33 results about "Crop phenology" patented technology

The invention relates to the technical field of agricultural remote sensing and cultivated land monitoring, in particular to an accurate cultivated land identification method integrating multi-source remote sensing and phenological response, which comprises the following steps: S100, data acquisition: acquiring time sequence data of multi-source remote sensing in a research area; s200, the phenological period of the crops is extracted; s300, generating a training sample: based on phenological information, obtaining a positive sample by taking an adaptive flowering index as a threshold value; generating a negative sample by adopting a reverse rule of the positive sample rule, and purifying to generate a sample group; s400, feature fusion and optimization: evaluating the category separability of different time phase feature sets by adopting a J-M distance method; s500, classifier evidence fusion: using a D-S synthesis rule to realize classification result fusion; and S600, applications are migrated annually. According to the method, the multi-source remote sensing data are fused, the sample automatic generation strategy is constructed in combination with the phenological period characteristics of the crops, the evidence theory is introduced to fuse the results of the multiple classifiers, and high-resolution and high-stability accurate recognition of the cultivated land in the complex terrain and cloudy and rainy environment is achieved.

The invention provides a soil moisture content remote monitoring system and method based on big data, and relates to the technical field of soil moisture content monitoring. Multi-temporal remote sensing images are used for recognizing the phenological stage of crops, collecting meteorological data and measuring soil parameters; calculating the reference water vapor evaporation capacity of the crops based on the meteorological data and the soil parameters, and calculating the actual water vapor evaporation capacity of the crops based on the phenological stage; calculating a soil heat flux value according to the atmospheric stability and the flow resistance coefficient; constructing an entropy balance equation based on the soil heat flux value, and calculating the soil entropy variation; and predicting the soil entropy based on the soil entropy variation, and classifying the soil moisture content.

The embodiment of the invention provides a dynamic space-time weighted agricultural value prediction method, and belongs to the field of agricultural big data and artificial intelligence, and the method comprises the steps: obtaining the data information of crops in a target farm; performing gating mechanism capture on the historical yield, the meteorological factors and the crop phenological period data through a three-layer bidirectional LSTM network to obtain growth period time sequence characteristics of crops in the target farm; performing semantic analysis on the market information to obtain crop price influence characteristics; constructing a double-layer LSTM-Attention network architecture according to the time sequence characteristics of the growth period and the crop price influence characteristics; determining a GIS three-level value grid architecture according to geographic factors, logistics influences, transportation conditions and supply-demand relationships; and constructing an agricultural value prediction model according to the double-layer LSTM-Attention network architecture and the GIS three-level value grid architecture. According to the method, cost reduction and efficiency improvement of agriculture are realized through the agricultural value prediction model, and an agricultural planting scheme is optimized.

The invention relates to a crop phenology monitoring method, system and device based on continuous accumulated temperature driving and a medium. The method comprises the following steps: acquiring optical remote sensing data of crops, and calculating to obtain annual vegetation index time series data; obtaining annual hour-level temperature monitoring data, constructing and obtaining an annual temperature model based on the annual hour-level temperature monitoring data, and calculating and obtaining annual effective accumulated temperature time sequence data based on the annual temperature model in combination with the growth base point temperature; constructing a phenology monitoring reference shape model based on the vegetation index time series data of each reference year and the effective accumulated temperature time series data of each reference year, and setting a standard phenology period; and based on the target annual vegetation index time series data and the target annual effective accumulated temperature time series data, constructing a target phenology monitoring effective accumulated temperature model, and combining a standard phenology period to generate a target annual phenology monitoring result. By adopting the method, the daily effective accumulated temperature can be calculated more accurately, and the estimation error of the phenological period is reduced.

The present invention discloses an AI-powered crop phenological period recognition system, comprising a memory, a timing device, an image data acquisition device, an image data processing device, a crop phenological period analysis module, a crop yield prediction module, and an output module. The memory is used to store trained crop recognition models and crop yield prediction models. The crop recognition model inputs image data and outputs crop phenological periods. The crop yield prediction model inputs image data and outputs predicted yields. The image data processing device processes image data obtained by the image data acquisition device and extracts and outputs image data with significant differences between the two images before and after the output. The present invention addresses the technical issues of low phenological period recognition accuracy, insufficient precision in phenological period recognition, and the inability to accurately predict yields.

The invention provides an agricultural drought risk assessment method based on machine learning, and relates to the technical field of agricultural big data. Comprising the steps of performing time sequence segmentation on multi-source monitoring data based on a crop phenological period standard, and constructing a time-space coupling data set; determining a moisture sensitivity coefficient by utilizing development key nodes and a physiological water demand threshold value, generating a dynamic attention weight matrix, and extracting a comprehensive drought feature vector set through a long short-term memory network; and then, constructing a nonlinear vulnerability fitting curve of the yield response mapping space by adopting a support vector regression algorithm, and constructing a reinforcement learning simulation environment according to the nonlinear vulnerability fitting curve. And constructing a state space vector, performing iterative optimization training of a water resource allocation action in a simulated environment by using a deep Q network algorithm to obtain an optimal risk management and control strategy network, and outputting an agricultural drought risk assessment result and a water resource allocation instruction. According to the invention, accurate quantification of drought risks and global dynamic optimal configuration of water resources are realized.

The application discloses a kind of crop phenophase satellite remote sensing monitoring methods, utilize Sentinel-2 satellite remote sensing data, calculate crop from sowing to harvest period positive NDVI time series data and positive NDVI peak value, reverse NDVI time series data and reverse NDVI peak value;Set positive reverse NDVI difference threshold;In threshold range, take the time point corresponding to the maximum NDVI value as final NDVI peak point;At final NDVI peak point, positive, reverse NDVI time series data are spliced and segmented, and are reconstructed into continuous NDVI time series data;Using S-G filter smoothing, using Logistic function fitting, combine curve curvature method and dynamic threshold method to extract the key phenophase of crop.The application is characterized in that the improved maximum synthesis method is used, and the NDVI data is smoothed by combining S-G filtering, which greatly improves the accuracy of crop phenophase monitoring in the process of remote sensing detection, cloud, atmospheric interference and vegetation coverage change.

The invention discloses an environment dynamic self-adaptive control method and system based on phenology driving and a storage medium, and belongs to the technical field of greenhouse environment intelligent control. The method comprises the following steps: firstly completing system initialization and control mode selection, then collecting environmental parameters through multiple sensors, calculating effective accumulated temperature GDD on line, accurately identifying a growth stage of a target crop based on a GDD value in combination with a lag tolerance mechanism, and matching a corresponding staged environmental control target; and then dynamically adjusting an environment control threshold value according to the GDD deviation, driving an execution mechanism by adopting a division lag control strategy for temperature, humidity and illumination, and meanwhile, realizing real-time dynamic matching of greenhouse environment parameters and physiological requirements of different growth stages of target crops by being compatible with an automatic control mode and a manual control mode, and performing cyclic execution to realize real-time dynamic matching of the greenhouse environment parameters and the physiological requirements of different growth stages of the target crops. According to the invention, crop phenology information is brought into regulation and control decision, and the problems of low matching degree and poor stability of traditional fixed threshold control are solved.

The application discloses a crop phenological season detection method based on stationary satellite data and belongs to the technical field of remote sensing monitoring. The method comprises the following steps: determining a research area range and a time interval, acquiring Himawari-8 AHI data, and obtaining a limited VI time sequence through band calculation; performing cloud identification on the AHI limited VI time sequence through a fast cloud detection method to obtain an AHI cloud-removed VI time sequence; performing data synthesis on the AHI cloud-removed VI time sequence through an n-day data 90th percentile synthesis method to generate an AHI n-day VI time sequence, and then smoothing the VI time sequence by using an SG filter; and performing phenological season detection on the smoothed AHI n-day VI time sequence by using an improved SMF-S method. The method can ensure the accuracy of the season detection, greatly reduce the data quantity of the early-stage processing, and is superior to the season detection accuracy of polar-orbit satellite MODIS data with the same spatial resolution.

The invention discloses a crop classification method of a self-adaptive SAM and ConvxLSTM mixed model, and relates to the technical field of remote sensing image processing, and the method comprises the steps: constructing a time sequence data set facing a crop phenological calendar, and screening an optimal classification time phase wave band combination through filtering and J-M distance; unmarked samples are generated according to the optimal classification time phase wave band combination, and crop pseudo labels with category labels are generated based on an adaptive SAM model; and performing crop classification based on the ConvxLSTM network processing time sequence data set, and outputting a crop classification result. According to the method, the crop category labeling can be provided for the pseudo labels while the high-quality crop pseudo labels are automatically obtained, the excessive dependence of the model on manual sample labeling can be greatly reduced, the spatial-temporal characteristics of the data are more effectively mined, and the crop classification precision is improved.

The present application provides a kind of corn phenology remote sensing monitoring method based on NIRv and crop progress report. Including: utilize remote sensing data to construct NIRv time curve;Combining public crop progress report and cultivated land use data to construct corn growth model;Utilize last year data to calibrate phenology parameter and growth model to obtain shape model;Optimize traditional SMF method, fit shape model and each year vegetation index time curve, calculate optimal parameter, monitor five main phenological stages of corn;Obtain pixel-level corn phenology monitoring information and carry out regional phenology mapping, quantitatively evaluate regional phenology.The present application solves the modeling problem that crop phenological stage can be accurately estimated without relying on long-term ground observation data, expands the application range of shape model fitting in phenology monitoring, evaluates the phenology monitoring ability of NIRv index, and is suitable for larger area research.Further improve the precision of crop phenology remote sensing monitoring, assist government and farmer to accurately carry out crop scientific management.

The invention belongs to the technical field of crop phenology identification, and particularly relates to a phenology identification method and system based on supervised standardized learning processing, and a medium. The method comprises the following steps: acquiring multi-modal original data of crops needing phenological recognition; inputting the multi-modal original data into a pre-trained phenology identification model to obtain a phenology identification result; the phenology identification model comprises a standardization unit, a feature extraction unit and a classification output unit; the standardization unit is used for carrying out standardization processing on the multi-modal original data through learnable mapping transformation; the feature extraction unit is used for performing feature extraction on the data output by the standardization layer; and the classification output unit is used for obtaining a phenology identification result according to the extracted features. According to the invention, the technical problem that the recognition rate of the finally obtained phenology recognition model is low due to the fact that the data standardization process and the model optimization are not directly associated when crop phenology recognition is carried out in the prior art is solved.

This invention discloses a near-real-time remote sensing monitoring method for crop phenology, belonging to the field of remote sensing monitoring technology. The method includes: acquiring the finite VI time-series curve of the current year and the complete VI time-series curve of historical years; generating a shape model for the current year; acquiring the complete VI time-series curves of N pixels of the same crop; selecting the top 10 complete VI time-series curves with the highest correlation coefficients between the finite VI time-series curve and the complete VI time-series curve of the target pixel; obtaining 10 first phenological estimates using the SMF-S method, and then combining them with the optimal translation step size to obtain 10 second phenological estimates for the current year of the target pixel; selecting the median of the second phenological estimates as the detection result. The near-real-time remote sensing monitoring method for crop phenology proposed in this invention, which integrates spatiotemporal information and shape model matching, can be used to detect the phenological stages of various crops during the growing season based on finite vegetation index time series, with significantly higher accuracy than other mid-season crop phenological detection methods.

The present invention discloses a method for monitoring the phenology of winter rapeseed based on an improved shape model, which includes: collecting the observation data of winter rapeseed and establishing a dynamic growth curve of winter rapeseed; selecting vegetation indices and establishing a shape model; using the shape model for phenology detection to obtain the phenological dynamics of winter rapeseed. The method of the present invention greatly saves the input of human and material costs, and further promotes the development of agricultural research and the transformation of achievements. Obtaining the crop phenological dynamics in a timely manner can provide a decision-making basis for the formulation of irrigation and fertilization systems, and while increasing crop yields, it can also provide important parameter support for the simulation of farmland ecological systems, which is of great significance in the context of the continuously increasing global food demand.

The invention discloses a sample set generation method and device, electronic equipment and a storage medium. The method comprises the following steps: determining a target phenological period of a main crop according to a main crop image of a ground observation station and a crop phenological period knowledge base; a target image recognition model is determined according to the target phenological period, the main crop images are input into the target image recognition model, the crop types and recognition credibility of the main crops are obtained, and the target image recognition model focuses on recognition of crop features of the target phenological period; when the identification credibility exceeds a credibility threshold value corresponding to the target phenological period, a crop distribution sample set is generated according to the main crop image, the geographic position of the ground observation station corresponding to the main crop image and historical main crop images, and the crop distribution sample set is used for providing samples for satellite remote sensing crop classification and mapping. According to the method, efficient and wide-coverage sample point acquisition is realized.

The invention provides a multi-mode and multi-task citrus chachiensis phenology monitoring method and system, and relates to the technical field of agricultural plant phenology monitoring, and the method comprises the steps: obtaining multi-mode data; the multi-modal data comprises high-frequency time sequence image sequence data and corresponding time sequence meteorological data of the target crop in a set time; and inputting the multi-modal data into the double-branch deep learning model to obtain a phenological stage classification result and a key development stage prediction result of the target crop. According to the method, the dual-branch deep learning model is cooperatively fused with the multi-modal time series data, and a multi-task learning strategy is combined, so that the problem that a traditional method is incomplete in single data source information and difficult to model a complex dynamic growth stage of crops is solved, and the recognition precision of the model on a complete growth cycle is improved; and moreover, the accuracy, the real-time performance and the predictability of phenology monitoring of the Citrus chachiensis crops are remarkably improved, and the high requirement of precision agriculture on phenology monitoring is met.

Embodiments of the present disclosure related to systems and methods of a field-scale crop phenology model for simulating / computing plant development stages of a crop. The field-scale crop phenology model is used to simulate plant development stages during a growing season. Knowledge of plant stages, especially as a forecast, helps the timing of chemical applications as well as other crop-dependent management decisions. Together with a user's field location, planting date, and varietal information, the crop phenology model serves as a robust field-scale decision-making tool. In certain embodiments, the phenology model can be run under three different scenarios: historical, preseason, or in-season. Using a blend of different weather data inputs, the phenology model can generate phenology results based on the desired scenario of a user.

The application discloses a kind of corn growth period real-time monitoring methods of farm cooperation ground camera and remote sensing.The method utilizes ground camera to continuously obtain the corn photo of observation plot, and the growth period of corn photo is classified and identified by deep learning model ResNet-50, and the Sentinel-2 satellite time series data of the corresponding area of observation point is continuously obtained, after radiation calibration, atmospheric correction, vegetation index calculation, the vegetation index time series is constructed, and the smooth curve is generated by interpolation reconstruction and Savitzky-Golay filtering, and the growth period date identified on the ground is accurately calibrated, to form the satellite scale standard reference curve with growth period label.Simultaneously obtain the Sentinel-2 satellite data of other plots in farm area, and the standard reference curve is used to fit it, to preliminarily predict the growth period of other plots.The method provides a feasible scheme for realizing the automation, high-precision monitoring of crop phenology at farm scale, and has important significance for guiding agricultural production management.

The invention discloses a method for determining the crop type of a high-resolution image agricultural planting plot under multilevel constraints, and the method comprises the steps: carrying out the administrative partitioning based on a high-resolution remote sensing image, and obtaining the boundary of the administrative partitioning; based on the boundary of the administrative partition, planting partition is carried out according to natural characteristics in the partition, and boundary vector data of each planting area, crop phenology information of each planting area and crop conditions of each planting area are obtained; classifying the plots with similar textures according to specific image texture features in the planting area, and performing cultivated land distinguishing on the plots with different textures; determining the land utilization type of each land block in each partition according to historical survey data; determining a crop type set of each land parcel according to the priority sequence of crop types in the planting area, the phenological characteristics and the space-time constraint relation of the land utilization type of each land parcel to the land coverage change, and calculating the confidence coefficient of each crop type; according to the invention, systematic cognition and efficient management of crops are improved.

The present application provides a kind of crop phenological period remote sensing extraction method based on shape model local matching, comprising: S1, by reference VI time curve and reference phenological period thereon, reference shape model is calculated using SMF method;S2, smooth target VI time curve;S3, reference shape model is matched with the target VI time curve after smoothing processing, and matching function is obtained;S4, phenology estimation: phenological period is estimated by iterative way;S5, the final result is calculated with the target VI time curve after smoothing processing;S6, if correlation coefficient is less than 0.8, then remove phenological period estimation and then output;If correlation coefficient is greater than or equal to 0.8, then directly output.The phenological period is estimated by iterative way, which solves the technical problem that the existing SMF method's phenology estimation, for later phenological period, usually has greater variance than early phenological period, makes the extracted phenological period spatial distribution and time variation produce deviation.

The invention discloses a farmland crop phenology extraction method and device, and relates to the technical field of remote sensing data measurement. The method comprises the following steps: acquiring a farmland crop heterogenous remote sensing original time sequence image and constructing an image pair; after deep features are extracted through a super-resolution model, step-by-step amplification is carried out through a convolution-normalization-activation cascade network, and a high-resolution image is reconstructed; and then time sequence reconstruction is carried out by using an original time sequence to obtain a high-temporal-spatial-resolution sequence. The vegetation index is further calculated and smoothed, the cumulative integral curvature change rate of the vegetation index is solved, the annual phenological extreme value of the crops is accurately locked, and finally the key phenological index is derived. According to the method, the continuity of observation data can be remarkably enhanced, the key inflection points of the crop growth period are accurately captured, and then accurate high-temporal-spatial-resolution crop phenology monitoring is carried out.

The application discloses a remote sensing crop recognition method and system based on multi-modal time sequence attention and a medium, relates to the technical field of remote sensing image processing; a multi-modal time sequence attention fusion recognition model is constructed based on an improved Attention UNet network architecture, optical spatial features and SAR spatial features are extracted based on an optical time sequence dataset and a SAR time sequence dataset respectively; a multi-modal time sequence matching mechanism is introduced, multi-modal spatial features are dynamically aligned and fused according to observation dates, and a lightweight time sequence attention encoder is combined to capture time sequence dependence, so that crop phenology evolution rules are deeply mined, and finally, end-to-end high-precision and rapid crop recognition is realized.

The application discloses a general crop mapping loss function based on phenology prior, which comprises crop phenology prior cross-entropy loss, and is verified by time series mapping of rape. The crop phenology prior cross-entropy loss comprises two key steps: firstly, the phenological characteristics of rape are extracted through a comprehensive vegetation index; and then, the loss is optimized by using the phenological characteristics as prior knowledge, so as to pay more attention to the identification of rape pixels. The overall framework of the rape mapping algorithm mainly comprises two parts: prior supervision and a deep learning model; the deep learning model comprises an LSTM, a 1DCNN and a DNN. The general crop mapping loss function based on the phenology prior is simple in technology and easy to operate; it provides a new solution for improving the precision of crop mapping of a deep learning model without changing the network structure and increasing the calculation amount; in addition, the idea of crop mapping by using the phenology prior is universal.

The invention provides an irrigation decision-making method and device based on a solar term and soil moisture balance model, and relates to the field of irrigation data processing, and the method comprises the steps: analyzing crop phenological period and meteorological characteristic data corresponding to each solar term in designated solar term data based on the designated solar term data and time sequence meteorological data; determining the most suitable soil water content of the crop in different solar terms according to the phenological period of the crop; correcting the most suitable soil water content according to the crop meteorological characteristic data to obtain a reference soil water content corresponding to each solar term of the crop, simulating the change data of the field soil water content in real time by using a soil water dynamic balance model, and calculating the remaining effective water amount in the soil every day based on the change data; the irrigation frequency is calculated according to the rainfall characteristics corresponding to the solar terms, and whether irrigation is executed or not is judged according to the irrigation frequency and the current remaining effective water amount; and if irrigation is executed, dynamically generating an irrigation decision result according to difference data between the actual soil water content and the reference soil water content corresponding to the solar terms.

The application discloses a crop classification method of a self-adaptive SAM and ConvxLSTM hybrid model, and relates to the technical field of remote sensing image processing. The method comprises the following steps: constructing a time series dataset facing crop phenology, filtering and screening an optimal classification time phase band combination through J-M distance; generating unmarked samples according to the optimal classification time phase band combination, generating crop pseudo-labels with category annotations based on a self-adaptive SAM model; processing the time series dataset based on a ConvxLSTM network to classify crops and output crop classification results. The application can ensure automatic acquisition of high-quality crop pseudo-labels, provide crop category annotations for the pseudo-labels, greatly reduce the excessive dependence of a model on artificially annotated samples, more effectively mine the space-time features of data, and thus improve the crop classification precision.

This invention discloses a near-real-time monitoring method for mid-season crop phenology and types based on dense temporal series data, belonging to the interdisciplinary field of satellite remote sensing Earth observation and agricultural information technology. The method includes: acquiring HLS imagery to construct a dense temporal series dataset; recursively updating the dataset using the Stochastic Continuous Change Detection (S-CCD) algorithm; fitting the vegetation index temporal characteristic curve for each pixel based on the S-CCD results to predict the phenological stage of the current year; classifying pixels into stable, uncertain, and variable classes, with the stable and uncertain classes inheriting historical planting types; training a random forest model using automatically selected stable class samples to classify the variable classes, and performing Bayesian temporal fusion with previous probability maps to determine the final crop type; fusing the results with vector plots and automatically publishing them through a network service. This invention achieves high-precision and high-efficiency dynamic monitoring of phenology and types within the crop growth cycle, supporting near-real-time weekly updates.

This application proposes a crop type identification method, apparatus, storage medium, and electronic device, comprising: acquiring the crop phenological characteristic index corresponding to each pixel in the target area based on at least one set of target remote sensing image data; wherein the target remote sensing image data includes remote sensing image data corresponding to the target area; and determining the type identification result corresponding to each pixel in the target area based on the crop phenological characteristic index corresponding to the target area and the crop phenological characteristic index corresponding to the sample area. This avoids a large amount of manual visual interactive interpretation and ground statistical survey work, and can quickly and accurately obtain the crop types in the target area.

The present invention provides a method, system, and device for predicting crop phenology based on whole-genome prediction. The method comprises the following steps: obtaining crop data; performing parameter correction on a growth model; simulating crop phenology data using the crop data and the corrected growth model; calculating the crop phenology data to obtain BLUP values; performing Bayesian whole-genome prediction on the BLUP values ​​to obtain a low-dimensional representation of the high-dimensional SNP data of the phenology; performing phenology-stage-specific segmentation on the crop data not included in the growth model prediction to obtain segmented data; combining the segmented data, interval time, and low-dimensional representation results into time series data segmented by phenology stage; and inputting the time series data into a trained model to obtain prediction results. The present invention utilizes whole-genome prediction technology to perform low-dimensional mapping on SNP data, overcoming the "genetic bottleneck" caused by simplifying GSPs and enhancing gene interpretability.

The application discloses a kind of regional scale crop yield near real-time prediction method based on deep learning, comprising: obtaining the source data of target pixel yield related variable, calculating the yield related variable of target area;Source data is processed into corresponding feature variable, and model training set and test set are generated;According to the characteristics of crop yield accumulation, construct a suitable LSTM model, the time series of feature variable in training set is imported into the model for training, and a yield prediction model is obtained;With R 2 And root mean square error (RMSE) as evaluation standard, the feature variable of test set is imported into yield prediction model for verification, and the optimal model is obtained.The application solves the restriction of existing yield estimation method due to the complex nonlinear relationship between yield and environmental variables changes with crop phenology, and also solves the problem that yield cannot be accurately predicted in near real time in the current method.

The application discloses a kind of similar crop classification systems and methods based on multi-temporal remote sensing and phenology fusion, belong to agricultural remote sensing monitoring and crop identification technical field. Including the following steps: S1, obtain the multi-temporal multispectral remote sensing image of whole growing season in study area and complete pretreatment and time sequence reconstruction;S2, extract crop phenology characteristics from the continuous vegetation index time sequence sequence obtained by pretreatment and analysis;S3, determine key phase based on phenology period and category separability analysis, extract corresponding spectral characteristics and index characteristics;S4, standardization fusion and optimization are carried out to spectral characteristics and phenology characteristics, and low-redundancy high-discriminative fusion feature space is constructed;S5, train supervised classifier based on fusion feature space, complete crop classification, precision evaluation and post-processing, and generate crop type distribution map. The system and method of the application can maintain robustness in cloud rain interference scene, and are suitable for large-area planting structure identification and business monitoring.