Early warning method, device and equipment for cereal fungal diseases and computer storage medium

Abstract

This application provides a method, apparatus, device, and computer storage medium for early warning of cereal fungal diseases. The method includes: constructing a fungal germination index model based on the coupling relationship between canopy temperature and leaf humidity of the cereal; inputting canopy temperature data and leaf humidity data of the cereal into the fungal germination index model to obtain the germination probability of fungal spores; and generating early warning information for cereal fungal diseases when the germination probability of fungal spores meets a threshold condition. This application, by constructing a fungal germination index model driven by the coupling of canopy temperature and leaf humidity, quantifies the biophysical parameters of cereals into fungal spore germination probabilities, and monitors the physiological responses of fungi in different environments in real time during the early warning process of cereal fungal diseases, thereby improving the accuracy of early warning for cereal fungal diseases.

Description

Technical Field

[0001] This application belongs to the field of Internet of Things technology, and in particular relates to a method, device, equipment and computer storage medium for early warning of fungal diseases of cereals. Background Technology

[0002] Cereal fungal diseases, such as wheat scab, corn ear rot, and rice blast, reduce cereal yield and quality, causing not only huge economic losses but also seriously jeopardizing food safety and grain security. Therefore, early warning of cereal fungal diseases is extremely important.

[0003] Among related technologies, control schemes for cereal fungal diseases differ significantly in their prediction mechanisms, data sources, and application objectives. Some schemes are limited to classifying the severity of disease after infection and cannot achieve proactive early warning. Some schemes are applicable to the middle and late stages of disease and cannot issue early warning instructions during the optimal prevention window (such as around the flowering period). Some schemes provide early warnings for cereal fungal diseases based on typical geographical environments or climates, thus having a limited scope of application. Some schemes, although integrating multi-source data and advancing the early warning time, rely heavily on statistical correlation in their models, resulting in low accuracy of the early warning results.

[0004] Application content

[0005] This application provides a method, apparatus, device, and computer storage medium for early warning of cereal fungal diseases, which can achieve high-precision early warning of cereal fungal diseases.

[0006] In a first aspect, embodiments of this application provide an early warning method for cereal fungal diseases, comprising: constructing a fungal germination index model based on the coupling relationship between the canopy temperature and leaf humidity of the cereal; inputting the canopy temperature data and leaf humidity data of the cereal into the fungal germination index model to obtain the germination probability of fungal spores; and generating early warning information for cereal fungal diseases when the germination probability of fungal spores meets a threshold condition.

[0007] In some embodiments of this application, the construction of a fungal germination index model based on the coupling relationship between canopy temperature and leaf humidity of the grain includes: constructing the fungal germination index model by exponential function coupling based on the canopy temperature, the leaf humidity, the optimal germination temperature of fungi, the critical humidity for fungal germination, and adjustment parameters.

[0008] In some embodiments of this application, before inputting the canopy temperature data and leaf humidity data of the grain into the fungal germination index model to obtain the fungal spore germination probability, the method further includes at least one of the following:

[0009] The canopy temperature data is calculated using a single-window algorithm based on atmospheric temperature, grain brightness temperature, and canopy emissivity.

[0010] The leaf surface humidity data is obtained by weighted fitting of atmospheric humidity and surface soil moisture content of grains.

[0011] In some embodiments of this application, generating early warning information for cereal fungal diseases when the germination probability of the fungal spores meets a threshold condition includes: generating indication information indicating that the fungal disease has the conditions for infection when the germination probability of the fungal spores is continuously higher than a preset threshold within a preset time period, wherein the early warning information includes indication information indicating that the fungal disease has the conditions for infection.

[0012] In some embodiments of this application, the method further includes: collecting grain remote sensing image data, meteorological data, and grain soil data, wherein the grain remote sensing image data includes hyperspectral data; obtaining canopy temperature data and leaf surface humidity data based on the remote sensing image data, the meteorological data, and the grain soil data, and obtaining chlorophyll content data by inversion from the hyperspectral data; constructing a latent development model of grain fungal diseases during the latent period based on the fungal germination index model and chlorophyll content; when the fungal spore germination probability meets a threshold condition, inputting the canopy temperature data, the leaf surface humidity data, and the chlorophyll content data into the latent development model to obtain the latent development potential value of the grain fungal disease during the latent period, wherein the early warning information includes the latent development potential value.

[0013] In some embodiments of this application, the method further includes: constructing a fungal spore diffusion function based on wind speed and rainfall, wherein constructing a latent development model of cereal fungal diseases during the latent period based on the fungal germination index model and the chlorophyll content includes: constructing the latent development model of the disease based on the fungal germination index model, the chlorophyll content, and the fungal spore diffusion function.

[0014] In some embodiments of this application, the meteorological data includes wind speed data and rainfall data;

[0015] When the germination probability of the fungal spores meets the threshold condition, the canopy temperature data, the leaf surface humidity data, and the chlorophyll content data are input into the disease latent development model to obtain the latent disease development potential value of the cereal fungal disease during the latent period, including:

[0016] When the germination probability of the fungal spores meets the threshold condition, the canopy temperature data, leaf humidity data, wind speed data, rainfall data, and chlorophyll content data are input into the disease latent development model to obtain the latent disease development potential value of the cereal fungal disease during the latent period.

[0017] In some embodiments of this application, the method further includes: constructing a health correction factor based on the chlorophyll content, wherein the step of constructing the disease latency development model based on the fungal germination index model, the chlorophyll content, and the fungal spore diffusion function includes: constructing the disease latency development model based on the fungal germination index model, the health correction factor, and the fungal spore diffusion function.

[0018] In some embodiments of this application, the step of obtaining chlorophyll content from the hyperspectral data includes: calculating the hyperspectral characteristic band ratio and the normalized vegetation index based on the hyperspectral data; and obtaining the chlorophyll content based on the hyperspectral characteristic band ratio and the normalized vegetation index.

[0019] In some embodiments of this application, the method further includes: calculating a predicted disease severity value by time integration based on the latent disease development potential value.

[0020] In some embodiments of this application, the method further includes: determining the risk level corresponding to the predicted disease severity value based on the correspondence between disease severity intervals and risk levels; and / or

[0021] According to the sampling cycle, the remote sensing image data, the meteorological data, and the grain soil data are automatically collected; the fungal spore germination probability and the predicted disease severity value are re-acquired; and a continuously updated disease risk curve and / or a disease risk distribution map represented by thermal color levels are generated; and / or

[0022] When the predicted severity of the disease meets the preset conditions, an early warning message for cereal fungal diseases and a high-risk location message are output.

[0023] In some embodiments of this application, after acquiring grain remote sensing image data, meteorological data, and grain soil data, the method further includes: performing temporal and spatial registration on the grain remote sensing image data, the meteorological data, and the grain soil data; performing pixel matching using bilinear interpolation; and performing data normalization processing to form a unified feature space.

[0024] Secondly, embodiments of this application provide an early warning device for cereal fungal diseases, comprising:

[0025] The fungal germination index model construction module is used to construct a fungal germination index model based on the coupling relationship between canopy temperature and leaf humidity of grains.

[0026] The fungal spore germination probability acquisition module is used to input the canopy temperature data and leaf humidity data of the grain into the fungal germination index model to obtain the fungal spore germination probability.

[0027] The early warning module is used to generate early warning information for cereal fungal diseases when the germination probability of the fungal spores meets a threshold condition.

[0028] Thirdly, embodiments of this application provide an early warning device for cereal fungal diseases, comprising: a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the early warning method for cereal fungal diseases described in any of the above-mentioned embodiments.

[0029] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the early warning method for cereal fungal diseases described in any of the above-mentioned embodiments.

[0030] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the early warning method for cereal fungal diseases described in any of the above embodiments.

[0031] In the early warning method, apparatus, device, and computer storage medium for cereal fungal diseases in this application embodiment, a fungal germination index model driven by the coupling of canopy temperature and leaf humidity is constructed to quantify the biophysical parameters of cereals into the probability of fungal spore germination. During the early warning process of cereal fungal diseases, the physiological response of fungi in different environments is monitored in real time, thereby improving the accuracy of early warning of cereal fungal diseases.

[0032] In some embodiments of this application, based on the temperature and humidity response patterns of cereal fungi, and according to the optimal germination temperature, critical germination humidity, and adjustment parameters of the fungi, the canopy temperature and leaf humidity are used as the core input variables of the fungal germination index model. The germination probability of fungal spores is calculated through exponential function coupling, enabling real-time monitoring of changes in fungal activity. Compared with correlation models in related technologies that rely solely on experience or historical data, the fungal germination index model can more accurately reflect the physiological responses of fungi under different climatic conditions, improving the scientific rigor, reliability, and accuracy of early warning systems for cereal fungal diseases.

[0033] In some embodiments of this application, by collecting grain remote sensing image data, meteorological data, and grain soil data, and constructing a disease latent development model using chlorophyll content, a fungal germination index model and a disease latent development model are calculated based on multi-source data to obtain more accurate fungal spore germination probability and latent disease development potential values, thereby improving the accuracy of early warning of grain fungal diseases. At the same time, the disease latent development model is dynamically corrected using a physiological correction algorithm based on chlorophyll content, thereby improving the accuracy of the model.

[0034] In some embodiments of this application, considering the promoting effect of climatic conditions on the spread of fungal spores, when constructing the disease latent development model, the fungal spore diffusion function generated based on the wind speed and the rainfall is used to simulate the climatic spread conditions. The spread rate of fungi during the latent period is reflected in the disease latent development model, thereby improving the accuracy of the disease latent development model and ultimately improving the accuracy of early warning of cereal fungal diseases.

[0035] In some embodiments of this application, considering the grain's own resistance to fungal diseases, when constructing the disease latency development model, a health correction factor calculated based on the chlorophyll content is used to reflect the change in the grain's disease resistance during the latency period. This improves the accuracy of the disease latency development model and ultimately enhances the accuracy of early warning of fungal diseases in grains. Attached Figure Description

[0036] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a flowchart illustrating an early warning method for cereal fungal diseases provided in an embodiment of this application;

[0038] Figure 2 This is a flowchart illustrating another method for early warning of cereal fungal diseases provided in this application embodiment;

[0039] Figure 3 This is a flowchart illustrating another method for early warning of cereal fungal diseases provided in this application embodiment;

[0040] Figure 4 This is a flowchart illustrating another method for early warning of cereal fungal diseases provided in this application embodiment;

[0041] Figure 5 This is a flowchart illustrating another method for early warning of cereal fungal diseases provided in this application embodiment;

[0042] Figure 6 This is a flowchart illustrating another method for early warning of cereal fungal diseases provided in this application embodiment;

[0043] Figure 7 This is a flowchart illustrating another method for early warning of cereal fungal diseases provided in this application embodiment;

[0044] Figure 8 This is a flowchart illustrating another method for early warning of cereal fungal diseases provided in this application embodiment;

[0045] Figure 9 This is a flowchart illustrating another method for early warning of cereal fungal diseases provided in this application embodiment;

[0046] Figure 10 This is a flowchart illustrating another method for early warning of cereal fungal diseases provided in this application embodiment;

[0047] Figure 11 This is a schematic flowchart of an early warning device for cereal fungal diseases provided in an embodiment of this application;

[0048] Figure 12 This is a schematic flowchart of another early warning device for cereal fungal diseases provided in an embodiment of this application;

[0049] Figure 13 This is a schematic flowchart of another early warning device for cereal fungal diseases provided in an embodiment of this application;

[0050] Figure 14 This is a schematic diagram of the structure of another early warning device for cereal fungal diseases provided in this application embodiment;

[0051] Figure 15 This is a schematic diagram of the structure of another early warning device for cereal fungal diseases provided in this application embodiment;

[0052] Figure 16 This is a schematic diagram of the structure of another early warning device for cereal fungal diseases provided in this application embodiment;

[0053] Figure 17 This is a schematic diagram of the structure of an early warning device for cereal fungal diseases provided in an embodiment of this application. Detailed Implementation

[0054] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0055] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0056] To address the problems in the prior art, embodiments of this application provide a method, apparatus, device, and computer storage medium for early warning of cereal fungal diseases.

[0057] The following section first introduces a method for early warning of cereal fungal diseases provided in the embodiments of this application.

[0058] Figure 1 This is a schematic flowchart illustrating an early warning method for cereal fungal diseases provided in an embodiment of this application. Figure 1 As shown, the method may include the following steps:

[0059] S100: Based on the coupling relationship between canopy temperature and leaf surface humidity of grains, a fungal germination index model was constructed.

[0060] S110: Input the canopy temperature data and leaf humidity data of the grain into the fungal germination index model to obtain the germination probability of fungal spores;

[0061] S120: When the germination probability of the fungal spores meets the threshold condition, an early warning message for cereal fungal diseases is generated.

[0062] The germination probability of fungal spores is used to characterize the likelihood of fungal spores germinating under the current environment.

[0063] In the early warning method for cereal fungal diseases provided in this application embodiment, the fungal germination index model driven by the coupling of the canopy temperature and the leaf surface humidity is constructed to quantify the biophysical parameters of cereals into the germination probability of fungal spores. In the early warning process of cereal fungal diseases, the physiological response of fungi in different environments is monitored in real time, thereby improving the accuracy of early warning of cereal fungal diseases.

[0064] Meanwhile, in the early warning method for cereal fungal diseases provided in this application embodiment, the fungal germination index model is constructed using cereal physiological and physical parameters such as canopy temperature and leaf humidity, which reduces the dependence on climate and geographical location, making the early warning method for cereal fungal diseases provided in this application embodiment widely applicable and highly practical.

[0065] In some embodiments of this application, such as Figure 2 As shown, S100: The construction of a fungal germination index model based on the coupling relationship between canopy temperature and leaf surface humidity of grains includes:

[0066] S1001: Based on the canopy temperature, leaf surface humidity, optimal germination temperature of fungi, critical humidity for fungal germination, and adjustment parameters, the fungal germination index model is constructed through exponential function coupling.

[0067] The early warning method for cereal fungal diseases provided in this application, based on the temperature and humidity response patterns of cereal fungi, uses the canopy temperature and leaf humidity as core input variables of the fungal germination index model, according to the optimal germination temperature, the critical humidity for fungal germination, and the adjustment parameters. The germination probability of fungal spores is calculated through exponential function coupling, achieving real-time monitoring of changes in fungal activity. Compared with correlation models in related technologies that rely solely on experience or historical data, the fungal germination index model more accurately reflects the physiological responses of fungi under different climatic conditions, improving the scientific rigor, reliability, and accuracy of early warning for cereal fungal diseases.

[0068] In some embodiments of this application, before inputting the canopy temperature data and leaf humidity data of the grain into the fungal germination index model to obtain the germination probability of fungal spores, the method further includes at least one of the following steps S130 and S140: S110.

[0069] like Figure 3 As shown, S130: The canopy temperature data is calculated using a single-window algorithm based on the atmospheric temperature, the brightness temperature of the grain, and the canopy emissivity.

[0070] In the early warning method for cereal fungal diseases provided in this application embodiment, the canopy temperature data is calculated using the single-window algorithm based on the atmospheric temperature, the light temperature, and the canopy emissivity, thereby improving the accuracy of the canopy temperature data. Furthermore, when the leaf surface humidity data is input into the fungal germination index model, the accuracy of the fungal spore germination probability is correspondingly improved, thus enhancing the accuracy of early warning for cereal fungal diseases.

[0071] like Figure 3 As shown, S140: Weighted fitting of atmospheric humidity and surface soil moisture content of grain to obtain the leaf surface humidity data.

[0072] In the early warning method for cereal fungal diseases provided in this application embodiment, leaf surface humidity data is obtained by weighted fitting of atmospheric humidity and surface soil moisture content. Since the empirical coefficients in the weighted fitting method can be obtained through training with historical data, the leaf surface humidity data has high accuracy. Furthermore, when the leaf surface humidity data is input into the fungal germination index model, the accuracy of the fungal spore germination probability is correspondingly improved, thereby enhancing the accuracy of early warning for cereal fungal diseases.

[0073] In some embodiments of this application, the parameters of the fungal germination index model include the canopy temperature data, the leaf surface humidity data, the optimal germination temperature of the fungus, the critical humidity for fungal germination, and the adjustment parameter, wherein the canopy temperature data and the leaf surface humidity data are input variables, and the optimal germination temperature of the fungus, the critical humidity for fungal germination, and the adjustment parameter are constants.

[0074] In some embodiments of this application, the adjustment parameters can be obtained by training with deep learning algorithms such as neural networks based on historical disease data. Different fungal germination index models can be constructed using different adjustment parameters.

[0075] In some embodiments of this application, the adjustment parameters can be adjusted periodically.

[0076] By periodically adjusting the aforementioned adjustment parameters, the fungal germination index model can be periodically calibrated to improve the accuracy of early warning for cereal fungal diseases.

[0077] In some embodiments of this application, such as Figure 4 As shown, S120: When the germination probability of the fungal spores meets the threshold condition, an early warning message for cereal fungal diseases is generated, including:

[0078] S1201: When the germination probability of the fungal spores is continuously higher than a preset threshold within a preset time period, an indication message indicating that the fungal disease has the conditions for infection is generated, wherein the warning message includes the indication message indicating that the fungal disease has the conditions for infection.

[0079] In the early warning method for cereal fungal diseases provided in this application embodiment, when the germination probability of fungal spores is continuously higher than a preset threshold within a preset time period, an indication message indicating that the fungal disease has the conditions for infection is generated in the early warning information. By monitoring the germination probability of fungal spores in real time, it is determined whether the fungus has the conditions for infection, so as to accurately predict the incubation period of the fungal disease and provide early warning for cereal fungal diseases.

[0080] For example, when the germination probability of the fungal spores is continuously higher than a preset threshold (e.g., 0.3) for 3 consecutive days, an indication message indicating that the fungal disease has the conditions for infection is generated, and the indication message indicates that the fungus has entered the incubation period.

[0081] In some embodiments of this application, such as Figure 5 As shown, the method further includes the following steps:

[0082] S150: Collect grain remote sensing image data, meteorological data, and grain soil data, wherein the grain remote sensing image data includes hyperspectral data;

[0083] S160: Obtain the canopy temperature data and leaf humidity data based on the remote sensing image data, the meteorological data, and the grain soil data, and retrieve the chlorophyll content data based on the hyperspectral data;

[0084] S170: Based on the fungal germination index model and chlorophyll content, construct a latent development model for cereal fungal diseases during the latent period;

[0085] S180: When the germination probability of the fungal spores meets the threshold condition, the canopy temperature data, the leaf humidity data, and the chlorophyll content data are input into the disease latent development model to obtain the latent disease development potential value of the cereal fungal disease during the latent period. The early warning information includes the latent disease development potential value.

[0086] The latent period disease development potential value is used to characterize the development potential of fungal diseases during the latent period.

[0087] During grain growth, when environmental conditions remain suitable for fungal germination, the grain enters a latent period for fungal diseases. At this time, although the fungus has invaded the grain, it has not yet shown obvious symptoms. The early warning method for grain fungal diseases provided in the above embodiments of this application predicts the latent period after conditions for fungal infection are met. By predicting the development potential of the fungus during the latent period and dynamically analyzing the development trend of the fungal disease, an early warning can be issued before the disease becomes apparent, thereby achieving proactive prediction.

[0088] In this prediction process, remote sensing image data, meteorological data, and grain soil data are collected. Using the fungal germination index model and the disease latency development model, more accurate fungal spore germination probabilities and latent disease development potential values ​​are obtained, improving the accuracy of early warning for grain fungal diseases. Simultaneously, the disease latency development model is constructed using chlorophyll content, and this physiological and physical parameter is dynamically used to correct the model, improving its accuracy and obtaining more precise prediction results.

[0089] In some embodiments of this application, the remote sensing image data may include the hyperspectral data and infrared image data. The hyperspectral data may include the reflectance of grains in a specific hyperspectral band, the surface reflectance in the near-infrared band, and the surface reflectance in the infrared band; the chlorophyll content can be calculated using this acquired data. The infrared image data may include the canopy emissivity, the brightness temperature, and the atmospheric temperature; the canopy temperature data can be calculated based on the canopy emissivity, the brightness temperature, and the atmospheric temperature.

[0090] In some embodiments of this application, the meteorological data includes atmospheric humidity, and the grain soil data may include the topsoil moisture content. The atmospheric humidity and the topsoil moisture content can be used to calculate the leaf surface humidity data.

[0091] In some embodiments of this application, such as Figure 6 As shown, the method further includes the following steps:

[0092] S190. Construct a fungal spore diffusion function based on wind speed and rainfall.

[0093] S170: The construction of a latent development model for cereal fungal diseases during the latent period based on the fungal germination index model and the chlorophyll content includes:

[0094] S1701: Construct the disease latent development model based on the fungal germination index model, the chlorophyll content, and the fungal spore diffusion function.

[0095] Considering the promoting effect of climatic conditions (such as wind speed and rainfall) on the spread of fungal spores, in the early warning method for cereal fungal diseases provided in this application embodiment, when constructing the disease latent development model, the fungal spore diffusion function generated based on the wind speed and rainfall is used to simulate climatic spread conditions. The spread rate of fungi during the latent period is reflected in the disease latent development model, thereby improving the accuracy of the disease latent development model and ultimately improving the accuracy of early warning for cereal fungal diseases.

[0096] In some embodiments of this application, such as Figure 7 As shown, the meteorological data includes wind speed data and rainfall data;

[0097] S180: When the germination probability of the fungal spores meets the threshold condition, the canopy temperature data, the leaf surface humidity data, and the chlorophyll content data are input into the disease latent development model to obtain the latent disease development potential value of the cereal fungal disease during the latent period, including:

[0098] S1801: When the germination probability of the fungal spores meets the threshold condition, the canopy temperature data, the leaf surface humidity data, the wind speed data, the rainfall data, and the chlorophyll content data are input into the disease latent development model to obtain the latent disease development potential value of the cereal fungal disease during the latent period.

[0099] The rainfall data and the wind speed data are used as input parameters for the fungal spore diffusion function.

[0100] In some embodiments of this application, such as Figure 8 As shown, the method further includes the following steps:

[0101] S200. Based on the chlorophyll content, construct a health correction factor.

[0102] Wherein, S1701: The construction of the disease latent development model based on the fungal germination index model, the chlorophyll content, and the fungal spore diffusion function includes:

[0103] S17011: Construct the disease latency and development model based on the fungal germination index model, the health correction factor, and the fungal spore diffusion function.

[0104] Considering the inherent resistance of grains to fungal diseases, in the early warning method for grain fungal diseases provided in this application embodiment, when constructing the disease latent development model, a health correction factor calculated based on the chlorophyll content is used to reflect the change in the grain's disease resistance during the latent period. This improves the accuracy of the disease latent development model and ultimately enhances the accuracy of early warning for grain fungal diseases.

[0105] In some embodiments of this application, such as Figure 9 As shown, step S160 includes the following steps:

[0106] S1601: Obtain the canopy temperature data and the leaf surface humidity data based on the remote sensing image data, the meteorological data, and the grain and soil data;

[0107] S1602: Calculate the hyperspectral characteristic band ratio and normalized vegetation index based on the hyperspectral data;

[0108] S1603: Obtain the chlorophyll content based on the hyperspectral characteristic band ratio and the normalized vegetation index.

[0109] In other words, the step S160, which involves retrieving the chlorophyll content from the hyperspectral data, includes steps S1602 and S1603.

[0110] In the early warning method for cereal fungal diseases provided in this application embodiment, the chlorophyll content is obtained based on the hyperspectral data, using the hyperspectral characteristic band ratio and the normalized vegetation index, thereby improving the calculation accuracy of the chlorophyll content.

[0111] In some embodiments of this application, such as Figure 10 As shown, the method further includes:

[0112] S210: Based on the latent disease development potential value, calculate the predicted disease severity value using time integration.

[0113] In the early warning method for cereal fungal diseases provided in this application embodiment, the latent disease development potential value is accumulated by using the time integral to calculate the disease severity prediction value. The disease severity prediction value is a continuous quantitative risk value of 0-1, which can be directly converted into a variable rate application (VRA) instruction, realizing full-process automation from disease prediction to precision application, and efficiently guiding the closed-loop prevention and control management of modern precision agriculture.

[0114] In some embodiments of this application, such as Figure 10 As shown, the method further includes:

[0115] S220: Based on the correspondence between disease severity ranges and risk levels, determine the risk level corresponding to the predicted disease severity value; and / or automatically collect the remote sensing image data, the meteorological data, and the grain soil data according to the sampling cycle, re-acquire the fungal spore germination probability and the predicted disease severity value, and generate a rolling updated disease risk curve and / or a disease risk distribution map represented by thermal color levels; and / or when the predicted disease severity value meets preset conditions, output grain fungal disease early warning prompts and high-risk area prompts.

[0116] In the early warning method for cereal fungal diseases provided in this application embodiment, the risk level corresponding to the predicted disease severity value is determined based on the correspondence between the disease severity range and the risk level. This risk level prediction result is concise and clear, and can be directly used for prevention and control decisions. For example, the risk level range includes a low-risk range, a medium-risk range, and a high-risk range. For instance, spraying can be automatically triggered when a medium-to-high risk level is reached.

[0117] The cereal fungal disease early warning method provided in this application establishes a dynamic early warning mechanism based on time series and spatial distribution by generating the disease risk curve and / or the disease risk distribution map, and / or outputting the cereal fungal disease early warning prompt and the high-risk area prompt information. This enables real-time updates and multi-dimensional display of disease risk, providing agricultural management departments with continuous, visualized, and traceable dynamic monitoring and decision support for disease risk.

[0118] In some embodiments of this application, such as Figure 10 As shown, S130: After acquiring grain remote sensing image data, meteorological data, and grain soil data, the method further includes:

[0119] S250: Perform temporal and spatial registration on the grain remote sensing image data, the meteorological data, and the grain soil data, and use bilinear interpolation for pixel matching;

[0120] S260: Perform data normalization processing to form a unified feature space.

[0121] The early warning method for cereal fungal diseases provided in this application improves the efficiency and accuracy of model calculation by performing time and space registration, pixel matching and normalization processing on multi-source data.

[0122] The method provided in this application can be applied to the early warning of cereal fungal diseases such as wheat scab, corn ear rot, and rice blast.

[0123] The following uses wheat scab as an example to explain the early warning method for cereal fungal diseases provided in this application. In the following embodiments, the early warning method for wheat scab uses remote sensing image data (including hyperspectral data and thermal infrared data), meteorological data, and soil data as core inputs to construct a multi-dimensional information fusion system. By continuously collecting hyperspectral data, thermal infrared data, and micro-weather station data during the key growth period of wheat, a comprehensive perception of the physiological state and environmental conditions of wheat is achieved.

[0124] The wheat scab early warning method provided in this application constructs a mathematical model driven by the mechanism of wheat scab, using parameters such as remote sensing image data, environmental data, and crop physiological data as dynamic input variables to establish a fungal germination index model and a disease latency and development model. This enables causal prediction of the wheat scab process from occurrence to spread, improving the scientific rigor and interpretability of the model. Furthermore, this application also introduces a growth correction and time-series accumulation mechanism, dynamically correcting the prediction results based on wheat chlorophyll content, wind speed, and rainfall. This allows for continuous quantitative assessment of disease severity, enabling dynamic early warning 5 to 7 days before the outbreak of wheat scab.

[0125] The wheat scab early warning method provided in this application includes the following steps:

[0126] S1: Multi-source data acquisition and fusion

[0127] In the occurrence and development of wheat scab, multiple factors, including meteorological, soil, and crop physiological states, play a combined role. To ensure comprehensive and accurate input data for the prediction models (fungal germination index model and disease latency development model), key parameters such as temperature, humidity, rainfall, and vegetation reflectance are continuously collected from multiple sources, including UAV remote sensing, meteorological sensors, and soil moisture monitoring equipment. Multi-source data collection avoids poor model prediction results due to missing data in certain categories. Simultaneously, temporal and spatial registration of the data aligns the multi-source data at the same time and location, providing high-quality input for subsequent model calculations. Multi-source data fusion not only improves the spatiotemporal continuity of the model but also lays a solid foundation for subsequent calculations of fungal spore germination probability and disease latency development models.

[0128] 1. Data collection period and data collection frequency

[0129] From the wheat jointing stage to the grain-filling stage (data collection period), UAV remote sensing imagery, meteorological data, and soil environmental data are collected daily or every two days (data collection frequency). The grain-filling stage of wheat is also a high-incidence period for Fusarium head blight.

[0130] 2. Data Sources and Types

[0131] (1) Hyperspectral data: Obtain reflectance in the 400-1000 nm band for inversion of chlorophyll content ( );

[0132] (2) Thermal infrared imagery: used to calculate canopy temperature ( ), Reflects crop transpiration and heat stress status;

[0133] (3) Micro-weather station data: including air temperature ( ), relative humidity ( ), rainfall ( ) and wind speed ( );

[0134] (4) Soil moisture sensor data: provides the surface soil moisture content ( ), used to calculate leaf surface humidity ;

[0135] (5) Historical disease data: Relevant data used for parameter regression fitting, boundary constraints, or confidence calibration, including: time data (past year / date / accumulated temperature / critical growth period), used to reconstruct the time window of disease infection; spatial data (field ID / latitude and longitude); disease data (manually surveyed disease level (0–5, or incidence rate %), disease area, severity level), which can be used as real label training and calibration adjustment parameters. ; disseminating environmental data, including wind speed, rainfall, and leaf surface humidity for the corresponding period. Measured or model values; disease growth rate factor (mean number of days of incubation period, Candidate curve interval).

[0136] 3. Data fusion and standardization

[0137] (1) Perform temporal and spatial registration on multi-source data and use bilinear interpolation for pixel matching;

[0138] (2) Normalize all input variables to form a unified feature space. .

[0139]

[0140] S2: Wheat Physiological Parameter Inversion and Calculation

[0141] Transforming spectral information in remote sensing images that is difficult to interpret directly into physiological indicators that reflect the health status of wheat, such as retrieving chlorophyll content through hyperspectral characteristic bands ( This can intuitively reflect the growth vitality and disease resistance of crops; canopy temperature can be retrieved through thermal infrared imaging. This can help determine the plant's transpiration and heat stress levels; simultaneously, by combining meteorological and soil data, leaf surface humidity can be calculated. These variables reflect the environmental suitability for pathogen attachment and germination. Since these variables directly influence the disease occurrence process, they are key biologically driven parameters in subsequent prediction models. Through this step, the embodiments of this application realize the transformation of wheat scab identification from "spectral signals" to "physiological characteristics."

[0142] 1. Leaf surface humidity estimation

[0143] Leaf surface humidity was obtained by weighted fitting of atmospheric humidity and soil moisture. :

[0144]

[0145] in, ∈[0,1]: Normalized relative humidity;

[0146] ∈[0,1]: Normalized surface soil moisture content (e.g., 0-30 cm);

[0147] , , This is an empirical coefficient. ≥0, ≥0, ≈1, This is a microenvironment drift correction term used to eliminate sensor noise and local water vapor retention errors in the canopy. Its absolute value satisfies | |≤0.005.

[0148] Preferably, The value range is 0.001–0.003. For example... = 0.002, to ensure the stability of the leaf surface humidity time series fitting and the ability to suppress calibration noise.

[0149] , , Empirical coefficients can be determined by observing field dew or by infrared thermography.

[0150] 2. Chlorophyll content inversion

[0151] A chlorophyll content inversion model was established based on the ratio of hyperspectral characteristic bands.

[0152]

[0153] in, , High spectral reflectance; The normalized vegetation index is calculated based on near-infrared surface reflectance and infrared surface reflectance. , , These are the empirical coefficients of the spectral-chlorophyll inversion model. This serves as a baseline offset to compensate for differences between different sensors and background radiation references. Quantitative red edge ratio / The intensity of the response to changes in chlorophyll content determines the dominant transition slope; Used for compensation The effects of canopy structure (coverage, leaf area index (LAI)) on the coupling of reflection and chlorophyll are reflected.

[0154] , , The determination was made by training linear or regularized regression methods using synchronous hyperspectral data from the field and measured chlorophyll samples.

[0155] 3. Canopy temperature inversion

[0156] This scheme is based on brightness temperature observed by a thermal infrared sensor. Emissivity relative to the canopy Linear compensation is applied to the emissivity loss, and a 710 nm reflectivity is used. Complete the empirical normalization scaling correction to inversely calculate the crop canopy physical temperature:

[0157]

[0158] in, This refers to the atmospheric temperature (actual air temperature). It is one of the parameters in the set of biophysical parameters for disease prediction.

[0159] S3: Calculation of fungal spore germination probability

[0160] Whether fungi can germinate on the crop surface is a key factor determining the occurrence of Fusarium head blight. By utilizing the coupling relationship between canopy temperature and leaf surface humidity, a Generating Speed ​​Index (GSI) model was established to calculate the probability of fungal spore germination under current conditions. This model quantifies complex environmental influences into a continuous numerical value, enabling real-time monitoring of changes in fungal activity. Compared to traditional correlation models that rely solely on experience or historical data, the GSI model more accurately reflects the physiological responses of fungi under different climatic conditions, improving the scientific validity and reliability of early warning systems.

[0161] Based on the temperature and humidity response patterns of fungal growth, the disease development during the latent period of wheat scab is predicted, and the probability of fungal spore germination under current environmental conditions is calculated.

[0162]

[0163] in, This is the optimal germination temperature for Fusarium head blight pathogens. This is the critical humidity for fungal germination. , To adjust the parameters; The germination probability of fungal spores (ranging from 0 to 1) represents the germination risk of fungal spores on that day.

[0164] S4: Disease incubation period development prediction

[0165] When environmental conditions remain suitable for fungal germination, wheat will enter a latent disease stage. At this time, although the fungus has invaded, it has not yet shown obvious symptoms. This step is used to predict the development potential of fungal diseases during the latent period, using the fungal spore diffusion function (FSD). ) and health-correcting factors ( This involves simulating changes in climate propagation conditions and crop disease resistance. In this way, the spread rate and development trend of fungal diseases during their latent period can be dynamically analyzed, enabling early warnings before the fungal diseases become apparent, thus achieving "proactive prediction."

[0166] 1. Triggering conditions:

[0167] when Three consecutive days above the threshold (For example, 0.3) indicates that the fungus has the conditions for infection, and the incubation period prediction begins. The latent period disease development potential value is:

[0168]

[0169] in, is the fungal spore diffusion function, representing the promoting effect of wind speed and rainfall on spore dispersal.

[0170]

[0171] in, Indicates wind speed. Indicates rainfall amount, This represents the sensitivity coefficient to the effect of wind speed on the airborne propagation of fungal spores. This represents the sensitivity coefficient to the effect of rainfall on the splashing or washout propagation of fungal spores. and As a regression constant used after model calibration, it can be determined by fitting field or historical propagation speed data.

[0172] The health correction factor indicates that when chlorophyll content decreases, the plant's disease resistance decreases.

[0173]

[0174] in, The optimal chlorophyll content for wheat, The nonlinear intensity constant is the response of crop health decline to the deviation of chlorophyll content from the optimal value, which is used to control the sensitivity and curvature morphology of the decline in health factors. The model remains fixed after calibration and can be determined by regression fitting of field chlorophyll and disease resistance data.

[0175]

[0176] This represents the incubation period, reflecting the pattern that the incubation period shortens as the temperature rises.

[0177]

[0178] in, For air temperature, This represents the optimal temperature constant for the disease. This is a nonlinear adjustment constant for the temperature response in the latency shortening model, used to control the air temperature. Optimal temperature for disease Sensitivity and curvature to the shortening of latency when deviating. It remains fixed after calibration and can be determined by regression fitting of field temperature and disease incubation period observation data.

[0179] Step S5: Dynamic identification of disease severity

[0180] This step quantifies the risk during the incubation period into a readily understandable severity value for the disease. Through the analysis of By accumulating data over time and performing dynamic calculations, the system integrates early fungal germination risks with latent development trends to form a continuous risk indicator. Using this mechanism, the system... The system automatically classifies risk levels based on numerical values, allowing predictions to be directly used for prevention and control decisions. For example, it can automatically trigger spraying or key monitoring instructions when the risk level reaches medium or high.

[0181] The severity of wheat scab increases cumulatively over time. The predicted severity can be represented by a disease severity prediction value, which is as follows:

[0182]

[0183] Based on the calculated predicted severity of the disease, risk levels can be dynamically classified, as follows:

[0184]

[0185] Step S6: Time-series update and dynamic early warning

[0186] This application establishes a dynamic early warning mechanism based on time series and spatial distribution, enabling real-time updates and multi-dimensional display of disease risk. The system automatically collects UAV remote sensing and ground sensor data on a daily basis, analyzing fungal germination index... and disease severity prediction value A recalculation is performed to generate a rolling, updated seven-day disease risk curve, reflecting the disease development trend for the coming week. Spatially, the predicted disease severity values ​​are mapped to field grids to generate a spatialized risk distribution map, which is then visually displayed as a heatmap using color gradients to represent disease hotspots. When the risk level exceeds the medium-risk threshold of 0.4 for two consecutive days, the system automatically triggers a Fusarium head blight risk warning, outputting warning prompts and high-risk area information. Ultimately, the system comprehensively outputs a disease risk curve (time dimension), a disease risk heat map (spatial dimension), and a warning report document (including risk level, probability of occurrence, and key monitoring areas), providing agricultural management departments with continuous, visualized, and traceable dynamic monitoring and decision support for disease risks.

[0187] Based on the same inventive concept, this application also provides an early warning device for cereal fungal diseases. Figure 11 This is a schematic diagram of the structure of an early warning device for cereal fungal diseases provided in an embodiment of this application. Figure 11 As shown, the device 100 includes a fungal germination index model construction module 101, a fungal spore germination probability acquisition module 102, and an early warning module 103. The fungal germination index model construction module 101 is used to construct a fungal germination index model based on the coupling relationship between the canopy temperature and leaf humidity of the grain. The fungal spore germination probability acquisition module 102 is used to input the canopy temperature data and leaf humidity data of the grain into the fungal germination index model to obtain the fungal spore germination probability. The early warning module 103 is used to generate early warning information for fungal diseases of the grain when the fungal spore germination probability meets a threshold condition.

[0188] The germination probability of fungal spores is used to characterize the likelihood of fungal spores germinating under the current environment.

[0189] The early warning device for cereal fungal diseases provided in this application embodiment quantifies the biophysical parameters of cereals into the germination probability of fungal spores by constructing a fungal germination index model driven by the coupling of canopy temperature and leaf surface humidity. During the early warning process of cereal fungal diseases, the device monitors the physiological response of fungi in different environments in real time, thereby improving the accuracy of early warning of cereal fungal diseases.

[0190] Meanwhile, the early warning device for cereal fungal diseases provided in this application uses the canopy temperature and leaf humidity, which are cereal physiological and physical parameters, to construct the fungal germination index model. This reduces the dependence on climate and geographical location, making the early warning device for cereal fungal diseases provided in this application widely applicable and highly practical.

[0191] In some embodiments of this application, the fungal germination index model construction module 101 is used to construct the fungal germination index model by exponential function coupling based on the canopy temperature, the leaf surface humidity, the optimal germination temperature of fungi, the critical humidity for fungal germination, and adjustment parameters.

[0192] The early warning device for cereal fungal diseases provided in this application embodiment is based on the temperature and humidity response patterns of cereal fungi. According to the optimal germination temperature of the fungus, the critical humidity for fungal germination, and the adjustment parameters, the canopy temperature and leaf humidity are used as core input variables of the fungal germination index model. The germination probability of fungal spores is calculated through exponential function coupling, achieving real-time monitoring of changes in fungal activity. Compared with correlation models in related technologies that rely solely on experience or historical data, the fungal germination index model can more accurately reflect the physiological responses of fungi under different climatic conditions, improving the scientific rigor, reliability, and accuracy of early warning for cereal fungal diseases.

[0193] In some embodiments of this application, such as Figure 12 As shown, the device also includes a canopy temperature data calculation module 104, which is used to calculate the canopy temperature data based on atmospheric temperature, grain brightness temperature and canopy emissivity before the fungal spore germination probability acquisition module 102 inputs the canopy temperature data and leaf humidity data of the grain into the fungal germination index model to obtain the fungal spore germination probability.

[0194] In some embodiments of this application, such as Figure 12 As shown, the device also includes a leaf surface humidity data acquisition module 105, which is used to obtain the leaf surface humidity data by weighted fitting of atmospheric humidity and surface soil moisture content of the grain before the canopy temperature data and leaf surface humidity data of the grain are input into the fungal germination index model by the fungal germination probability acquisition module 102.

[0195] In some embodiments of this application, the early warning module 103 is used to generate indication information indicating that the fungal disease has the conditions for infection when the germination probability of the fungal spores is continuously higher than a preset threshold within a preset time period. The early warning information includes indication information indicating that the fungal disease has the conditions for infection.

[0196] In some embodiments of this application, such as Figure 13As shown, the device further includes: a data acquisition module 106, a data acquisition module 107, a disease latent development model construction module 108, and a latent disease development potential value acquisition module 109. The data acquisition module 106 is used to acquire grain remote sensing image data, meteorological data, and grain soil data, wherein the grain remote sensing image data includes hyperspectral data. The data acquisition module 107 is used to acquire canopy temperature data and leaf surface humidity data based on the remote sensing image data, meteorological data, and grain soil data, and to retrieve chlorophyll content data from the hyperspectral data. The disease latent development model construction module 108 is used to construct a disease latent development model for grain fungal diseases during the latent period based on the fungal germination index model and chlorophyll content. The latent disease development potential value acquisition module 109 is used to input the canopy temperature data, the leaf surface humidity data, and the chlorophyll content data into the disease latent development model when the germination probability of the fungal spores meets the threshold condition, and to obtain the latent disease development potential value of the cereal fungal disease during the latent period. The early warning information includes the latent disease development potential value.

[0197] The latent period disease development potential value is used to characterize the development potential of fungal diseases during the latent period.

[0198] In some embodiments of this application, the remote sensing image data may include the hyperspectral data and infrared image data. The hyperspectral data may include the reflectance of grains in a specific hyperspectral band, the surface reflectance in the near-infrared band, and the surface reflectance in the infrared band; the chlorophyll content can be calculated using this acquired data. The infrared image data may include the canopy emissivity, the brightness temperature, and the atmospheric temperature; the canopy temperature data can be calculated based on the canopy emissivity, the brightness temperature, and the atmospheric temperature.

[0199] In some embodiments of this application, the meteorological data includes atmospheric humidity, and the grain soil data may include the topsoil moisture content. The atmospheric humidity and the topsoil moisture content can be used to calculate the leaf surface humidity data.

[0200] In some embodiments of this application, such as Figure 14 As shown, the device also includes a fungal spore diffusion function construction module 200, used to construct a fungal spore diffusion function based on wind speed and rainfall. The disease latent development model construction module 108 is used to construct the disease latent development model based on the fungal germination index model, the chlorophyll content, and the fungal spore diffusion function.

[0201] In some embodiments of this application, the meteorological data includes wind speed data and rainfall data. The latent disease development potential value acquisition module 109 is used to input the canopy temperature data, leaf surface humidity data, wind speed data, rainfall data, and chlorophyll content data into the disease latent development model when the fungal spore germination probability meets a threshold condition, thereby obtaining the latent disease development potential value of the cereal fungal disease during the latent period. The rainfall data and wind speed data are used as input parameters for the fungal spore diffusion function.

[0202] In some embodiments of this application, such as Figure 15 As shown, the device further includes a health correction factor construction module 201, used to construct a health correction factor based on the chlorophyll content, wherein the disease latent development model construction module 108 is used to construct the disease latent development model based on the fungal germination index model, the health correction factor, and the fungal spore diffusion function.

[0203] In some embodiments of this application, the data acquisition module 107 is used to calculate the hyperspectral characteristic band ratio and the normalized vegetation index based on the hyperspectral data; and to obtain the chlorophyll content based on the hyperspectral characteristic band ratio and the normalized vegetation index.

[0204] In some embodiments of this application, such as Figure 15 As shown, the device further includes a disease severity prediction value calculation module 202, used to calculate the disease severity prediction value by time integration based on the latent period disease development potential value.

[0205] In some embodiments of this application, such as Figure 15 As shown, the device further includes: a risk warning module 203, used to determine the risk level corresponding to the predicted disease severity value based on the correspondence between the disease severity range and the risk level; and / or used to automatically collect the remote sensing image data, the meteorological data, and the grain soil data according to the sampling cycle, re-acquire the fungal spore germination probability and the predicted disease severity value, and generate a rolling updated disease risk curve and / or a disease risk distribution map represented by thermal color levels; and / or used to output a grain fungal disease early warning prompt and a high-risk area prompt information when the predicted disease severity value meets preset conditions.

[0206] In some embodiments of this application, such as Figure 16As shown, the device also includes a data processing module 206, which is used to perform temporal and spatial registration on the grain remote sensing image data, meteorological data and grain soil data after the acquisition module 106 acquires grain remote sensing image data, meteorological data and grain soil data, and to perform pixel matching by using bilinear interpolation; and to perform data normalization processing to form a unified feature space.

[0207] Based on the same inventive concept, this application also provides an early warning device for cereal fungal diseases. Figure 17 This diagram illustrates the hardware structure of an early warning device for cereal fungal diseases according to an embodiment of this application. Figure 17 As shown, the early warning device for cereal fungal diseases includes a processor 301 and a memory 302 storing computer program instructions.

[0208] Specifically, the processor 301 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0209] Memory 302 may include mass storage for data or instructions. For example, and not limitingly, memory 302 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. In some embodiments, memory 302 may include removable or non-removable (or fixed) media, or memory 302 may be non-volatile solid-state memory. Memory 302 may be internal or external to the integrated gateway disaster recovery device.

[0210] In some embodiments, memory 302 may be read-only memory (ROM). The ROM may be masked read-only memory (MROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), electrically erasable programmable read-only memory (EAROM), or flash memory, or a combination of two or more of these.

[0211] Memory 302 may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method for early warning of cereal fungal diseases according to one aspect of this disclosure.

[0212] The processor 301 implements the early warning method for cereal fungal diseases in any of the above embodiments by reading and executing computer program instructions stored in the memory 302.

[0213] In some embodiments, the early warning device for cereal fungal diseases further includes a communication interface 303 and a bus 304. For example... Figure 17 As shown, the processor 301, memory 302 and communication interface 303 are connected through bus 304 and complete communication with each other.

[0214] The communication interface 303 can be used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0215] Bus 304 includes hardware, software, or both, that couples components of a cereal fungal disease early warning device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 304 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application considers any suitable bus or interconnection.

[0216] The early warning device for cereal fungal diseases can execute the early warning method for cereal fungal diseases in the embodiments of this application.

[0217] In addition, in conjunction with the early warning method for cereal fungal diseases in the above embodiments, this application also provides a computer storage medium. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the early warning methods for cereal fungal diseases in the above embodiments.

[0218] This application also provides a computer program product, including a computer program, which, when executed, implements any of the early warning methods for cereal fungal diseases described in the above embodiments.

[0219] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0220] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, ASICs, appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, EROM, floppy disks, compact disc-read-only memory (CD-ROM), optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0221] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0222] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0223] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method of early warning of fungal diseases of cereals, characterized in that, include: A fungal germination index model was constructed based on the coupling relationship between canopy temperature and leaf surface humidity of grains. The canopy temperature data and leaf humidity data of the grain are input into the fungal germination index model to obtain the probability of fungal spore germination. When the germination probability of the fungal spores meets the threshold condition, an early warning message for cereal fungal diseases is generated. The step of generating early warning information for cereal fungal diseases when the germination probability of the fungal spores meets a threshold condition includes: When the germination probability of the fungal spores is continuously higher than a preset threshold within a preset time period, an indication message indicating that the fungal disease has the conditions for infection is generated, wherein the warning message includes the indication message indicating that the fungal disease has the conditions for infection. The fungal germination index model is as follows: wherein, is the canopy temperature, is the optimum germination temperature of the fungus, is the leaf wetness, is the critical wetness for germination of the fungus, , is the adjustment parameter; is the probability of spore germination, indicating the risk of spore germination of the fungus on that day.

2. The method according to claim 1, characterized in that, Before inputting the canopy temperature data and leaf humidity data of the grain into the fungal germination index model to obtain the fungal spore germination probability, the method further includes at least one of the following: The canopy temperature data is calculated using a single-window algorithm based on atmospheric temperature, grain brightness temperature, and canopy emissivity. The leaf surface humidity data is obtained by weighted fitting of atmospheric humidity and surface soil moisture content of grains.

3. The method according to claim 1, characterized in that, The method further includes: Collect grain remote sensing image data, meteorological data, and grain soil data, wherein the grain remote sensing image data includes hyperspectral data; The canopy temperature data and leaf humidity data are obtained based on the remote sensing image data, the meteorological data, and the grain soil data, and the chlorophyll content data is obtained by inversion based on the hyperspectral data. Based on the fungal germination index model and chlorophyll content, a latent development model for cereal fungal diseases during the incubation period is constructed. When the fungal spore germination probability meets the threshold condition, the canopy temperature data, leaf humidity data, and chlorophyll content data are input into the latent development model to obtain the latent development potential value of the cereal fungal disease during the incubation period. The early warning information includes the latent development potential value.

4. The method according to claim 3, characterized in that, The method further includes: Based on wind speed and rainfall, a fungal spore diffusion function was constructed. The step of constructing a latent development model for cereal fungal diseases during the latent period based on the fungal germination index model and the chlorophyll content includes: The disease latency and development model is constructed based on the fungal germination index model, the chlorophyll content, and the fungal spore diffusion function.

5. The method according to claim 4, characterized in that, The meteorological data includes wind speed data and rainfall data; When the germination probability of the fungal spores meets the threshold condition, the canopy temperature data, the leaf surface humidity data, and the chlorophyll content data are input into the disease latent development model to obtain the latent disease development potential value of the cereal fungal disease during the latent period, including: When the germination probability of the fungal spores meets the threshold condition, the canopy temperature data, leaf humidity data, wind speed data, rainfall data, and chlorophyll content data are input into the disease latent development model to obtain the latent disease development potential value of the cereal fungal disease during the latent period.

6. The method according to claim 5, characterized in that, The method further includes: Based on the chlorophyll content, a health correction factor was constructed. The step of constructing the disease latency and development model based on the fungal germination index model, the chlorophyll content, and the fungal spore diffusion function includes: The disease latency and development model is constructed based on the fungal germination index model, the health correction factor, and the fungal spore diffusion function.

7. The method according to claim 3, characterized in that, The chlorophyll content obtained by inversion from the hyperspectral data includes: Based on the hyperspectral data, calculate the hyperspectral characteristic band ratio and the normalized vegetation index; The chlorophyll content is obtained based on the ratio of the hyperspectral characteristic bands and the normalized vegetation index.

8. The method according to claim 3, characterized in that, The method further includes: Based on the latent disease development potential value, the disease severity prediction value is calculated using time integration.

9. The method according to claim 8, characterized in that, The method further includes: Based on the correspondence between disease severity ranges and risk levels, determine the risk level corresponding to the predicted disease severity value; and / or According to the sampling cycle, the remote sensing image data, the meteorological data, and the grain soil data are automatically collected; the fungal spore germination probability and the predicted disease severity value are re-acquired; and a continuously updated disease risk curve and / or a disease risk distribution map represented by thermal color levels are generated; and / or When the predicted severity of the disease meets the preset conditions, an early warning message for cereal fungal diseases and a high-risk location message are output.

10. The method according to claim 3, characterized in that, After acquiring grain remote sensing image data, meteorological data, and grain soil data, the method further includes: Temporal and spatial registration is performed on the grain remote sensing image data, the meteorological data, and the grain soil data, and bilinear interpolation is used for pixel matching. Data normalization is performed to form a unified feature space.

11. An early warning device for fungal diseases of cereals, characterized in that, The device includes: The fungal germination index model construction module is used to construct a fungal germination index model based on the coupling relationship between canopy temperature and leaf humidity of grains. The fungal spore germination probability acquisition module is used to input the canopy temperature data and leaf humidity data of the grain into the fungal germination index model to obtain the fungal spore germination probability. The early warning module is used to generate early warning information for cereal fungal diseases when the germination probability of the fungal spores meets a threshold condition. Specifically, the early warning module is used for: When the germination probability of the fungal spores is continuously higher than a preset threshold within a preset time period, an indication message indicating that the fungal disease has the conditions for infection is generated, wherein the warning message includes the indication message indicating that the fungal disease has the conditions for infection. The fungal germination index model is as follows: in, For canopy temperature, This is the optimal temperature for fungal germination. Leaf surface humidity, This is the critical humidity for fungal germination. , To adjust the parameters; The probability of fungal spore germination represents the risk of fungal spore germination on that day.

12. An early warning device for fungal diseases of cereals, characterized in that, The device includes: a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the early warning method for cereal fungal diseases as described in any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the early warning method for cereal fungal diseases as described in any one of claims 1-10.

14. A computer program product, characterized in that, The invention includes a computer program that, when executed by a processor, implements the early warning method for cereal fungal diseases as described in any one of claims 1-10.

Images