4479 results about "Agricultural crops" patented technology

The invention discloses an intelligent crop growth prediction and optimization method based on multi-source data fusion, and belongs to the technical field of crop analysis, and the method specifically comprises the steps: obtaining space remote sensing data, ground sensor data and meteorological data, and carrying out the space-time alignment processing to generate fusion data representation; inputting the fused data representation into a prediction model, and outputting a crop future growth state sequence and a yield prediction result by coupling a crop growth mechanism and a dynamic environment response relationship; based on a yield prediction result, simulating long-term effects of different management strategies in a virtual growth environment, and screening out an irrigation scheme and a fertilization scheme with the optimal target function; transmitting the irrigation scheme and the fertilization scheme to a farmland execution terminal; collecting crop state feedback data and environmental parameter feedback data, and updating internal parameters of the prediction model based on the feedback data; according to the invention, crop growth management is converted from passive response to active regulation and control, and a whole-process intelligent solution is provided for precision agriculture.

The invention relates to the technical field of electric digital data processing, in particular to an agricultural planting optimization system and method based on big data analysis. The method comprises the following steps: acquiring agricultural planting environment parameter data, and performing preprocessing and standardization to obtain a standardized environment feature vector; acquiring image, sound and smell data of crops; performing deep feature extraction on the image, sound and smell data to generate a multi-modal feature representation matrix; and performing multi-modal data fusion based on the standardized environment feature vector and the multi-modal feature representation matrix to obtain a comprehensive feature space. According to the invention, through multi-modal feature fusion and digital twinborn modeling, the precision and real-time performance of crop growth risk and pest and disease prediction are improved, and optimal regulation and control and efficient resource utilization of precision agriculture are realized.

The invention provides a crop monitoring system and method based on multispectral remote sensing and deep learning, and the system comprises a data preprocessing module which is used for carrying out the data preprocessing of a multispectral remote sensing image, and generating a standard reflectivity data set; the feature extraction module is used for extracting a high-dimensional spectral feature vector from the standard reflectivity data set through a multi-scale convolutional neural network; the time sequence dynamic analysis module is used for performing time sequence correlation analysis on the high-dimensional spectral feature vector through a long short-term memory network to generate a weighted time sequence feature vector; the physiological parameter quantification module is used for mapping the weighted time sequence feature vectors into quantitative indexes of crop physiological parameters; and the monitoring result generation module is used for performing dynamic deduction according to the quantitative index and generating dynamic trend prediction data of the crop growth state. The system can dynamically sense the growth stage characteristics of crops and adaptively adjust the spectral feature extraction strategy, thereby improving the crop monitoring precision in a complex agricultural environment.

The invention provides an agricultural environment monitoring method and system based on the Internet of Things. According to the method, multi-source data weights are dynamically distributed through a soil sensor array connected with Internet of Things nodes, and a global soil parameter set is generated; deploying a micro-electro-mechanical micro-fluidic chip in the coverage area to carry out soil solution selective permeation, converting the target ion concentration into an electric signal, and synchronously transmitting the electric signal and soil parameters; historical time series data are extracted, coherence is established through time correlation analysis, and undeployed area data are filled in combination with a spatial interpolation algorithm to construct a dynamic prediction model; according to the nutrient space change trend output by the model, crop growth requirements are matched to generate a fertilization amount adjustment instruction, and the fertilization amount adjustment instruction is issued to field fertilization equipment through the Internet of Things to execute dynamic regulation. Space-time precise sensing of soil nutrients and self-adaptive fertilization regulation and control are realized, and the utilization efficiency of agricultural resources and crop growth sustainability are improved.

The invention discloses an entity alignment method for a multi-modal crop knowledge graph, and belongs to the technical field of knowledge graphs and agricultural intelligent analysis, and the method comprises the steps: obtaining a data feature item set of an agricultural field, and carrying out the time sequence compensation, and generating a growth time sequence feature parameter; performing feature extraction on the data feature item set, performing fusion to generate a multi-modal fusion feature mapping graph, constructing a dynamic feature matching network based on growth time sequence feature parameters, and performing entity node traversal on a reference knowledge graph to generate a candidate alignment set and a corresponding difference unit set; filtering conflict nodes in the candidate alignment set according to a three-dimensional confidence evaluation model to generate an effective alignment chain; and generating a graph updating instruction based on the difference unit set, and reconstructing a knowledge graph topological structure in combination with the effective alignment chain. According to the method, multi-modal feature bridging, dynamic weight optimization of growth stage perception and an incremental conflict resolution mechanism are adopted, so that cross-domain agricultural entity accurate alignment and real-time adaptive updating of the knowledge graph can be realized.

The invention relates to the technical field of water and fertilizer control, in particular to a water and fertilizer integrated control system and method based on the Internet of Things. The method comprises the following steps of obtaining environment measured data, historical environment data and regional geographic information of a farmland region, performing spatial modeling and time sequence learning on the farmland region, and constructing a farmland digital twinborn model; simulating the state of an area without sensors by using a farmland digital twinborn model to obtain virtual sensing node data; collecting multispectral image data of crops, and extracting physiological feature data of the crops; and constructing a crop physiological state model by utilizing the environment measured data, the virtual sensing node data and the crop physiological feature data, and generating crop physiological state evaluation data. Through multi-source data fusion and three-dimensional visualization integration, data-driven accurate regulation and control and whole-process intelligent management of the water and fertilizer integrated system are realized, and the intelligent level of irrigation and fertilization and the resource utilization efficiency are comprehensively improved.

The invention discloses a crop growth analysis system based on machine vision, and relates to the technical field of agricultural intelligent monitoring and analysis, the system comprises a multi-source acquisition module, a disturbance identification module, a growth behavior modeling module, an environmental adaptability correction module and a feedback prediction module; wherein the multi-source acquisition module can synchronously acquire visible light, near-infrared and depth images, and generates a joint index in combination with environmental data; the disturbance identification module identifies abnormal areas such as wind disturbance and shielding based on the residual image and the image structure network; the growth behavior modeling module is used for extracting internode change, leaf surface tension and bifurcation angle characteristics by using a three-dimensional structure time sequence alignment and hidden change rate coding network; the environment adaptability correction module constructs a crop-environment double-domain mapping relation; the feedback prediction module outputs personalized intervention suggestions in combination with deviation analysis and crop variety embedding vectors; the system has the advantages of high modeling precision, strong adaptability, fast feedback response and the like, and is suitable for intelligent planting management of various crops.

The invention discloses a non-point source pollution control and ecological agriculture decision-making method based on reinforcement learning, and relates to the technical field of new-generation information. The method comprises the steps that meteorological parameters, soil parameters and crop growth parameters are collected through a farmland Internet of Things system, and historical management data in the crop growth process and water quality monitoring information of surface runoff are collected to serve as original data; preprocessing the original data to construct a multi-modal data set; constructing an ecological agriculture multi-modal reinforcement learning model based on the multi-modal data set; integrating the ecological agriculture multi-modal reinforcement learning model to an agricultural intelligent decision-making platform, so that the ecological agriculture multi-modal reinforcement learning model is coupled with the agricultural intelligent decision-making platform; and an agricultural intelligent decision-making platform is utilized to issue operation instructions to irrigation, fertilization and pesticide application equipment so as to realize non-point source pollution management and control and ecological agriculture decision-making. Through a machine learning algorithm and real-time data analysis, many limitations of traditional ecological agriculture are overcome.

The invention relates to the technical field of farmland fertilization management, and discloses an intelligent fertilization management method and system based on machine learning. The method comprises the steps that a soil parameter set and an environment parameter set of a target farmland are collected, soil parameters comprise soil humidity, nitrogen phosphorus and potassium content and pH value, and environment parameters comprise illumination intensity, temperature and rainfall; constructing a soil nutrient dynamic change model according to historical data, and predicting a soil nutrient consumption trend in a future preset period; generating an initial fertilization scheme based on the nutrient consumption trend and the crop growth stage characteristics; monitoring the growth state of crops in real time by using a multi-mode sensor, and obtaining a leaf surface color index, a stem height and a fruit development progress to form a growth state data set; and inputting the growth state data set and the initial fertilization scheme into a fertilization decision model, and comparing growth state deviation to adjust the nutrient distribution ratio to generate an optimized fertilization scheme.

The invention discloses a planting optimization method and system based on crop yield estimation in a saline-alkali land area, and relates to the field of crop yield prediction and planting optimization, and the method comprises the steps: data collection and fusion processing; performing dynamic prediction on soil water and salt migration, and realizing water and salt space-time distribution prediction by adopting a space-time cubic modeling self-adaptive model combined with physical correction; crop salt tolerance modeling: establishing a multi-interval salt tolerance model based on physiological response fitting and threshold segmentation, and introducing covariable correction; carrying out migration salt tolerance coupling modeling, introducing a salinity memory factor and a stage sensitivity regulation factor, and dynamically simulating growth response of crops under salinity stress; and crop yield estimation and planting optimization: generating a regional yield prediction and sowing configuration scheme based on coupling model output, and forming an optimization strategy in combination with measures such as irrigation and fertilization. According to the method, model-driven integrated optimization from yield estimation to planting decision of crops in the saline-alkali region is realized, and the method has high precision and wide applicability.

The invention relates to the technical field of agricultural planting, and discloses a crop planting suggestion generation method adapting to different climate conditions. Real-time climate data are collected through a multi-source climate sensor, climate dynamic feature data are generated through a spatial-temporal feature fusion algorithm, and planting strategy parameters are obtained by inputting the climate dynamic feature data into a pre-trained mixed decision model. And constructing a multi-objective optimization model taking the crop adaptability matching degree and the resource utilization efficiency as objectives, and globally optimizing a planting scheme by adopting a hierarchical dynamic programming algorithm integrating fuzzy logic constraint and an adaptive decomposition strategy. A multi-level regulation and control framework comprising a decision-making layer, an adaptation layer and an execution layer is constructed, the decision-making layer generates a global planting sequence, the adaptation layer uses a sliding window optimization algorithm to adjust local parameters, the execution layer regulates and controls soil humidity and illumination intensity based on a robust feedback control algorithm, and finally a planting control instruction is output. And accurate and efficient climate adaptability planting decision is realized.

The invention provides a crop planting area intelligent extraction method and system based on multispectral remote sensing, and relates to the field of remote sensing image processing, and the method comprises the steps: obtaining and correcting a multiband remote sensing image; calculating a vegetation index and constructing a crop growth characterization index to extract canopy features; obtaining a multi-period feature map, calculating a spatial distribution entropy, and establishing an evaluation function to determine a time sequence fusion weight; a spatial constraint function is established based on the spectral distance, and a segmentation criterion is constructed by combining the spatial constraint function with time sequence features for classification iteration. According to the method, the accuracy and the discrimination degree of crop planting area extraction are improved, and crop identification requirements in a complex agricultural environment are met.

The invention discloses a pure bio-based PHA aqueous dispersion as well as a preparation method and application thereof, and belongs to the technical field of pure bio-based polymer aqueous dispersion. According to the dispersion, polyhydroxyalkanoate is used as a unique film forming matter, Pickering solid particles and a natural surfactant are adopted for synergistic stabilization, and a bio-based plasticizer can be selected. The emulsion or slurry with the polyhydroxyalkanoate content of 40-85wt% and the particle size of 0.2-3m is prepared through a melting high-pressure homogenization method, a low-temperature wet grinding method or a solvent replacement method. The coating does not contain petrochemical polymer protective colloid and perfluorinated and polyfluoroalkyl substances, and the bio-based content is greater than or equal to 99%. Due to the excellent stability, rheological property and film-forming property of the modified starch, the modified starch becomes an ideal basic material for constructing a multi-layer programmable controlled release and degradation functional coating system, can be used in the fields of paper-based barrier coatings, adhesives, advanced crop seed coats and the like, realizes excellent barrier, bonding and controlled release properties, meets the industrial compost and repulping property standards, and has wide application prospects. The method has green, environment-friendly and industrial potential.

The invention discloses a crop disease diffusion prediction method and system based on multi-modal fusion, and the method comprises the following steps: S1, collecting and preprocessing an RGB image sequence and a sensor data sequence of a crop growth environment, and generating an RGB image time sequence difference result and a sensor difference result through time difference processing; s2, mapping the RGB image time sequence difference result and the sensor difference result to a shared time sequence space through a time alignment algorithm, and generating a sensor alignment result and an RGB alignment result; s3, an FD-ViT prediction model is constructed; inputting the sensor alignment result and the RGB alignment result into an FD-ViT prediction model for prediction, and generating a prediction result; and S4, generating a disease diffusion thermodynamic diagram and early warning information according to a prediction result. According to the method, RGB image data and sensor network data are fused, a Transform-based time sequence prediction model is constructed, and early recognition and diffusion trend prediction of crop diseases are realized.

The invention belongs to the field of agricultural information perception, and relates to a plant leaf scab segmentation method and system based on RGB-D cross-modal fusion, and the method comprises the steps: collecting a color image and a depth image of a crop through a synchronous collection device; registering the color image and the depth image to obtain a registered color image and a corresponding registered depth image; constructing an initial segmentation network, and performing model training on the initial segmentation network; the initial segmentation network comprises a cross attention-based feature aggregation module and an attention-guided adaptive feature fusion module; inputting the registered color image and the registered depth image into a trained segmentation network for segmentation to obtain a segmentation result; through heterogeneous data fusion of a depth sensor and a visible light camera, a multi-dimensional feature system covering two-dimensional textures and three-dimensional deformation is constructed; in combination with a cross-modal feature complementation mechanism, the recognition robustness of weakly dominant diseases and insect pests is enhanced, and the segmentation precision in a complex illumination and branch and leaf shielding scene is significantly improved.

The invention relates to the technical field of image enhancement, in particular to a field-level crop image enhancement system based on multi-source remote sensing data, and the system comprises an artifact joint detection module which analyzes the mutation or periodicity of a statistical mean value and a variance value in the row and column directions of an input field-level remote sensing image, and recognizes an artifact stripe region. According to the invention, the method achieves the high-precision removal of thin clouds and stripe artifacts through carrying out the mutability analysis of the local mean and variance of the input remote sensing image in the row and column directions, positioning a stripe artifact region, and building an attenuation numerical relationship in combination with the spectral information of an adjacent clear sky reference region, and reduces the ground feature information loss in the image. Multi-scale coefficient decomposition is further performed on the image after artifact removal, texture features are extracted from homogeneous crop canopies in adjacent undamaged areas, and high-frequency coefficients of damaged areas are dynamically replaced and reconstructed, so that the texture structures of the damaged areas are highly consistent with those of the adjacent areas, and the regional texture continuity and authenticity are improved.

The invention discloses a multi-modal agricultural question and answer method and system for generating RAG based on retrieval enhancement, and the method comprises the steps: collecting and constructing crop disease image data containing a farmland complex background and corresponding text description, and forming an agricultural image-text knowledge database; based on the agricultural image-text knowledge database, multi-modal features of an input image and a query text are extracted, image-text joint similarity retrieval is carried out, and knowledge image-text candidates are obtained; inputting the knowledge image-text candidates into an image-text rearrangement module for rearrangement; taking the reordered image-text knowledge as condition input, accessing a large language model, and generating diagnosis description and prevention and treatment suggestions for the current crop diseases; and outputting a multi-modal question and answer result according to the image and question input by the user. According to the method, the agricultural image-text database is constructed, and multi-modal retrieval, rearrangement and large language model generation technologies are combined, so that accurate and efficient crop disease multi-modal question answering is realized, and the reliability of diagnosis and prevention suggestions is improved.

The invention provides a saline-alkali soil distribution remote sensing extraction method and device based on a self-adaptive time window, which are applied to the technical field of remote sensing, and the method comprises the steps: obtaining a preprocessed time sequence remote sensing image of a target crop; extracting a farmland parcel in the time sequence remote sensing image to obtain a field parcel area; in the minimum continuous observation times of the growth cycle of the target crop, when the pixel categories of the field area are all bare soil, determining a time period between the minimum continuous observation times as a saline-alkali soil extraction window period of the field area; extracting a target time sequence remote sensing image of each saline-alkali land in the field area in a window period, and synthesizing based on a remote sensing index value of the target time sequence remote sensing image according to a weighted average method to obtain a self-adaptive bare soil image; determining a salt-alkali comprehensive index of the adaptive bare soil image based on a plurality of remote sensing indexes through a principal component analysis method; through the method, the saline-alkali soil distribution range can be accurately extracted.

The invention is suitable for the field of crop fertilization control, and provides a fertilization control method and system based on corn protective farming, and the method comprises the steps: synchronously collecting time-space multi-dimensional data of a target planting region, and constructing a multi-modal data cube; generating a seed fertilizer ratio decision vector; according to the seed-fertilizer ratio decision vector, controlling the multi-channel ratio of mechanical precision seed-fertilizer simultaneous sowing equipment, so as to realize the dynamic ratio and variable fertilization of the seed fertilizer; a multi-spectral image and soil moisture content data are collected through an unmanned aerial vehicle group, and a space-time continuous crop growth monitoring network is constructed; dynamically adjusting the topdressing amount and the water and fertilizer concentration of the unmanned aerial vehicle group based on the growth monitoring network data; according to the method, by constructing a multi-modal data cube, the dynamic proportioning and variable fertilization of seeds and fertilizers are realized, the proportioning precision is improved by utilizing fuzzy PID and machine vision, a space-time monitoring network is constructed by virtue of an unmanned aerial vehicle group, the dynamic adjustment of topdressing is realized, and a data-driven closed-loop fertilization system is formed.

The embodiment of the invention provides a multi-crop yield prediction method and device based on remote sensing collaborative inversion, and is applied to the technical field of remote sensing images. The method comprises the following steps: performing time sequence remote sensing data reconstruction processing on acquired multi-source remote sensing image data to generate a time sequence remote sensing data set; generating crop area identification data according to the time sequence remote sensing data set based on a preset multi-crop area identification model; generating agricultural condition multi-parameter inversion data in the to-be-processed region according to the time sequence remote sensing data set and the crop area identification data based on a preset multi-agricultural condition multi-parameter inversion model; and based on a preset multi-crop yield prediction model, generating crop product prediction data according to the agricultural condition multi-parameter inversion data. In conclusion, a multi-stage linkage full-process model of'time sequence remote sensing data reconstruction + crop area identification + agricultural condition parameter inversion + crop yield prediction 'can be constructed, and a high-precision, high-timeliness and automatic integrated yield prediction solution is formed.

The invention relates to the technical field of satellite remote sensing application, and discloses a crop classification method based on a multi-source satellite image, and the method comprises the steps: firstly obtaining multi-temporal satellite image data, extracting spectral reflectivity characteristics, generating a matrix, and constructing a classification model set; setting a feature parameter category set, and establishing a feature fusion correlation model based on the obtained texture, vegetation index parameters and spatial resolution data of the historical image; extracting spectrum and texture feature parameters of a crop area in the current image, and generating an optimized feature set in combination with model optimization; updating classification logic based on the optimized feature set and the classification model, generating a target classification scheme and calibrating a spatial relationship; and finally, acquiring crop growth cycle data, and establishing a time sequence feature association rule to optimize a crop type spatial distribution map. According to the method, through multi-source feature fusion and dynamic optimization, the crop classification precision and reliability are improved, and the method is suitable for a precision agricultural management scene.

The invention discloses a farmland soil humidity intelligent monitoring system based on the Internet of Things, and relates to the field of resource optimization decision crossing, a soil humidity monitoring module executes a soil humidity adjustment plan, monitors farmland soil humidity time sequence data in real time, and obtains a farmland soil humidity monitoring result through time sequence analysis and K-means clustering; obtaining an association rule between the soil humidity time sequence data and the crop yield; and the humidity monitoring report generation module is used for optimizing the soil humidity adjustment plan by tracking an optimal soil humidity threshold value in real time by utilizing a dynamic programming hybrid optimization algorithm according to the optimal soil humidity range, and generating a farmland soil humidity monitoring report. Through an optimization model coupled by a crop moisture production function and a multi-objective genetic algorithm, and in combination with Monte Carlo global sensitivity analysis, an optimal soil humidity range is identified, so that accurate quantitative modeling of a humidity-yield nonlinear relationship is realized, the defect of a static soil humidity threshold is avoided, and the sensitivity of moisture stress early warning is improved.

The invention discloses a crop growth change detection method and device based on an unmanned aerial vehicle hyperspectral image, and the method comprises the steps: collecting and preprocessing hyperspectral image data, and constructing a dual-time-sequence paired hyperspectral image data set; constructing a crop growth change detection initial model; inputting the double-time-sequence paired hyperspectral image into the crop growth change detection initial model, calculating a loss function value and executing back propagation, and obtaining a crop growth change detection model through multiple rounds of optimization; and inputting the double-time-sequence paired hyperspectral image into a crop growth change detection model, and outputting a grey-scale map reflecting crop growth change. According to the invention, based on a linear attention mechanism, modeling is carried out through a parameterized spatial position weight table, and the capability of distinguishing a crop region from a background is enhanced; and fusing multi-scale captured local space textures and enhanced global spectrum-space association in a multi-scale linear attention module to realize efficient fusion and accurate change detection of multi-temporal hyperspectral information.

The invention provides a lodging area determination method and system based on a lodging monitoring spectral index image, and relates to the field of crop form prediction.The method comprises the steps that firstly, a target farmland remote sensing image and a digital surface model are obtained, radiation and geometric correction are completed in combination with GNSS positioning data and meteorological data, and a standardized orthoimage is generated; calculating a vegetation index on the image and carrying out difference to obtain change information; executing opening and closing operation by adopting a structural element adaptive to the image resolution and the crop row spacing, filtering noise according to the area of a connected domain or a pixel number threshold value, and extracting a spectral index abnormal region and a boundary thereof; and then fusing the boundary and the digital surface model under a unified coordinate reference, accumulating the area according to the pixel resolution, and outputting the area of the abnormal region. The method has parameter self-adaption and multi-source data fusion capabilities, can stably obtain a consistent abnormal region area in a multi-resolution and complex field environment, and provides reliable technical support for agricultural condition monitoring and disaster assessment.

The embodiment of the invention provides a modern agriculture digital authentication large model, and belongs to the field of agricultural big data and artificial intelligence, an agricultural data authentication method comprises the steps that data information of a target farm is acquired, and the data information comprises crop information, farm information and production information; according to the crop information, the farm information and the production information, a block chain is constructed, and the block chain comprises a main chain, a logistics sub-chain, a quality inspection sub-chain and a production sub-chain; block chain evidence storage is carried out on the block chain to obtain an authentication certificate of each crop in the target farm, and the block chain evidence storage comprises production data evidence storage, environmental data evidence storage, management data evidence storage, processing data evidence storage and tactile data evidence storage; and performing data tracking on the crops in the target farm according to the authentication certificate. According to the method, the agricultural yield and value are accurately estimated, and the agricultural planting scheme is optimized.

The invention discloses an irrigation water demand calculation method considering fine distribution of crops, electronic equipment and a storage medium, and aims to accurately calculate the irrigation water demand and spatial distribution of the crops in a target area through a remote sensing technology, meteorological data and a soil moisture balance model. The method comprises the following steps: collecting remote sensing crop classification, weather and soil parameter data; reference crop evapotranspiration is calculated at the grid scale; configuring crop parameters; calculating root zone soil moisture change based on a water balance model; and calculating the water demand of crops and the water demand of irrigation by adopting an FAO-56 crop coefficient method. Through refined crop distribution and dynamic soil moisture simulation, high-resolution irrigation water demand distribution information is provided, and a scientific basis is provided for agricultural water resource management.

The invention belongs to the technical field of visual processing, and particularly relates to a time sequence NDVI crop distribution extraction method based on a mask auto-encoder, which mainly comprises four steps. Firstly, time sequence NDVI data are prepared, a multi-temporal remote sensing image in a complete growth cycle of target crops in a target area is obtained and processed, and the recognition precision is improved by using NDVI feature changes in the growth stage of the crops. And then performing time sequence transformation on the ViT model, dividing data space dimensions, completing Patch flattening and embedding, enabling the Patch to be adaptive to time sequence data, and simultaneously performing image processing advantages. Then, model training is carried out, a mask auto-encoder is pre-trained in a self-supervised mode through a large amount of unlabeled data, and then supervised fine tuning is carried out through a small amount of labeled data; and finally, processing new data by using the fine-tuned model, obtaining pixel-level crop category prediction, and generating a complete distribution map. According to the method, by means of time sequence data and model transformation, crop types and growth stage differences are effectively distinguished, and accurate extraction is achieved.

The invention discloses a crop disease and insect pest image recognition algorithm based on dynamic adaptive multispectral fusion Transform, and belongs to the crossing field of agricultural information technology and computer vision. The objective of the invention is to solve the problems of insufficient multi-spectral feature fusion, poor complex background adaptability and insufficient precision in traditional recognition. Acquiring pest and disease damage images of crops in different wave bands (visible light, near-infrared light and the like) to construct a data set; through a dynamic adaptive fusion module, spectral weight distribution is learned in real time based on an attention mechanism, weights are adjusted according to spectral response differences of disease and insect pest areas, and accurate feature aggregation is achieved; the fusion features are input into an improved Transform model, a self-attention mechanism of crop semantic priori knowledge is introduced, focusing of key features of diseases and insect pests is enhanced, and background interference is inhibited; and finally outputting the disease and pest category and confidence. According to the method, through dynamic fusion and Transform cooperation, the recognition accuracy and robustness in a complex scene are improved, support is provided for early warning and prevention of diseases and insect pests, and the application value is remarkable.

The invention discloses a soil improvement measure decision-making method and system based on multi-modal deep learning. According to the method, firstly, soil state parameter change data and crop growth data of a target planting site are acquired, and a preliminary soil improvement scheme is established by combining the two data; then, a multi-modal deep learning network model is constructed, climate change characteristics and soil conditioner content change characteristics after improvement measures are implemented are fused and analyzed, and data characteristics of influences of climate changes on the conditioner are extracted; and based on the influence data, further identifying the failure characteristics of the modifier, including the failure propagation path and the dose change characteristics of the modifier. And finally, performing dynamic compensation on the original soil improvement measures according to the failure characteristics to form a refined compensation scheme. According to the method, intelligent adjustment and dynamic optimization of the soil improvement strategy can be realized, and the method has relatively high agricultural application value and popularization prospect.

The invention discloses an unmanned aerial vehicle multi-scale crop detection method based on a neurodynamics model, and belongs to the technical field of crop detection, and the method comprises the steps: obtaining a visible light image, a long-wave infrared image and hyperspectral data of a crop under the multi-scale condition of an unmanned aerial vehicle; performing registration fusion processing on the visible light image, the long-wave infrared image and the hyperspectral data to obtain fused hyperspectral cube data; constructing a neurodynamic model for crop detection, inputting the fused hyperspectral cube data into the neurodynamic model for crop detection for training, and outputting a crop detection result; and calculating a loss function of the neurodynamic model for crop detection based on a crop detection result, and feeding back the loss function to the model for constraint. According to the invention, visual processing, deep learning and agricultural scene perception technologies are combined, and efficient and accurate crop monitoring is realized by using the parallel computing capability and anti-interference characteristics of the neurodynamics model.