Satellite remote sensing-based early warning method, device and medium for wild apple orchard pests and diseases

Abstract

The present application discloses a method, device, and medium for warning pests and diseases in wild apple orchards based on satellite remote sensing. The method comprises: determining, based on satellite remote sensing images corresponding to wild apple orchards in their growing season, NDVI values ​​and IPVI values ​​for determining whether a target area of ​​the wild apple orchard is healthy; determining, based on the NDVI values ​​and IPVI values, the health status of the target area; if the health status is healthy, determining, based on the satellite remote sensing images, a sequence of NDVI values, IPVI values, and 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 predicting, based on the comprehensive spectral response function, probability information of pests and diseases occurring in the target area, and issuing a warning for pests and diseases in the target area based on the probability information.

Description

Technical Field

[0001] The present application relates to the field of satellite remote sensing technology, and in particular to a method, device and medium for warning of pests and diseases in wild apple orchards based on satellite remote sensing. Background Art

[0002] Currently, the National Forestry and Grassland Administration only conducts forecasts, predictions, and assessments for approximately 100 pests and diseases. The vast majority of these threats to forests remain undetected or ignored. Pests are diverse and complex, and simple, crude prevention measures cannot fundamentally address the problem.

[0003] Among them, the published patent CN111602639A provides an intelligent control method for pest control in citrus orchards, including the following steps: S1: The acquisition module regularly collects 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 to the training module through the communication module, and the training module labels the training data, marking them as training data corresponding to the pest occurrence period and training data when there is no pest, and saves the training data in a training database; the acquisition module collects the training data to train an intelligent recognition model, and the intelligent recognition model classifies and judges the basic data collected in real time, predicts whether there is pest occurrence, and pushes warning information to management personnel through the early warning module. At the same time, the spraying system is activated to spray the orchard in advance for prevention. This avoids passive control.

[0004] Patent CN111507940A, which has been published, provides a method for identifying and alerting pests and diseases in citrus orchards based on image recognition. The method includes the following steps: S1: Collecting photos of normal fruit trees and photos of infested trees and saving them to a training database as a training dataset; S2: A preprocessing module performs noise reduction and smoothing preprocessing on the images in the training dataset to enhance the features of the images in the dataset; S3: A feature extraction module extracts the features of the photos in the dataset to obtain a feature dataset; S4: A data processing module trains an image recognition model, using the feature dataset as input data. The image recognition model outputs a result indicating whether the fruit trees are infested with pests. An image acquisition system is used to capture images of fruit trees in the orchard. The trained image recognition model then recognizes the images, eliminating the errors and interference caused by manual experience while significantly improving efficiency and accuracy.

[0005] Xinjiang wild apple, also known as the Sewe apple, is found only in the Ili River Valley and Tacheng areas of Xinjiang. It plays a vital role in maintaining regional ecosystem stability, soil and water conservation, and biodiversity. Through long-term evolution, it has developed excellent traits such as cold tolerance, drought tolerance, and disease resistance. Currently, the vast majority of wild apple orchards are not included in national protected areas. Their natural regeneration capacity is extremely low, and most are overmature and susceptible to pests and diseases. However, early warning for wild apple orchards still faces the following challenges:

[0006] (1) The main monitoring methods for forest pests and diseases include manual monitoring, equipment monitoring, and drone monitoring. However, they are all subject to constraints in terms of manpower, professional technical level, and financial resources, and can only be used to monitor small areas. If the data after monitoring is not processed and analyzed by professionals, it can only remain at the raw data stage and cannot meet the needs of pest and disease monitoring and prevention.

[0007] (2) Wild apple orchard pest control requires continuous, long-term, and uninterrupted monitoring to truly achieve control. Relying on continuous, long-term, and uninterrupted monitoring by manpower is costly, requires high professional and technical skills, and has high maintenance costs for equipment monitoring, which seriously restricts the implementation of epidemic prevention and control work.

[0008] With respect to the above technical problems existing in the above-mentioned prior art, no effective solutions have been proposed so far. Summary of the Invention

[0009] The embodiments of the present disclosure provide a method, device, and medium for early warning of pests and diseases in wild apple orchards based on satellite remote sensing, so as to at least solve the technical problems existing in the prior art.

[0010] According to one aspect of an embodiment of the present disclosure, a wild apple orchard pest and disease early warning method based on satellite remote sensing is provided, comprising: determining NDVI values ​​and IPVI values ​​for determining whether a target area of ​​the wild apple orchard is healthy based on satellite remote sensing images corresponding to the wild apple orchard in its growth period; determining a health status of the target area based on the NDVI values ​​and IPVI values; when the health status is healthy, determining an NDVI value sequence, an IPVI value sequence, and an LST value sequence for determining whether pests and diseases occur in the target area based on the satellite remote sensing images; determining a comprehensive spectral response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence; and predicting probability information of the occurrence of pests and diseases in the target area based on the comprehensive spectral response function, and issuing an early warning for pests and diseases in the target area based on the probability information.

[0011] 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 method is executed by a processor when the program is running.

[0012] According to another aspect of the embodiments of the present disclosure, a wild apple forest pest and disease early warning device based on satellite remote sensing is also provided, including: a vegetation index determination module, used to determine the NDVI value and IPVI value for determining whether the target area of ​​the wild apple forest is healthy based on the satellite remote sensing image corresponding to the wild apple forest in the growth period; a health status determination module, used to determine the health status of the target area based on the NDVI value and the IPVI value; a numerical sequence determination module, used to determine the NDVI value sequence, IPVI value sequence and LST value sequence for determining whether pests and diseases occur in the target area based on the satellite remote sensing image when the health status is healthy; a spectral response determination module, used to determine the comprehensive spectral response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence; and an early warning module, used to predict the probability information of the occurrence of pests and diseases in the target area based on the comprehensive spectral response function, and to issue an early warning for the pests and diseases in the target area based on the probability information.

[0013] According to another aspect of the embodiments of the present disclosure, a wild apple forest pest and disease early warning device based on satellite remote sensing is also provided, including: a processor; and a memory connected to the processor, for providing the processor with instructions for processing the following processing steps: determining the NDVI value and IPVI value for determining whether the target area of ​​the wild apple forest is healthy based on the satellite remote sensing image corresponding to the wild apple forest in the growth period; determining the health status of the target area based on the NDVI value and the 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 based on the satellite remote sensing image; 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 the occurrence of pests and diseases in the target area based on the comprehensive spectral response function, and issuing an early warning for the pests and diseases in the target area based on the probability information.

[0014] In the disclosed embodiments, the use of satellite remote sensing imagery to provide early warning of pests and diseases in target areas of wild apple orchards is proposed, providing a new solution for monitoring and early warning of forest pests. Using remote sensing imagery for early warning offers several advantages: large-scale monitoring areas and near-real-time monitoring of dynamic changes in pests and diseases, providing data support for continuous monitoring, forecasting, and early warning services for forest pests and diseases. The integration of the internet and virtual reality technologies has driven the application of spatial information technology, big data and cloud computing, and artificial intelligence in forestry. This has eliminated technical bottlenecks in the development of intelligent platforms for monitoring, early warning, and control of forest pests and diseases based on satellite imagery. This solves the technical problems identified in the prior art. Furthermore, according to this embodiment, not only is the health status of the target area determined based on NDVI and IPVI values, but also, if the target area is healthy, the probability of pest and disease occurrence in the target area is predicted based on the integrated spectral response function of the NDVI and IPVI value sequences relative to the LST value sequence. This allows for the identification of target areas at risk of future pest and disease outbreaks based on the intensity and speed of changes in NDVI and IPVI values ​​in response to LST values, enabling early warning of pests and diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are used to provide a further understanding of the present disclosure and constitute 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 of the present disclosure. In the drawings:

[0016] Figure 1 is a hardware structure block diagram of a computing device for implementing the method according to embodiment 1 of the present disclosure;

[0017] Figure 2 2 is a schematic diagram of a wild apple orchard pest and disease early warning system based on satellite remote sensing according to Example 1 of the present disclosure;

[0018] Figure 3 1 is a flow chart of the satellite remote sensing-based early warning method for wild apple orchard pests and diseases according to the first aspect of Example 1 of the present disclosure;

[0019] Figure 4 is a schematic diagram of early warning of pests and diseases in wild apple orchards based on satellite remote sensing according to Example 2 of the present disclosure; and

[0020] Figure 5 This is a schematic diagram of the early warning of pests and diseases in wild apple orchards based on satellite remote sensing according to Example 3 of the present disclosure. DETAILED DESCRIPTION

[0021] In order 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 in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present disclosure.

[0022] 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 are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] Example 1

[0024] According to this embodiment, a method embodiment of a wild apple orchard pest and disease early warning method 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 a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] The method embodiment provided in this embodiment can be executed in a server or similar computing device. Figure 1 The hardware structure block diagram of a computing device for implementing a satellite remote sensing-based early warning method for wild apple orchard pests and diseases is shown. Figure 1 As shown, a computing device may include one or more processors (the processor may include, but is not limited to, a microprocessor (MCU) or a programmable logic device (FPGA) or other processing device), a memory for storing data, a transmission device for communication functions, and an input / output interface. The memory, transmission device, and input / output interface are connected to the processor via a bus. In addition, it may also include: a display, a keyboard, and a cursor control device connected to the input / output interface. Those skilled in the art will understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1More or fewer components than shown, or with Figure 1 Different configurations shown.

[0026] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry." The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be fully or partially integrated into any of the other components of the computing device. As discussed in the embodiments of the present disclosure, the data processing circuitry functions as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0027] 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 satellite remote sensing-based early warning method for wild apple orchard pests and diseases in the embodiment 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, the satellite remote sensing-based early warning method for wild apple orchard pests and diseases of the above-mentioned application program is realized. The memory may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely located relative to the processor, and these remote memories may be connected to the computing device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0028] The transmission device is used to receive or send data via a network. Specific examples of the aforementioned network may include a wireless network provided by a communications provider of the computing device. In one embodiment, the transmission device includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0029] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computing device.

[0030] It should be noted that, in some optional embodiments, the above Figure 1 The computing device shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. Figure 1This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computing device described above.

[0031] Figure 2 Schematic diagram of the wild apple orchard pest warning system based on satellite remote sensing according to this embodiment. Figure 2 As shown, the system includes: a satellite 10, a gateway station 20, and a wild apple orchard pest and disease early warning platform 30 (hereinafter referred to as the "early warning platform"). Satellite 10 transmits remote sensing images of the wild apple orchard area to gateway station 20 on the ground, which then transmits the images to early warning platform 30. Early warning platform 30 can then issue early warnings based on the remote sensing images regarding pests and diseases in the wild apple orchard area.

[0032] It should be noted that the early warning platform 30 in the system can be applied to the hardware structure described above.

[0033] Under the above operating environment, according to the first aspect of this embodiment, a method for warning of pests and diseases in wild apple orchards based on satellite remote sensing is provided. Figure 2 The early warning platform 30 shown in is implemented. Figure 3 A schematic diagram of the process is shown in FIG. Figure 3 As shown, the method includes:

[0034] S302: determining, based on a satellite remote sensing image corresponding to the wild apple forest in its growing period, an NDVI value and an IPVI value for determining whether the wild apple forest is healthy;

[0035] S304: Determine the health status of the wild apple forest based on the NDVI value and the IPVI value;

[0036] S306: When the health status is healthy, determining the NDVI value sequence, IPVI value sequence, and LST value sequence for determining whether the wild apple forest is affected by pests and diseases based on the satellite remote sensing image;

[0037] S308: Determine the comprehensive spectrum response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence; and

[0038] S310: Predicting probability information of occurrence of pests and diseases in the wild apple forest based on the comprehensive spectral response function, and issuing early warning of the pests and diseases in the wild apple forest based on the probability information.

[0039] Specifically, refer to Figure 2As shown, the early warning platform 30 can receive satellite remote sensing images corresponding to the wild apple orchard collected by satellite 10 in real time via the gateway station 20. Thus, during the wild apple orchard's growing season (April to September), the early warning platform 30 can obtain satellite remote sensing images corresponding to the wild apple orchard at predetermined intervals (daily). After obtaining the satellite remote sensing images, the early warning platform 30 determines the NDVI and IPVI values ​​used to determine the health of the target area of ​​the wild apple orchard (S302).

[0040] Specifically, each pixel of the satellite remote sensing image corresponds to an area of ​​the wild apple forest, so the NDVI value and IPVI value corresponding to the target area can be determined based on the pixel data corresponding to the target area.

[0041] The NDVI value (normalized difference vegetation index) can be determined, for example, according to the following formula (1):

[0042] (1)

[0043] NIR is the reflectance of the wild apple forest in the near-infrared band, and RED is the reflectance of the wild apple forest in the infrared band.

[0044] The IPVI value (Infrared Percent Vegetation Index) can be determined, for example, according to the formula (2) shown below:

[0045] (2)

[0046] Since the satellite remote sensing images acquired by the early warning platform 30 are image sequences of satellite remote sensing images acquired at predetermined intervals, the NDVI values ​​calculated based on the pixels corresponding to the target area in each satellite remote sensing image can be averaged, as can the IPVI values ​​calculated based on the pixels corresponding to the target area in each satellite remote sensing image can be averaged, thereby determining the NDVI value and IPVI value used to determine whether the target area is healthy.

[0047] The early warning platform 30 then determines the health status of the target area based on the NDVI and IPVI values. Specifically, in this embodiment, the health status of the wild apple orchard in the arid area is divided into four categories based on the NDVI values. The details are shown in Table 1 below:

[0048] Table 1: NDVI value range and health level settings

[0049]

[0050] Category code 0 (bare land or buildings, non-vegetative): NDVI values ​​below 0 indicate that the ground has no plant cover.

[0051] Category Code 1 (Unhealthy): NDVI values ​​below 0.2 typically indicate very sparse vegetation cover or almost no vegetation. For wild apple trees, this could mean they are experiencing extreme drought and are in poor health.

[0052] Category Code 2 (Moderate Health): NDVI values ​​between 0.2 and 0.4 indicate moderate vegetation cover, indicating that wild apple trees are experiencing some growth activity despite drought stress. This range may indicate that the trees are adapting to the drought or are experiencing growth during a drought.

[0053] Category code 3 (Healthy): NDVI values ​​above 0.5 are usually associated with healthy vegetation status, indicating that wild apple trees have good vegetation cover and sufficient water and are in a healthy growth state.

[0054] Thus, the early warning platform 30 can determine whether the target area of ​​the wild apple orchard is healthy based on the NDVI value. For example, when the category code is 0 or 1, the target area can be determined to be unhealthy; when the category code is 2 or 3, the target area can be determined to be healthy.

[0055] In addition, in this embodiment, the health status of wild apple orchards in arid areas can be divided into five categories based on the IPVI value. The details are shown in Table 1 below:

[0056] Table 2: IPVI value range and health level settings

[0057]

[0058] Category code 0 indicates that the surface has no plant cover (such as bare land or buildings);

[0059] Category code 1 indicates sparse vegetation and potential for severe drought impacts;

[0060] Category code 2 indicates moderate vegetation cover and plants are under some drought stress;

[0061] Category code 3 indicates good vegetation cover and healthy plants; and

[0062] Category code 4 indicates that the prepared cover is excellent and the plants are in a healthy condition.

[0063] Thus, the early warning platform 30 can determine whether the target area is healthy based on the IPVI value. For example, when the category code is 0 or 1, the target area can be determined to be unhealthy; when the category code is 2 to 4, the target area can be determined to be healthy.

[0064] Thus, the early warning platform 30 can combine the NDVI and IPVI values ​​to determine the health status of the target area of ​​the wild apple orchard. For example, the target area is determined to be healthy only if both the NDVI and IPVI values ​​determine that the target area is healthy. Otherwise, the target area is determined to be unhealthy.

[0065] Then, if the target area is determined to be healthy, the NDVI value sequence, IPVI value sequence and LST value sequence corresponding to the remote sensing image sequence are further used to determine whether the target area has pests and diseases. 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 in the remote sensing image sequence. m The IPVI value sequence IPVI0~IPVI can also be determined based on the IPVI value corresponding to each remote sensing image in the remote sensing image sequence. m Then, the early warning platform 30 can obtain the daily average temperature value corresponding to each remote sensing image from the weather forecast platform according to the acquisition time corresponding to the remote sensing image, as the LST value corresponding to the remote sensing image, thereby forming an LST value sequence LST0~LST m . And the NDVI value in the NDVI value series NDVI i 、IPVI value in IPVI value sequence i and the LST value LST in the LST value sequence i They correspond one to one in time, where i=0~m (S306).

[0066] Then, the NDVI value sequence NDVI0~NDVI is determined according to the early warning platform 30. m and IPVI value sequence IPVI0~IPVI m Relative to the LST sequence LST0~LST m The integrated spectrum response function H(f) is calculated (S308). The integrated spectrum response function H(f) reflects the integrated response characteristics of the NDVI and IPVI values ​​relative to the LST value at different frequencies. The integrated spectrum response function H(f) will be described in detail below.

[0067] Then, the early warning platform 30 predicts the probability information of the occurrence of pests and diseases in the target area according to the determined integrated spectrum response function, and issues an early warning for the pests and diseases in the target area according to the probability information ( S310 ).

[0068] For example, if the probability information is greater than 50%, it can be determined that pests and diseases have occurred in the target area, and an early warning can be issued. Otherwise, if it is determined that pests and diseases have not occurred in the target area, no early warning is required. The specific method for determining probability information will be explained in detail below.

[0069] As described in the background technology, early warning for wild apple orchards also faces the following problems:

[0070] (1) The main monitoring methods for forest pests and diseases include manual monitoring, equipment monitoring, and drone monitoring. However, they are all subject to constraints in terms of manpower, professional technical level, and financial resources, and can only be used to monitor small areas. If the data after monitoring is not processed and analyzed by professionals, it can only remain at the raw data stage and cannot meet the needs of pest and disease monitoring and prevention.

[0071] (2) Wild apple orchard pest control requires continuous, long-term, and uninterrupted monitoring to truly achieve control. Relying on continuous, long-term, and uninterrupted monitoring by manpower is costly, requires high professional and technical skills, and has high maintenance costs for equipment monitoring, which seriously restricts the implementation of epidemic prevention and control work.

[0072] In view of this, this application proposes the use of satellite remote sensing images to provide early warning of pests and diseases in target areas of wild apple orchards, providing a new solution for the monitoring and early warning of forest pests. The use of remote sensing images for early warning has the following advantages: large-scale monitoring areas and quasi-real-time monitoring of dynamic changes in pests and diseases, providing data support for continuous monitoring, forecasting and early warning services for forest pests and diseases. The integration of the Internet and virtual reality technology has driven the application of spatial information technology, big data and cloud computing technology, and artificial intelligence technology in forestry. The intelligent platform for monitoring, early warning and prevention of forest pests and diseases based on satellite images no longer has technical bottlenecks. This solves the above-mentioned technical problems.

[0073] In addition, according to this embodiment, not only is the health status of the target area determined based on the NDVI and IPVI values, but also, when the target area is in a healthy state, the probability information of the occurrence of pests and diseases in the target area is predicted based on the comprehensive spectral response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence. Thus, the target area where pests and diseases may occur in the future can be identified in advance based on the intensity and speed of the changes in the NDVI and IPVI values ​​in response to the LST values, thereby enabling early warning of pests and diseases.

[0074] Optionally, the operation of determining the health status of the target area of ​​the wild apple orchard based on the NDVI value and the IPVI value includes: determining a first health category corresponding to the NDVI value based on a pre-set NDVI value interval corresponding to different health categories; determining a second health category corresponding to the IPVI value based on a pre-set IPVI value interval corresponding to different health categories; and determining the health status of the target area based on the first health category and the second health category.

[0075] Specifically, referring to the above, the early warning platform 30 can match the NDVI value corresponding to the target area with the various numerical ranges shown in Table 1 to determine the corresponding health category, namely, the first health category (e.g., healthy or unhealthy). Furthermore, the early warning platform 30 can match the IPVI value corresponding to the target area with the various numerical ranges shown in Table 2 to determine the corresponding health category, namely, the second health category (e.g., healthy or unhealthy). The early warning platform 30 can then determine whether the target area is healthy based on the first and second health categories. This will not be further elaborated here.

[0076] 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 differential sequence corresponding to the NDVI value sequence, a second differential sequence corresponding to the IPVI value sequence, and a third differential sequence corresponding to the LST value sequence; determining a first spectral response function based on the first differential sequence and the third differential sequence, wherein the first spectral response function reflects the response characteristics of the changes in the NDVI values ​​corresponding to the target area relative to the LST values ​​at different frequencies; determining a second spectral response function based on the second differential sequence and the third differential sequence, wherein the second spectral response function reflects the response characteristics of the changes in the IPVI values ​​corresponding to the target area relative to the LST values ​​at different frequencies; and determining a comprehensive spectral response function based on the first spectral response function and the second spectral response function.

[0077] Specifically, the early warning platform 30 determines the first differential sequence y1~y corresponding to the NDVI value sequence by the following formula: m , the second differential sequence z1~z corresponding to the IPVI value sequence m And the third difference sequence x1~x corresponding to the LST value sequence m :

[0078] x j =LST j -LST j-1 (3);

[0079] y j =NDVI j -NDVI j-1 (4);

[0080] z j= IPVI j -IPVI j-1 (5).

[0081] Among them, j=1~m.

[0082] Then, the early warning platform 30 calculates the first differential sequence y1~y m and the third difference sequence x1~xm , determine the first spectrum response function h1(f), where the first spectrum response function h1(f) reflects the response characteristics of the change of the NDVI value corresponding to the target area relative to the LST value at different frequencies.

[0083] Then, the early warning platform 30 calculates the second differential sequence z1~z m and the third difference sequence x1~x m , determine the second spectrum response function h2(f), where the second spectrum response function h2(f) reflects the response characteristics of the change of the IPVI value corresponding to the target area relative to the LST value at different frequencies.

[0084] Then, the early warning platform 30 determines the comprehensive spectrum response function H(f) according to the formula shown below:

[0085] (6).

[0086] Where a1, a2≥0, and a1+a2=1.

[0087] Therefore, by calculating the difference series, the non-monotonicity of the seasonal trend can be eliminated, so that the pests and diseases in wild apple orchards can be predicted more accurately.

[0088] Optionally, the operation of determining the first spectral response function based on 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 based on the autocorrelation function of the third difference sequence, wherein the first convolution equation reflects the first cross-correlation function between the first difference sequence and the third difference sequence; and performing Fourier transform on the first convolution equation using the first linear operator to determine the first spectral response function.

[0089] Specifically, the early warning platform 300 establishes an input-output relationship, treating the change of NDVI value as a linear response to the change of LST value, and obtains the first linear operator F1( ):

[0090] (7).

[0091] The corresponding value pairs in the LST value sequence and the NDVI value sequence can be used as training samples to determine the parameters b0 and b1 in the first linear operator F1( ).

[0092] Then, the early warning platform 300 constructs a first convolution equation according to the autocorrelation function of the third difference sequence:

[0093] (8).

[0094] Where h1(τ) is the response function (weight function) used to describe the sensitivity and response delay of NDVI to LST changes;

[0095] is the autocorrelation function of the third difference sequence x; and

[0096] is the cross-correlation function of the first difference sequence y and the third difference sequence x.

[0097] Then the early warning platform 30 performs Fourier transform on the first convolution equation to obtain the first spectrum response function H1(f):

[0098] (9).

[0099] The first spectral response function H1(f) reflects the response characteristics of NDVI to LST changes at different frequencies.

[0100] Optionally, the operation of determining the second spectral response function based on the second difference sequence and the third difference sequence includes: determining a second linear operator that maps from the space of the LST value sequence to the space of the IPVI value sequence; constructing a second convolution equation based on the autocorrelation function of the third difference sequence, wherein the second convolution equation reflects the second cross-correlation function between the second difference sequence and the third difference sequence; and performing Fourier transform on the second convolution equation using the second linear operator to determine the second spectral response function.

[0101] Specifically, the early warning platform 300 establishes an input-output relationship, treating the change of the IPVI value as a linear response to the change of the LST value, and obtains the second linear operator F2( ):

[0102] (10).

[0103] The corresponding value pairs in the LST value sequence and the IPVI sequence value can be used as training samples to determine the parameters c0 and c1 in the second linear operator F2( ).

[0104] Then, the early warning platform 300 constructs a second convolution equation according to the autocorrelation function of the third difference sequence:

[0105] (11).

[0106] Where h2(τ) is the response function (weight function) used to describe the sensitivity and response delay of IPVI to LST changes;

[0107] is the autocorrelation function of the third difference sequence x; and

[0108] is the cross-correlation function of the second difference sequence z and the third difference sequence x.

[0109] Then the early warning platform 30 performs Fourier transform on the second convolution equation to obtain the second spectrum response function H2(f):

[0110] (12).

[0111] The second spectral response function H2(f) reflects the response characteristics of IPVI to LST changes at different frequencies.

[0112] On this basis, the early warning platform 30 determines the comprehensive spectrum response function H(f) according to formula (6).

[0113] Optionally, the operation of predicting the probability information of pests and diseases occurring in the target area based on the comprehensive spectral response function includes: determining the first spectral power of the comprehensive spectral response function in a preset low-frequency range and the second spectral power in a preset high-frequency range; and determining the probability information based on the first spectral power and the second spectral power.

[0114] Specifically, according to this embodiment, the low frequency interval and the high frequency interval may be preset:

[0115] Low frequency range (LF): frequency f<0.16 day -1 The slow integrated response of NDVI or IPVI to LST changes reflects the inertia of the system.

[0116] High frequency range (HF): frequency f > 0.35 day -1 , which corresponds to the rapid integrated response of NDVI or IPVI to LST changes.

[0117] Then, after determining the comprehensive spectrum response function H(f), the early warning platform 30 integrates the function in the low-frequency range to obtain the first spectrum power LF:

[0118] (13).

[0119] Furthermore, the early warning platform 30 integrates the function in the high frequency range to obtain the second spectrum power HF:

[0120] (14).

[0121] The integrated value quantitatively describes the intensity and speed of the combined response of NDVI and IPVI to LST changes.

[0122] For example, when pests and diseases have been attacking wild apple orchards for a predetermined time (e.g., two years), LF will increase significantly and HF will decrease. This means that the vegetation in this target area will respond more slowly to temperature fluctuations, which can be used as an early warning indicator to identify areas where pests may occur in the future.

[0123] In order to obtain probability information, the early warning platform 30 substitutes LF and HF into the following formula to obtain probability information Q:

[0124] (15)

[0125] (16)

[0126] Therefore, the early warning platform 30 can determine the probability information Q of the occurrence of pests and diseases in the target area based on the first spectrum power LF and the second spectrum power HF.

[0127] Therefore, when Q is greater than 50%, it is determined that pests and diseases exist in the target area; otherwise, it is determined that pests and diseases do not exist in the target area.

[0128] Therefore, the early warning platform 30 can issue early warnings for pests and diseases in the target area based on the probability information Q.

[0129] Optionally, the method also includes collecting statistics on the pest and disease data of the wild apple forest. For example, the early warning platform 30 can collect statistics on the pest and disease data of each area of ​​the wild apple forest based on historical data and perform curve chart analysis. For example, the early warning platform 30 can monitor the number of pests and diseases that occur each year in each area of ​​the wild apple forest, and use common analysis tools (bar charts, curve charts, pie charts) to perform statistics. In addition, the data uploaded after the field survey can be analyzed by forming a bar chart with the number of surveys and the amount of pests and diseases; or the proportion of regional occurrence of insects and diseases in the field survey and the proportion of insects and diseases after prevention and control can be used to represent the proportion of pests and diseases with a pie chart. The methods shown after three different data statistics complete the simple data analysis task in the monitoring module.

[0130] In addition, the early warning platform 30 can also perform the following operations:

[0131] Detect the changed areas and conduct continuous, high-frequency and cyclic monitoring of changes during the 8-day, monthly and quarterly growth period of the trees in the current year, and provide real-time geographical location information, degree of change and area of ​​change for prevention and control.

[0132] Pest and disease control is carried out in key areas, combining ground surveys with remote sensing monitoring to determine control plans. Based on these surveys and monitoring, control plans can be provided via a client (not shown) that communicates with the early warning platform 30. Depending on control requirements and objectives, the system can provide both physical and chemical control. The client platform also implements a remote expert consultation system, where experts draw on ground survey data and client-side analysis data to provide more precise control plans, enabling continuous control.

[0133] Intelligent early warning, based on neural network models, predicts relevant information such as the affected area and extent.

[0134] Task processing: The system performs continuous task processing, detects disaster-stricken areas based on remote sensing images, performs task processing on key areas, and enters manual processing.

[0135] Task allocation: After manual task processing, the regional ground field survey process begins, and survey tasks (geographic information, survey area, and survey content) are assigned to investigators. After field calibration, prevention and control are carried out. After monitoring the effect of prevention and control, ground surveys can be carried out again.

[0136] For pest and disease investigation, after the computer client processes the task, it will manually assign the task. The investigators will use the field work assistant to conduct on-site surveys of the areas where pests and diseases occur, providing the client with more accurate ground disaster information for monitoring the occurrence of pests and diseases, and providing more accurate and detailed solutions for prevention and control.

[0137] The system will visualize data such as the extent of pest and disease occurrence over the years, the affected area, ground survey information, and prevention and control information in a common statistical manner, such as bar charts, pie charts, and curves.

[0138] In addition, reference Figure 1 As shown, according to a second aspect of this embodiment, a storage medium is provided, wherein the storage medium includes a stored program, wherein when the program is run, a processor executes any one of the above methods.

[0139] Therefore, according to this embodiment, the use of satellite remote sensing imagery to provide early warning of pests and diseases in target areas of wild apple orchards is proposed, providing a new solution for monitoring and early warning of forest pests. Using remote sensing imagery for early warning offers the following advantages: large-scale monitoring areas and near-real-time monitoring of dynamic changes in pests and diseases, providing data support for continuous monitoring, forecasting, and early warning services for forest pests and diseases. The integration of the internet and virtual reality technologies has driven the application of spatial information technology, big data and cloud computing, and artificial intelligence technologies in forestry. This has eliminated technical bottlenecks in the development of intelligent platforms for monitoring, early warning, and prevention of forest pests and diseases based on satellite imagery. This solves the technical problems identified in the prior art. Furthermore, according to this embodiment, not only is the health status of the target area determined based on NDVI and IPVI values, but also, if the target area is healthy, the probability of pest and disease occurrence in the target area is predicted based on the integrated spectral response function of the NDVI and IPVI value sequences relative to the LST value sequence. This allows for the identification of target areas at risk of future pest and disease outbreaks based on the intensity and speed of changes in NDVI and IPVI values ​​in response to LST values, thus enabling early warning of pests and diseases.

[0140] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that the present invention is not limited by the order of the actions described, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0141] Through the description of the above embodiments, those skilled in the art will clearly understand that the methods according to the above embodiments can be implemented using software plus the necessary general-purpose hardware platform. Of course, hardware can also be used, but in many cases the former is a more preferred embodiment. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, or optical disk) and includes a number of instructions for enabling 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.

[0142] Example 2

[0143] Figure 4 FIG4 shows a satellite remote sensing-based early warning device 400 for wild apple orchard pests and diseases according to this embodiment, which corresponds to the method described in the first aspect of Example 1. Figure 4As shown, the device 400 includes: a vegetation index determination module 410, which is used to determine the NDVI value and IPVI value for determining whether the target area of ​​the wild apple forest is healthy based on the satellite remote sensing image corresponding to the wild apple forest in the growing period; a health status determination module 420, which is used to determine the health status of the target area based on the NDVI value and the IPVI value; a numerical sequence determination module 430, which is used to determine the NDVI value sequence, IPVI value sequence and LST value sequence for determining whether the target area has pests and diseases based on the satellite remote sensing image when the health status is healthy; a spectrum response determination module 440, which is used to determine the comprehensive spectrum response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence; and an early warning module 450, which is used to predict the occurrence of the target area based on the comprehensive spectrum response function.

[0144] Optionally, the health status determination module 420 includes: a first health determination submodule, used to determine a first health category corresponding to the NDVI value based on a pre-set NDVI value interval corresponding to different health categories; a second health determination submodule, used to determine a second health category corresponding to the IPVI value based on a pre-set IPVI value interval corresponding to different health categories; and a third health determination submodule, used to determine the health status of the target area based on the first health category and the second health category.

[0145] Optionally, the spectral response determination module 440 includes: a differential submodule, used to determine a first differential sequence corresponding to the NDVI value sequence, a second differential sequence corresponding to the IPVI value sequence, and a third differential sequence corresponding to the LST value sequence; a first spectral response determination submodule, used to determine a first spectral response function based on the first differential sequence and the third differential sequence, wherein the first spectral response function reflects the response characteristics of the NDVI value corresponding to the target area relative to the LST value at different frequencies; a second spectral response determination submodule, used to determine a second spectral response function based on the second differential sequence and the third differential sequence, wherein the second spectral response function reflects the response characteristics of the IPVI value corresponding to the target area relative to the LST value at different frequencies; and a third spectral response determination submodule, used to determine a comprehensive spectral response function based on the first spectral response function and the second spectral response function.

[0146] Optionally, the first spectral response determination submodule includes: a first linear operator determination unit, used to determine the first linear operator mapping from the space of the LST value sequence to the space of the NDVI value sequence; a first convolution equation construction unit, used to construct a first convolution equation based on the autocorrelation function of the third difference sequence, wherein 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, used to perform Fourier transform on the first convolution equation using the first linear operator to determine the first spectral response function.

[0147] Optionally, the second spectral response determination submodule includes: a second linear operator determination unit, used to determine a second linear operator that maps from the space of the LST value sequence to the space of the IPVI value sequence; a second convolution equation construction unit, used to construct a second convolution equation based on the autocorrelation function of the third difference sequence, wherein 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, used to perform Fourier transform on the second convolution equation using the second linear operator to determine the second spectral response function.

[0148] Optionally, the early warning module 450 includes: a spectral power determination submodule, used to determine the first spectral power of the comprehensive spectral response function in a preset low-frequency range and the second spectral power in a preset high-frequency range; and a probability determination submodule, used to determine probability information based on the first spectral power and the second spectral power.

[0149] Optionally, the device includes a statistical module for collecting statistics on pest and disease data of wild apple orchards.

[0150] Therefore, according to this embodiment, the use of satellite remote sensing imagery to provide early warning of pests and diseases in target areas of wild apple orchards is proposed, providing a new solution for monitoring and early warning of forest pests. Using remote sensing imagery for early warning offers the following advantages: large-scale monitoring areas and near-real-time monitoring of dynamic changes in pests and diseases, providing data support for continuous monitoring, forecasting, and early warning services for forest pests and diseases. The integration of the internet and virtual reality technologies has driven the application of spatial information technology, big data and cloud computing, and artificial intelligence technologies in forestry. This has eliminated technical bottlenecks in the development of intelligent platforms for monitoring, early warning, and prevention of forest pests and diseases based on satellite imagery. This solves the technical problems identified in the prior art. Furthermore, according to this embodiment, not only is the health status of the target area determined based on NDVI and IPVI values, but also, if the target area is healthy, the probability of pest and disease occurrence in the target area is predicted based on the integrated spectral response function of the NDVI and IPVI value sequences relative to the LST value sequence. This allows for the identification of target areas at risk of future pest and disease outbreaks based on the intensity and speed of changes in NDVI and IPVI values ​​in response to LST values, thus enabling early warning of pests and diseases.

[0151] Example 3

[0152] Figure 5 FIG2 shows a wild apple orchard pest warning device 500 based on satellite remote sensing according to this embodiment, which corresponds to the method according to the first aspect of embodiment 1. Figure 5 As shown, the device 500 includes: a processor; and a memory connected to the processor, for providing the processor with instructions for processing the following processing steps: determining the NDVI value and IPVI value for determining whether the target area of ​​the wild apple forest is healthy based on the satellite remote sensing image corresponding to the wild apple forest in the growing period; determining the health status of the target area based on the NDVI value and the IPVI value; when the health status is healthy, determining the NDVI value sequence, IPVI value sequence and LST value sequence for determining whether the target area has pests and diseases based on the satellite remote sensing image; 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 the occurrence of pests and diseases in the target area based on the comprehensive spectral response function, and issuing an early warning of the pests and diseases in the target area based on the probability information.

[0153] Optionally, the operation of determining the health status of the target area of ​​the wild apple orchard based on the NDVI value and the IPVI value includes: determining a first health category corresponding to the NDVI value based on a pre-set NDVI value interval corresponding to different health categories; determining a second health category corresponding to the IPVI value based on a pre-set IPVI value interval corresponding to different health categories; and determining the health status of the target area based on the first health category and the second health category.

[0154] 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 differential sequence corresponding to the NDVI value sequence, a second differential sequence corresponding to the IPVI value sequence, and a third differential sequence corresponding to the LST value sequence; determining a first spectral response function based on the first differential sequence and the third differential sequence, wherein the first spectral response function reflects the response characteristics of the changes in the NDVI values ​​corresponding to the target area relative to the LST values ​​at different frequencies; determining a second spectral response function based on the second differential sequence and the third differential sequence, wherein the second spectral response function reflects the response characteristics of the changes in the IPVI values ​​corresponding to the target area relative to the LST values ​​at different frequencies; and determining a comprehensive spectral response function based on the first spectral response function and the second spectral response function.

[0155] Optionally, the operation of determining the first spectral response function based on 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 based on the autocorrelation function of the third difference sequence, wherein the first convolution equation reflects the first cross-correlation function between the first difference sequence and the third difference sequence; and performing Fourier transform on the first convolution equation using the first linear operator to determine the first spectral response function.

[0156] Optionally, the operation of determining the second spectral response function based on the second difference sequence and the third difference sequence includes: determining a second linear operator that maps from the space of the LST value sequence to the space of the IPVI value sequence; constructing a second convolution equation based on the autocorrelation function of the third difference sequence, wherein the second convolution equation reflects the second cross-correlation function between the second difference sequence and the third difference sequence; and performing Fourier transform on the second convolution equation using the second linear operator to determine the second spectral response function.

[0157] Optionally, the operation of predicting the probability information of pests and diseases occurring in the target area based on the comprehensive spectral response function includes: determining the first spectral power of the comprehensive spectral response function in a preset low-frequency range and the second spectral power in a preset high-frequency range; and determining the probability information based on the first spectral power and the second spectral power.

[0158] Optionally, the memory is further used to provide the processor with instructions for processing the following processing steps: collecting statistics on pest and disease data of wild apple orchards.

[0159] Therefore, according to this embodiment, the use of satellite remote sensing imagery to provide early warning of pests and diseases in target areas of wild apple orchards is proposed, providing a new solution for monitoring and early warning of forest pests. Using remote sensing imagery for early warning offers the following advantages: large-scale monitoring areas and near-real-time monitoring of dynamic changes in pests and diseases, providing data support for continuous monitoring, forecasting, and early warning services for forest pests and diseases. The integration of the internet and virtual reality technologies has driven the application of spatial information technology, big data and cloud computing, and artificial intelligence technologies in forestry. This has eliminated technical bottlenecks in the development of intelligent platforms for monitoring, early warning, and prevention of forest pests and diseases based on satellite imagery. This solves the technical problems identified in the prior art. Furthermore, according to this embodiment, not only is the health status of the target area determined based on NDVI and IPVI values, but also, if the target area is healthy, the probability of pest and disease occurrence in the target area is predicted based on the integrated spectral response function of the NDVI and IPVI value sequences relative to the LST value sequence. This allows for the identification of target areas at risk of future pest and disease outbreaks based on the intensity and speed of changes in NDVI and IPVI values ​​in response to LST values, thus enabling early warning of pests and diseases.

[0160] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0161] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0162] In the 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 schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0163] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0164] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0165] If the integrated unit is implemented as 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, or the portion that contributes to the prior art, or all or part of the 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, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), a mobile hard drive, a magnetic disk, or an optical disk.

[0166] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection 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, NDVI values ​​and IPVI values ​​for determining whether a target area of ​​the wild apple forest is healthy; determining a 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; Determine the comprehensive spectrum response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence , the integrated spectrum response function It reflects the comprehensive response characteristics of NDVI and IPVI values ​​relative to LST value changes at different frequencies; as well as The probability information of the occurrence of pests and diseases in the target area is predicted according to the integrated spectrum response function, and an early warning of the pests and diseases in the target area is issued according to the probability information, and wherein, The operation of predicting the probability information of the occurrence of pests and diseases in the target area based on the integrated spectral response function includes: determining a first spectral power of the integrated spectral response function in a preset low-frequency interval and a second spectral power in a preset high-frequency interval, wherein the first spectral power is determined by integrating the integrated spectral response function in the low-frequency interval, and the second spectral power is determined by integrating the integrated spectral response function in the high-frequency interval; and determining the probability information based on the first spectral power and the second spectral power.

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 based on the NDVI value and the IPVI value includes: Determining a first health category corresponding to the NDVI value according to pre-set NDVI value intervals corresponding to different health categories; Determining a second health category corresponding to the IPVI value based on pre-set IPVI value intervals 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 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 based on 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 spectral response function based on the second difference sequence and the third difference sequence, wherein 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 The integrated spectral response function is determined according to the first spectral response function and the second spectral response function.

4. The method according to claim 3, characterized in that The operation of determining a first spectral 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 Performing Fourier transform on the first convolution equation using the first linear operator to determine the first spectral response function.

5. The method according to claim 3, characterized in that The operation of determining a second spectral 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 transform using the second linear operator to determine the second spectral response function.

6. The method according to claim 1, characterized in that It also includes statistics on pest and disease data of the wild apple forest.

7. 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 6.

8. A satellite remote sensing-based early warning device for wild apple orchard pests and diseases, characterized by: 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, configured to determine the health status of the target area based on the NDVI value and the IPVI value; a numerical sequence determination module for determining, 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 based on the satellite remote sensing image; A spectrum response determination module is used to determine the comprehensive spectrum response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence. , the integrated spectrum response function It reflects the comprehensive response characteristics of NDVI and IPVI values ​​relative to LST value changes at different frequencies; as well as An early warning module is used to predict the probability information of the occurrence of pests and diseases in the target area according to the integrated spectrum response function, and to issue an early warning for the pests and diseases in the target area according to the probability information, and wherein, The early warning module includes: a spectral power determination submodule, used to determine 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, wherein the first spectral power is determined by integrating the comprehensive spectral response function in the low-frequency interval, and the second spectral power is determined by integrating the comprehensive spectral response function in the high-frequency interval; and a probability determination submodule, used to determine probability information based on the first spectral power and the second spectral power.

9. A satellite remote sensing-based early warning device for wild apple orchard pests and diseases, characterized by: 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, NDVI values ​​and IPVI values ​​for determining whether a target area of ​​the wild apple forest is healthy; determining a 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; Determine the comprehensive spectrum response function of the NDVI value sequence and the IPVI value sequence relative to the LST value sequence , the integrated spectrum response function It reflects the comprehensive response characteristics of NDVI and IPVI values ​​relative to LST value changes at different frequencies; as well as The probability information of the occurrence of pests and diseases in the target area is predicted according to the integrated spectrum response function, and an early warning of the pests and diseases in the target area is issued according to the probability information, and wherein, The operation of predicting the probability information of the occurrence of pests and diseases in the target area based on the integrated spectral response function includes: determining a first spectral power of the integrated spectral response function in a preset low-frequency interval and a second spectral power in a preset high-frequency interval, wherein the first spectral power is determined by integrating the integrated spectral response function in the low-frequency interval, and the second spectral power is determined by integrating the integrated spectral response function in the high-frequency interval; and determining the probability information based on the first spectral power and the second spectral power.

Images