559 results about "Agricultural information" patented technology

The invention relates to the technical field of agricultural information perception and decision making, in particular to a multi-source perception fused agricultural monitoring method and system. The method comprises the following steps: converting a multi-source heterogeneous agricultural sensing signal into a space-time tensor, constructing a semantic resonance field to simulate nonlinear coupling between modals, and driving multi-modal data to adaptively aggregate by using a gravitational evolution mechanism to form a fused semantic field; calculating non-linear response to generate an agricultural state emergence index, and according to the index, identifying a potential risk area and constructing a binary risk map; for the risk area, semantic disturbance is mapped into an agricultural variable disturbance vector through a modal decoupling matrix, a minimum intervention strategy is generated in combination with sparse optimization of an operation response matrix, and feasible operation suggestions are output after verification of an agricultural knowledge graph; a drift potential energy function is constructed based on strategy execution feedback, strategy parameters are dynamically updated through gradient descent, and closed-loop self-evolution optimization is achieved in combination with trend prediction. According to the invention, full-link adaptive optimization from multi-source sensing to regulation and control decision is realized.

The invention discloses a close planting farmland growth vigor assessment method and system based on image processing, and relates to the field of agricultural information, and the method comprises the following steps: S1, multi-source data collection and preprocessing; s2, improving image segmentation, and extracting crop features; and S3, multi-dimensional growth vigor evaluation. According to the method, the field block level, the plant level and the whole growth period are covered through multi-source data collection, a generative adversarial network is used for repairing and shielding the plant image and restoring complete form information, the segmentation problem in a close planting scene is solved, the accuracy of close planting crop image analysis is improved, accurate registration of multi-modal data is achieved by means of feature point matching, and the accuracy of close planting crop image analysis is improved. The graph neural network optimizes image segmentation, effectively distinguishes overlapped leaves and stalks, deeply fuses multi-modal features and dynamically selects a fusion strategy, improves feature distinguishability, constructs a dynamic adaptive evaluation model, improves generalization ability and evaluation precision, identifies and intervenes abnormities in real time, and improves crop anti-risk ability and yield prediction accuracy.

The present invention relates to the technical field of agricultural information, and specifically to a plant factory information automatic acquisition method and system based on unmanned aerial vehicle machine vision. The method comprises the following steps: using a camera mounted on an unmanned aerial vehicle to capture an image, and using a deep learning and image segmentation technology to generate a plant region segmentation image. According to the present invention, the unmanned aerial vehicle is used to carry the camera to capture a plant image, and efficient and accurate plant region segmentation is realized by using the deep learning technology. A plant health assessment report is generated by means of a computer vision technology, and a health problem is early warned. A plant health analysis report comprehensively considering environmental factors is generated on the basis of ground sensor data and time series analysis, and comprehensive and accurate health assessment is provided. A multi-dimensional plant health monitoring model provides support for all-round health monitoring. A plant disease nutrition analysis report is generated on the basis of a machine learning classification algorithm, a problem is accurately recognized, and a fertilization and pesticide-spraying strategy is formulated on the basis of a decision support system, thereby optimizing resource utilization, and improving the yield and quality.

The invention discloses a farmland soil quality dynamic diagnosis method based on multi-source remote sensing collaborative inversion, and relates to the technical field of agricultural information, and the method comprises the steps: collecting physical and chemical parameters of soil temperature, humidity, pH value, organic matter content, nitrogen phosphorus and potassium concentration and the like in real time through a multi-source sensor network; removing abnormal values by using a data preprocessing algorithm, performing standardization processing, generating a standardized soil parameter set for subsequent climate and management factor correlation analysis, automatically generating a risk early warning signal, pushing the risk early warning signal to an agricultural management decision platform, and completing full-process analysis from data acquisition to decision support; the farmland soil quality dynamic diagnosis method based on multi-source remote sensing collaborative inversion can provide a scientific basis for agricultural management decision, effectively guide farmland management practice, and improve soil quality and agricultural production efficiency.

The invention relates to the technical field of agricultural information management, and particularly discloses an agricultural information management system and method based on a big data platform, and the method comprises the steps: firstly deploying a multi-source data collection module at an edge calculation node, and obtaining and standardizing the soil moisture content, meteorological environment and equipment operation data in real time; secondly, constructing a local dynamic irrigation strategy model, and realizing multi-objective optimization through a reinforcement learning algorithm; establishing a federated learning framework at the cloud, dynamically distributing node weights by adopting an attention mechanism, and realizing model aggregation of privacy protection in combination with secure multi-party computing; an optimal irrigation instruction is generated through a multi-source data fusion engine, and a three-level response exception handling mechanism is established; and finally, a closed-loop feedback system containing short-term incremental learning and long-term architecture optimization is formed. The corresponding management system comprises six functional modules, namely a data acquisition module, a local modeling module, a federated learning module, a real-time decision-making module, an abnormal monitoring module and a closed-loop optimization module.

The invention discloses a crop growth prediction system and method based on an agricultural unmanned aerial vehicle remote sensing technology, and relates to the technical field of agricultural information and intelligent monitoring, the system uses an unmanned aerial vehicle remote sensing module and a ground Internet of Things sensor module to collect multi-source data of banana planting, fish pond breeding and hog house breeding, and the multi-source data is used as a data expression recording carrier. The edge computing node module preprocesses data, and the cloud intelligent platform module is internally provided with a multi-modal data fusion model, a growth prediction model and the like as processing record carriers to realize data depth analysis and prediction. And realizing automatic control of the production process according to the data through block chain evidence storage and the intelligent contract. And constructing a disease prevention and control model by using the hyperspectral image of the unmanned aerial vehicle and related data. According to the invention, the collection, processing and application capabilities of agricultural production data are improved, accurate prediction and intelligent regulation are realized, the resource utilization efficiency is improved, the disease loss is reduced, and the agricultural intelligent development is promoted.

The invention discloses a remote sensing image cultivated land segmentation method and system fusing context and boundary perception, and belongs to the technical field of remote sensing image processing and agricultural information. Constructing a cultivated land segmentation initial model composed of a backbone network, a feature enhancement module, a multi-scale feature fusion de-wharf module and a mask prediction module; training set data are input into the initial model, a composite loss function value is calculated, back propagation is executed, and a cultivated land segmentation model with boundary sensing ability is obtained through multi-round iterative optimization; and inputting the remote sensing image into the trained cultivated land segmentation model, and outputting a binary segmentation image representing the cultivated land position. Visual state space modeling and large receptive field convolution are combined, deep and shallow layer information is fused through feature injection, boundary perception supervision and composite loss are introduced, cultivated land boundary discrimination is improved, remote sensing image cultivated land high-precision extraction is achieved, and the method is suitable for agricultural interpretation and monitoring.

The invention relates to the field of agricultural information processing and artificial intelligence, in particular to a farmland yield prediction method and system based on a heterogeneous graph neural network, and the method comprises the steps: obtaining multi-source farmland data, and extracting an initial feature vector of a farmland plot node; on the basis of the initial feature vector, constructing a heterogeneous graph structure containing multiple semantic relationships; performing node feature updating on the heterogeneous graph structure by using a heterogeneous graph neural network, and dynamically aggregating information of multiple types of neighbor nodes through relation-aware message passing and an edge propagation gating mechanism; performing enhancement processing on the node features by using a space-time dependency enhancement mechanism and a knowledge-guided reasoning mechanism; and outputting a regression prediction result of the farmland yield through a prediction module based on the enhanced node features. The invention aims to realize modeling and intelligent yield prediction based on multi-source heterogeneous data in an agricultural system, and improve the environmental adaptability, prediction generalization ability and interpretability of farmland yield prediction.

The invention relates to the technical field of agricultural information fusion, in particular to an agricultural multi-source information fusion method and system and a storage medium. The method comprises the following steps: collecting and fusing multi-source agricultural data, generating a three-dimensional reconstruction agricultural model, then analyzing a cross-layer coupling structure of the model, obtaining a ground-air segmentation agricultural model, deriving a regional supply-demand relationship, analyzing and compensating nutrient demands based on growth demand parameters, mapping a fertilization prescription, generating a fertilization prescription map, and finally obtaining a fertilization result. And performing supply development simulation by utilizing the fertilization prescription map to obtain a simulated supply response model, determining irrigation opportunity according to the simulated supply response model, generating an irrigation prescription map, interactively integrating the fertilization prescription map and the irrigation prescription map, and generating agricultural fusion feedback information. According to the invention, a more accurate and more reliable agriculture-oriented multi-source information fusion method is realized.

The invention relates to the technical field of agricultural information, and discloses a visual analysis method and system based on an agricultural big data model. According to the system, crop growth time sequence data are processed by using a multi-scale feature extraction algorithm combining a recurrent neural network and wavelet transform, and key conversion points of a crop growth stage are automatically identified by using a deep learning architecture combining a variational auto-encoder and a hidden Markov model. A standard growth track model and a multi-dimensional deviation measurement index are constructed to evaluate the abnormal growth condition of crops, a dynamic threshold model based on reinforcement learning is applied to realize early warning of abnormal growth, and a multi-dimensional visual interface based on a clock metaphor is designed to visually display crop growth information. The crop growth stage recognition precision and early warning timeliness are improved, and the agricultural production management efficiency is remarkably enhanced.

The invention relates to the technical field of agricultural information, discloses a corn precise topdressing prescription map generation method based on unmanned aerial vehicle multispectral remote sensing, and effectively solves the key problems of insufficient monitoring precision, poor environmental adaptability, low decision intelligent level and the like in the traditional fertilization technology. Through the unmanned aerial vehicle multispectral imaging technology, efficient and accurate monitoring of the corn nitrogen nutrition condition is achieved; in combination with a machine learning algorithm, an intelligent fertilization decision model adapted to different environmental conditions is established, and the fertilization precision in a complex farmland scene is remarkably improved; and a multi-source data fusion technology is adopted, and crop growth, soil characteristics and meteorological factors are comprehensively considered, so that the fertilization scheme is more scientific and reasonable. Compared with a traditional method, the method has the advantages that accurate variable fertilization can be realized according to actual needs of crops, the utilization rate of the fertilizer is increased, environmental pollution is reduced, and reliable technical support is provided for sustainable development of modern agriculture.

The invention discloses a garlic disease and insect pest dynamic diagnosis system based on temperature and humidity time sequence data, relates to the technical field of agricultural information processing, and solves the problems that in the prior art, a fixed parameter model is prone to sensitivity sudden drop, false alarm sudden increase and systematic deviation under sudden or semi-sudden changes of field environment and management variables. According to the scheme, semantic processing of temperature and humidity and farming events is carried out through an acquisition module, a system coupling module carries out segmented identification on distribution mutation caused by environment and operation, a domain representation module constructs causal threatening features, a prediction calibration module carries out dual-path drift decomposition and rapid correction, and a prediction result is obtained. The sample adding and label collecting module generates anti-fact samples and actively collects labels, and the decision attribution module outputs a structured evidence chain; according to the method, the dynamic adaptive capacity and reliability of the diagnosis system under the conditions of non-stationary distribution and concept drift are remarkably improved.

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 information, in particular to an intelligent agricultural information big data intelligent acquisition management system and method. The method comprises the following steps: acquiring farm sensing data, and performing crop growth analysis according to the farm sensing data so as to obtain crop growth data; performing crop health state feature extraction and crop physiological feature extraction according to the crop growth data so as to obtain crop health state data and crop physiological data; performing disease and pest detection according to the crop health state data and the crop physiological data to obtain crop disease and pest data; the method comprises the following steps: acquiring farm remote sensing data, performing crop multispectral analysis according to the farm remote sensing data so as to obtain crop multispectral data, and performing crop moisture state evaluation according to the crop multispectral data so as to obtain crop moisture state data. The pesticide spraying strategy is optimized based on the information technology, and the agricultural production management efficiency is improved.

The invention discloses a traditional Chinese medicinal material standard base intelligent irrigation and fertilization method based on the Internet of Things and a decision making system, and relates to the technical field of agricultural informatization. Through multi-source data acquisition and intelligent analysis, the limitation of an existing irrigation and fertilization method is solved, accurate decision making and resource optimization are realized, comprehensive data are acquired by utilizing a soil moisture content sensor, a meteorological station and plant image acquisition equipment, and by combining principal component analysis, a long-short-term memory neural network and a block chain technology, the intelligent irrigation and fertilization method is realized. According to the system, the water and fertilizer requirements are accurately predicted, an irrigation and fertilization scheme is optimized, data credibility and traceability are ensured, meanwhile, real-time control and collaborative operation of equipment are achieved through edge calculation and a wireless sensor network, the resource utilization efficiency is improved, the production cost is reduced, and scientificity and sustainability of traditional Chinese medicine planting are remarkably improved.

The invention belongs to the technical field of farmland tail water pollution load analysis and evaluation, particularly relates to a farmland tail water pollution load analysis and evaluation method, and aims to overcome the obvious defects of an existing monitoring and evaluation method in the aspects of monitoring point layout, index coverage, data processing, analysis depth and the like. In order to solve the problems that farmland tail water pollution load analysis and evaluation cannot meet accurate and dynamic farmland tail water pollution load analysis and evaluation requirements and pollution prevention and control decisions are difficult to effectively support in the prior art, the invention provides the following scheme: the method comprises the following steps: S1, carrying out multi-source acquisition on farmland information data, and carrying out fusion processing; s2, setting a fixed sampling unit and a movable sampling unit according to farmland information setting; according to the method, multi-source data such as farmland basic information, agricultural production activity data, meteorological data and water quality monitoring data are comprehensively considered, and comprehensive and accurate quantification and evaluation of farmland tail water pollution load are realized through a data preprocessing and fusion technology.

The invention relates to the technical field of agricultural information, in particular to a tobacco agriculture standard named entity recognition method and system based on a hybrid neural network, and the method comprises the steps: carrying out the embedded representation of an input tobacco agriculture standard text through a BERT pre-training language model, and generating a word vector sequence containing global semantic information; performing local feature extraction on the word vector sequence by using an iterative expansion convolutional neural network to obtain a local feature vector; splicing the global semantic information and the local feature vectors, and inputting the spliced global semantic information and local feature vectors into a bidirectional long-short-term memory network for context feature extraction to generate context enhancement features; weight optimization is carried out on the context enhancement features through a multi-head attention mechanism, and key semantic features are highlighted; and performing label prediction on the optimized feature sequence by adopting a conditional random field decoder, and outputting a standard article element entity identification result. According to the method, high-precision and high-robustness named entity recognition is realized, and the method is particularly suitable for complex semantic and low-resource field scenes.

The invention discloses an intelligent wheat yield prediction method and system, and relates to the technical field of agricultural information. According to the method, basic geography, climate, soil, crop physiology and agricultural management multi-source data are collected, and an input feature set is obtained through preprocessing and feature engineering; constructing an Attention-LSTM-CNN model fused with an improved attention mechanism, extracting local features through CNN, capturing time sequence association through LSTM, highlighting key contribution through an attention layer, and finishing model training in combination with an RMSE loss function and an Adam optimizer; and dynamically updating data and a prediction result in a wheat growth cycle, and outputting and triggering early warning in multiple forms. The system correspondingly comprises a data acquisition module, a data storage module, a data preprocessing module, a model calculation module, a prediction output and early warning module and a communication module. The method solves the problems that a traditional method is single in data, poor in model adaptability and lack of dynamic prediction, high-precision full-period prediction is achieved, and scientific support is provided for agricultural decision making.

The invention belongs to the technical field of remote sensing image intelligent processing and agricultural information extraction, and particularly relates to a remote sensing large model pre-training and multi-granularity boundary supervision natural field type extraction method, which comprises the following steps: firstly, pre-training a model on a large-scale space-time spectrum remote sensing data set, and combining anchor point sensing mask and geographic information coding; secondly, inputting the multi-scale features into a multi-branch structure sensing network, and outputting a semantic segmentation prediction map through high and low resolution double input and dynamic attention fusion; generating a multi-scale field boundary label through morphological operation, and outputting a boundary prediction map through multi-task supervision after domain enhancement of features by a frequency space double-domain enhancement module; and finally, aligning the two images and performing pixel-level operation to obtain a high-precision extraction result. Through the method, the global classification error during cross-region migration is greatly reduced, the method is adaptive to a low-pixel wide ridge, the boundary detection value and the closure rate of a small-scale field are improved, and the extraction precision of a large field and a small field is considered.

The invention belongs to the technical field of agricultural information, and discloses a rape variety environmental adaptability evaluation system based on machine learning. The system is composed of a data acquisition standardization unit, a regional environment feature modeling unit, a variety phenotype and pedigree association unit, a feature screening and model training unit, a regional adaptability scoring and decision-making unit, a dynamic learning and evolution updating unit and an evaluation visualization and variety recommendation unit. By performing standardization processing on multi-source data, format and dimension differences are eliminated, and a high-quality data foundation is laid for subsequent analysis. Fusing environment and variety bilateral characteristics, and enabling the model to capture environment influence and variety heredity characteristics at the same time. Advanced methods such as ensemble learning and a time sequence neural network are adopted, and the complex relation is accurately mined. Compared with a traditional field test and the prior art, errors are greatly reduced, the adaptation degree of the variety in different areas is more accurately judged, a scientific basis is provided for planting recommendation, and the yield and quality of the oilseed rape are improved.

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 relates to the technical field of intelligent agricultural information processing, and provides a crop variety suitable planting area recommendation method and device based on deep reinforcement learning, and the method comprises the steps: obtaining crop variety features, environment data of candidate planting areas, and a pre-trained crop variety suitable planting area recommendation model; the recommendation model is trained through the following mode: training a pre-constructed intelligent agent based on variety planting data in different environments and environment data of planting sites and non-planting sites, and obtaining a trained deep reinforcement learning model. And adjusting the trained deep reinforcement learning model based on the variety promotion condition data to obtain a crop variety suitable planting area recommendation model. The recommendation model can accurately match the crop variety and the planting environment according to the input crop variety characteristics and the environment data of the candidate planting area, and accurate recommendation of the crop variety suitable planting area is realized.

The invention discloses a sensor-based agricultural information data acquisition system and method, and belongs to the technical field of agricultural information acquisition. Multi-type sensor nodes are arranged in an agricultural target area in a heterogeneous manner; the method comprises the following steps: constructing a multi-dimensional influence factor model according to crop growth stages and environmental historical fluctuation data, dividing initial sensing sub-regions, and configuring a sensor cluster; dynamically updating the sensing boundary based on the historical change rate and the spatial gradient information; fusing the heterogeneous data by adopting a multi-channel time synchronization mechanism to generate a standardized environment vector set W; calculating a sampling priority matrix according to a parameter change trend in the W, and adaptively adjusting a node state; integrating an energy consumption estimation model, and executing low-power-consumption scheduling; when any parameter exceeds the threshold, high-density sampling and remote early warning are triggered; according to the method, high-precision, low-power-consumption and dynamic-response data acquisition and intelligent early warning can be realized, and the efficiency and reliability of an agricultural sensing system are improved.

The invention discloses a method and a system for predicting diseases and insect pests of saline-alkaline tolerant rice based on artificial intelligence. The method comprises the steps of collecting rice data, optimizing the rice data, establishing a prediction model for the diseases and insect pests of the saline-alkaline tolerant rice and predicting the diseases and insect pests of the saline-alkaline tolerant rice. The invention belongs to the technical field of agricultural information, and particularly relates to a method and a system for predicting diseases and insect pests of saline-alkali tolerant rice based on artificial intelligence. According to the scheme, rhombic plot segmentation is dynamically adjusted according to the irregular terrain and the saline-alkali accumulation area boundary of the saline-alkali tolerant rice field, and the collaborative weight is calculated based on the saline-alkali stress degree and the disease and insect pest risk level; key region learning is enhanced in combination with a plot total score and a selection probability formula; a plot score, a neighborhood pest and disease density mean value and a neighborhood saline-alkaline gradient are introduced into a spatial branch, so that the capturing capability of spatial correlation is improved; on the basis of the dynamic adjustment tolerance threshold, the influence of the extreme value is limited through the loss upper limit coefficient, a pest and disease prediction error regulation and control function is constructed, and the pest and disease prediction accuracy is improved.

The invention discloses an agricultural knowledge graph construction and retrieval method, and relates to the field of knowledge graph technology, information retrieval technology and agricultural information technology. The method aims to cope with data fragmentation and isomerism challenges in agricultural informatization. The method comprises the following steps: firstly, collecting agricultural text data from multiple channels, performing data preprocessing by using SpaCy, and then developing a specific algorithm to integrate multi-source data; and data features in the agricultural field are optimized by training an adaptive deep learning model, and a large-scale corpus is adopted for fine tuning of the pre-training model, so that the accuracy and generalization ability of the pre-training model are improved. In order to construct a detailed agricultural field ontology, entities, attributes and relationships are automatically extracted and fused, and real-time monitoring and updating of data are realized in combination with a crawler technology; user query is analyzed and converted into formalized expression, complex logic operation is executed by means of an inference engine, and visual answers and natural dialogue experience are provided. And finally, in combination with real-time data, historical experience and expert knowledge, accurate decision suggestions are generated, and the agricultural field is accurately served.

The invention relates to the technical field of agricultural informatization and intelligent decision making, and discloses a vegetable growth cycle pest control decision making system and method based on a knowledge graph. According to the method, an unstructured agricultural data stream including vegetable varieties, growth stages, environmental parameters, pest and disease records and geographic information is collected from an original database. A data tuple set with a time stamp is generated by performing scanning identification and content extraction on a data stream. Then, clustering is carried out according to the growth stages to which the tuples belong, and stage feature clusters sorted according to the growth cycle are formed; and performing multi-dimensional feature correlation analysis on the stage feature cluster, and establishing a dynamic coupling relationship among the environmental parameters, the disease and pest history and the geographic space features under the growth cycle dimension. And based on the dynamic coupling relationship, generating disease and pest control decision parameters of the vegetables in the specific planting area in each growth cycle stage. According to the invention, accurate matching between the control decision and the crop physiological time sequence and regional characteristics is realized.

The invention discloses a smart agricultural information management method based on the satellite Internet of Things, and the method comprises the steps: obtaining original farmland data, extracting temporal-spatial resolution and updating frequency parameters, and then generating farmland macroscopic data with high temporal-spatial resolution through employing a temporal-spatial interpolation algorithm; based on a data fusion algorithm, integrating the multi-source data obtained by the Internet of Things sensor to obtain local farmland environment parameters; performing data alignment on the farmland macroscopic data and the local farmland environment data, and establishing a farmland information data set; constructing an environment change prediction model based on machine learning, and training the environment change prediction model based on the farmland information data set; outputting a farmland environment change prediction result based on the trained environment change prediction model; and generating a farmland management suggestion based on a farmland environment change prediction result, and adjusting irrigation and fertilization strategies. According to the invention, intelligent monitoring, accurate prediction and dynamic management of the farmland environment are realized, and the agricultural production efficiency and the resource utilization rate are effectively improved.

The invention discloses a field-ditch-pond extraction method based on unmanned aerial vehicle photogrammetry and deep learning, and belongs to the technical field of remote sensing technology and agricultural informationization, and the method comprises the steps: employing an unmanned aerial vehicle to carry a multispectral camera and an optical lens, and obtaining original image data through an oblique photogrammetry technology; preprocessing the obtained original image data to generate a multispectral image map (DOM) and a digital surface model (DSM); starting from the spectrum, terrain and texture features of a small watershed field-ditch-pond system, a U-net algorithm with a built-in attention mechanism, an image segmentation model supporting zero sample learning, a multi-scale segmentation technology and a multiple extraction framework of a shape feature extraction algorithm are constructed, image segmentation, classification and interpretation are carried out, and a multi-scale image segmentation model is constructed. Fine extraction of the small watershed field-ditch-pond system is realized; the design can improve the extraction precision and efficiency under complex terrains, and is suitable for current small watershed agricultural non-point source pollution migration trajectory simulation and farmland fine management.

The invention discloses a construction method of a soil microorganism nitrogen metabolism function prediction model, and relates to the technical field of environmental microbiology and agricultural information, and the method comprises the following steps: S1, constructing a spatial-temporal heterogeneity representation engine, and dynamically decoupling a multi-level gradient of a soil environment through an adaptive spatial-temporal mesh generation algorithm; according to the construction method of the soil microorganism nitrogen metabolism function prediction model, the adaptive capacity of the soil microorganism nitrogen metabolism function prediction model in a complex environment is improved, and multi-level environment gradient dynamic analysis from a centimeter-level rhizosphere microdomain to a kilometer-level landscape scale is realized; the problem of cross-scale feature fusion caused by temporal-spatial resolution mismatch of a traditional model is solved, the simplified hypothesis of a traditional statistical model on the synergistic-antagonistic relationship of microbial functional genes is broken through, a dynamic coupling mechanism of a nitrogen metabolism path under environmental disturbance is accurately quantified, and the prediction error is reduced compared with the prior art.

The invention provides a crop growth prediction method and system based on multi-modal data, and relates to the technical field of agricultural information, and the method comprises the steps: 1, collecting real-time environment data and crop physiological data of a heterogeneous multi-source sensor in a greenhouse environment, and constructing a multi-modal original data set; 2, performing preprocessing and space-time alignment on the multi-modal original data set to form a multi-modal data fusion matrix with a unified timestamp; step 3, based on the multi-modal data fusion matrix, selecting a reference data feature set, generating an environmental evolution mode and a physiological evolution mode, and calculating a correlation degree between the two modes to determine a feature response dimension; and respectively selecting dynamic monitoring feature sets inside and outside the feature response dimension, constructing a feature evolution trajectory according to a time sequence evolution relationship, and generating a dynamic compensation coefficient. By integrating environment and crop physiology multi-source data, the association rule of crop growth and environment is predicted, and the agricultural production efficiency is improved.