64 results about "Phenology" patented technology

The invention discloses a phenology-based multi-source remote sensing ecosystem carbon flux estimation method, which comprises the following steps of: calculating direct and scattered photosynthetically active radiation of a target area by using multi-source remote sensing data; the method comprises the following steps: acquiring regional biological characteristic data of the same time sequence, performing nonlinear least square fitting by adopting a double-S-shaped curve to extract phenological characteristics of vegetation, setting a threshold value according to the phenological characteristics, and constructing a phenological constraint factor; based on a double-leaf light energy utilization efficiency framework, establishing an ecological system carbon flux model in combination with phenological constraint factors; and optimizing model parameters by using a Markov chain Monte Carlo method. And generating global total primary productivity data by using the model after parameter optimization, the method is superior to a traditional light energy utilization efficiency model, has advantages in the aspect of total primary productivity spatial-temporal change simulation, and improves the simulation precision of global carbon flux.

The invention provides an artificial intelligence land biodiversity real-time on-line monitoring evaluation-risk early warning-risk elimination method and system, and the method comprises the steps: collecting and monitoring biological information, geographic and phenological information, environment quality information and other information, carrying out the data comparison and analysis, carrying out the data evaluation and influence factor analysis, and carrying out the risk diagnosis and early warning. A risk elimination method; the system sequentially comprises a data acquisition and monitoring module, a data analysis and diversity evaluation module, a risk diagnosis and early warning module, a risk elimination module and the like. Scientific basis and technical support are provided for land biodiversity protection, management and decision making, and the land biodiversity protection strength is enhanced.

The invention discloses a phenological self-adaptive corn automatic mapping method, which comprises the following steps of: 1, screening to obtain Sentinel-2 time sequence satellite image data of a target area, preprocessing, and synthesizing a time sequence clear sky image data set with one scene in a half month; 2, filtering the time sequence clear sky image data set to obtain a denoised and smoothed time sequence satellite image data set; step 3, based on peak and valley values of the NDVI index of the filtered image, adaptively acquiring a corn identification key phenological period of the target area; 4, analyzing typical spectrum differences of the corn and other main background ground objects, providing a corrected red edge normalized vegetation index, and forming a typical index data set of the corn identification key phenological period with an NDVI index and an LSWI index; and step 5, automatically realizing rapid mapping of the corn in the target area by utilizing the division rule of the typical index data of the key phenological period of the corn and the main background ground feature, and realizing a corn planting distribution monitoring effect with higher precision and efficiency.

The embodiment of the invention provides a rice identification method fusing time sequence spectrum difference and phenological information similarity matching, and belongs to the technical field of image identification, and the method specifically comprises the steps: combining phenology and land cover products to generate an automatic generation identification sample; training the first sample in each month of the target year in parallel to obtain 12 time sequence extraction classifiers, applying the 12 time sequence extraction classifiers to the second sample to obtain a prediction probability, and dividing the prediction probability into a third sample and a fourth sample; calculating the separable index of each time sequence based on the prediction probability of the third sample, and determining the phenological weight of each phenological period; taking the phenological weight as an adjustment parameter, transferring the prediction probability of the third sample to a time domain, calculating the similarity by using a time-weighted dynamic warping algorithm, cooperatively supervising, learning and training a prediction classifier, and verifying by a fourth sample; and forming an identification model and identifying the target area. Through the scheme disclosed by the invention, the recognition accuracy and adaptability are improved.

The invention relates to the field of ecological environment and climate change research, and discloses a vegetation phenology change trend comprehensive evaluation method, which comprises the following steps: acquiring climate data and tree ring data of a target area, simulating a relationship between radial growth and phenology of a tree by using a Vaganov-Shashki n model based on the acquired data, and generating a time sequence of phenology change; extracting phenological key nodes such as growing season starting time, end time and growing season length; analyzing the driving effect of climatic factors on phenological key nodes, and determining main influence factors; on the basis of the climate model and different emission scenes, predicting the vegetation phenological trend under future climate change; the response of the regional ecosystem to climate changes is evaluated based on historical and future data. Through simulation and quantitative analysis, a scientific basis is provided for long-term trend prediction and regional ecological management of vegetation phenological change, and the method has high applicability and reliability.

The embodiment of the invention relates to the technical field of artificial intelligence, and provides a coastal salt marsh vegetation carbon sink estimation method and system based on multi-temporal phenological characteristics. The method comprises the following steps: acquiring a remote sensing image of a target coastal salt marsh area in a key phenological period; extracting an initial vegetation contour of a vegetation coverage range in the target area from the remote sensing image by adopting an unsupervised classification method; constructing a phenological decision tree model by taking an NDVI threshold method as a core, and integrating a machine learning enhanced node division mechanism and a phenological period slope analysis method to enhance the phenological decision tree model; inputting the initial vegetation contour into a phenology decision tree model, and performing multi-level classification on vegetation types according to the initial vegetation contour through the phenology decision tree model to distinguish vegetation coverage ranges of various types of vegetation in the target coastal salt marsh area; and vegetation carbon density parameters are obtained, and the estimation of the total carbon sink amount of the target coastal salt marsh area is completed through spatial superposition calculation in combination with a vegetation coverage range, so that accurate classification of vegetation and efficient estimation of carbon sink are realized.

The invention relates to a crown segmentation method based on a CSAF framework, and the method comprises the steps: integrating Fourier transform and a state space model through a GM-Mama module, and effectively improving the extraction capability of a fuzzy crown contour; a forgetting factor is dynamically regulated and controlled by using an MASA-Optimizer module in combination with a multi-agent negotiation mechanism, and continuous self-adaptive learning of dynamic changes of species and phenology is realized; a physical constraint based on a Poisson equation is introduced by means of an MPC-Poisson module, and spectral interference of non-target vegetation is significantly inhibited; according to the method provided by the invention, high-precision crown instance segmentation and counting can be realized in a cross-species and cross-phenological complex scene, accurate calculation of a vegetation index of a single plant level is supported, and a flexible and powerful method is provided for analysis of different types of forest crowns.

The invention provides a method for estimating soil moisture through a combined assimilation strategy considering phenology, and relates to the technical field of soil moisture estimation. Using the calibrated WOFOST model to obtain downscaled root zone soil moisture data of the to-be-measured area; determining assimilation frequency according to different growth stages of the crops; obtaining observation data of the to-be-measured region according to the assimilation frequency, wherein the observation data comprises soil moisture and a leaf area index; fusing the root zone soil moisture data and the observation data by using ensemble Kalman filtering and generating assimilation data; and determining the soil moisture of the to-be-detected area according to the assimilation data. The problems that in the prior art, an unnecessary assimilation process exists, efficiency is greatly reduced, and higher calculation cost is brought by model simulation on the aspect of finer resolution are solved.

The invention discloses a japonica rice high-yield cultivation method based on temperature and light resources, and relates to the technical field of crop precise cultivation, and the method comprises the steps: calculating a TPU increment value based on field real-time temperature and light data, obtaining a historical TPU value data set, carrying out TPU growth prediction in combination with future weather forecast data, and generating a phenological period prediction instruction; based on the phenological period prediction instruction, identifying a phenological period time interval set, extracting meteorological data from future weather forecast data according to the phenological period time interval set, and generating a phenological period meteorological risk data set; and calculating the risk probability of low-temperature cold damage and high-temperature heat damage according to the phenological period meteorological risk data set, generating a meteorological risk probability set, carrying out risk early warning judgment according to the meteorological risk probability set, and generating a third-level risk early warning instruction signal. According to the invention, through generating the three-level risk early warning instruction signal, active and graded response to potential disasters is realized, and the accuracy and timeliness of disaster prevention and control are enhanced.

The invention discloses an under-forest autumn phenology quantification method and system based on an infrared camera, and belongs to the technical field of ecological detection, and the method comprises the steps: S1, under-forest vegetation image collection: employing the infrared camera to carry out the under-forest vegetation image shooting and collection at a phenology stage; s2, obtaining a daily-scale vegetation optimal image: carrying out image feature obtaining through an under-forest vegetation daily optimal image selection algorithm fusing multi-feature clustering and hierarchical screening; s3, checking the consistency of the meteorological data of the under-forest infrared camera and the data of the canopy meteorological station; s4, vegetation phenology dynamic extraction: adopting a dynamic quantile method to obtain a time sequence change curve, and determining a change rate curvature and a remote sensing phenology period of a dynamic threshold value based on a vegetation index; according to the method, forest under-forest vegetation dynamic monitoring is carried out by combining dynamic threshold identification and infrared camera imaging, redundant or low-quality images are effectively eliminated, the vegetation index extraction efficiency is improved, and the phenological period judgment precision is improved; and meanwhile, the algorithm is lightweight and efficient.

The invention provides a method for removing and treating harmful vegetation such as spartina alterniflora by using phenological characteristics, and provides a natural-based solution (NbS) by using biological phenological characteristics in combination with actual growth conditions and engineering cases of the spartina alterniflora. On one hand, the control opportunity is accurately butted with the key phenological periods (such as a seedling period, an elongation period, a blooming period and a seed maturation period) of the spartina alterniflora, and on the other hand, the phenological difference between the spartina alterniflora and the reed of the same gramineae which is most likely to be mixed and difficult to distinguish is fully utilized, and the reed which is most fragile, most likely to kill and difficult to distinguish is selected. And intervention is carried out on a time window which has the minimum influence on an ecological system, so that the efficient, environment-friendly and sustainable treatment target is achieved.

This invention discloses a deep learning-based method for predicting the phenological synchronization of specialized butterflies and their host plants, belonging to the interdisciplinary field of biodiversity conservation, ecological prediction, and deep learning technology. The method includes: collecting environmental climate variables, butterfly occurrence data, and phenological time-series data of their host plants; preprocessing the data to create training and validation sets; constructing a dual-label system with the day of year (DOY) of butterfly occurrence peaks (e.g., emergence peak, egg-laying peak) as the primary label and the normalized value of synchronization deviation as the secondary label; building a deep learning model with ecological weights, including an embedding layer, an LSTM layer, and a fusion layer; inputting a vector concatenated from daily or weekly climate time-series features and ecological dynamic features; and outputting the primary and secondary labels through a dual-output layer; designing a hybrid loss function that integrates the main regression loss, ecological synchronization constraint loss, and small-sample regularization loss; training the model using the Adam optimizer and implementing an early stopping mechanism; and validating and evaluating the model using regression accuracy and ecological synchronization accuracy indicators. The method includes modules for data acquisition, preprocessing, label construction, model training, prediction evaluation, and storage. This invention improves the accuracy of phenological synchronous prediction by embedding ecological dynamic feature weights and dual-label constraints, adapts to small sample scenarios, and provides technical support for the monitoring and protection management of rare butterfly species (such as the Golden Birdwing and the Chinese Tiger Swallowtail).

The invention discloses a wetland vegetation phenology monitoring method based on cooperation of ground observation and satellite remote sensing. The method comprises the following steps: arranging sample points in the field to obtain wetland vegetation ground observation phenology data; preprocessing the high / low resolution remote sensing data and generating dense EVI time sequence data by adopting a multi-source remote sensing image space-time fusion algorithm; carrying out smooth denoising on the time sequence EVI data based on an SG filtering algorithm; performing inversion based on a dynamic threshold method to obtain wetland vegetation satellite remote sensing phenological data; the relationship between ground observation phenological data and satellite remote sensing phenological inversion data is analyzed based on a linear regression method, a collaborative inversion model is constructed, and the wetland vegetation phenological inversion precision is improved. According to the method, the problem of scale errors caused by different observation scales of ground observation and remote sensing inversion data modeling is solved through cooperation of ground observation and remote sensing inversion data modeling, the wetland vegetation phenology inversion precision and robustness are remarkably improved, large-scale wetland vegetation phenology remote sensing inversion is achieved, and theoretical and technical supports are provided for health assessment of a wetland ecosystem.

The invention discloses a poplar and willow catkin flying concentration space-time diffusion forecasting method based on deep learning, and relates to the technical field of environmental monitoring, and the method specifically comprises the steps: firstly collecting multi-source data such as meteorology, phenology, poplar and willow distribution, terrain and the like, carrying out the preprocessing, unifying the data to a grid with a preset size, then standardizing the data, quantifying the phenology characteristics, and carrying out the prediction of the poplar and willow catkin flying concentration. The method comprises the following steps: determining phenological parameters and effective weights, calculating initial flying concentration by combining area types, tree density and a temperature and humidity correction function, integrating the initial flying concentration into a multi-dimensional tensor, and finally, fusing meteorological and terrain correction factors through a three-section model of spatial-temporal feature extraction-phenological attention fusion-diffusion prediction, and performing phenological period weighted mean square error loss function training to obtain the phenological period. According to the method, the phenological period is quantified into a continuously changing dynamic factor by setting the phenological validity weight, so that the rationality of source estimation is improved.

The invention discloses a method for extracting spring phenology of an evergreen broad-leaved forest, and relates to the technical field of ecological observation, and the method comprises the following steps: carrying out negative pixel correction processing and time interpolation processing on collected sunlight-induced chlorophyll fluorescence data; fusing the processed sunlight-induced chlorophyll fluorescence data with the temperature variable data, constructing a time sequence, and performing fitting processing to obtain a target time sequence; extracting spring phenology of the evergreen broad-leaved forest by adopting a plurality of preset vegetation phenology extraction methods based on the target time sequence; performing precision evaluation on the extracted spring phenology of the evergreen broad-leaved forest by using ground observation data; and based on a precision evaluation result, determining the optimal spring phenology of the evergreen broad-leaved forest from the extracted spring phenology of the evergreen broad-leaved forest. According to the method, through negative value pixel correction and time interpolation processing, sunlight-induced chlorophyll fluorescence data and temperature variable data are fused, and the combination of a multi-fitting method and a multi-extraction method is adopted, so that the accuracy of a result is improved.

The present invention discloses a method for calculating the probability and biomass of large drift algae appearing in the sea area, including using monitoring means to obtain relevant data of environmental factors and the sea area where large drift algae are located, combining the basic principles of phenology, constructing a large drift algae multi-source time series database, based on the database, distinguishing volatile environmental factors and stable environmental factors, calculating the information entropy of large drift algae appearing in the sea area, and obtaining the probability of large drift algae appearing in the grid within a set time scale; using a causal analysis method to determine the key stability environmental limiting factors for the growth of large drift algae; analyzing the influence of key stability environmental limiting factors on the growth of large drift algae biomass, constructing a large drift algae growth model, and calculating the growth amount of large drift algae biomass in each grid within a set time scale. The present invention is helpful for the early comprehensive prevention and control of large algae blooms, and is helpful for improving the ability to respond to major marine disasters and marine environmental security.

The application discloses a kind of evergreen broad-leaved forest spring phenology extraction method, it is related to ecological observation technical field, the method comprises: to the collected sunlight-induced chlorophyll fluorescence data is handled with negative value pixel correction and time interpolation processing;The sunlight-induced chlorophyll fluorescence data after processing is fused with temperature variable data, constructs time series and is handled to obtain target time series;Based on target time series, a variety of preset vegetation phenology extraction methods are used to extract evergreen broad-leaved forest spring phenology respectively;The accuracy of the extracted evergreen broad-leaved forest spring phenology is evaluated using ground observation data;Based on the accuracy evaluation result, the optimal evergreen broad-leaved forest spring phenology is determined from the extracted evergreen broad-leaved forest spring phenology.The application improves the accuracy of the results by negative value pixel correction and time interpolation processing, the fusion of sunlight-induced chlorophyll fluorescence data and temperature variable data, the combination of multiple fitting methods and multiple extraction methods.

The invention discloses a camellia oleifera phenology observation device and method, and particularly relates to the technical field of camellia oleifera phenology observing.The camellia oleifera phenology observation device comprises a fixed supporting rod, the bottom end of the fixed supporting rod is machined into a cone which can be conveniently inserted into a camellia oleifera field, and an observation assembly is arranged on the fixed supporting rod and comprises a movable supporting plate arranged on the outer wall of the fixed supporting rod in a sleeving mode; an electric holder is fixed to the top end of the movable supporting plate, an observation camera is installed on the electric holder, a base assembly is fixed to the bottom of the outer wall of the fixed supporting rod, and after the fixed supporting rod is inserted into an oil-tea field, the base assembly is located on the ground and used for supporting; a second monitoring module is arranged on the outer side of the base assembly. The influence of different environmental conditions on the phenological stage of camellia oleifera can be analyzed in combination with camellia oleifera growth environment data, the limitation of single observation data is effectively reduced, meanwhile, the interference of rainwater and small animals on camellia oleifera observation can be reduced, and the accuracy and reliability of camellia oleifera phenological observation are improved.

The application discloses a kind of near real-time remote sensing estimation method and device for crop agronomic phenophase, which comprises the following steps: obtaining historical remote sensing image and target remote sensing image of target area;According to the historical remote sensing image, a plurality of time curve model sets of different lengths starting from the starting time are constructed;According to the target remote sensing image, a target time curve is constructed, the target time curve is translated and stretched, the best matching time curve model is adaptively determined, and the corresponding translation and stretching factor and the agronomic phenophase information of the target crop are calculated.The above technical scheme is used, the user can combine historical remote sensing image and ground phenology statistical survey data to establish crop time curve model;And through model adaptive matching, the time curve model matched with the target time curve under the current non-complete growth cycle is obtained, and then the near real-time estimation of crop agronomic phenophase in target remote sensing image is realized, to meet the use demand of user.

The present invention discloses a multi-source remote sensing ecosystem carbon flux estimation method based on phenology, comprising the following steps: using multi-source remote sensing data to calculate the direct and diffuse photosynthetically active radiation of the target area; obtaining regional biological characteristic data of the same time series, using double S-curves to perform nonlinear least squares fitting to extract vegetation phenological characteristics, setting thresholds according to phenological characteristics, and constructing phenological constraint factors; based on the two-leaf light energy utilization efficiency framework, combining phenological constraint factors, establishing an ecosystem carbon flux model; and optimizing the model parameters using the Markov chain Monte Carlo method. Using the model after parameter optimization, global gross primary productivity data is generated. The method of the present invention is superior to the traditional light energy utilization efficiency model, and has advantages in simulating the temporal and spatial changes of gross primary productivity, and improves the simulation accuracy of global carbon flux.

The invention discloses a soil nutrient remote sensing intelligent agricultural decision-making system, which relates to the technical field of intelligent agriculture, takes laboratory test as an anchor, fuses data such as multi-temporal remote sensing, climate and solar geometry, and performs geometry-atmosphere consistency correction and observation confidence evaluation; performing state space coding of phenological phase alignment on the multi-year sequence to obtain a stable substrate and abnormal characterization; sample point-observation pairing and robust aggregation are completed in a time window based on comprehensive weights of factors such as climate, geometry, phase, stability, crop and growth vigor; quality gating and BRDF normalization are combined, and VIF and multi-output importance write-back screening features are grouped; simultaneously modulating loss and sampling according to data value scores in training; and outputting the pixel-level N / P / K continuous grid, the level division and the uncertainty, and performing capitalization recording. The system is high in precision, strong in robustness, reproducible and suitable for large-scale deployment.

The invention discloses an integrated fertilization system based on crop key phenology following, which is characterized in that a spectral data acquisition module is used for acquiring canopy reflection spectral data of crops to obtain a time sequence spectral matrix; the spectrum data processing module processes the time sequence spectrum matrix to generate a multi-dimensional phenological sensitive index time sequence vector; the phenology prediction module inputs the multi-dimensional phenology sensitive index time sequence vector into a two-channel long short-term memory network-full connection layer regression model to obtain a predicted phenology node date sequence; and the fertilization prediction module generates a fertilization formula, a fertilization amount and a fertilization time suggestion matched with the key phenological period of the crop based on the crop growth model and the nutrient demand model according to the phenological node date sequence, and outputs a control instruction to the fertilization execution mechanism. Through spectral data acquisition and a deep learning model, crop growth nodes are accurately judged, a scientific basis is provided for fertilization, and the problem that crop growth cannot be dynamically tracked in a traditional fertilization mode is solved.

The invention relates to the technical field of data extraction, and discloses a lake phytoplankton phenological parameter extraction method and system based on multi-scale parameter migration and a dynamic threshold, and the method comprises the steps: obtaining remote sensing image data of a target region, and constructing image data of a multi-scale time sequence; the method comprises the following steps: dividing a growth cycle of a plant, constructing a growth curve reference model and a parameter mapping model to obtain phenological morphological parameters of the plant in the growth cycle, and identifying and extracting key phenological parameters of the growth cycle through a preset dynamic threshold value. According to the method, the fitting stability of the high-noise sparse time sequence is improved, the fitting parameter mapping model is established, direct fitting of high-noise data is avoided, and the model robustness is improved; the dynamic self-adaptive adjustment of the phenological threshold is realized, so that the threshold is self-adaptively changed along with the algal bloom intensity, and the adaptability to lakes with different nutrition states and different years is improved; and long-time-sequence lake algal bloom phenology monitoring in different climate regions and different nutrition levels is supported.

The invention belongs to the technical field of ecological monitoring, and discloses a tree fallen leaf phenology prediction method based on a nonlinear model and a cold temperature day, and the method comprises the following steps: 1, carrying out the phenology observation of fallen leaves of a target tree species; 2, standardizing the number of fallen leaves of the target tree species; 3, the cold temperature day of the target tree species is calculated; 4, determining the cold temperature threshold temperature of the target tree species; and step 5, establishing a phenological prediction model of fallen leaves of the target tree species. The invention provides a high-precision and high-applicability method for dynamically monitoring and predicting phenology of tree fallen leaves. By introducing the cold temperature day and nonlinear model fitting, the dynamic process of the fallen leaves can be quantitatively described, the problems of high subjectivity, data discontinuity and the like existing in a traditional method are solved, and a new thought is provided for plant ecology research and climate change response evaluation.

The invention discloses a drought and flood remain effect tradeoff and synergistic effect quantification method, and belongs to the technical field of vegetation phenology in ecology, and the method comprises the steps: carrying out the spatial partitioning of spring and autumn phenology; constructing a spring and autumn phenology model by adopting a linear mixed effect model; and on the basis of a spring and autumn phenological model, constructing a leaving effect phenological model under different space partitions. According to the method, the core problem of limited explanatory force of a single factor and a single effect in the prior art is comprehensively solved through a refined space partition, a multi-factor integration model and a partition differentiation legacy effect model, and accurate quantification of a drought and flood legacy effect tradeoff and a synergistic effect is realized; and a more systematic and efficient method support is provided for phenological research in the arid region and scientific application in related ecological and climate fields.

The invention discloses a lake surface temperature reconstruction and freeze-thaw phenology extraction method based on filtering-automatic identification. The method comprises the steps of obtaining thermal infrared remote sensing data of a target lake in historical time; dividing a freeze-thaw period and a non-freeze-thaw period of the target lake; for a non-freeze-thaw period, acquiring a lake surface temperature time sequence of the non-freeze-thaw period; aiming at the freezing and thawing period, performing nonlinear curve fitting, and determining a freezing starting day, a freezing ending day, an ablation starting day and an ablation ending day of the target lake; according to the method, the continuity and precision of the lake surface temperature time sequence in the non-freezing-thawing period are improved, so that the error of traditional data caused by cold deviation is effectively reduced; and four accurate phenological key dates, namely freezing start and end and ablation start and end, can be scientifically, automatically and quantitatively extracted according to the freezing and thawing period, so that the deviation and low efficiency of subjective visual interpretation are avoided.

Systems and methods are provided for use in applying treatments to crops in fields. One example computer-implemented method includes determining a growth stage vector indicative of a growth stage of a crop in a field, using a GRU-based phenology model, based on a planting date of the crop and weather data for the field. The method also includes determining a disease risk for the crop in the field based on a disease risk model and the growth stage vector, determining a residual protection of the field for a prior treatment of the field, and determining whether application of the treatment is recommended for the field based on the disease risk and the determined residual protection. The method then includes, in response to determining that application of the treatment is recommended, identifying application intervals for the treatment based on the weather data for the application intervals.

The invention discloses a phenology-based leymus chinensis community distribution remote sensing identification method. The method comprises the following steps: step 1, obtaining a time sequence remote sensing image; 2, analyzing an NDVI time sequence curve; step 3, determining an effective time period; step 4, constructing a classification sample set; 5, constructing a classification feature set; step 6, remote sensing image classification; according to the method, the NDVI mutation time period caused by human factors in the NDVI time sequence curve is eliminated, and the effective time period of leymus chinensis community identification is determined, so that the accuracy of data is ensured; a dynamic time warping algorithm is used for evaluating the similarity between a time sequence curve of a pixel position and a time sequence curve of a typical sample point, sample amplification is completed, and a more representative classification sample set is constructed; a classification feature set is constructed by combining and integrating typical phenological parameters and common image features, so that the classification result is more accurate, and efficient and accurate recognition of the leymus chinensis community based on the random forest algorithm is realized.

The application discloses a cultivated land non-agricultural remote sensing monitoring system and method based on multi-source feature fusion and XGBoost, and the system comprises a feature extraction module, a sample balancing module, a model training and prediction module and a post-processing module. Through the whole-process collaborative optimization of multi-source feature fusion, sample balancing, model improvement and spatial post-processing, under different terrains, on the one hand, the problem that the sample is extremely unbalanced, the missing detection rate is high and the small illegal graph spot is difficult to identify is solved; and on the other hand, the complex feature of ground objects, the interference of seasons, phenology and linear ground objects and the false alarm rate are reduced; based on the single feature extraction method, the ground object feature is constructed, the hyperparameter is adjusted by the artificial trial and error method, the collaborative optimization monitoring framework is formed, and the post-processing is not combined with the actual business logic of cultivated land protection, so that the monitoring result still cannot meet the actual application requirement.

The invention belongs to the field of biological gene engineering, and particularly discloses a high-throughput sequencing-based conglomerate desert soil microbial diversity analysis method, which comprises the following steps of: sampling conglomerate desert soil in a key period of a plant growth season, preliminarily removing impurities, extracting DNA (deoxyribonucleic acid) in a sample, performing PCR (polymerase chain reaction) amplification on the obtained DNA, constructing a library, performing high-throughput sequencing, and determining the microbial diversity of the conglomerate desert soil in the key period of the plant growth season. The method comprises the following steps: splicing a conglomerate desert soil microflora, carrying out OTU clustering classification and chimera elimination on a spliced sequence by an operation classification unit, leveling according to a minimum sample sequence to obtain an OTU sequence set, and systematically analyzing alpha and beta diversity characteristics of the conglomerate desert soil microflora in different phenological periods by innovatively combining linear discriminant analysis and a random forest algorithm. Desert ecosystem microbial gate level dominant flora is disclosed for the first time. According to the method, an important technical support is provided for directionally regulating and controlling the composition of soil microorganisms, enhancing the carbon sequestration capability of a desert ecosystem and promoting vegetation recovery by revealing a coupling mechanism of the dynamic microbial community structure and the phenology of plants.