Forest carbon sink remote sensing detection method and device based on neural network

Abstract

The application discloses a forest carbon sink remote sensing detection method and device based on a neural network, and the method comprises the following steps: acquiring remote sensing data of a target forest area; determining soil characteristic information of the target forest area based on soil data; determining tree characteristic information of the target forest area based on tree data; performing first carbon sink matching processing on the soil characteristic information to obtain first carbon sink information; performing second carbon sink matching processing on the tree characteristic information to obtain second carbon sink information; and determining target carbon sink information of the target forest area based on the first carbon sink information and the second carbon sink information. Through the application, the problem of low carbon sink detection precision is solved, and the effect of improving carbon sink detection precision and efficiency is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, in particular to a forest carbon sink amount remote sensing detection method and device based on a neural network. BACKGROUND

[0002] As the main body of the terrestrial ecosystem, forests play a very important role in global carbon cycle, so detecting the forest carbon sink capacity is of great significance for studying global climate change.

[0003] In the prior art, the forest area is vast, and the use of manpower is low in efficiency and high in cost. The Food and Agriculture Organization of the United Nations (FAO) defines forest as: "land with an area of more than 0.5 hectares, trees higher than 5 meters, and canopy coverage rate of more than 10%, or trees in the original habitat can reach this threshold". The forest area is at least 5000 square meters, and most of them are far more than this data, which can reach hundreds of thousands to millions of square meters. Forestry survey personnel go deep into the forest, consume huge energy and time cost, and it is not easy to collect and count forest data in some remote or harsh forest areas. It is very difficult to collect forest data and real-time data. SUMMARY

[0004] The embodiments of the present application provide a forest carbon sink amount remote sensing detection method and device based on a neural network, to at least solve the problem of low carbon sink amount detection precision in the related art.

[0005] A forest carbon sink amount remote sensing detection method based on a neural network, comprising the following steps:

[0006] Obtain remote sensing data of a target forest area, wherein the remote sensing data comprises soil data and tree data;

[0007] Determine soil feature information of the target forest area based on the soil data, wherein the soil data at least comprises soil reflectivity data;

[0008] Determine tree feature information of the target forest area based on the tree data, wherein the tree data at least comprises tree morphology data;

[0009] Perform first carbon sink amount matching processing on the soil feature information to obtain first carbon sink amount information, and perform second carbon sink amount matching processing on the tree feature information to obtain second carbon sink amount information;

[0010] Determine target carbon sink amount information of the target forest area based on the first carbon sink amount information and the second carbon sink amount information.

[0011] As an implementable manner, the determining the forest feature information of the target forest region based on the forest data comprises the following steps:

[0012] determining first heat data of the target forest region based on the remote sensing data;

[0013] determining forest canopy feature information of the target forest region by a preset first model according to the first heat data and the forest morphological data, wherein the forest feature information comprises the forest canopy feature information.

[0014] As an implementable manner, after the first carbon sink amount matching processing of the soil feature information to obtain first carbon sink amount information and the second carbon sink amount matching processing of the forest feature information to obtain second carbon sink amount information, the method further comprises:

[0015] determining target shortwave data of a first sub-region based on the remote sensing data, wherein the target forest region comprises the first sub-region, the target forest region is composed of a plurality of first sub-regions, the first sub-region is obtained by GIS region division, and the target shortwave data comprises first shortwave biological heat radiation energy wave proportion data of the first sub-region;

[0016] determining first biological information of the first sub-region according to the target shortwave data by a preset second model, wherein the first biological information comprises biological group information;

[0017] performing third carbon sink amount matching on the first biological information to determine third carbon sink amount information;

[0018] determining target carbon sink amount information of the target forest region based on the first carbon sink amount information, the second carbon sink amount information and the third carbon sink amount information.

[0019] As an implementable manner, after the first carbon sink amount matching processing of the soil feature information to obtain first carbon sink amount information and the second carbon sink amount matching processing of the forest feature information to obtain second carbon sink amount information, the method further comprises:

[0020] determining audio data of a second sub-region based on the remote sensing data, wherein the target forest region comprises the second sub-region, the target forest region is composed of a plurality of second sub-regions, and the second sub-region is obtained by GIS region division;

[0021] determining second biological information of the second sub-region based on the audio data by a preset third model, wherein the second biological information comprises biological group information;

[0022] performing fourth carbon sink amount matching on the second biological information to determine fourth carbon sink amount information;

[0023] determining target carbon sink amount information of the target forest region based on the first carbon sink amount information, the second carbon sink amount information, and the fourth carbon sink amount information.

[0024] A device for detecting forest carbon sink amount based on a neural network, comprising a remote sensing data acquisition module, a soil feature determination module, a tree feature determination module, a first matching module, and a first carbon sink amount determination module.

[0025] The remote sensing data acquisition module is configured to acquire remote sensing data of a target forest region, wherein the remote sensing data comprises soil data and tree data.

[0026] The soil feature determination module is configured to determine soil feature information of the target forest region based on the soil data, wherein the soil data at least comprises soil reflectance data.

[0027] The tree feature determination module is configured to determine tree feature information of the target forest region based on the tree data, wherein the tree data at least comprises tree morphology data.

[0028] The first matching module is configured to perform first carbon sink amount matching processing on the soil feature information to obtain first carbon sink amount information, and perform second carbon sink amount matching processing on the tree feature information to obtain second carbon sink amount information.

[0029] The first carbon sink amount determination module is configured to determine target carbon sink amount information of the target forest region based on the first carbon sink amount information and the second carbon sink amount information.

[0030] As an implementable manner, the tree feature determination module comprises:

[0031] A first heat unit is configured to determine first heat data of the target forest region based on the remote sensing data.

[0032] A canopy feature determination unit is configured to determine tree canopy feature information of the target forest region based on the first heat data and the tree morphology data through a preset first model, wherein the tree feature information comprises the tree canopy feature information.

[0033] As an implementable manner, the device further comprises:

[0034] The short wave determination module is configured to, after the first carbon sink amount matching processing on the soil characteristic information to obtain first carbon sink amount information and the second carbon sink amount matching processing on the forest tree characteristic information to obtain second carbon sink amount information, determine target short wave data of a first sub-region based on the remote sensing data, wherein the target forest region includes the first sub-region, the target forest region is composed of a plurality of first sub-regions, the first sub-region is obtained through GIS region division, and the target short wave data includes first short wave proportion data of biological thermal radiation energy waves in the first sub-region.

[0035] The biological information determination module is configured to determine first biological information of the first sub-region through a preset second model according to the target short wave data, wherein the first biological information includes biological group information.

[0036] The second matching module is configured to perform third carbon sink amount matching on the first biological information to determine third carbon sink amount information.

[0037] The second carbon sink amount determination module is configured to determine target carbon sink amount information of the target forest region based on the first carbon sink amount information, the second carbon sink amount information and the third carbon sink amount information.

[0038] As an implementation manner, the device further includes,

[0039] The audio data acquisition module is configured to, after the first carbon sink amount matching processing on the soil characteristic information to obtain first carbon sink amount information and the second carbon sink amount matching processing on the forest tree characteristic information to obtain second carbon sink amount information, determine audio data of a second sub-region based on the remote sensing data, wherein the target forest region includes the second sub-region, the target forest region is composed of a plurality of second sub-regions, and the second sub-region is obtained through GIS region division.

[0040] The second biological information module is configured to determine second biological information of the second sub-region through a preset third model based on the audio data, wherein the second biological information includes biological group information.

[0041] The third matching module is configured to perform fourth carbon sink amount matching on the second biological information to determine fourth carbon sink amount information.

[0042] The third carbon sink amount determination module is configured to determine target carbon sink amount information of the target forest region based on the first carbon sink amount information, the second carbon sink amount information and the fourth carbon sink amount information.

[0043] A computer-readable storage medium storing a computer program, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.

[0044] An electronic device includes a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0045] This invention improves the accuracy of carbon sink detection by using remote sensing to precisely detect forest carbon sinks, thus solving the problem of low detection accuracy and achieving the effect of improving both the accuracy and efficiency of carbon sink detection. Attached Figure Description

[0046] Figure 1 This is a hardware structure block diagram of a mobile terminal for a remote sensing detection method for forest carbon sink based on neural networks, according to an embodiment of the present invention.

[0047] Figure 2 This is a flowchart of a remote sensing method for forest carbon sink based on a neural network according to an embodiment of the present invention;

[0048] Figure 3 This is a structural block diagram of a remote sensing device for forest carbon sink based on a neural network according to an embodiment of the present invention. Detailed Implementation

[0049] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings and examples.

[0050] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0051] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a remote sensing detection method for forest carbon sinks based on neural networks, according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1The illustrated structure is merely schematic and does not limit the structure of the mobile terminal described above. For example, the mobile terminal can further include more or less components than those shown, or have different configurations of the components shown. Figure 1 The illustrated structure is merely schematic and does not limit the structure of the mobile terminal described above. For example, the mobile terminal can further include more or less components than those shown, or have different configurations of the components shown. Figure 1 The illustrated structure is merely schematic and does not limit the structure of the mobile terminal described above. For example, the mobile terminal can further include more or less components than those shown, or have different configurations of the components shown.

[0052] The memory 104 can be used to store computer programs, such as software programs of application software and modules, such as a computer program corresponding to the forest carbon sink remote sensing detection method based on a neural network according to an embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, that is, implements the method described above. The memory 104 can include a high-speed random access memory, and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include a memory remotely arranged with respect to the processor 102, which can be connected to the mobile terminal through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0053] The transmission device 106 is used to receive or send data via a network. Specific examples of the network can include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet in a wireless manner.

[0054] In the present embodiment, a forest carbon sink remote sensing detection method based on a neural network is provided, Figure 2 which is a flowchart of a forest carbon sink remote sensing detection method based on a neural network according to an embodiment of the present application, as shown in Figure 2 The flowchart includes the following steps:

[0055] In step S201, remote sensing data of a target forest region is acquired, wherein the remote sensing data includes soil data and tree data.

[0056] In the present embodiment, the target forest region is detected by remote sensing data, without manual detection, which improves the detection efficiency and the detection accuracy.

[0057] The target forest region includes a forest region to be detected for carbon sink amount, and the target forest region can also be a region such as shrubbery, grassland, river, and desert. The remote sensing data can include, but is not limited to, the following types: satellite remote sensing data obtained by satellite remote sensing of the target forest region by a remote sensing satellite, flight remote sensing data obtained by low-altitude remote sensing and laser point cloud scanning of the target forest region by a remote sensing scanning device and a laser scanning device carried by an unmanned aerial vehicle, and ground remote sensing data obtained by ground remote sensing scanning and laser scanning of the ground of the target forest region by a laser device and a remote sensing scanning device carried by a ground patrol vehicle or a ground unmanned vehicle. The remote sensing data can also include terrain data such as mountainous land, basin, and plateau according to data content. The remote sensing data can also include optical signal data, electromagnetic wave signal data, and image data according to data format.

[0058] The forest data and the soil data are obtained by remote sensing of forest and soil by a remote sensing satellite, a remote sensing aerial vehicle, or a remote sensing ground patrol vehicle.

[0059] In step S202, soil feature information of the target forest region is determined based on the soil data, and the soil data at least includes soil reflectivity data.

[0060] In this embodiment, the soil texture, water content, organic matter content, and mineral composition of the target forest region can be determined by the soil reflectivity data, so that the subsequent carbon sink amount calculation can be performed according to the information.

[0061] The soil reflectivity data includes data formed by absorption and reflection of remote sensing signals (usually electromagnetic waves) by soil, including but not limited to signal intensity (energy amplitude), signal frequency, signal distribution, signal energy distribution, signal beam condition, and the like. The soil feature information includes but is not limited to organic matter content, soil texture, mineral composition, and water content.

[0062] For example, in the same type of soil, the higher the organic matter content, the higher the degree of dark brown to black of the soil, the lower the signal reflectivity, the lower the image gray value, and the lower the optical signal transmittance. The higher the content of iron oxide in the soil, the lower the spectral reflectivity. The higher the soil texture hardness, the higher the signal reflectivity, and vice versa. The higher the soil water content, the lower the signal reflectivity, and the difference increases with the increase of signal wavelength. It should be noted that the water holding capacity of various soils is different, so the sensitivity range corresponding to the change of reflectivity due to the change of humidity is also different. Generally, when the water content is 10% to 25%, the reflectivity changes significantly. The sensitivity range of soil with poor water holding capacity can be less than 10%, for example, due to the formation of specular reflection by the surface film water layer of the soil, the reflectivity of this type is higher than 10%, and so on.

[0063] In step S203, the tree feature information of the target forest area is determined based on the tree data, wherein the tree data at least includes tree shape data.

[0064] In the embodiment, the water content of different tree species, the cell wall amount of cells, and the crown shape, diameter at breast height, and height of the same tree species at different times (e.g., different seasons or different growth states) are different, which will affect the collection of tree data or the calculation of carbon sink amount, and thus the feature information of the tree at the current time needs to be determined to accurately calculate the carbon sink amount.

[0065] The tree feature information includes, but is not limited to, tree species, tree canopy area, tree height, tree water content, tree diameter at breast height, and tree cell wall amount. It should be noted that the tree includes herbaceous (e.g., moss) and woody (e.g., shrubs and trees) plants, and the tree shape data includes, but is not limited to, crown shape (whether there is a crown and the crown style, such as bell-shaped, spherical, etc.), and tree branch distribution shape.

[0066] In step S204, the first carbon sink amount matching processing is performed on the soil feature information to obtain first carbon sink amount information, and the second carbon sink amount matching processing is performed on the tree feature information to obtain second carbon sink amount information.

[0067] In the embodiment, after the soil feature and the tree feature are determined, the soil feature and the tree feature are matched with the pre-set carbon sink amount database respectively to determine the corresponding carbon sink amount of the soil and the tree.

[0068] The matching process can be implemented by a matching algorithm, such as a floating-point algorithm. It should be noted that the pre-set carbon sink amount database can be determined based on big data statistics or by a specific algorithm. For example, the carbon sink amount of the tree can be calculated based on formula 1:

[0069]

[0070] In formula 1, Ci is the carbon sink amount of a tree species, ri is the tree species cell wall rate of the tree species, and Vi is the volume of the tree species. Then, the carbon sink amounts of all tree species are summed to calculate the carbon sink of the forest, i.e., C is the carbon sink amount of the forest, and n is the total number of tree species.

[0071] In particular, when performing the in-forest remote sensing scanning, the water content of the forest and the diameter at breast height of the forest can also be determined through the echo energy and echo distribution of the ultrasonic wave, because the ultrasonic wave after passing through the liquid can determine the type information (for example, pine, shrub, etc.) of the forest according to the water content and the diameter at breast height of the forest, and then determine the carbon sink amount of the forest based on the type information of the forest and the current growth state of the forest; that is, the water content information and the diameter at breast height information of the target forest in the target forest area are determined through the ultrasonic remote sensing detection data, and the forest feature information is determined based on the water content information and the diameter at breast height information; the second carbon sink amount information is determined based on the forest feature information.

[0072] In step S205, the target carbon sink amount information of the target forest area is determined based on the first carbon sink amount information and the second carbon sink amount information.

[0073] In this embodiment, after the carbon sink amount of the soil and the carbon sink amount of the forest are determined respectively, the two are summed to obtain the target carbon sink amount information.

[0074] Through the above steps, the accurate detection and calculation of the carbon sink amount are realized based on remote sensing detection and big data matching, which solves the problem of insufficient accuracy of the carbon sink amount calculation and improves the calculation accuracy and efficiency of the carbon sink amount.

[0075] The execution subject of the above steps can be a base station, a terminal, etc., but is not limited thereto.

[0076] The execution order of steps S202 and S203 can be interchanged, that is, step S204 can be executed first, and then S202 can be executed.

[0077] In an optional embodiment, the determination of the forest feature information of the target forest area based on the forest data comprises:

[0078] In step S2031, the first heat data of the target forest area is determined based on the remote sensing data.

[0079] In step S2032, the forest canopy feature information of the target forest area is determined through a preset first model according to the first heat data and the forest form data, wherein the forest feature information comprises the forest canopy feature information.

[0080] In this embodiment, because the heat absorption and heat radiation of different forests are different, and the forest mainly absorbs heat through the canopy, the forest data can be corrected through the heat data, thereby assisting in determining the features of the forest; it should be noted that the first heat data is not limited to determining the canopy features of the forest, but can also be applied to auxiliary determination of the soil layer features.

[0081] The first heat data includes heat distribution, heat value, heat radiation short wave distribution and the like. The forest canopy feature information includes, but is not limited to, canopy shape, canopy height, canopy area and the like. The first model can be a point cloud cutting clustering model based on laser point cloud data, such as Opencv series, or an image recognition model based on image data, such as YOLO series.

[0082] In an optional embodiment, after the soil feature information is subjected to the first carbon sink matching processing to obtain the first carbon sink information, and the forest feature information is subjected to the second carbon sink matching processing to obtain the second carbon sink information, the method further includes:

[0083] In step S2041, target short wave data of a first sub-region is determined based on the remote sensing data. The target forest region includes the first sub-region, and the target forest region is composed of a plurality of first sub-regions. The first sub-region is obtained by GIS region division. The target short wave data includes first short wave proportion data of biological thermal radiation energy wave in the first sub-region.

[0084] In step S2042, first biological information of the first sub-region is determined based on the target short wave data and a preset second model. The first biological information includes biological group information.

[0085] In step S2043, the biological group information is subjected to third carbon sink matching to determine third carbon sink information.

[0086] In step S2044, target carbon sink information of the target forest region is determined based on the first carbon sink information, the second carbon sink information and the third carbon sink information.

[0087] In this embodiment, in order to further improve the calculation accuracy of carbon sink, the carbon sink of some microorganisms and organisms that can store carbon in the forest region also needs to be calculated. Compared with forest and soil, the remote sensing data of other organisms and microorganisms is not easy to process, and therefore heat detection can be used to collect data of these microorganisms and organisms, so as to avoid the neglect of microorganisms and other organisms by remote sensing detection.

[0088] Since the heat radiation and heat absorption of different organisms and microorganisms in different states are different, the reflected heat radiation short wave and the emitted heat radiation short wave are also different. Therefore, the proportion of the heat radiation short wave of a specific frequency in the corresponding region can be used to determine the biological population.

[0089] The first short wave includes a specific frequency of thermal radiation short wave, and the target short wave data further includes a transmission direction of the first short wave, a short wave energy amplitude and the like.

[0090] In an optional embodiment, after the soil feature information is subjected to the first carbon sink matching processing to obtain the first carbon sink information, and the forest feature information is subjected to the second carbon sink matching processing to obtain the second carbon sink information, the method further includes:

[0091] In step S2045, audio data of a second sub-region is determined based on the remote sensing data, the target forest region includes the second sub-region, the target forest region is composed of a plurality of second sub-regions, and the second sub-region is obtained through GIS region division.

[0092] In step S2046, second biological information of the second sub-region is determined based on the audio data through a preset third model, and the second biological information includes biological group information.

[0093] In step S2047, fourth carbon sink information is determined by matching the biological form information with the fourth carbon sink.

[0094] In step S2048, target carbon sink information of the target forest region is determined based on the first carbon sink information, the second carbon sink information and the fourth carbon sink information.

[0095] In the embodiment, because the audio of different biological species in different states is different, the audio information can be captured to assist in judging the biological group situation in the target forest region, and the biological population situation can be more accurately judged.

[0096] The audio information includes audio frequency, audio amplitude, audio amplitude distribution, audio energy distribution and the like.

[0097] Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software and a necessary general hardware platform, and of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, an optical disk) and includes a plurality of instructions for causing a terminal device (which can be a mobile phone, a computer, a server or a network device) to execute the method described in each embodiment of the present application.

[0098] This embodiment also provides a remote sensing device for forest carbon sink detection based on neural networks. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0099] Figure 3 This is a structural block diagram of a forest carbon sink remote sensing detection device based on a neural network according to an embodiment of the present invention, as shown below. Figure 3 As shown, the device includes:

[0100] The remote sensing data acquisition module 31 is used to acquire remote sensing data of the target forest area, wherein the remote sensing data includes soil data and forest data;

[0101] Soil feature determination module 32 is used to determine soil feature information of the target forest area based on the soil data, wherein the soil data includes at least soil reflectance data;

[0102] The forest feature determination module 33 is used to determine the forest feature information of the target forest area based on the forest data, wherein the forest data includes at least forest morphology data;

[0103] The first matching module 34 is used to perform a first carbon sink matching process on the soil feature information to obtain first carbon sink information; and to perform a second carbon sink matching process on the forest feature information to obtain second carbon sink information.

[0104] The first carbon sink determination module 35 is used to determine the target carbon sink information of the target forest area based on the first carbon sink information and the second carbon sink information.

[0105] In an optional embodiment, the forest feature determination module 33 includes:

[0106] The first thermal unit is used to determine the first thermal data of the target forest area based on the remote sensing data;

[0107] The canopy feature determination unit is used to determine the canopy feature information of the target forest area based on the first heat data and the tree morphology data through a preset first model, wherein the tree feature information includes the canopy feature information.

[0108] In an optional embodiment, the apparatus further includes:

[0109] The shortwave determination module is used to determine the target shortwave data of a first sub-region based on the remote sensing data after performing a first carbon sink matching process on the soil feature information to obtain first carbon sink information and a second carbon sink matching process on the forest feature information to obtain second carbon sink information. The target forest region includes the first sub-region, which is composed of several first sub-regions. The first sub-regions are obtained by GIS region division. The target shortwave data includes the proportion of the first shortwave biothermal radiation energy wave in the first sub-region.

[0110] The biological information determination module is used to determine the first biological information of the first sub-region based on the target shortwave data and a preset second model, wherein the first biological information includes biological group information.

[0111] The second matching module is used to perform third carbon sink matching on the biological group information to determine the third carbon sink information.

[0112] The second carbon sink determination module is used to determine the target carbon sink information of the target forest area based on the first carbon sink information, the second carbon sink information, and the third carbon sink information.

[0113] In an optional embodiment, the device further includes,

[0114] An audio data acquisition module is used to determine audio data of a second sub-region based on the remote sensing data after performing a first carbon sink matching process on the soil feature information to obtain first carbon sink information and a second carbon sink matching process on the forest feature information to obtain second carbon sink information. The target forest region includes the second sub-region, and the target forest region is composed of several second sub-regions. The second sub-regions are obtained by GIS region division.

[0115] The second bio-information module is used to determine the second bio-information of the second sub-region based on the audio data using a preset third model, wherein the second bio-information includes biological group information;

[0116] The third matching module is used to perform a fourth carbon sink matching on the biological morphology information to determine the fourth carbon sink information.

[0117] The third carbon sink determination module is used to determine the target carbon sink information of the target forest area based on the first carbon sink information, the second carbon sink information, and the fourth carbon sink information.

[0118] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0119] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.

[0120] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0121] Embodiments of the present invention also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0122] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0123] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0124] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0125] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A neural network-based method for detecting forest carbon sink capacity by remote sensing, characterized in that, The method comprises the following steps: obtaining remote sensing data of a target forest area, wherein the remote sensing data comprises soil data and forest data; determining soil feature information of the target forest area based on the soil data, wherein the soil data at least comprises soil reflectance data, and the soil reflectance data comprises signal strength, signal frequency, signal distribution, signal energy distribution, and signal beam condition formed by absorption and reflection of the soil to remote sensing signals; and the soil feature information comprises organic matter content, soil texture, mineral composition, and water content; determining forest feature information of the target forest area based on the forest data, wherein the forest data at least comprises forest morphology data; performing first carbon sink matching processing on the soil feature information to obtain first carbon sink information, and performing second carbon sink matching processing on the forest feature information to obtain second carbon sink information; determining target carbon sink information of the target forest area based on the first carbon sink information and the second carbon sink information; wherein, after the first carbon sink matching processing on the soil feature information to obtain the first carbon sink information, and the second carbon sink matching processing on the forest feature information to obtain the second carbon sink information, the method further comprises: determining audio data of a second sub-area based on the remote sensing data, wherein the target forest area comprises the second sub-area, the target forest area is composed of a plurality of second sub-areas, and the second sub-area is obtained by GIS area division; the audio data comprises audio frequency, audio amplitude, audio amplitude distribution, and audio energy distribution; determining second biological information of the second sub-area based on the audio data through a preset third model, wherein the second biological information comprises biological group information; performing fourth carbon sink matching on the second biological information to determine fourth carbon sink information; and determining the target carbon sink information of the target forest area based on the first carbon sink information, the second carbon sink information, and the fourth carbon sink information. 2.The neural network-based forest carbon sink remote sensing detection method according to claim 1, characterized in that, The determining of the forest feature information of the target forest area based on the forest data comprises the following steps: determining first heat data of the target forest area based on the remote sensing data; determining forest canopy feature information of the target forest area through a preset first model according to the first heat data and the forest morphology data, wherein the forest feature information comprises the forest canopy feature information.

3. The method of claim 1, wherein, after the first carbon sink matching processing on the soil feature information to obtain the first carbon sink information, and the second carbon sink matching processing on the forest feature information to obtain the second carbon sink information, the method further comprises: determining target shortwave data of a first sub-area based on the remote sensing data, wherein the target forest area comprises the first sub-area, the target forest area is composed of a plurality of first sub-areas, the first sub-area is obtained by GIS area division, and the target shortwave data comprises first shortwave proportion data of biological heat radiation energy waves in the first sub-area; ​ According to the target shortwave data, first biological information of the first sub-region is determined through a preset second model, wherein the first biological information comprises biological group information; Third carbon sink amount matching is performed on the first biological information to determine third carbon sink amount information; Target carbon sink amount information of the target forest region is determined based on the first carbon sink amount information, the second carbon sink amount information and the third carbon sink amount information.

4. A neural network-based forest carbon sink remote sensing detection device, characterized in that, The device comprises a remote sensing data acquisition module, a soil feature determination module, a forest feature determination module, a first matching module and a first carbon sink amount determination module; The remote sensing data acquisition module is configured to acquire remote sensing data of a target forest region, wherein the remote sensing data comprises soil data and forest data; The soil feature determination module is configured to determine soil feature information of the target forest region based on the soil data, wherein the soil data at least comprises soil reflectivity data, and the soil reflectivity data comprises signal strength, signal frequency, signal distribution, signal energy distribution and signal beam condition formed by absorption and reflection of soil to remote sensing signals; and the soil feature information comprises organic matter content, soil texture, mineral composition and water content; The forest feature determination module is configured to determine forest feature information of the target forest region based on the forest data, wherein the forest data at least comprises forest morphology data; The first matching module is configured to perform first carbon sink amount matching processing on the soil feature information to obtain first carbon sink amount information, and perform second carbon sink amount matching processing on the forest feature information to obtain second carbon sink amount information; The first carbon sink amount determination module is configured to determine target carbon sink amount information of the target forest region based on the first carbon sink amount information and the second carbon sink amount information; The device further comprises, An audio data acquisition module is configured to determine audio data of a second sub-region based on the remote sensing data after the first carbon sink amount matching processing on the soil feature information to obtain first carbon sink amount information, and the second carbon sink amount matching processing on the forest feature information to obtain second carbon sink amount information, wherein the target forest region comprises the second sub-region, the target forest region is composed of a plurality of second sub-regions, and the second sub-region is obtained through GIS region division; and the audio data comprises sound wave frequency, sound wave amplitude, sound wave amplitude distribution and sound wave energy distribution; A second biological information module is configured to determine second biological information of the second sub-region based on the audio data through a preset third model, wherein the second biological information comprises biological group information; A third matching module is configured to perform fourth carbon sink amount matching on the second biological information to determine fourth carbon sink amount information; A third carbon sink amount determination module is configured to determine target carbon sink amount information of the target forest region based on the first carbon sink amount information, the second carbon sink amount information and the fourth carbon sink amount information. 5.The neural network-based forest carbon sink remote sensing detection device according to claim 4, characterized in that, The forest feature determination module comprises: A first heat unit is configured to determine first heat data of the target forest region based on the remote sensing data; The canopy feature determination unit is configured to determine, according to the first heat data and the forest form data, forest canopy feature information of the target forest region by using a preset first model, wherein the forest feature information comprises the forest canopy feature information. 6.The neural network-based forest carbon sink remote sensing detection device according to claim 4, characterized in that, The device further comprises: The shortwave determination module is configured to, after performing the first carbon sink amount matching processing on the soil feature information to obtain first carbon sink amount information and performing the second carbon sink amount matching processing on the forest feature information to obtain second carbon sink amount information, determine target shortwave data of a first sub-region based on the remote sensing data, wherein the target forest region comprises the first sub-region, the target forest region is composed of a plurality of first sub-regions, the first sub-region is obtained by GIS region division, and the target shortwave data comprises first shortwave proportion data of biological thermal radiation energy waves in the first sub-region. The biological information determination module is configured to determine first biological information of the first sub-region by using a preset second model according to the target shortwave data, wherein the first biological information comprises biological group information. The second matching module is configured to perform third carbon sink amount matching on the first biological information to determine third carbon sink amount information. The second carbon sink amount determination module is configured to determine target carbon sink amount information of the target forest region based on the first carbon sink amount information, the second carbon sink amount information, and the third carbon sink amount information.

7. A computer readable storage medium characterized in that, The computer readable storage medium stores a computer program, wherein the computer program is configured to execute the method in any one of claims 1 to 3 when running. 8.An electronic device comprising a memory and a processor, the electronic device comprising: The memory stores a computer program, and the processor is configured to execute the computer program to execute the method in any one of claims 1 to 3.

Images