166 results about "Leaf area index" patented technology

The invention provides a rice growth model construction method and system based on salt stress, and relates to the technical field of growth model.The rice growth model construction method comprises the steps that firstly, monitoring points are arranged in a planting sample area, and soil conductivity data of different depths are obtained through a multi-depth soil conductivity sensor and a Kriging interpolation method; collecting root system density, a multispectral remote sensing image and a leaf area index, and calculating a canopy salt stress index; measuring the concentration of related ions to obtain a sodium adsorption ratio, and establishing a salt stress coefficient by combining the soil conductivity and the irrigation volume; fusing canopy and soil stress indexes to generate a stress comprehensive index, and introducing a salinity feedback item to represent the crop compensation capability; and finally, constructing a hybrid machine learning model by adopting a convolutional neural network and a long-short-term memory network to realize rice growth dynamic prediction. According to the method, multi-dimensional salinity stress quantification of a soil-crop system is realized, and decision support is provided for salinization treatment in precision agriculture.

The invention provides a single tree segmentation-biological parameter estimation method based on a vehicle-mounted LiDAR point cloud, and belongs to the technical field of urban landscaping intelligent monitoring. The point cloud individual tree segmentation algorithm based on tree geometric feature constraint is designed for solving the problem that individual tree segmentation is difficult due to crown overlapping in an urban scene, and the method takes a tree geometric structure as a constraint, combines point cloud reflection intensity information, a clustering algorithm, a main direction index and other means, and obtains the individual tree segmentation algorithm based on the tree geometric feature constraint. And accurate extraction of trunks and crowns in the scene point cloud is realized. Aiming at the problems of high feature redundancy, poor model interpretability and the like in an existing estimation method, a random forest model is taken as a basis, an adaptive feature selection algorithm is introduced to improve variable screening efficiency, hyper-parameters are dynamically adjusted by utilizing pigeon inspired optimization, and generalization and stability of the model are enhanced; an estimation model used for estimating biological parameters such as leaf area index, biomass and carbon reserve is designed.

The invention discloses a method for predicting the irrigation amount of crops in an arid saline-alkali soil area and related equipment. The method comprises the steps that the potential evapotranspiration of a target crop is calculated through a double-source evapotranspiration mechanism model based on key meteorological parameters, obtained through prediction, of a target area, and the leaf area index and the plant height are dynamically updated according to the accumulated temperature process; respectively constructing different stress inhibition functions aiming at the attention salt ions and the pH value in the saline-alkali soil solution, and applying composite inhibition at the stomatal conductance and / or the apparent evapotranspiration resistance site to correct the potential evapotranspiration so as to obtain the ideal crop evapotranspiration corrected by the salinity and the pH value; and based on the corrected ideal crop evapotranspiration, predicting day-by-day irrigation amount and water distribution schedule suggestions in a future preset period. The method can solve the problem that current crop irrigation of saline-alkali soil in an arid inland region depends on experience, influences on different salt types and contents are caused, and quantitative analysis is lacked.

The invention discloses an alpine meadow aboveground biomass monitoring method based on PROSAIL-BP, and belongs to the field of ecological remote sensing information processing. In order to overcome the defect that samples in the alpine region are insufficient and have high precision and high reliability, the method comprises the steps that an alpine meadow mask, remote sensing images and field biomass data in a target region are obtained, the remote sensing images are spliced, the wave band reflectivity is normalized, and the grassland region reflectivity is reserved in combination with mask cutting; predefining a PROSAIL model matched with the region features; performing Sobol global sensitivity analysis to obtain a first-order sensitivity index and a total-order sensitivity index of the parameter; screening a key wave band and four high-sensitivity parameters; uniformly sampling to generate a parameter group, simulating a hyperspectrum through PROSAIL, extracting the reflectivity of a key wave band, and constructing a data set by multiplying a leaf area index by a dry matter content as a target variable; and training a three-layer BP neural network, and processing the reflectivity output pixel biomass of the remote sensing key wave band. The method is applied to a remote sensing information processing system and has high precision and high reliability.

The invention relates to the technical field of information management, in particular to a smart agriculture precision big data information management system, which comprises a growth index extraction module, a stage data clustering module, a nutrient fluctuation identification module, an agricultural material strategy generation module and a scheduling information scheduling module. According to the method, the acceleration criterion is constructed based on the continuous period leaf area index change sequence, transition node identification is completed in combination with the photosynthetically active radiation utilization rate and the nitrogen absorption rate change trend, accurate positioning of crop growth stage change time points is achieved, the stability of stage classification in a space region is enhanced, and the accuracy of crop growth stage classification is improved. The agricultural material putting grade is judged and the fertilization frequency and dosage are blended by analyzing a root zone soil nutrient concentration difference value and a rate fluctuation frequency detection mode in combination with moisture content and root activity conditions, and operation period adjustment is guided in a task schedule in cooperation with a meteorological element fluctuation rate. The precision of farmland crop stage identification and the timeliness of nutrient fluctuation response are integrally improved.

The invention discloses a ground vegetation leaf area index remote sensing inversion method based on a remote sensing image. The method comprises the following steps: data acquisition and preprocessing; performing multi-scale space-time non-local filtering fusion; dynamic feature extraction; carrying out transfer learning fine tuning; time sequence deep learning integration; and model output and post-processing. According to the invention, through multi-source space-time fusion and dynamic feature distribution, vegetation LAI inversion with high resolution and high continuity is realized; the transfer learning and the time sequence deep network enhance the adaptability of the model to a new region and time sequence change; the stability and reliability of large-scale application are guaranteed through full-process automation and uncertainty evaluation, and the model is obviously superior to an existing single-source or static model.

The invention discloses a wheat yield remote sensing prediction method combining phenological parameters, which comprises the following steps: S1, performing field observation in a key growth period of winter wheat, synchronously collecting canopy hyperspectral reflectivity data, leaf area index (LAI) and SPAD value of each observation sample point, and recording wheat grain yield of the corresponding sample point; s2, performing noise reduction preprocessing on the acquired canopy hyperspectral data, and extracting sensitive spectral parameters by combining principal component analysis (PCA) and correlation analysis methods; s3, taking the sensitive spectrum parameters, LAI and SPAD values as independent variables, taking the wheat grain yield as a dependent variable, and adopting partial least squares regression (PLSR) to construct a multivariable yield prediction model; and S4, performing wheat yield prediction on an independent test sample or regional scale remote sensing data by using the trained model. The method overcomes the defect that only yield sensitive spectrum parameters are used for predicting the effect, and accurate estimation of the model is achieved.

The invention relates to the technical field of smart agriculture, and specifically provides a crop growth situation prediction method based on YOLO and Transform space-time collaboration. The method aims at solving the problem that in the prior art, prediction precision is insufficient due to splitting of spatial features and time sequence information, and crop phenotypic features (plant height, leaf area index, canopy coverage and the like) in a farmland video stream are extracted in real time through an improved YOLO model; constructing a spatial-temporal feature encoder, and modeling a coupling relationship between historical time sequence environmental data (temperature, illumination and soil moisture content) and phenotypic features through a Transform network; designing a feature collaborative fusion module, and integrating spatial visual features and time sequence environment features by adopting an adaptive weight distribution mechanism; and establishing a growth situation prediction model based on space-time cooperation characteristics, and outputting key parameter probability distribution of a future growth stage.

The invention relates to the technical field of image processing, in particular to a GEE-based leaf area index remote sensing product spatial downscaling method, which comprises the following steps: acquiring a single image of a remote sensing product, screening out a surface reflectance image according to a space-time range of the single image of the remote sensing product, and preprocessing the surface reflectance image and the single image of the remote sensing product; establishing a screening mechanism to remove heterogeneous pixels in the preprocessed surface reflectance image to obtain a spatial homogeneous pixel set; aggregating the preprocessed surface reflectance image to a resolution which is the same as that of a single image of the remote sensing product, and constructing a space-time matching pixel set; randomly extracting pixels from the space-time matching pixel set to construct a training sample library, and optimizing data in the training sample library to obtain an optimized training sample library; and applying the machine learning model to the preprocessed surface reflectance image to generate a leaf area index remote sensing product in continuous spatial distribution. According to the invention, the precision and resolution of the LAI product are improved, and the applicability is enhanced.

The invention relates to the technical field of intelligent agriculture and crop cultivation, in particular to a soybean planting chemical control self-adaptive regulation and control method and system based on canopy risk identification, and the method comprises the steps: constructing a digital twinborn model for dynamically simulating the growth process of a soybean population; monitoring a canopy structure, a leaf area index LAI and a light interception rate of the soybean in the key growth period by using an unmanned aerial vehicle or a sensor, and calibrating the digital twinborn model; future weather forecast data are input into the calibrated digital twinborn model for growth simulation, and light distribution is simulated by means of a pre-established AI model to identify soybean population closing and illumination competition risks; and according to the risk identification result, a chemical control decision is generated autonomously, and the variable pesticide spraying machine is controlled to perform precise variable operation of soybean planting based on the chemical control decision. According to the method, group development can be predicted in a prospective manner, and risks can be accurately quantified, so that an intelligent regulation and control mechanism with prospective and active properties is actively triggered, and active intervention of planting is realized.

The invention relates to the field of agricultural yield prediction, and particularly discloses a crop yield prediction method and system based on artificial intelligence, and the method comprises the steps: S1, recognizing crop types through the spectral features of a remote sensing image and field sampling data, and dividing corresponding key growth stages; s2, collecting multi-source feature data for each key growth stage, wherein the multi-source feature data comprises remote sensing image data, an extracted normalized difference vegetation index NDVI, an enhanced vegetation index EVI and a topographic factor; acquiring hourly temperature, humidity, precipitation and illumination intensity of each sub-region through a distributed sensor according to micro-meteorological data; obtaining plant height, leaf area index and fruit development parameters through unmanned aerial vehicle three-dimensional imaging according to crop phenotype data; by adopting the technical scheme of the invention, the terrain, microclimate and crop dynamic growth characteristics can be accurately fused, and the problem of non-uniform sample distribution is solved, so that the accuracy and regional adaptability of yield prediction are improved.

The invention provides a crop growth state intelligent analysis method based on a multi-source remote sensing image, and belongs to the technical field of crop growth analysis based on computer data processing. The method comprises the following steps: firstly, collecting a multi-source remote sensing time sequence image covering the whole growth cycle, and constructing a multi-modal growth characteristic data set with a uniform structure; secondly, designing a multi-channel time sequence modeling structure, and cooperatively extracting dynamic evolution trajectories of core characteristics such as canopy height, leaf area index, SPAD value and the like based on space-based spectrum and foundation form information; then, a current state deviation type is identified through a multi-type track distribution learning model, and problem tracing and explanation analysis are carried out in combination with a diffusion matching mechanism; finally, a variable adjustment strategy is generated based on a trajectory deviation result and a management target, and optimization recommendation of management measures such as irrigation frequency and fertilization intensity is realized. The method can be widely applied to the scenes of agricultural remote sensing monitoring, intelligent agricultural machinery scheduling, precise planting guidance and the like, and has high interpretability and practical value.

Provided is a method for quantitatively estimating potassium demand of regional corn plants during key growth stages. The method includes: S1: calculating critical potassium concentration values Kc for each growth stage of corn; S2: calculating potassium nutrition indexes (KNIs) for each growth stage of the corn; S3: constructing KNI inversion models for each growth stage of the corn; S4: obtaining leaf area index (LAI) data of the corn and calculating above-ground biomass W for each growth stage of the corn; S5: calculating potassium fertilizer utilization rates KAE for each growth stage of the corn based on above-ground potassium accumulations in each growth stage of the corn; S6: calculating relative dry biomass RDW for each growth stage of the corn, and optimal KNI values, denoted as KNItarget, for each growth stage of the corn; and S7: obtaining a plant potassium content absorption model Kabs for each growth stage of the corn.

The invention discloses a basin hydrological simulation method and system embedded with a canopy interception mechanism, and the method comprises the steps: embedding a revised Gash canopy interception model module in an SWAT model, dividing a rainfall event into a wetting stage, a saturation stage and a drying stage according to the parameters of rainfall, a leaf area index and a tree height, dynamically calculating the canopy interception amount and the interception evaporation amount, and carrying out the calculation of the canopy interception amount and the interception evaporation amount. The effective rainfall capacity is used for replacing original rainfall input in the SWAT model, the adjusting effect of the forest canopy on the rainfall process is reflected more truly, and the basin hydrological simulation precision is improved. According to the method, the response and simulation capability of the SWAT model to the hydrological process of the underlying surface of the forest is effectively improved, the dynamic response to effective rainfall and evaporation terms is enhanced, the method is suitable for watershed hydrological process modeling of various forest types, and the reliability of flood forecasting and water conservation evaluation is improved.

The invention provides a multi-scheme collaborative yield forecasting method based on data assimilation and model parameter optimization, and belongs to the technical field of agricultural information, and the method comprises the steps: obtaining historical and real-time data of a target region and a target crop growth season; constructing a plurality of combined simulation schemes of the WOFOST model; carrying out data assimilation on the leaf area index and the soil humidity by utilizing an ensemble Kalman filter (EnKF) method and combining a Gaussian disturbance strategy; performing sensitivity analysis and optimization on photosynthetic parameters of the WOFOST model, determining an optimal photosynthetic parameter combination and operating the model; improving a water stress function; constructing a rolling updating yield prediction framework, and dynamically optimizing a yield prediction result; and dynamically selecting an optimal simulation strategy to simulate and forecast the yield. According to the method, the yield simulation precision and forecasting stability of the crop model under different moisture years are remarkably improved, and a reference is provided for developing a new meteorological year adaptive dynamic simulation framework of the crop model.

The invention relates to the technical field of forest vegetation monitoring, in particular to a forest vegetation parameter real-time monitoring method based on unmanned aerial vehicle images, which comprises the following steps: starting an unmanned aerial vehicle, carrying out real-time image acquisition on a predetermined forest area through a camera, carrying out continuous image capture, synchronously calibrating the camera and setting matched differentiated illumination and depth-of-field conditions; and generating forest image acquisition data. According to the method, the chlorophyll concentration and the leaf area index can be accurately measured through analysis of different color wavelength reflectance, the understanding and tracking precision of the vegetation physiological state is improved, long-term vegetation changes can be carefully monitored through time sequence analysis, the prediction capacity of forest ecological behaviors is enhanced, and the method is suitable for popularization and application. Drought response and pest and disease damage signs are monitored in real time, the timeliness and accuracy of health state evaluation are enhanced, the real-time performance and continuity of data are ensured by dynamically updating a forest vegetation database, and the dynamic monitoring and decision support capacity of forest management is remarkably improved.

The invention provides a rice leaf area index inversion method based on an unmanned aerial vehicle, and relates to the technical field of smart agriculture, and the method comprises the steps: S1, obtaining an RGB image of a to-be-detected rice canopy, a training feature set, and a corresponding rice leaf area index measured value; s2, processing the RGB image of the rice canopy to be measured to generate a digital orthoimage and a digital earth surface model; s3, generating spectral features, height features and texture features based on at least one of the RGB image, the digital orthoimage and the digital earth surface model of the rice canopy to be measured; s4, training a machine learning model by using the training feature set and the corresponding rice leaf area index measured value to obtain a rice leaf area index inversion model; and S5, inputting the spectral features, the height features and the texture features into a rice leaf area index inversion model to obtain a leaf area index prediction value of the rice canopy to be detected. And rice leaf area index inversion is carried out only by using the RGB sensor to collect images.

The invention discloses a self-adaptive crop growth prediction and farming decision-making system based on multi-source environmental data. The system comprises a multi-source data acquisition module, a data preprocessing module, an adaptive parameter adjustment module, an intelligent prediction engine and a user interaction module. According to the system, soil physical and chemical parameters, meteorological elements and crop variety characteristics can be fused, and a dynamic environment-crop feature vector is constructed; driving a parameter adaptive optimization mechanism through a multi-source data acquisition and feature analysis module, and dynamically adjusting key parameters of a prediction and decision model by adopting a Bayesian optimization framework; the whole-growth-period growth prediction of the leaf area index, biomass accumulation and the mature period is realized in combination with an improved LSTM neural network, and farming suggestions such as sowing, fertilization and irrigation are generated; and outputting a result through a visual platform, and supporting user feedback closed-loop optimization. According to the method, a'region-variety 'two-dimensional response mechanism is designed, collaborative self-adaption of growth prediction and decision parameters is realized, and the generalization and precision of the model are improved.

The invention discloses an unmanned aerial vehicle remote sensing monitoring method and system for a wheat leaf area index, and relates to the field of smart agriculture, and the method comprises the steps: collecting the spectral reflection and texture structure characteristics of wheat for the elongation stage, heading stage and flowering stage of wheat under different planting densities and fertilization conditions through employing a multispectral unmanned aerial vehicle remote sensing technology, taking as a data set; and on the basis of the data set, aiming at a single growth period and multiple growth periods, monitoring the wheat leaf area index by constructing different monitoring models. The invention provides an effective method for multispectral unmanned aerial vehicle remote sensing monitoring of wheat LAI, and has important guiding significance for realizing precise agricultural management and improving wheat yield.

The invention discloses an irrigation decision determination method considering a multi-source water conversion process, and relates to the technical field of agricultural water conservancy irrigation, and the method comprises the steps: obtaining a multi-spectral image and a thermal infrared image of crops in a target irrigation region, calculating a vegetation index and a leaf area index, and combining with the actually measured growth vigor data of the crops, a growth vigor model of crops is constructed by establishing a mapping relation, the rainfall, the irrigation volume, the canal system infiltration replenishment volume and the groundwater capillary rise volume of a target irrigation area are obtained, and a soil moisture income and expenditure model is constructed based on a water circulation process. According to the method, a plurality of paths such as rainfall, irrigation, canal system leakage and groundwater capillary rise are considered through the constructed soil water volume income and expenditure model, crop physiological moisture inflection points are accurately recognized by simulating the root zone volumetric moisture content and growth vigor response curve, threshold control irrigation based on crop requirements is achieved, and the crop yield is improved. And the multi-source input and conversion process of the farmland hydrological system is comprehensively reflected.

The invention relates to the technical field of intelligent water conservancy, in particular to an irrigation area water demand prediction and scheduling system based on intelligent water conservancy, which comprises a disturbance identification module, a humidity sensing module, a deviation judgment module, an irrigation sequencing module and an instruction generation module. According to the method, the change degree of future weather forecast and weather data on that day is quantified to pre-judge the disturbance of the future environment, the soil moisture sensitive areas which are violently responded to the disturbance are dynamically screened out from the global irrigation area on the basis of the pre-judge, and the soil moisture sensitive areas which are violently responded to the disturbance are selected for the screened areas. Further combining with the ideal moisture demand of the crops at the current growth stage, analyzing the dynamic deviation trend between the actual soil humidity and the ideal value in the continuous time, thereby accurately identifying the land parcels really in the moisture supply deviation state, abandoning a fixed irrigation plan, and improving the irrigation efficiency. And acquiring physiological indexes such as evapotranspiration rate and leaf area index of the crops in the deviated area in real time, thereby judging the real urgent degree of the crops in each area to moisture and carrying out irrigation sequencing.

The invention provides a winter wheat leaf area index estimation method and system based on unmanned aerial vehicle remote sensing, and the method comprises the following steps: S1, data acquisition: obtaining unmanned aerial vehicle multispectral remote sensing image data of a research region, and collecting corresponding field actual measurement data in different growth periods of winter wheat; according to the winter wheat leaf area index estimation method and system based on unmanned aerial vehicle remote sensing provided by the invention, through the step design of S1 to S7, especially the collaborative cooperation of data preprocessing, data fusion, model construction and optimization, during use, on one hand, the leaf area index of the winter wheat can be estimated; in S2, splicing and geographic coordinate system embedding processing are carried out on unmanned aerial vehicle multispectral remote sensing image data, spatial positions of different wavebands can be automatically aligned, the problem that the number of rows and columns of multiband data is inconsistent is solved fundamentally, and a spatially unified data source is provided for subsequent vegetation index calculation and feature extraction.

The invention provides a garden carbon sink function zoning method fusing multi-source remote sensing data, and relates to the technical field of garden carbon sink evaluation and remote sensing monitoring. The method comprises the following steps: acquiring multi-source remote sensing data such as optical remote sensing, radar remote sensing and laser radar; performing radiometric calibration, atmospheric correction and geometric correction preprocessing on the data; vegetation characteristic parameters such as a normalized vegetation index, a leaf area index and surface temperature are extracted; calculating garden carbon sink efficiency parameters based on the vegetation characteristic parameters; calculating garden carbon sink function zoning parameters in combination with topographic data; performing carbon sink function zoning on the garden area by adopting a clustering algorithm, and dividing high, medium and low carbon sink function level areas; and outputting a carbon sink function division spatial distribution diagram and a data report. According to the method, evaluation comprehensiveness is improved through multi-source data fusion, accurate quantification is realized through innovative parameter calculation, scientificity and repeatability are improved through an objective partitioning method, and garden carbon sink fine management is effectively supported.

The present application relates to the technical field of climate change warning, and discloses a mangrove blue carbon ecological risk identification and warning method and system for climate change, comprising the following steps: acquiring time series of global land surface characteristic satellite leaf area index data and environmental factors, performing detrending, deseasonalization and standardization processing to extract abnormal sequences; determining climate oscillation windows and neutral periods according to multivariate El Nino-Southern Oscillation index and dipole mode index, and calculating the mean value of the environmental factors in the neutral period as a reference; inputting the environmental factors into a long short-term memory network to extract attention weights, calculating the factor difference between the mean value of the climate oscillation window and the reference, mapping the factor difference by using a nonlinear saturation kernel function, combining the weights to obtain contribution amplitude, and selecting a dominant risk factor by comparing the direction; processing the absolute value of the leaf area index anomaly by using an S function to output risk intensity, and predicting future leaf area index anomaly based on the dominant risk factor to generate a warning evaluation.

The present invention relates to the technical field of crop yield analysis, and specifically to a crop yield prediction method based on time-series remote sensing images. In the present invention, optical remote sensing images and synthetic aperture radar images during the crop growth period are acquired, and time-series images are constructed through complementary information fusion and cloud-underground information recovery. Cloud interference and data missing problems are addressed, and a multi-scale time-regulated convolution module is used to process the time-series images, extract multi-scale time-series features, and perform feature fusion in combination with attention differential jump connections to obtain a rice distribution map. Rice-planting areas are determined based on the rice distribution map, and an optimal assimilation period is selected within the rice-planting areas. A leaf area index obtained by remote sensing inversion is assimilated with crop growth model simulation results to generate an assimilated simulated yield. Based on the multi-scale time-series features, a parameter dynamic response matrix related to crop growth model parameters is established, and residual correction is performed on the assimilated simulated yield, thereby improving the accuracy of rice yield prediction.

The present application relates to the technical field of agricultural remote sensing and machine learning, and particularly relates to a leaf area index estimation method based on improved XGBoost. The method comprises the following steps: acquiring unmanned aerial vehicle multi-spectral images and sample leaf area index measured values, and constructing a vegetation index map sample data set after preprocessing; performing feature extraction and fusion on the vegetation index map by using a deep learning network; constructing an improved beaver optimization algorithm, generating an initial population by using a two-stage initialization strategy, updating the position of the architect subpopulation by using an elite directional felling strategy, recombining individuals and the global optimal solution by using a vertical and horizontal cross strategy; optimizing the XGBoost hyperparameters by using the improved beaver optimization algorithm, and establishing a leaf area index estimation model. The leaf area index estimation method based on improved XGBoost combines deep learning feature extraction, improved swarm intelligence optimization algorithm and integrated learning regression modeling, and is helpful to improve the prediction accuracy and stability of the leaf area index estimation model.

The invention relates to a leaf area index time sequence processing method, which comprises the following steps of: inputting a time sequence remote sensing image and suburb forest and economic forest classification data of the same region; calculating a normalized differential vegetation index of the research area and carrying out time sequence sorting; calculating vegetation coverage data of the research area and carrying out time sequence sorting; synthesizing to obtain monthly FVC time sequence data of the suburb forest region and the economic forest region; calculating a suburb forest leaf area index LAI in the research area and performing time sequence sorting; calculating the economic forest leaf area index LAI of the research area and performing time sequence sorting; performing seasonal decomposition on the suburb forest time sequence data after adaptive filtering; performing seasonal decomposition on the economic forest time series data after adaptive filtering; merging the suburb forest time sequence data and the economic forest time sequence data; and outputting to obtain final optimized data. The invention further relates to a leaf area index time sequence processing system. According to the invention, a purification LAI time sequence product which clearly represents long-term trend, mutation and gradual change signals of respective vegetation canopy structures can be output.

The invention discloses a leaf area index inversion calculation method, and aims to solve the technical problem that the existing leaf area index estimation accuracy is limited. According to the method, collected crop canopy data is analyzed by adopting internal feature importance, a feature importance ranking is output by adopting a random forest algorithm, the most valuable feature is effectively screened out to participate in inversion of the leaf area index, and the inversion complexity can be greatly reduced. Bayesian optimization parameters are adopted, and historical parameter adjustment information is fully utilized through Bayesian optimization iteration, so that deep search of the parameters is fully realized, unnecessary objective function evaluation is reduced, and parameter adjustment efficiency is improved. Wherein the Bayesian optimization adopts a Gaussian process, previous parameter information is further considered, prior information is continuously updated, and the prediction precision is improved.

The invention belongs to the technical field of ecological hydrology, and particularly discloses a forest underlying surface earth surface evapotranspiration estimation and component segmentation method based on kNDVI. According to the method, based on a maximum entropy increase model, under the constraint of a surface energy balance equation, the surface state parameters of a forest vegetation-free area are used for resolving to obtain the soil evaporation capacity of the bare soil; on the basis of a maximum entropy increase model, under the constraint of a canopy energy balance equation, the vegetation transpiration amount is obtained through calculation according to the canopy state parameters of the forest vegetation coverage area; calculating the canopy interception evaporation capacity according to the leaf area index and the rainfall capacity of the forest vegetation coverage area; and finally, based on the kNDVI index, carrying out weighted summation on the bare soil evaporation amount, the vegetation evaporation amount and the canopy interception evaporation amount in the forest to obtain the total evapotranspiration of the underlying surface of the forest. Compared with an existing evapotranspiration estimation model, the forest underlying surface earth surface evapotranspiration estimation method is lower in complexity and higher in estimation precision.

The invention discloses a tea garden ecological condition assessment method based on a laser radar point cloud, and belongs to the technical field of agricultural ecological monitoring, and the method comprises the following steps: S1, collecting tea garden point cloud data through an unmanned aerial vehicle-mounted laser radar system; s2, extracting key ecological parameters including canopy density, leaf area index, three-dimensional green quantity, gradient and spatial heterogeneity; s3, analyzing and determining a key threshold value of each parameter based on an empirical cumulative distribution function; s4, respectively adopting a Logistic function, an inverted S-shaped curve and a piecewise linear scoring method to construct a scoring model of each parameter; s5, the final weight of each scoring model is determined through grey correlation degree analysis in combination with expert scoring; s6, performing weighted calculation to obtain a comprehensive ecological index so as to evaluate the ecological condition of the tea garden; and S7, dynamically updating model parameters. According to the method, accurate and objective evaluation of the ecological condition of the tea garden is realized by means of laser radar point cloud data, the evaluation model can be optimized by a dynamic updating mechanism, and scientific guidance is provided for sustainable development of the tea garden.