Agricultural and forestry monitoring method and system based on remote sensing technology

Abstract

The present application relates to the technical field of agricultural and forestry data processing, and provides an agricultural and forestry monitoring method and system based on remote sensing technology. The method comprises the following steps: obtaining image data of agricultural and forestry crops; performing standardization processing on the image data to generate first data, band-encoding the first data based on the quantum state generated by the randomly sampled phase angle, and generating a space-time stereo tensor; performing mean processing on the space-time stereo tensor to generate an initial state, iteratively processing the space-time stereo tensor through the initial state, and generating a denoised feature tensor; classifying crop diseases based on the denoised feature tensor to determine the disease level of the crop diseases; determining dynamic attribute parameters based on the acquired real-time environmental data, and outputting a disaster warning level according to the disease level and the dynamic level determined by the dynamic attribute parameters. The accuracy and efficiency of agricultural and forestry monitoring are significantly improved.

Description

Technical Field

[0001] The present application relates to the technical field of agricultural and forestry data processing, and in particular to an agricultural and forestry monitoring method and system based on remote sensing technology. Background Art

[0002] Remote sensing technology, with its large-scale, non-contact, and multi-temporal observation capabilities, has become a core tool for agricultural and forestry monitoring. In agriculture, it is widely used for crop growth monitoring, yield forecasting, soil moisture assessment, and pest and disease early warning. Spectral information acquired through satellites or drones provides data support for precision fertilization, irrigation, and disaster prevention and control. In forestry, remote sensing technology is used for forest resource inventory, dynamic monitoring of fires, pests, and diseases, carbon sink assessment, and ecological protection. Combining high-resolution imagery with lidar enables tree species classification, biomass estimation, and forest fire spread simulation. However, in actual applications, despite acquiring a large amount of data, it is difficult to extract precise features from it, resulting in low accuracy in agricultural and forestry monitoring based on remote sensing data. Summary of the Invention

[0003] The present application provides an agricultural and forestry monitoring method and system based on remote sensing technology, which can at least to some extent solve the problem of low accuracy of agricultural and forestry monitoring based on remote sensing data.

[0004] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by practice of the present application.

[0005] According to one aspect of the present application, a remote sensing technology-based agricultural and forestry monitoring method is provided, comprising: acquiring image data of agricultural and forestry crops; performing standardization processing on the image data to generate first data, performing band encoding on the first data based on a quantum state generated by a randomly sampled phase angle, and generating a space-time stereo tensor; performing mean processing on the space-time stereo tensor to generate an initial state, and performing iterative processing on the space-time stereo tensor through the initial state to generate a denoised feature tensor; performing grade classification on crop diseases based on the denoised feature tensor to determine the disease grade of the crop diseases; determining dynamic attribute parameters based on the acquired real-time environmental data, and outputting a disaster warning grade according to the disease grade and the dynamic grade determined by the dynamic attribute parameters.

[0006] In the present application, based on the aforementioned scheme, the image data is standardized to generate first data, and the first data is band-encoded based on the quantum state generated by the randomly sampled phase angle to generate a spatiotemporal stereo tensor, including: standardizing the image data to generate first data; generating a spatial distance factor at each pixel coordinate based on the crop center coordinates in the image data, so as to determine an exponential attenuation factor through the spatial distance factor; generating a quantum state based on the randomly sampled phase angle, and band-encoding the pixel information in the first data according to the quantum state and the exponential attenuation factor to generate a spatiotemporal stereo tensor.

[0007] In the present application, based on the aforementioned scheme, the spatiotemporal stereo tensor is subjected to mean processing to generate an initial state, and the spatiotemporal stereo tensor is subjected to iterative processing through the initial state to generate a denoised feature tensor, including: performing mean processing on the spatiotemporal stereo tensor to generate an initial state; and iteratively processing the spatiotemporal stereo tensor based on the initial state and a preset time step to generate a denoised feature tensor.

[0008] In the present application, based on the aforementioned scheme, the crop diseases are classified based on the denoised feature tensor to determine the disease level of the crop diseases, including: reducing the dimension of the feature tensor through principal component analysis to generate a first feature; training a classification model through quantum annealing and support vector machine, inputting the first feature into the trained classification model, and determining the disease level of the crop disease.

[0009] In the present application, based on the aforementioned scheme, the dynamic attribute parameters are determined based on the acquired real-time environmental data, and the disaster warning level is output according to the disease level and the dynamic level determined by the dynamic attribute parameters, including: determining the dynamic attribute parameters based on the acquired real-time environmental data; comparing the dynamic attribute parameters with a preset dynamic threshold to determine the dynamic level; comparing the dynamic level with the disease level, and outputting the disaster warning level according to the comparison result.

[0010] In the present application, based on the aforementioned scheme, the determination of dynamic attribute parameters based on the acquired real-time environmental data includes: determining the probability distribution of the real-time environmental data at a set time based on the acquired real-time environmental data, and determining the time factor based on the probability distribution; determining the data factor based on the minimum number of grids required to cover the data set in the real-time environmental data; and determining the dynamic attribute parameters based on the time factor and the data factor.

[0011] In the present application, based on the above scheme, the probability distribution of the real-time environmental data at the set time is determined based on the acquired real-time environmental data, and the time factor is determined based on the probability distribution, including: based on the acquired real-time environmental data, determining the probability distribution of the real-time environmental data i at time t as ; Determine the time factor based on the probability distribution for:

[0012]

[0013] in, i and N Respectively represent the identifier and total amount of the real-time environment data.

[0014] In the present application, based on the above solution, the data factor is determined based on the minimum number of grids required to cover the data set in the real-time environmental data, including: , determine the data factor for:

[0015]

[0016] in, represents the grid scale, and s represents the data dimension.

[0017] In the present application, based on the aforementioned scheme, the dynamic attribute parameters are determined based on the acquired real-time environmental data, and after the disaster warning level is outputted according to the dynamic level determined by the disease level and the dynamic attribute parameters, it also includes: retrieving the warning filing information from the database, querying the warning measures related to the disaster warning level; generating an agricultural and forestry warning report based on the disaster warning level and the warning measures; and sending the agricultural and forestry warning report to the management terminal.

[0018] According to one aspect of the present application, there is provided an agricultural and forestry monitoring system based on remote sensing technology, comprising:

[0019] An acquisition unit, used for acquiring image data of agricultural and forestry crops;

[0020] a spatial unit, configured to perform standardization processing on the image data to generate first data, and perform band encoding on the first data based on quantum states generated by randomly sampled phase angles to generate a space-time stereo tensor;

[0021] a feature unit, configured to perform mean processing on the spatiotemporal stereo tensor to generate an initial state, and iteratively process the spatiotemporal stereo tensor using the initial state to generate a denoised feature tensor;

[0022] a grading unit, configured to categorize the crop diseases based on the denoised feature tensor to determine the disease grade of the crop diseases;

[0023] The early warning unit is used to determine dynamic attribute parameters based on the acquired real-time environmental data, and output a disaster early warning level according to the disease level and the dynamic level determined by the dynamic attribute parameters.

[0024] According to one aspect of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the agricultural and forestry monitoring method based on remote sensing technology as described in the above embodiments is implemented.

[0025] According to one aspect of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the agricultural and forestry monitoring method based on remote sensing technology as described in the above embodiments.

[0026] According to one aspect of the present application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the agricultural and forestry monitoring methods based on remote sensing technology provided in the various optional implementations described above.

[0027] In the technical solution of the present application, the acquired image data is standardized to generate first data, which is then band-encoded and space-time tensor processed. The random phase angle encoding of the quantum state enhances the feature expression capability, and the iterative denoising of the space-time stereo tensor retains the key details of crop growth.

[0028] Furthermore, by converting the multidimensional information of image data into dynamic features and introducing dynamic attribute parameters, the early warning model can adapt to environmental changes. Combined with dynamic attribute parameters determined by real-time environmental data, this allows for precise linkage between disease severity and disaster warnings. Ultimately, the output is a disaster warning level that combines disease severity with environmental risk, significantly improving the accuracy, intelligence, and real-time nature of agricultural and forestry monitoring.

[0029] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0031] Figure 1 The flowchart of the agricultural and forestry monitoring method based on remote sensing technology in one embodiment of the present application is schematically shown.

[0032] Figure 2 The flowchart of generating a spatiotemporal stereo tensor in one embodiment of the present application is schematically shown.

[0033] Figure 3 A schematic diagram of an agricultural and forestry monitoring system based on remote sensing technology in an embodiment of the present application is shown schematically.

[0034] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0035] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0036] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner.In the following description, many specific details are provided so as to provide a full understanding of the embodiments of the present application. However, it will be appreciated by those skilled in the art that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps etc. can be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0037] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0038] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0039] The implementation details of the technical solution of this application are described in detail below:

[0040] Figure 1 FIG2 shows a flow chart of an agricultural and forestry monitoring method based on remote sensing technology according to an embodiment of the present application. Figure 1 As shown, the agricultural and forestry monitoring method based on remote sensing technology includes at least steps S110 to S150, which are described in detail as follows:

[0041] S110, acquiring image data of agricultural and forestry crops.

[0042] In one embodiment of this application, image data of agricultural and forestry crops is primarily collected and acquired through satellite remote sensing, drone aerial photography, and smart sensors. In practical applications, satellite data has wide coverage, enabling regular monitoring of crop growth across large areas. Drones, on the other hand, are flexible and maneuverable, enabling high-resolution photography of specific plots, capturing detailed crop changes. Furthermore, a network of ground sensors simultaneously collects environmental data such as soil moisture, temperature, and humidity, providing auxiliary information for image analysis.

[0043] Specifically, satellite data collection is conducted by aligning orbital cycles with key crop growth periods. For example, observations are conducted more frequently during the heading period. Drone aerial photography routes are planned in advance to ensure coverage of target areas and avoid duplication or omissions. By continuously collecting multi-temporal data, such as images from different months, crop growth cycles and disaster occurrences can be tracked dynamically.

[0044] Optionally, the collected image data undergoes preprocessing, such as radiometric and geometric correction, to ensure data accuracy. Subsequently, the optical imagery is spatially registered and fused with multi-source data, including radar data, to enhance the ability to identify characteristics such as crop types and pests and diseases, ultimately creating a structured dataset for subsequent analysis.

[0045] S120 , performing standardization processing on the image data to generate first data, performing band coding on the first data based on quantum states generated by randomly sampled phase angles, and generating a space-time stereo tensor.

[0046] In an embodiment of the present application, the acquired image data is standardized, and the dimensional differences of different bands and sensors are eliminated through normalization or standardization algorithms to generate first data of a unified range; then, a quantum state is constructed based on the phase angle generated by random sampling, and the phase encoding of each band of the first data is performed using the quantum superposition characteristic, and the spatiotemporal information (time information, spatial information, and spectral information) is mapped to the amplitude and phase dimensions of the quantum state, and finally integrated into a spatiotemporal three-dimensional tensor containing multi-dimensional correlation information, providing structured input for subsequent quantum algorithm analysis.

[0047] like Figure 2 As shown, in one embodiment of the present application, the image data is normalized to generate first data, and the first data is band-encoded based on the quantum state generated by the randomly sampled phase angle to generate a space-time stereo tensor, including:

[0048] S210, performing standardization processing on the image data to generate first data;

[0049] S220, generating a spatial distance factor at each pixel coordinate based on the crop center coordinate in the image data, and determining an exponential decay factor through the spatial distance factor;

[0050] S230 , generating a quantum state based on the randomly sampled phase angle, and performing band coding on pixel information in the first data according to the quantum state and the exponential decay factor to generate a spatiotemporal stereo tensor.

[0051] In one embodiment of the present application, the image data is normalized to generate first data. Specifically, for each data band, a mean and a standard deviation are calculated, and then normalization is performed based on the mean and the standard deviation to generate the first data.

[0052] In one embodiment of the present application, the coordinate information of the crop is extracted from the image data by threshold segmentation, and the center coordinates of the crop are defined as Then, based on the crop center coordinates in the image data , generating the pixel coordinates The spatial distance factor for:

[0053]

[0054] Afterwards, an exponential decay factor is determined based on the distance factor for:

[0055]

[0056] in, Represents the attenuation coefficient, which can be 0.1.

[0057] In one embodiment of the present application, based on the phase angle of random sampling Generating quantum states for:

[0058]

[0059] in, represents the randomly sampled phase angle, i The symbol representing the phase angle, j Represents an imaginary number.

[0060] Then, according to the quantum state and the exponential decay factor, the pixel information in the first data is band-coded to generate a spatiotemporal tensor. for:

[0061]

[0062] in, i and N denote the identity and total number of phase angles, respectively. Represents the preset weight coefficient, represents the original spectrum value, that is t Time, space position ( x,y ) at the data band The corresponding radiation brightness value is represents the first data generated by the normalization process, Indicates the phase angle i The corresponding quantum state, Represents the calculated exponential decay factor.

[0063] In this embodiment, standardization provides normalized input for band coding, and spatial weight calculation enhances crop characteristics. Impact data collected by satellites (macro), drones (mesoscopic), and ground sensors (microscopic) are uniformly expressed through band coding, breaking through the linear limitations of traditional multi-source fusion. Tensor fusion is then used to extract nonlinear features, compressing the data and enhancing feature expression through nonlinear fusion. The final output is a quantized spatiotemporal tensor verified for compression and noise immunity, providing high-quality input for subsequent analysis.

[0064] The above process encodes standardized image data based on quantum states generated by random phase angles, quantifies the correlation strength between pixels and crop centers using spatial distance factors, and maps the two-dimensional image into a spatiotemporal tensor. This process leverages the superposition properties of quantum states to expand the spectral information of a single band into a joint spatiotemporal and phase encoding. This preserves local details, such as lesion texture, while suppressing edge noise through an attenuation factor, thereby improving the spatial continuity and spectral discrimination of the feature tensor.

[0065] S130 , performing mean processing on the spatiotemporal stereo tensor to generate an initial state, and performing iterative processing on the spatiotemporal stereo tensor using the initial state to generate a denoised feature tensor.

[0066] In an embodiment of the present application, the spatiotemporal stereo tensor is averaged in the time or space dimension to generate a smooth initial state to reduce local noise; then, based on this state, the outliers in the tensor are iteratively corrected through recursive filtering or adaptive optimization algorithm to gradually suppress random interference and retain the key spatiotemporal characteristics of crop growth, and finally generate a denoised feature tensor.

[0067] In one embodiment of the present application, performing mean processing on the spatiotemporal stereo tensor to generate an initial state, and performing iterative processing on the spatiotemporal stereo tensor using the initial state to generate a denoised feature tensor includes:

[0068] Performing mean processing on the space-time stereo tensor to generate an initial state;

[0069] Based on the initial state and a preset time step, the spatiotemporal stereo tensor is iteratively processed to generate a denoised feature tensor.

[0070] In one embodiment of the present application, the spatiotemporal stereo tensor is averaged to generate an initial state After initialization, the true distribution of quantum coded data is gradually approximated through iteration. Based on the initial state and the preset time step, the space-time stereo tensor is iteratively processed as follows to generate the denoised feature tensor for:

[0071]

[0072] in, a, b, c Represent the linear growth coefficient, difference suppression coefficient and nonlinear oscillation amplitude respectively, express t The state characteristics of the moment, express t The space-time tensor of the moment, Through the above process, the signal and noise in the spatiotemporal tensor can be separated to generate a denoised feature tensor.

[0073] In the above process, after generating an initial state through averaging, an iterative algorithm based on time steps is used to denoise the spatiotemporal tensor. This initial state serves as a baseline, gradually correcting for abnormal pixel values, such as cloud cover or sensor errors. The iterative process incorporates temporal information, such as the crop growth cycle, to dynamically adjust the filter intensity. The resulting feature tensor removes random noise while preserving the temporal characteristics of disease development, such as the spread rate of lesions, providing a cleaner data foundation for subsequent classification.

[0074] S140 , classifying the crop diseases based on the denoised feature tensor to determine the disease level of the crop diseases.

[0075] In this example, a machine learning model extracts key features of crop diseases, such as spectral anomalies and texture changes, from the denoised feature tensor. Combined with a preset disease severity threshold or model-predicted probability, the feature intensities are mapped to a disease severity scale of 0-5, with 0 representing healthy disease and 5 representing severe disease. This enables a quantitative conversion from data to disease severity.

[0076] In one embodiment of the present application, based on the denoised feature tensor, crop diseases are classified to determine the disease level of the crop diseases, including:

[0077] Performing dimensionality reduction on the feature tensor by principal component analysis to generate a first feature;

[0078] A classification model is trained by quantum annealing and support vector machine, and the first feature is input into the trained classification model to determine the disease level of the crop disease.

[0079] In one embodiment of the present application, after generating the feature tensor, entanglement entropy is used to screen features with high correlation strength, such as chlorophyll index, lesion texture, etc., to eliminate noise interference items; then principal component analysis is used to reduce the feature tensor from high dimension to within a preset dimension, retaining key information, and providing a concise and effective input for the classification model.

[0080] In this example, quantum annealing is used to optimize a support vector machine (SVM), combining the efficient search capabilities of the quantum annealing algorithm with the SVM's classification boundary optimization properties. Quantum annealing is used to globally optimize SVM hyperparameters, such as the penalty coefficient. Chaotic sequences are introduced during the search process to increase the diversity of parameter exploration, avoid falling into local optima, and ultimately generate a classification model that adapts to complex disease patterns.

[0081] Optionally, this embodiment defines a 0-5 disease level standard, ranging from healthy to severely necrotic. Grading thresholds are set for key features, such as the percentage of lesion area, and the disease probability output by the classification model is proportionally mapped to specific levels, such as a probability of 0.8 corresponding to level 4. This ensures that the judgment results are consistent with physiological indicators while taking into account the uncertainty of model predictions.

[0082] Optionally, after determining the disease level of the crop disease, a disease level map and dynamic analysis report with consistent spatial resolution is generated, including level distribution statistics and key feature contributions, such as a 30% decrease in chlorophyll leading to a 2-level increase in level.

[0083] The above process uses principal component analysis (PCA) based on the denoised feature tensor to extract key features, such as chlorophyll index and texture complexity. Classification is then performed using a quantum annealing-optimized support vector machine (QSVM). Dimensionality reduction reduces redundant information. The QSVM uses quantum annealing to globally search for optimal hyperparameters, such as the penalty coefficient, addressing the problem of traditional SVMs easily falling into local optimality. This significantly improves the accuracy of disease grade classification, especially for early identification of minor diseases.

[0084] S150, determining dynamic attribute parameters based on the acquired real-time environmental data, and outputting a disaster warning level according to the disease level and the dynamic level determined by the dynamic attribute parameters.

[0085] In this example, dynamic attribute parameters are extracted based on real-time environmental data, such as temperature, humidity, rainfall, and wind speed. Their impact on disease development is quantified using a weighting model to generate a dynamic grade. This is then combined with the static disease grade to generate a comprehensive early warning grade that takes into account both the current environment and disease severity. This enables a transition from single disease assessment to a precise early warning system that combines environmental and disease characteristics.

[0086] In one embodiment of the present application, dynamic attribute parameters are determined based on the acquired real-time environmental data, and a disaster warning level is output according to the disease level and the dynamic level determined by the dynamic attribute parameters, including:

[0087] Determine dynamic attribute parameters based on the acquired real-time environmental data;

[0088] Comparing the dynamic attribute parameter with a preset dynamic threshold to determine a dynamic level;

[0089] A comparison is made between the dynamic level and the disease level, and a disaster warning level is output according to the comparison result.

[0090] In one embodiment of the present application, determining dynamic attribute parameters based on acquired real-time environmental data includes:

[0091] Determining a probability distribution of the real-time environmental data at a set time based on the acquired real-time environmental data, and determining a time factor based on the probability distribution;

[0092] determining a data factor based on a minimum number of grids required to cover a data set in the real-time environmental data;

[0093] A dynamic attribute parameter is determined based on the time factor and the data factor.

[0094] In one embodiment of the present application, based on the acquired real-time environment data, it is determined that the real-time environment data is t The probability distribution of the time instant, and the time factor is determined based on the probability distribution for:

[0095]

[0096] in, i and N Respectively represent the identifier and total amount of the real-time environmental data, Indicates real-time environmental data in t The probability distribution of time.

[0097] In one embodiment of the present application, the data factor is determined based on the minimum number of grids required to cover the data set in the real-time environmental data. for:

[0098]

[0099] in, represents the minimum number of grids required to cover the dataset, Represents the grid scale, and s represents the identifier of the data dimension.

[0100] In one embodiment of the present application, the dynamic attribute parameter is determined based on the time factor and the data factor. for:

[0101]

[0102] in, represents the time factor, represents the data factor, Represent the smoothing factor and threshold parameter of the integral term, s The identifier that represents the data dimension.

[0103] In one embodiment of the present application, after determining the dynamic attribute parameter, a dynamic level is determined based on a comparison between the dynamic attribute parameter and a preset parameter threshold. The dynamic level is then compared with the disease level, and the maximum value of the two is taken as the final disaster warning level based on the comparison result.

[0104] For example, the calculated dynamic attribute parameters =0.8. After comparing with the valuation of the Disabled Persons’ Federation, the dynamic level is 4. The disease level obtained by the above calculation is also 4. The final disaster warning level is determined to be 4.

[0105] The above process generates a time factor based on the probability distribution of environmental data to reflect changing trends; a data factor is determined based on the minimum number of grid cells to quantify data complexity. Dynamic attribute parameters are then generated based on the time and data factors, and the disaster warning level is determined by combining the disease level with the dynamic threshold. For example, if the time factor of real-time temperature and humidity data shows abnormal fluctuations, such as a sudden increase in humidity due to continuous rainfall, and the data factor indicates insufficient data density, the system automatically raises the warning level. This compensates for the static threshold's inability to adapt to dynamic environmental changes and enables coupled disease and environmental risk assessment.

[0106] In one embodiment of the present application, after determining a dynamic attribute parameter based on the acquired real-time environmental data and outputting a disaster warning level according to the disease level and the dynamic level determined by the dynamic attribute parameter, the method further includes:

[0107] Retrieve early warning record information from the database and query early warning measures related to the disaster warning level;

[0108] generating an agricultural and forestry warning report based on the disaster warning level and the warning measures;

[0109] The agriculture and forestry early warning report is sent to the management terminal.

[0110] In one embodiment of the present application, based on the disaster warning level output by the dynamic threshold model, such as Level 4 severe disease, the corresponding level of preparedness measures are retrieved from a pre-installed agricultural and forestry disaster database. In this embodiment, the database uses a hierarchical index structure, matching the disaster type (disease / pest / meteorological disaster) with the level double keyword to return warning measures, such as chemical control plans and isolation zone establishment standards.

[0111] Based on the retrieved early warning measures, the system populates the current disaster's spatiotemporal information (occurrence area, area, crop type) and environmental data (temperature, humidity, wind speed) to generate a structured agricultural and forestry early warning report. This report contains three levels of information: the first level includes a summary of the disaster and its severity; the second level includes specific measures, such as spraying 50% carbendazim wettable powder at an 800-fold concentration; and the third level includes the implementation timeline and responsible departments.

[0112] Agricultural and forestry early warning reports are sent to management terminals, such as government regulatory platforms, via data transmission interfaces, triggering SMS notifications. Sending logs are recorded. If no terminal confirmation is received within a preset time, the report is automatically resent and marked for follow-up, ensuring reliable delivery of early warning information.

[0113] This process automatically generates agricultural and forestry warning reports, including spatiotemporal distribution maps and dynamic factor analysis, and sends them to management terminals. This process automates the entire chain from data collection to decision-making, reducing delays caused by manual intervention and ensuring timely disaster response.

[0114] In this application's technical solution, acquired image data is standardized to generate primary data, which is then subjected to band encoding and spatiotemporal tensor processing. This transforms the multidimensional information (spatial, temporal, and spectral) of remote sensing images into dynamic features. This, combined with real-time environmental data, enables precise linkage between disease levels and disaster warnings. Quantum state random phase angle encoding enhances feature expression, while iterative denoising of spatiotemporal tensors preserves key details of crop growth. The introduction of dynamic attribute parameters (time factor and data factor) enables the early warning model to adapt to environmental changes. Ultimately, the output is a disaster warning level that combines disease severity and environmental risk, significantly improving the intelligence and real-time nature of agricultural and forestry monitoring.

[0115] The following introduces an embodiment of the agricultural and forestry monitoring system based on remote sensing technology of the present application, which can be used to execute the agricultural and forestry monitoring method based on remote sensing technology in the above-mentioned embodiment of the present application. It can be understood that the agricultural and forestry monitoring system based on remote sensing technology can be a computer program (including program code) running on a computer device, for example, the agricultural and forestry monitoring system based on remote sensing technology is an application software; the agricultural and forestry monitoring system based on remote sensing technology can be used to execute the corresponding steps in the method provided in the embodiment of the present application. For details not disclosed in the embodiment of the agricultural and forestry monitoring system based on remote sensing technology of the present application, please refer to the embodiment of the agricultural and forestry monitoring method based on remote sensing technology mentioned above in the present application.

[0116] Figure 3 A block diagram of an agriculture and forestry monitoring system based on remote sensing technology according to an embodiment of the present application is shown.

[0117] Reference Figure 3 As shown, according to an embodiment of the present application, an agriculture and forestry monitoring system based on remote sensing technology includes:

[0118] An acquisition unit 310 is used to acquire image data of agricultural and forestry crops;

[0119] The spatial unit 320 is configured to perform standardization processing on the image data to generate first data, and perform band encoding on the first data based on quantum states generated by randomly sampled phase angles to generate a space-time stereo tensor;

[0120] A feature unit 330 is configured to perform mean processing on the spatiotemporal stereo tensor to generate an initial state, and iteratively process the spatiotemporal stereo tensor using the initial state to generate a denoised feature tensor;

[0121] a grading unit 340 for grading the crop diseases based on the denoised feature tensor to determine the disease grade of the crop diseases;

[0122] The early warning unit 350 is used to determine dynamic attribute parameters based on the acquired real-time environmental data, and output a disaster early warning level according to the disease level and the dynamic level determined by the dynamic attribute parameters.

[0123] In the present application, based on the aforementioned scheme, the image data is standardized to generate first data, and the first data is band-encoded based on the quantum state generated by the randomly sampled phase angle to generate a spatiotemporal stereo tensor, including: standardizing the image data to generate first data; generating a spatial distance factor at each pixel coordinate based on the crop center coordinates in the image data, so as to determine an exponential attenuation factor through the spatial distance factor; generating a quantum state based on the randomly sampled phase angle, and band-encoding the pixel information in the first data according to the quantum state and the exponential attenuation factor to generate a spatiotemporal stereo tensor.

[0124] In the present application, based on the aforementioned scheme, the spatiotemporal stereo tensor is subjected to mean processing to generate an initial state, and the spatiotemporal stereo tensor is subjected to iterative processing through the initial state to generate a denoised feature tensor, including: performing mean processing on the spatiotemporal stereo tensor to generate an initial state; and iteratively processing the spatiotemporal stereo tensor based on the initial state and a preset time step to generate a denoised feature tensor.

[0125] In the present application, based on the aforementioned scheme, the crop diseases are classified based on the denoised feature tensor to determine the disease level of the crop diseases, including: reducing the dimension of the feature tensor through principal component analysis to generate a first feature; training a classification model through quantum annealing and support vector machine, inputting the first feature into the trained classification model, and determining the disease level of the crop disease.

[0126] In the present application, based on the aforementioned scheme, the dynamic attribute parameters are determined based on the acquired real-time environmental data, and the disaster warning level is output according to the disease level and the dynamic level determined by the dynamic attribute parameters, including: determining the dynamic attribute parameters based on the acquired real-time environmental data; comparing the dynamic attribute parameters with a preset dynamic threshold to determine the dynamic level; comparing the dynamic level with the disease level, and outputting the disaster warning level according to the comparison result.

[0127] In the present application, based on the aforementioned scheme, the determination of dynamic attribute parameters based on the acquired real-time environmental data includes: determining the probability distribution of the real-time environmental data at a set time based on the acquired real-time environmental data, and determining the time factor based on the probability distribution; determining the data factor based on the minimum number of grids required to cover the data set in the real-time environmental data; and determining the dynamic attribute parameters based on the time factor and the data factor.

[0128] In the present application, based on the above scheme, the probability distribution of the real-time environmental data at the set time is determined based on the acquired real-time environmental data, and the time factor is determined based on the probability distribution, including: based on the acquired real-time environmental data, determining the probability distribution of the real-time environmental data i at time t as ; Determine the time factor based on the probability distribution for:

[0129]

[0130] in, i and N Respectively represent the identifier and total amount of the real-time environment data.

[0131] In the present application, based on the above solution, the data factor is determined based on the minimum number of grids required to cover the data set in the real-time environmental data, including: , determine the data factor for:

[0132]

[0133] in, represents the grid scale, and s represents the data dimension.

[0134] In the present application, based on the aforementioned scheme, the dynamic attribute parameters are determined based on the acquired real-time environmental data, and after the disaster warning level is outputted according to the dynamic level determined by the disease level and the dynamic attribute parameters, it also includes: retrieving the warning filing information from the database, querying the warning measures related to the disaster warning level; generating an agricultural and forestry warning report based on the disaster warning level and the warning measures; and sending the agricultural and forestry warning report to the management terminal.

[0135] In this application's technical solution, acquired image data is standardized to generate primary data, which is then subjected to band encoding and spatiotemporal tensor processing. This transforms the multidimensional information (spatial, temporal, and spectral) of remote sensing images into dynamic features. This, combined with real-time environmental data, enables precise linkage between disease levels and disaster warnings. Quantum state random phase angle encoding enhances feature expression, while iterative denoising of spatiotemporal tensors preserves key details of crop growth. The introduction of dynamic attribute parameters (time factor and data factor) enables the early warning model to adapt to environmental changes. Ultimately, the output is a disaster warning level that combines disease severity and environmental risk, significantly improving the intelligence and real-time nature of agricultural and forestry monitoring.

[0136] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown.

[0137] It should be noted that the computer system of the electronic device in this embodiment is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0138] In this embodiment, the computer system includes a central processing unit (CPU) 401, which can execute various appropriate actions and processes based on programs stored in read-only memory (ROM) 402 or programs loaded from storage unit 408 into random access memory (RAM) 403, such as executing the agricultural and forestry monitoring method based on remote sensing technology described in the above embodiments. RAM 403 also stores various programs and data required for system operation. CPU 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output interface 405 is also connected to bus 404.

[0139] The following components are connected to the input / output interface 405: an input section 406 including a keyboard, mouse, and the like; an output section 407 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and speakers; a storage section 408 including devices such as a hard disk; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output interface 405 as needed. Removable media 411, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 410 as needed, so that computer programs read from the removable media can be installed in the storage section 408 as needed.

[0140] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product that includes a computer program carried on a computer-readable medium, the computer program including a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 409 and / or installed from a removable medium 411. When the computer program is executed by the central processing unit 401, the various functions defined in the system of the present application are performed.

[0141] It should be noted that the computer-readable medium described in the embodiments of the present application may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal transmitted in baseband or as part of a carrier wave, which carries a computer-readable computer program. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0142] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0143] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. In some cases, the names of these units do not constitute limitations on the units themselves.

[0144] According to one aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations described above.

[0145] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments, or may exist independently and not be incorporated into the electronic device. The computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device implements the agricultural and forestry monitoring method based on remote sensing technology described in the above embodiments.

[0146] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the application, the features and functions of two or more modules or units described above can be concretized in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0147] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0148] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed herein.

[0149] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for monitoring agriculture and forestry based on remote sensing technology, characterized in that: include: Obtain image data of agricultural and forestry crops; Standardizing the image data to generate first data, and band-encoding the first data based on quantum states generated by randomly sampled phase angles to generate a space-time stereo tensor; Performing mean processing on the spatiotemporal stereo tensor to generate an initial state, and iteratively processing the spatiotemporal stereo tensor using the initial state to generate a denoised feature tensor; classifying the crop diseases based on the denoised feature tensor to determine the disease grade of the crop diseases; Determining dynamic attribute parameters based on the acquired real-time environmental data, and outputting a disaster warning level according to the disease level and the dynamic level determined by the dynamic attribute parameters; The method includes performing standardization processing on the image data to generate first data, performing band encoding on the first data based on quantum states generated by randomly sampled phase angles, and generating a space-time stereo tensor. The method includes: performing standardization processing on the image data to generate first data; generating a spatial distance factor at each pixel coordinate based on the crop center coordinate in the image data, so as to determine an exponential decay factor through the spatial distance factor; A quantum state is generated based on the randomly sampled phase angle, and pixel information in the first data is band-coded according to the quantum state and the exponential decay factor to generate a spatiotemporal stereo tensor.

2. The agricultural and forestry monitoring method based on remote sensing technology according to claim 1, characterized in that: Performing mean processing on the spatiotemporal stereo tensor to generate an initial state, and iteratively processing the spatiotemporal stereo tensor using the initial state to generate a denoised feature tensor, including: Performing mean processing on the space-time stereo tensor to generate an initial state; Based on the initial state and a preset time step, the spatiotemporal stereo tensor is iteratively processed to generate a denoised feature tensor.

3. The agricultural and forestry monitoring method based on remote sensing technology according to claim 1, characterized in that: Based on the denoised feature tensor, the crop diseases are classified to determine the disease level of the crop diseases, including: Performing dimensionality reduction on the feature tensor by principal component analysis to generate a first feature; A classification model is trained by quantum annealing and support vector machine, and the first feature is input into the trained classification model to determine the disease level of the crop disease.

4. The agricultural and forestry monitoring method based on remote sensing technology according to claim 1, characterized in that: Determining dynamic attribute parameters based on the acquired real-time environmental data, and outputting a disaster warning level according to the disease level and the dynamic level determined by the dynamic attribute parameters, including: Determine dynamic attribute parameters based on the acquired real-time environmental data; Comparing the dynamic attribute parameter with a preset dynamic threshold to determine a dynamic level; A comparison is made between the dynamic level and the disease level, and a disaster warning level is output according to the comparison result.

5. The agricultural and forestry monitoring method based on remote sensing technology according to claim 4 is characterized in that: Determine dynamic attribute parameters based on the acquired real-time environmental data, including: Determining a probability distribution of the real-time environmental data at a set time based on the acquired real-time environmental data, and determining a time factor based on the probability distribution; determining a data factor based on a minimum number of grids required to cover a data set in the real-time environmental data; A dynamic attribute parameter is determined based on the time factor and the data factor.

6. The agricultural and forestry monitoring method based on remote sensing technology according to claim 5, characterized in that: Determining a probability distribution of the real-time environmental data at a set time based on the acquired real-time environmental data, and determining a time factor based on the probability distribution, including: Based on the acquired real-time environmental data, determine the real-time environmental data i exist t The probability distribution of time is ; Determine a time factor based on the probability distribution for: in, i and N Respectively represent the identifier and total amount of the real-time environment data.

7. The agricultural and forestry monitoring method based on remote sensing technology according to claim 5, characterized in that: Determine a data factor based on the minimum number of grids required to cover the data set in the real-time environmental data, including: Based on the minimum number of grids required to cover the dataset in the real-time environment data , determine the data factor for: in, represents the grid scale, and s represents the data dimension.

8. The agricultural and forestry monitoring method based on remote sensing technology according to any one of claims 1 to 7, characterized in that: After determining dynamic attribute parameters based on the acquired real-time environmental data and outputting a disaster warning level according to the disease level and the dynamic level determined by the dynamic attribute parameters, the method further includes: Retrieve early warning record information from the database and query early warning measures related to the disaster warning level; generating an agricultural and forestry warning report based on the disaster warning level and the warning measures; The agriculture and forestry early warning report is sent to the management terminal.

9. An agricultural and forestry monitoring system based on remote sensing technology, characterized in that: include: An acquisition unit, used for acquiring image data of agricultural and forestry crops; a spatial unit, configured to perform standardization processing on the image data to generate first data, and perform band encoding on the first data based on quantum states generated by randomly sampled phase angles to generate a space-time stereo tensor; a feature unit, configured to perform mean processing on the spatiotemporal stereo tensor to generate an initial state, and iteratively process the spatiotemporal stereo tensor using the initial state to generate a denoised feature tensor; a grading unit, configured to categorize the crop diseases based on the denoised feature tensor to determine the disease grade of the crop diseases; An early warning unit, configured to determine a dynamic attribute parameter based on the acquired real-time environmental data, and output a disaster early warning level according to the disease level and the dynamic level determined by the dynamic attribute parameter; The method includes performing standardization processing on the image data to generate first data, performing band encoding on the first data based on quantum states generated by randomly sampled phase angles, and generating a space-time stereo tensor. The method includes: performing standardization processing on the image data to generate first data; generating a spatial distance factor at each pixel coordinate based on the crop center coordinate in the image data, so as to determine an exponential decay factor through the spatial distance factor; A quantum state is generated based on the randomly sampled phase angle, and pixel information in the first data is band-coded according to the quantum state and the exponential decay factor to generate a spatiotemporal stereo tensor.

Images