Wild apple forest disease and insect pest early warning method and device based on satellite remote sensing and medium

Abstract

The invention discloses a wild apple forest disease and insect pest early warning method and device based on satellite remote sensing and a medium. The method comprises the following steps: according to a satellite remote sensing image corresponding to a wild apple forest in a growing period, determining an NDVI value and an IPVI value which are used for judging whether a target area of the wild apple forest is healthy or not; determining the health state of the target area according to the NDVI value and the IPVI value; under the condition that the health state is healthy, determining an NDVI value sequence, an IPVI value sequence and an LST value sequence used for judging whether diseases and pests occur in the target area or not according to the satellite remote sensing image; determining a comprehensive spectrum response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence; and according to the comprehensive spectrum response function, predicting probability information of occurrence of plant diseases and insect pests in the target area, and according to the probability information, carrying out early warning on the plant diseases and insect pests in the target area.

Description

Technical Field

[0001] This application relates to the field of satellite remote sensing technology, and particularly to a method, device and medium for early warning of wild apple forest pests and diseases based on satellite remote sensing. Background Art

[0002] Currently, the National Forestry and Grassland Administration only forecasts, predicts and evaluates nearly a hundred kinds of pests and diseases. Most of the pests and diseases that threaten forests are not discovered or are ignored. Pests and diseases have diversity and complexity, and simple and extensive epidemic prevention measures cannot fundamentally solve the problem.

[0003] The already published patent CN111602639A provides an intelligent control method for preventing and controlling pests and diseases in citrus orchards, including the following steps: S1: The acquisition module regularly acquires temperature data, humidity data, light intensity data and carbon dioxide concentration data in the citrus orchard as training data; S2: The acquisition module transmits the basic data into the training module through the communication module, and the training module marks the training data, and respectively marks the training data corresponding to the pest occurrence period and the training data without pest occurrence, and saves the training data in the training database; The intelligent recognition model is trained by collecting the training data through the acquisition module. The intelligent recognition model classifies and judges the real-time acquired basic data to predict whether there is a pest occurrence. Through the early warning module, a warning message is pushed to the management personnel. At the same time, the spraying system is started to spray the fruit forest in advance to prevent pests. Passive prevention and control are avoided.

[0004] The already published patent CN111507940A provides a method for identifying and alarming pests and diseases in citrus orchards based on image recognition, including the following steps: S1: Collect normal photos and photos of fruit trees suffering from pests and save them in the training database as a training data set; S2: The preprocessing module performs denoising and smoothing preprocessing on the pictures in the training data set to strengthen the features of the images in the data set; S3: The feature extraction module extracts the features of the photos in the data set to obtain a feature data set; S4: The data processing module trains the image recognition model, uses the feature data set as input data, and the image recognition model outputs the result of whether the fruit tree has pests. The image acquisition system is used to collect the images of fruit trees in the fruit forest, and the trained image recognition model is used to identify the images, eliminating the errors and interferences brought by manual experience. At the same time, the efficiency and accuracy are greatly improved.

[0005] Malus sieversii, also known as wild apple, is only distributed in the Ili River Valley and Tacheng area of Xinjiang. It plays an important role in maintaining the stability of the regional ecosystem, soil and water conservation, and biodiversity, and has formed excellent characteristics such as cold tolerance, drought tolerance, and disease resistance during the long-term evolution process. At present, the vast majority of wild apple forests are not included in the national nature reserves, the natural regeneration ability of the forest land is extremely low, most of them are over-mature forests and are suffering from pest and disease infestations. However, the early warning of wild apple forests still faces the following problems: (1)The main monitoring methods for forest pests and diseases include manual monitoring, equipment monitoring, and UAV monitoring, etc. However, they are all restricted by manpower, professional technical level, and financial resources, and can only monitor small areas. If the data after monitoring is not processed and analyzed by professionals, it can only stay at the original data stage and cannot meet the needs of pest and disease monitoring and control.

[0006] (2)The prevention and control of wild apple forest pests and diseases require continuous, long-term, and uninterrupted monitoring to truly achieve the prevention and control work. Relying on manpower for continuous, long-term, and uninterrupted monitoring has high costs, high requirements for professional technical levels, and high costs for post-maintenance of equipment monitoring, which seriously restricts the development of epidemic prevention work and the implementation of prevention and control work.

[0007] In view of the above technical problems existing in the prior art, no effective solution has been proposed yet. Summary of the Invention

[0008] Embodiments of the present disclosure provide a method, device, and medium for early warning of wild apple forest pests and diseases based on satellite remote sensing to at least solve the technical problems existing in the prior art.

[0009] According to one aspect of the embodiments of the present disclosure, a method for early warning of wild apple forest pests and diseases based on satellite remote sensing is provided, including: determining the NDVI value and IPVI value for determining whether the target area of the wild apple forest is healthy according to the satellite remote sensing image corresponding to the wild apple forest in the growth period; determining the health status of the target area according to the NDVI value and IPVI value; in the case where the health status is healthy, determining the NDVI value sequence, IPVI value sequence, and LST value sequence for determining whether pests and diseases occur in the target area according to the satellite remote sensing image; determining the comprehensive spectral response function of the NDVI value sequence and IPVI value sequence relative to the LST value sequence; and predicting the probability information of pests and diseases occurring in the target area according to the comprehensive spectral response function, and giving an early warning of the pests and diseases in the target area according to the probability information.

[0010] According to another aspect of the embodiments of the present disclosure, a storage medium is further provided. The storage medium includes a stored program, wherein the above-mentioned method is executed by a processor when the program runs.

[0011] According to another aspect of the embodiments of the present disclosure, there is also provided a pest and disease warning device for wild apple forests based on satellite remote sensing, including: a vegetation index determination module, configured to determine the NDVI value and the IPVI value for determining whether the target area of the wild apple forest is healthy according to the satellite remote sensing image corresponding to the wild apple forest in the growth period; a health status determination module, configured to determine the health status of the target area according to the NDVI value and the IPVI value; a numerical sequence determination module, configured to determine the NDVI value sequence, the IPVI value sequence and the LST value sequence for determining whether pests and diseases occur in the target area according to the satellite remote sensing image when the health status is healthy; a spectral response determination module, configured to determine the comprehensive spectral response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence; and a warning module, configured to predict the probability information of pests and diseases occurring in the target area according to the comprehensive spectral response function, and warn of the pests and diseases in the target area according to the probability information.

[0012] According to another aspect of the embodiments of the present disclosure, there is also provided a pest and disease warning device for wild apple forests based on satellite remote sensing, including: a processor; and a memory, connected to the processor, for providing instructions for the processor to perform the following processing steps: determining the NDVI value and the IPVI value for determining whether the target area of the wild apple forest is healthy according to the satellite remote sensing image corresponding to the wild apple forest in the growth period; determining the health status of the target area according to the NDVI value and the IPVI value; determining the NDVI value sequence, the IPVI value sequence and the LST value sequence for determining whether pests and diseases occur in the target area according to the satellite remote sensing image when the health status is healthy; determining the comprehensive spectral response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence; and predicting the probability information of pests and diseases occurring in the target area according to the comprehensive spectral response function, and warning of the pests and diseases in the target area according to the probability information.

[0013] In the embodiments of the present disclosure, a method is proposed for early warning of pests and diseases in the target area of wild apple forests using satellite remote sensing images, providing a new solution for the monitoring and early warning of forest pests. There are the following advantages in using remote sensing images for early warning: large-scale monitoring areas, quasi-real-time monitoring of the dynamic changes of pests and diseases, etc., providing data support for the continuous monitoring, prediction and early warning services of forest pests. The integration of the Internet and virtual reality technologies has driven the application of spatial information technology, big data and cloud computing technology, and artificial intelligence technology in forestry. There are no longer technical bottlenecks in the intelligent platform for forest pest monitoring, early warning and prevention based on satellite images. Thus, the technical problems proposed in the prior art are solved. In addition, according to this embodiment, not only the health status of the target area is determined based on the NDVI value and the IPVI value, but also when the target area is in a certain state, the probability information of pests and diseases occurring in the target area is predicted according to the comprehensive spectral response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence. Therefore, the target areas that may be affected by pests and diseases in the future can be identified in advance according to the intensity and speed of the NDVI value and the IPVI value in response to the change of the LST value, and thus the early warning of pests and diseases can be realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings described herein are used to provide a further understanding of the present disclosure and form a part of this application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation to the present disclosure. In the drawings: Figure 1 is a hardware structure block diagram of a computing device for implementing the method according to Embodiment 1 of the present disclosure; Figure 2 is a schematic diagram of a wild apple forest pest and disease early warning system based on satellite remote sensing according to Embodiment 1 of the present disclosure; Figure 3 is a flowchart of a wild apple forest pest and disease early warning method based on satellite remote sensing according to the first aspect of Embodiment 1 of the present disclosure; Figure 4 is a schematic diagram of a wild apple forest pest and disease early warning based on satellite remote sensing according to Embodiment 2 of the present disclosure; and Figure 5 is a schematic diagram of a wild apple forest pest and disease early warning based on satellite remote sensing according to Embodiment 3 of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0015] To enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present disclosure without creative efforts shall fall within the protection scope of the present disclosure.

[0016] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described herein can be implemented in an order different from those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0017] Embodiment 1 According to this embodiment, a method embodiment of a pest and disease warning method for wild apple forests based on satellite remote sensing is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0018] The method embodiment provided in this embodiment can be executed in a server or a similar computing device. Figure 1 A hardware structure block diagram of a computing device for implementing a pest and disease warning method for wild apple forests based on satellite remote sensing is shown. As Figure 1 shown, the computing device may include one or more processors (the processor may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory for storing data, a transmission device for communication functions, and an input / output interface. Among them, the memory, the transmission device, and the input / output interface are connected to the processor through a bus. In addition, it may further include: a display, a keyboard, and a cursor control device connected to the input / output interface. Those of ordinary skill in the art can understand that Figure 1 the structure shown is only schematic and does not limit the structure of the above-mentioned electronic device. For example, the computing device may further include more or fewer components than Figure 1 shown, or have a structure different from Figure 1The different configurations shown.

[0019] It should be noted that one or more of the above processors and / or other data processing circuits can generally be referred to herein as "data processing circuits". The data processing circuit can be embodied in whole or in part as software, hardware, firmware, or any combination thereof. In addition, the data processing circuit can be a single independent processing module, or be incorporated in whole or in part into any one of the other elements in the computing device. As involved in the embodiments of the present disclosure, the data processing circuit is a kind of processor control (such as the selection of a variable resistance terminal path connected to an interface).

[0020] The memory can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method for early warning of wild apple forest pests and diseases based on satellite remote sensing in the embodiments of the present disclosure. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizes the method for early warning of wild apple forest pests and diseases based on satellite remote sensing of the above application program. The memory can include high-speed random access memory, and can also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memories. In some instances, the memory can further include a memory remotely located relative to the processor, and these remote memories can be connected to the computing device through a network. Examples of the above network include but are not limited to the Internet, enterprise intranet, local area network, mobile communication network, and combinations thereof.

[0021] The transmission device is used to receive or send data via a network. Specific examples of the above network can include a wireless network provided by a communication provider of the computing device. In one instance, the transmission device includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station and thus communicate with the Internet. In one instance, the transmission device can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0022] The display can be, for example, a touch-screen liquid crystal display (LCD), which enables a user to interact with the user interface of the computing device.

[0023] It should be noted here that in some alternative embodiments, the above Figure 1 shown computing device can include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware elements and software elements. It should be pointed out that Figure 1 is only an example of a specific specific instance, and is intended to show the types of components that can exist in the above computing device.

[0024] Figure 2 is a schematic diagram of the wild apple forest pest and disease warning system based on satellite remote sensing according to this embodiment. Refer to Figure 2 As shown, the system includes: a satellite 10, a gateway station 20, and a wild apple forest pest and disease warning platform 30 (hereinafter referred to as the "warning platform" for short). Among them, the satellite 10 transmits the remote sensing image of the area where the wild apple forest is located to the gateway station 20 on the ground, and sends it to the warning platform 30 through the gateway station 20, so that the warning platform 30 can warn of the pests and diseases of the wild apple forest in this area according to the remote sensing image.

[0025] It should be noted that the warning platform 30 in the system can be applied to the above-mentioned hardware structure.

[0026] Under the above operating environment, according to the first aspect of this embodiment, a method for warning pests and diseases of wild apple forests based on satellite remote sensing is provided. This method is implemented by Figure 2 the warning platform 30 shown in Figure 3 shows the flow schematic diagram of this method. Refer to Figure 3 As shown, this method includes: S302: Determine the NDVI value and IPVI value for determining whether the wild apple forest is healthy according to the satellite remote sensing image corresponding to the wild apple forest in the growth period; S304: Determine the health status of the wild apple forest according to the NDVI value and IPVI value; S306: When the health status is healthy, determine the NDVI value sequence, IPVI value sequence, and LST value sequence for determining whether the wild apple forest has pests and diseases according to the satellite remote sensing image; S308: Determine the comprehensive spectral response function of the NDVI value sequence and IPVI value sequence relative to the LST value sequence; and S310: Predict the probability information of the occurrence of pests and diseases in the wild apple forest according to the comprehensive spectral response function, and warn of the pests and diseases of the wild apple forest according to the probability information.

[0027] Specifically, refer to Figure 2 As shown, the warning platform 30 can receive in real time through the gateway station 20 the satellite remote sensing image collected by the satellite 10 corresponding to the wild apple forest. Thus, during the growth period (April - September) of the wild apple forest, the warning platform 30 can obtain the satellite remote sensing image corresponding to the wild apple forest every predetermined period (every day). Thus, after the warning platform 30 obtains the satellite remote sensing image, it determines the NDVI value and IPVI value for determining whether the target area of the wild apple forest is healthy (S302).

[0028] Specifically, each pixel of the satellite remote sensing image corresponds to an area of the wild apple forest, so that the NDVI value and IPVI value corresponding to the target area can be determined according to the pixel data corresponding to the target area. This will not be elaborated here.

[0029] The NDVI value (Normalized Difference Vegetation Index) can be determined, for example, according to the following formula (1): (1) where NIR is the reflectance of the near-infrared band of the wild apple forest, and RED is the reflectance of the infrared band of the wild apple forest.

[0030] The IPVI value (Infrared Percentage Vegetation Index) can be determined, for example, according to the following formula (2): (2) Since the satellite remote sensing images obtained by the early warning platform 30 are an image sequence of satellite remote sensing images obtained at every predetermined period, the average value of the NDVI values calculated based on the pixels corresponding to the target area in each satellite remote sensing image can be obtained, and the average value of the IPVI values calculated based on the pixels corresponding to the target area in each satellite remote sensing image can be obtained, so as to determine the NDVI value and IPVI value for determining whether the target area is healthy.

[0031] Then, the early warning platform 30 determines the health status of the target area according to the NDVI value and IPVI value. Specifically, in this embodiment, the health status of the wild apple forest in the arid area is divided into four categories according to the NDVI value. Specifically, as shown in Table 1 below: Table 1: NDVI value range and health level setting

[0032] Category code 0 (bare land or building, non-plant): The NDVI value below 0 indicates that there is no plant cover on the ground surface.

[0033] Category code 1 (unhealthy): The NDVI value below 0.2 usually indicates that the vegetation cover is very sparse or there is almost no vegetation. For wild apple trees, this may mean being affected by extreme drought and having a poor health condition.

[0034] Category code 2 (medium health): The NDVI value between 0.2 and 0.4 indicates a medium vegetation cover degree, indicating that although the wild apple trees are facing drought stress, they still maintain a certain degree of growth activity. This interval may represent that the trees are adapting to the drought environment or the growth state during the drought period.

[0035] Category code 3 (Health): An NDVI value higher than 0.5 is usually associated with a healthy vegetation state, indicating that the wild apple trees have good vegetation cover and sufficient moisture and are in a healthy growth state.

[0036] Therefore, the early warning platform 30 can determine whether the target area of the wild apple forest is healthy based on the NDVI value. For example, when the category codes are 0 and 1, it can be determined that the target area is unhealthy; when the category codes are 2 and 3, it can be determined that the target area is healthy.

[0037] In addition, in this embodiment, the health status of the wild apple forest in the arid area can be divided into five categories according to the IPVI value. Specifically, as shown in Table 1 below: Table 2: IPVI value range and health level settings

[0038] Category code 0 indicates no plant cover on the ground surface (such as bare land or buildings); Category code 1 indicates sparse vegetation and may be severely affected by drought; Category code 2 indicates medium vegetation cover and plants are under certain drought stress; Category code 3 indicates good vegetation cover and plants are in a healthy state; and Category code 4 indicates excellent vegetation cover and plants are in a healthy state.

[0039] Therefore, the early warning platform 30 can determine whether the target area is healthy based on the IPVI value. For example, when the category codes are 0 and 1, it can be determined that the target area is unhealthy; when the category codes are 2-4, it can be determined that the target area is healthy.

[0040] Therefore, the early warning platform 30 can comprehensively consider the NDVI value and the IPVI value to determine the health status of the target area of the wild apple forest. For example, only when it is determined that the target area is healthy based on both the NDVI value and the IPVI value, it is determined that the target area is healthy; otherwise, it is determined that the target area is unhealthy.

[0041] Then, in the case of determining that the target area is healthy, further determine whether the target area has pests and diseases through the NDVI value sequence, IPVI value sequence, and LST value sequence corresponding to the remote sensing image sequence. Specifically, the early warning platform 30 can determine the NDVI value sequence NDVI0~NDVI according to the NDVI value corresponding to each remote sensing image of the remote sensing image sequence m and can also determine the IPVI value sequence IPVI0~IPVI according to the IPVI value corresponding to each remote sensing image of the remote sensing image sequence mThen, the early warning platform 30 can obtain the daily average temperature value corresponding to this time from the meteorological forecast platform according to the acquisition time corresponding to each remote sensing image, and use it as the LST value corresponding to this remote sensing image, so as to form the LST value sequence LST0~LST m And the NDVI value NDVI in the NDVI value sequence i , the IPVI value IPVI in the IPVI value sequence i And the LST value LST in the LST value sequence i Correspond one by one in time respectively, where i = 0~m (S306).

[0042] Then, according to the early warning platform 30, determine the NDVI value sequence NDVI0~NDVI m And the IPVI value sequence IPVI0~IPVI m Relative to the LST sequence LST0~LST m Of the comprehensive spectral response function H(f) (S308). Among them, the comprehensive spectral response function H(f) reflects the comprehensive response characteristics of the NDVI value and the IPVI value relative to the change of the LST value at different frequencies. Among them, the comprehensive spectral response function H(f) will be described in detail below.

[0043] Then, the early warning platform 30 predicts the probability information of pests and diseases occurring in the target area according to the determined comprehensive spectral response function, and issues an early warning for the pests and diseases in the target area according to the probability information (S310).

[0044] For example, when the probability information is greater than 50%, it can be determined that pests and diseases have occurred in the target area, so as to issue an early warning; otherwise, it is determined that no pests and diseases have occurred in the target area, and no early warning is required. The specific determination method of the probability information will be described in detail below.

[0045] As described in the background technology, the early warning for wild apple forests also faces the following problems: (1) The main monitoring methods for forest pests and diseases include manual monitoring, equipment monitoring, and UAV monitoring, etc. However, they are all restricted by manpower, professional technical level, and financial resources, and can only be monitored in small areas. If the monitored data is not processed and analyzed by professionals, it can only stay at the raw data stage and cannot meet the needs of pest and disease monitoring and control.

[0046] (2) The prevention and control of wild apple forest pests and diseases requires continuous, long-term, and uninterrupted monitoring to truly achieve the prevention and control work. Relying on manpower for continuous, long-term, and uninterrupted monitoring has high costs, high requirements for professional technical level, and high costs for post-maintenance of equipment monitoring, which severely restricts the development of epidemic prevention work and the progress of prevention and control work.

[0047] In view of this, the present application proposes to use satellite remote sensing images to conduct pest and disease early warning on the target area of wild apple forests, providing a new solution for the monitoring and early warning of forest pests. There are the following advantages in using remote sensing images for early warning: characteristics such as large-scale monitoring areas and quasi-real-time monitoring of the dynamic changes of pests and diseases provide data support for the continuous monitoring, prediction and early warning services of forest pests and diseases. The integration of Internet and virtual reality technologies drives the application of spatial information technology, big data and cloud computing technology, and artificial intelligence technology in forestry. There is no longer a technical bottleneck for the intelligent platform for forest pest monitoring, early warning and prevention and control based on satellite images. Thus, the above technical problems are solved.

[0048] In addition, according to this embodiment, not only the health status of the target area is determined based on the NDVI value and the IPVI value, but also when the target area is in a certain state, the probability information of pests and diseases occurring in the target area is predicted according to the comprehensive spectral response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence. Thus, the target areas that may have pests and diseases in the future can be identified in advance according to the intensity and speed of the NDVI value and the IPVI value responding to the change of the LST value, and early warning of pests and diseases can be realized.

[0049] Optionally, the operation of determining the health status of the target area of the wild apple forest according to the NDVI value and the IPVI value includes: determining the first health category corresponding to the NDVI value according to the NDVI value interval preset for different health categories; determining the second health category corresponding to the IPVI value according to the IPVI value interval preset for different health categories; and determining the health status of the target area according to the first health category and the second health category.

[0050] Specifically, as described above, the early warning platform 30 can match the NDVI value corresponding to the target area with each numerical interval shown in Table 1, so as to determine the corresponding health category, that is, the first health category (such as healthy or unhealthy). In addition, the early warning platform 30 can match the IPVI value corresponding to the target area with each numerical interval shown in Table 2, so as to determine the corresponding health category, that is, the second health category (such as healthy or unhealthy). Then the early warning platform 30 can determine whether the target area is healthy according to the first health category and the second health category. Details are not described herein again.

[0051] Optionally, the operation of determining the comprehensive spectral response function of the NDVI value sequence and the IPVI value sequence with respect to the LST value sequence includes: determining a first difference sequence corresponding to the NDVI value sequence, a second difference sequence corresponding to the IPVI value sequence, and a third difference sequence corresponding to the LST value sequence; determining a first spectral response function according to the first difference sequence and the third difference sequence, where the first spectral response function reflects the response characteristics of the change in the NDVI value corresponding to the target area with respect to the LST value at different frequencies; determining a second spectral response function according to the second difference sequence and the third difference sequence, where the second spectral response function reflects the response characteristics of the change in the IPVI value corresponding to the target area with respect to the LST value at different frequencies; and determining the comprehensive spectral response function according to the first spectral response function and the second spectral response function.

[0052] Specifically, the warning platform 30 determines the first difference sequence y1~y corresponding to the NDVI value sequence through the following formula m , the second difference sequence z1~z corresponding to the IPVI value sequence m and the third difference sequence x1~x corresponding to the LST value sequence m : x j =LST j -LST j-1 (3); y j =NDVI j -NDVI j-1 (4); z j= IPVI j -IPVI j-1 (5).

[0053] Among them, j = 1~m.

[0054] Then, the warning platform 30 determines the first spectral response function h1(f) according to the first difference sequence y1~y m and the third difference sequence x1~x m , where the first spectral response function h1(f) reflects the response characteristics of the change in the NDVI value corresponding to the target area with respect to the LST value at different frequencies.

[0055] Then, the warning platform 30 determines the second spectral response function h2(f) according to the second difference sequence z1~z m and the third difference sequence x1~x m , where the second spectral response function h2(f) reflects the response characteristics of the change in the IPVI value corresponding to the target area with respect to the LST value at different frequencies.

[0056] Then, the early warning platform 30 determines the comprehensive spectral response function H(f) according to the formula shown below: (6).

[0057] Where a1, a2 ≥ 0, and a1 + a2 = 1.

[0058] Thus, by calculating the difference sequence, the non - monotonicity of the seasonal trend can be eliminated, and thus the pests and diseases of wild apple forests can be predicted more accurately.

[0059] Optionally, the operation of determining the first spectral response function according to the first difference sequence and the third difference sequence includes: determining a first linear operator that maps the space of the LST value sequence to the space of the NDVI value sequence; constructing a first convolution equation according to the autocorrelation function of the third difference sequence, where the first convolution equation reflects the first cross - correlation function between the first difference sequence and the third difference sequence; and performing a Fourier transform on the first convolution equation using the first linear operator to determine the first spectral response function.

[0060] Specifically, the early warning platform 300 establishes an input - output relationship, regards the change of NDVI value as a linear response to the change of LST value, and obtains the first linear operator F1( ): (7).

[0061] Wherein, each corresponding numerical pair in the LST value sequence and the NDVI sequence value can be used as a training sample to determine the parameters b0 and b1 in the first linear operator F1( ).

[0062] Then, the early warning platform 300 constructs a first convolution equation according to the autocorrelation function of the third difference sequence: (8).

[0063] Where h1(τ) is the response function (weight function), which is used to describe the sensitivity and response delay of NDVI to the change of LST; is the autocorrelation function of the third difference sequence x; and is the cross - correlation function between the first difference sequence y and the third difference sequence x.

[0064] Then the early warning platform 30 performs a Fourier transform on the above - mentioned first convolution equation to obtain the first spectral response function H1(f): (9).

[0065] Where the first spectral response function H1(f) reflects the response characteristics of NDVI to the change of LST at different frequencies.

[0066] Optionally, the operation of determining the second spectral response function according to the second difference sequence and the third difference sequence includes: determining a second linear operator that maps the space of the LST value sequence to the space of the IPVI value sequence; constructing a second convolution equation according to the autocorrelation function of the third difference sequence, where the second convolution equation reflects the second cross-correlation function between the second difference sequence and the third difference sequence; and performing a Fourier transform on the second convolution equation using the second linear operator to determine the second spectral response function.

[0067] Specifically, the early warning platform 300 establishes an input-output relationship, regards the change of the IPVI value as a linear response to the change of the LST value, and obtains the second linear operator F2(): (10).

[0068] Among them, each corresponding numerical pair in the LST value sequence and the IPVI sequence value can be used as a training sample to determine the parameters c0 and c1 in the second linear operator F2().

[0069] Then, the early warning platform 300 constructs a second convolution equation according to the autocorrelation function of the third difference sequence: (11).

[0070] Where h2(τ) is the response function (weight function), which is used to describe the sensitivity and response delay of IPVI to the change of LST; is the autocorrelation function of the third difference sequence x; and is the cross-correlation function between the second difference sequence z and the third difference sequence x.

[0071] Then the early warning platform 30 performs a Fourier transform on the above second convolution equation to obtain the second spectral response function H2(f): (12).

[0072] Among them, the second spectral response function H2(f) reflects the response characteristics of IPVI to the change of LST at different frequencies.

[0073] Based on this, the early warning platform 30 determines the comprehensive spectral response function H(f) according to formula (6).

[0074] Optionally, the operation of predicting the probability information of pests and diseases occurring in the target area according to the comprehensive spectral response function includes: determining the first spectral power of the comprehensive spectral response function in a preset low-frequency interval and the second spectral power in a preset high-frequency interval; and determining the probability information according to the first spectral power and the second spectral power.

[0075] Specifically, according to this embodiment, a low-frequency range and a high-frequency range can be preset: Low-frequency range (LF): frequency f < 0.16 day -1 corresponding to the slow comprehensive response of NDVI or IPVI to the change in LST, reflecting the inertia of the system.

[0076] High-frequency range (HF): frequency f > 0.35 day -1 , corresponding to the rapid comprehensive response of NDVI or IPVI to the change in LST.

[0077] Then, after the warning platform 30 determines the comprehensive spectral response function H(f), it integrates this function over the low-frequency range to obtain the first spectral power LF: (13).

[0078] And the warning platform 30 integrates this function over the high-frequency range to obtain the second spectral power HF: (14).

[0079] The integral value quantitatively describes the intensity and speed of the comprehensive response of NDVI and IPVI to the change in LST.

[0080] For example, when pests attack the wild apple forest for a predetermined time threshold (e.g., 2 years), LF will increase significantly and HF will decrease. This is reflected in the fact that the response of the vegetation in the target area to temperature fluctuations becomes more lagged, which can be used as a warning indicator to identify in advance the areas where pests may occur in the future.

[0081] In order to obtain probability information, the warning platform 30 substitutes LF and HF into the following formula to obtain the probability information Q: (15) (16) Thus, the warning platform 30 can determine the probability information Q of pests occurring in the target area according to the first spectral power LF and the second spectral power HF.

[0082] Thus, when Q is greater than 50%, it is determined that there are pests in the target area, otherwise it is determined that there are no pests in the target area.

[0083] Thus, the warning platform 30 can give a warning about the pests in the target area according to the probability information Q.

[0084] Optionally, the method further includes statistically analyzing the pest and disease data of the wild apple forest. For example, the early warning platform 30 can statistically analyze the pest and disease data of various regions of the wild apple forest based on historical data and conduct curve graph analysis. For example, the early warning platform 30 can monitor the number of pest and disease occurrences in each region of the wild apple forest every year and perform statistics using common analysis tools (bar graphs, curve graphs, pie charts). In addition, data uploaded after field surveys can also be used to create a bar graph showing the relationship between the number of survey times and the amount of pest and disease occurrences; or, for the proportion of pest and disease occurrences in a region during field surveys and after prevention and control, a pie chart can be used to represent the proportion of pest and disease occurrences. The methods shown after the statistical analysis of these three different types of data complete the simple data analysis tasks in the monitoring module.

[0085] In addition, the early warning platform 30 can also perform the following operations: Detect change areas and conduct continuous, high-frequency, cyclic change monitoring of the forest during the 8-day period, monthly, and quarterly growth periods of the trees in the current year, and provide real-time geographical location information, change degree, and change area for prevention and control.

[0086] Carry out pest and disease prevention and control in key areas. The prevention and control combines on-the-ground actual surveys and remote sensing monitoring to determine the prevention and control plan. Based on the surveys and monitoring, a prevention and control plan can be provided through a client (not shown in the figure) that communicates with the early warning platform 30. According to the prevention and control requirements and objectives, the system can provide physical and chemical prevention and control methods. A remote expert consultation system is also implemented on the client platform. Experts can retrieve on-the-ground survey data and client analysis data to provide a more precise prevention and control plan and enable continuous prevention and control.

[0087] Intelligent early warning, predicting relevant information such as the affected area and degree based on a neural network model.

[0088] Task processing: The system performs continuous task processing. It detects the affected areas from remote sensing images, processes tasks for key areas, and enters the manual processing stage.

[0089] Task assignment: After manual task processing, it enters the on-the-ground field investigation process for the area. The investigation tasks (geographical information, investigation area, and investigation content) are assigned to the investigators. After on-the-ground calibration, prevention and control are carried out, and the effectiveness of the prevention and control is monitored, after which on-the-ground investigation can be carried out again.

[0090] Pest and disease investigation: After the computer client processes the task, manual task assignment is carried out. The investigators hold field work assistants to conduct on-the-ground surveys of the areas affected by pests and diseases, providing more precise on-the-ground disaster information for the monitoring information of pest and disease occurrences on the client and a more accurate and detailed plan for prevention and control.

[0091] The system will visually display data such as the occurrence degree of pests and diseases, the affected area, ground survey information, and control information over the years in a general statistical manner, such as bar charts, pie charts, and curves.

[0092] In addition, referring to Figure 1 As shown, according to the second aspect of this embodiment, a storage medium is provided. The storage medium includes a stored program, wherein the above-mentioned method is executed by a processor when the program runs.

[0093] Thus, according to this embodiment, a new solution for monitoring and warning of forest pests is proposed by using satellite remote sensing images to conduct pest and disease early warning on the target area of wild apple forests. There are the following advantages in using remote sensing images for early warning: large-scale monitoring area, quasi-real-time monitoring of the dynamic changes of pests and diseases, etc., which provide data support for the continuous monitoring, prediction, and early warning services of forest pests and diseases. The integration of the Internet and virtual reality technologies drives the application of spatial information technology, big data and cloud computing technology, and artificial intelligence technology in forestry. There are no longer technical bottlenecks in the intelligent platform for forest pest and disease monitoring, early warning, and prevention and control based on satellite images. Thus, the technical problems proposed in the prior art are solved. In addition, according to this embodiment, not only the health status of the target area is determined based on the NDVI value and the IPVI value, but also when the target area is in a certain state, the probability information of the occurrence of pests and diseases in the target area is predicted according to the comprehensive spectral response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence. Thus, the target areas that may have pests and diseases in the future can be identified in advance according to the intensity and speed of the NDVI value and the IPVI value in response to the change of the LST value, so as to realize the early warning of pests and diseases.

[0094] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0095] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0096] Embodiment 2 Figure 4 Fig. shows a wild apple forest pest and disease warning device 400 based on satellite remote sensing according to the present embodiment. The device 400 corresponds to the method described in the first aspect of Embodiment 1. Refer to Figure 4 As shown, the device 400 includes: a vegetation index determination module 410 for determining the NDVI value and IPVI value for determining whether the target area of the wild apple forest is healthy according to the satellite remote sensing image corresponding to the wild apple forest in the growth period; a health status determination module 420 for determining the health status of the target area according to the NDVI value and IPVI value; a numerical sequence determination module 430 for determining the NDVI value sequence, IPVI value sequence and LST value sequence for determining whether the target area has pests and diseases according to the satellite remote sensing image when the health status is healthy; a spectral response determination module 440 for determining the comprehensive spectral response function of the NDVI value sequence and IPVI value sequence relative to the LST value sequence; and a warning module 450 for predicting the occurrence of the target area according to the comprehensive spectral response function.

[0097] Optionally, the health status determination module 420 includes: a first health determination sub-module for determining the first health category corresponding to the NDVI value according to the pre-set NDVI value interval corresponding to different health categories; a second health determination sub-module for determining the second health category corresponding to the IPVI value according to the pre-set IPVI value interval corresponding to different health categories; and a third health determination sub-module for determining the health status of the target area according to the first health category and the second health category.

[0098] Optionally, the spectral response determination module 440 includes: a difference sub-module for determining a first difference sequence corresponding to the NDVI value sequence, a second difference sequence corresponding to the IPVI value sequence, and a third difference sequence corresponding to the LST value sequence; a first spectral response determination sub-module for determining a first spectral response function according to the first difference sequence and the third difference sequence, where the first spectral response function reflects the response characteristics of the change in the NDVI value corresponding to the target area relative to the LST value at different frequencies; a second spectral response determination sub-module for determining a second spectral response function according to the second difference sequence and the third difference sequence, where the second spectral response function reflects the response characteristics of the change in the IPVI value corresponding to the target area relative to the LST value at different frequencies; and a third spectral response determination sub-module for determining a comprehensive spectral response function according to the first spectral response function and the second spectral response function.

[0099] Optionally, the first spectral response determination sub-module includes: a first linear operator determination unit for determining a first linear operator that maps the space of the LST value sequence to the space of the NDVI value sequence; a first convolution equation construction unit for constructing a first convolution equation according to the autocorrelation function of the third difference sequence, where the first convolution equation reflects the first cross-correlation function between the first difference sequence and the third difference sequence; and a first spectral response determination unit for performing a Fourier transform on the first convolution equation using the first linear operator to determine the first spectral response function.

[0100] Optionally, the second spectral response determination sub-module includes: a second linear operator determination unit for determining a second linear operator that maps the space of the LST value sequence to the space of the IPVI value sequence; a second convolution equation construction unit for constructing a second convolution equation according to the autocorrelation function of the third difference sequence, where the second convolution equation reflects the second cross-correlation function between the second difference sequence and the third difference sequence; and a second spectral response determination unit for performing a Fourier transform on the second convolution equation using the second linear operator to determine the second spectral response function.

[0101] Optionally, the warning module 450 includes: a spectral power determination sub-module for determining a first spectral power of the comprehensive spectral response function in a preset low-frequency interval and a second spectral power in a preset high-frequency interval; and a probability determination sub-module for determining probability information according to the first spectral power and the second spectral power.

[0102] Optionally, the device includes a statistics module for statistically analyzing the pest and disease data of wild apple forests.

[0103] Therefore, according to this embodiment, a new solution is proposed for monitoring and early warning of forest pests and diseases by using satellite remote sensing images to conduct early warning on the target area of wild apple forests. There are the following advantages in using remote sensing images for early warning: characteristics such as large-scale monitoring area and quasi-real-time monitoring of the dynamic changes of pests and diseases provide data support for the continuous monitoring, prediction and early warning services of forest pests and diseases. The integration of Internet and virtual reality technologies drives the application of spatial information technology, big data and cloud computing technology, and artificial intelligence technology in forestry. There is no longer a technical bottleneck for the intelligent platform for forest pest monitoring, early warning and prevention and control based on satellite images. Thus, the technical problems raised in the prior art are solved. In addition, according to this embodiment, not only the health status of the target area is determined based on the NDVI value and IPVI value, but also when the target area is in a certain state, the probability information of pests and diseases occurring in the target area is predicted according to the comprehensive spectral response function of the NDVI value sequence and IPVI value sequence relative to the LST value sequence. Therefore, the target areas that may have pests and diseases in the future can be identified in advance according to the intensity and speed of the NDVI value and IPVI value responding to the change of the LST value, so as to realize the early warning of pests and diseases.

[0104] Embodiment 3 Figure 5 Fig. shows a wild apple forest pest and disease early warning device 500 based on satellite remote sensing according to this embodiment. The device 500 corresponds to the method described in the first aspect of Embodiment 1. Refer to Figure 5 As shown, the device 500 includes: a processor; and a memory connected to the processor for providing instructions for the processor to perform the following processing steps: determining the NDVI value and IPVI value for determining whether the target area of the wild apple forest is healthy according to the satellite remote sensing image corresponding to the wild apple forest in the growth period; determining the health status of the target area according to the NDVI value and IPVI value; when the health status is healthy, determining the NDVI value sequence, IPVI value sequence and LST value sequence for determining whether pests and diseases occur in the target area according to the satellite remote sensing image; determining the comprehensive spectral response function of the NDVI value sequence and IPVI value sequence relative to the LST value sequence; and predicting the probability information of pests and diseases occurring in the target area according to the comprehensive spectral response function, and warning against the pests and diseases in the target area according to the probability information.

[0105] Optionally, the operation of determining the health status of the target area of the wild apple forest according to the NDVI value and IPVI value includes: determining the first health category corresponding to the NDVI value according to the preset NDVI value interval corresponding to different health categories; determining the second health category corresponding to the IPVI value according to the preset IPVI value interval corresponding to different health categories; and determining the health status of the target area according to the first health category and the second health category.

[0106] Optionally, the operation of determining the comprehensive spectral response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence includes: determining a first difference sequence corresponding to the NDVI value sequence, a second difference sequence corresponding to the IPVI value sequence, and a third difference sequence corresponding to the LST value sequence; determining a first spectral response function according to the first difference sequence and the third difference sequence, where the first spectral response function reflects the response characteristics of the change of the NDVI value corresponding to the target area relative to the LST value at different frequencies; determining a second spectral response function according to the second difference sequence and the third difference sequence, where the second spectral response function reflects the response characteristics of the change of the IPVI value corresponding to the target area relative to the LST value at different frequencies; and determining the comprehensive spectral response function according to the first spectral response function and the second spectral response function.

[0107] Optionally, the operation of determining the first spectral response function according to the first difference sequence and the third difference sequence includes: determining a first linear operator that maps the space of the LST value sequence to the space of the NDVI value sequence; constructing a first convolution equation according to the autocorrelation function of the third difference sequence, where the first convolution equation reflects the first cross-correlation function between the first difference sequence and the third difference sequence; and performing a Fourier transform on the first convolution equation using the first linear operator to determine the first spectral response function.

[0108] Optionally, the operation of determining the second spectral response function according to the second difference sequence and the third difference sequence includes: determining a second linear operator that maps the space of the LST value sequence to the space of the IPVI value sequence; constructing a second convolution equation according to the autocorrelation function of the third difference sequence, where the second convolution equation reflects the second cross-correlation function between the second difference sequence and the third difference sequence; and performing a Fourier transform on the second convolution equation using the second linear operator to determine the second spectral response function.

[0109] Optionally, the operation of predicting the probability information of pests and diseases occurring in the target area according to the comprehensive spectral response function includes: determining a first spectral power of the comprehensive spectral response function in a preset low-frequency interval and a second spectral power in a preset high-frequency interval; and determining the probability information according to the first spectral power and the second spectral power.

[0110] Optionally, the memory is further configured to provide instructions for the processor to process the following processing steps: statistically analyzing the pest and disease data of the wild apple forest.

[0111] Therefore, according to this embodiment, a new solution for monitoring and early warning of forest pests and diseases is proposed by using satellite remote sensing images to conduct early warning on the target area of wild apple forests. There are the following advantages in using remote sensing images for early warning: characteristics such as large-scale monitoring area and quasi-real-time monitoring of the dynamic changes of pests and diseases provide data support for the continuous monitoring, prediction and early warning services of forest pests and diseases. The integration of Internet and virtual reality technologies drives the application of spatial information technology, big data and cloud computing technology, and artificial intelligence technology in forestry. There is no longer a technical bottleneck for the intelligent platform for forest pest monitoring, early warning and prevention and control based on satellite images. Thus, the technical problems proposed in the prior art are solved. In addition, according to this embodiment, not only the health status of the target area is determined based on the NDVI value and IPVI value, but also when the target area is in a certain state, the probability information of pests and diseases occurring in the target area is predicted according to the comprehensive spectral response function of the NDVI value sequence and IPVI value sequence relative to the LST value sequence. Therefore, the target areas that may have pests and diseases in the future can be identified in advance according to the intensity and speed of the change of the NDVI value and IPVI value in response to the LST value, and thus the early warning of pests and diseases can be realized.

[0112] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0113] In the above embodiments of the present invention, the descriptions of each embodiment have their own focuses. For the parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0114] In several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some interfaces. The indirect coupling or communication connection of units or modules can be in an electrical or other form.

[0115] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0116] In addition, in each embodiment of the present invention, each functional unit can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0117] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention. The foregoing storage medium includes: various media such as USB flash drives, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0118] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A satellite remote sensing-based early warning method for wild apple orchard pests and diseases, characterized in that: include: Determining, based on satellite remote sensing images corresponding to a wild apple forest in a growing period, an NDVI value and an IPVI value for determining whether a target area of ​​the wild apple forest is healthy; Determining the health status of the target area according to the NDVI value and the IPVI value; When the health status is healthy, determining, based on the satellite remote sensing image, a sequence of NDVI values, a sequence of IPVI values, and a sequence of LST values ​​for determining whether pests and diseases occur in the target area; Determining a comprehensive spectral response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence; and The probability information of the occurrence of pests and diseases in the target area is predicted according to the comprehensive spectrum response function, and an early warning of the pests and diseases in the target area is issued according to the probability information.

2. The method according to claim 1, characterized in that The operation of determining the health status of the target area of ​​the wild apple forest according to the NDVI value and the IPVI value includes: Determining a first health category corresponding to the NDVI value according to a preset NDVI value interval corresponding to different health categories; Determining a second health category corresponding to the IPVI value according to a preset IPVI value interval corresponding to different health categories; and A health status of the target area is determined based on the first health category and the second health category.

3. The method according to claim 1, characterized in that The operation of determining the integrated spectral response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence comprises: Determine a first difference sequence corresponding to the NDVI value sequence, a second difference sequence corresponding to the IPVI value sequence, and a third difference sequence corresponding to the LST value sequence; Determine a first spectral response function according to the first difference sequence and the third difference sequence, wherein the first spectral response function reflects the response characteristics of the change of the NDVI value corresponding to the target area relative to the LST value at different frequencies; Determining a second spectrum response function according to the second difference sequence and the third difference sequence, wherein the second spectrum response function reflects the response characteristics of the change of the IPVI value corresponding to the target area relative to the LST value at different frequencies; and The comprehensive spectrum response function is determined according to the first spectrum response function and the second spectrum response function.

4. The method according to claim 3, characterized in that: The operation of determining a first spectrum response function according to the first differential sequence and the third differential sequence includes: Determining a first linear operator that maps from the space of the LST value sequence to the space of the NDVI value sequence; constructing a first convolution equation according to the autocorrelation function of the third difference sequence, wherein the first convolution equation reflects a first cross-correlation function between the first difference sequence and the third difference sequence; and The first convolution equation is subjected to Fourier transformation using the first linear operator to determine the first spectrum response function.

5. The method according to claim 3, characterized in that: The operation of determining a second spectrum response function according to the second differential sequence and the third differential sequence includes: determining a second linear operator that maps from the space of the LST value sequences to the space of the IPVI value sequences; constructing a second convolution equation according to the autocorrelation function of the third difference sequence, wherein the second convolution equation reflects a second cross-correlation function between the second difference sequence and the third difference sequence; and The second convolution equation is subjected to Fourier transformation using the second linear operator to determine the second spectrum response function.

6. The method according to claim 1, characterized in that The operation of predicting the probability information of the occurrence of pests and diseases in the target area according to the comprehensive spectrum response function includes: Determining a first spectral power of the integrated spectrum response function in a preset low frequency interval and a second spectral power in a preset high frequency interval; and The probability information is determined according to the first spectral power and the second spectral power.

7. The method according to claim 1, characterized in that It also includes statistics on pests and diseases in the wild apple forest.

8. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is run, the processor executes the method according to any one of claims 1 to 7.

9. A satellite remote sensing-based early warning device for pests and diseases in wild apple orchards, characterized in that: include: A vegetation index determination module, for determining, based on a satellite remote sensing image corresponding to a wild apple forest in a growing period, an NDVI value and an IPVI value for determining whether a target area of ​​the wild apple forest is healthy; A health status determination module, used to determine the health status of the target area according to the NDVI value and the IPVI value; A numerical sequence determination module is used to determine, when the health status is healthy, a NDVI value sequence, an IPVI value sequence and a LST value sequence for determining whether pests and diseases occur in the target area according to the satellite remote sensing image; A spectrum response determination module, used to determine the comprehensive spectrum response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence; as well as The early warning module is used to predict the probability information of the occurrence of pests and diseases in the target area according to the comprehensive spectrum response function, and to issue an early warning for the pests and diseases in the target area according to the probability information.

10. A satellite remote sensing-based early warning device for pests and diseases in wild apple orchards, characterized in that: include: processor; as well as A memory, connected to the processor, configured to provide the processor with instructions for processing the following processing steps: Determining, based on satellite remote sensing images corresponding to a wild apple forest in a growing period, an NDVI value and an IPVI value for determining whether a target area of ​​the wild apple forest is healthy; Determining the health status of the target area according to the NDVI value and the IPVI value; When the health status is healthy, determining, based on the satellite remote sensing image, a sequence of NDVI values, a sequence of IPVI values, and a sequence of LST values ​​for determining whether pests and diseases occur in the target area; Determining a comprehensive spectral response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence; and The probability information of the occurrence of pests and diseases in the target area is predicted according to the comprehensive spectrum response function, and an early warning of the pests and diseases in the target area is issued according to the probability information.

Images