponding to the first sub-region / time period A1 and the remote sensing vegetation index Pre1, and use the difference as the quantification result of the impact of human activities on vegetation.

6. The method according to claim 1, characterized in that, The deep learning model is a ConvLSTM model. A convolution operation is introduced into the gating mechanism of the ConvLSTM model, and the weights and biases of the gating are calculated through convolutional kernels.

7. A quantification device for the impact of climate change and human activities on vegetation, characterized in that, Including: An acquisition module that acquires the remote sensing vegetation index and climate data of the area to be quantified; A residual trend module that determines the first sub-region / time period A1 according to the remote sensing vegetation index and climate data of the area to be quantified by using the residual trend method; wherein, the first sub-region / time period A1 is the sub-region or time period in the area to be quantified where climate change and human activities jointly affect vegetation growth; A prediction module that inputs the climate data corresponding to the first sub-region / time period A1 into the deep learning model to obtain the remote sensing vegetation index Pre1 corresponding to the first sub-region / time period A1, and inputs the detrended climate data corresponding to the first sub-region / time period A1 into the deep learning model to obtain the remote sensing vegetation index Pre2 corresponding to the first sub-region / time period A1; wherein, the detrended climate data is the climate data after removing the climate change trend data; A first quantification module that calculates the quantification result of the impact of climate change on vegetation according to the remote sensing vegetation index Pre1 and the remote sensing vegetation index Pre2; A second quantification module that calculates the quantification result of the impact of human activities on vegetation according to the remote sensing vegetation index Pre1 and the remote sensing vegetation index corresponding to the first sub-region / time period A1; The process of determining the sub-region / time period by using the residual trend method according to the remote sensing vegetation index and climate data includes: Predict the remote sensing vegetation index according to the climate data by using a pre-constructed regression model; wherein, in the regression model, the remote sensing vegetation index is used as the dependent variable and the climate data is used as the independent variable; Calculate the residual between the obtained remote sensing vegetation index and the predicted remote sensing vegetation index; If the trend of the residual is not significant, it is considered that the sub-region / time period corresponding to the residual is the sub-region or time period where only climate change affects vegetation growth; If the trend of the residual is significant, it is considered that the sub-region / time period corresponding to the residual is the sub-region or time period where climate change and human activities jointly affect vegetation growth.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores one or more programs, and the one or more programs include instructions that, when executed by a computing device, cause the computing device to execute the method according to any one of claims 1 to 6.

9. A computer device, characterized in that, Including: One or more processors and one or more memories. One or more programs are stored in the one or more memories and are configured to be executed by the one or more processors. The one or more programs include instructions for executing the method according to any one of claims 1 to 6.

Images