138 results about "Environmental factor" patented technology

The invention relates to the cross technical field of artificial intelligence and environment monitoring, and discloses an algal community structure change prediction algorithm and system based on multi-source data fusion, and the algorithm comprises the steps: obtaining water quality, weather and plankton multi-source time sequence data; performing time alignment and missing value interpolation; eliminating and screening key environment factors through recursive features; performing dynamic weighted fusion on the multi-modal features by using a space-time attention mechanism; inputting a three-layer stacked LSTM network to output future algae dominant species abundance prediction; and model parameters are corrected on line based on measured data. The system comprises a multi-source data acquisition module, a preprocessing module, a key factor extraction module, a space-time attention fusion module, a dynamic prediction module and an adaptive correction module. According to the method, the prediction accuracy and stability are remarkably improved, and algal bloom early warning and ecological regulation are effectively supported.

The invention belongs to the technical field of environment regulation and control, and discloses a livestock breeding environment dynamic prediction and regulation and control method based on machine learning. Comprising the following six key steps: firstly, preprocessing multi-source data, and constructing a standardized feature data set; secondly, performing time sequence feature extraction and environment-biological response correlation analysis to obtain a multi-factor interaction network; then, constructing a dynamic coupling model of the environmental parameters and the production efficiency; a multi-target reinforcement learning regulation and control model is constructed based on the animal husbandry production efficiency prediction space; predictive environmental parameter regulation and risk assessment are carried out in combination with real-time monitoring data; and finally, intelligent environment intervention is executed, and a regulation and control strategy is iteratively optimized through production index feedback. According to the method, the breeding environment is converted from passive response to active prediction, complex correlation understanding between environmental factors and biological indexes is established, and multi-target balance optimization of production efficiency, energy consumption and animal welfare is achieved.

The invention discloses a soil fertilizer nutrition customization regulation and control method and system. The system comprises a data acquisition module, an environment compensation module, a soil nutrient dynamic prediction module, a target demand management module, a multi-target optimization module, a safety evaluation module, a monitoring self-adaptive learning module and the like, soil nutrition and safety indexes and external environment factors are acquired, data are corrected by using a compensation function, nutrient changes are predicted, a target range is set according to different growth stages of crops, and a monitoring self-adaptive learning module is established. A multi-objective optimization model is established based on organic fertilizer contribution and missing nutrients, an optimal formula is generated by comprehensively considering crop requirements, cost and environmental risks, and the model is dynamically updated through continuous monitoring and feedback closed loop after fertilization. According to the method, the fertilizer utilization rate and the fertilization precision can be remarkably improved, the soil acidification and heavy metal risks are reduced, and the balance of yield, quality and ecological safety is achieved.

The invention discloses a method for predicting abundance of plankton by using marine ecological observation data, which belongs to the technical field of marine organism prediction, and comprises the following steps: collecting multi-source marine environment data to obtain a data set; processing short-term correlation characteristics among variables from the data set to obtain an environmental factor interaction vector; processing the time dynamic change of the environmental factor interaction vector to obtain a plankton abundance change trend; enhancing the association strength of the environmental factor interaction vector and the plankton abundance change trend to obtain a weighted dynamic feature set; extracting subsets having influence on plankton abundance prediction from the weighted dynamic feature set to obtain a prediction feature group; and constructing a regression model according to the prediction feature group, and processing the newly obtained multi-source marine environment data by adopting the regression model to obtain a plankton abundance prediction value. The method for predicting the abundance of the plankton by using the marine ecological observation data solves the problems that the current prediction result is lagged or not accurate enough, and the timeliness and reliability of a decision are influenced.

The invention provides a hydrogen-rich water concentration dynamic adjustment method, and relates to the field of concentration adaptive adjustment, and the method comprises the following steps: S1, data acquisition; step S2, data preprocessing; s3, key influence factors are extracted; s4, acquiring the initial concentration of the hydrogen-rich water; and S5, obtaining the optimized concentration of the hydrogen-rich water: obtaining a dynamic concentration adjustment amount, an extreme environment adjustment amount and an implicit stress adjustment amount through reinforcement learning dynamic optimization, extreme environment adaptation and implicit stress early warning, and obtaining the final concentration of the hydrogen-rich water. According to the method, self-adaptive adjustment of the concentration of the hydrogen-rich water can be performed according to the growth state of the plant and environmental factors, the accuracy of the concentration of the applied hydrogen-rich water is ensured, and the problem that normal growth of the plant is affected due to too high or too low concentration of the hydrogen-rich water is avoided.

The invention relates to the technical field of species ecological niche modeling, and provides a coastal wetland waterfowl ecological corridor construction method and system, and the method comprises the steps: collecting target waterfowl species distribution point data, and obtaining a waterfowl species distribution data set; performing habitat suitability modeling on environmental factor data and the waterfowl species distribution data set through a species distribution model to obtain a coastal wetland ecological source land; habitat suitability prediction modeling is carried out on the environment variables through a random forest algorithm, resistance value assignment is carried out on suitability indexes, and a coastal wetland comprehensive resistance surface is obtained; and carrying out multi-scene corridor path identification on the coastal wetland comprehensive resistance surface and the coastal wetland ecological source land to obtain the coastal wetland waterfowl ecological corridor. According to the method, the functionality of the ecological corridor under different ecological backgrounds can be comprehensively reflected, so that the ecological suitability of the constructed corridor is improved.

The invention relates to the technical field of environment monitoring and intelligent sensors, and particularly discloses a soil pollutant detection and analysis system based on an intelligent sensor. The system comprises a sensor array module, a data preprocessing and fusion module, an ecological toxicity dynamic evaluation module and a decision output module. According to the invention, the biological response sensing unit capable of directly reflecting the ecological effect is integrated, and the ecological toxicity dynamic evaluation model fusing the concentration, the biological response and the environmental factors is innovatively constructed, so that direct and dynamic quantification from the pollutant content to the ecological risk is realized. According to the method, the problem that an existing assessment method is insufficient in biological correlation is solved, the risk assessment result is closer to the real ecological environment effect, and a reliable basis is provided for precise treatment.

The invention belongs to the technical field of precise environment control for pig breeding, and particularly relates to a method and system for pig breeding environment-behavior correlation modeling and cooperative regulation and control. The method comprises the following steps: S1, modeling an association mechanism of a multi-element environment factor and a pig abnormal behavior: fully mining the association between the multi-element environment factor and the pig abnormal behavior in an existing knowledge base by introducing a pre-trained large language model LLM, and modeling; s2, construction of an environment-behavior collaborative decision-making system guided by the large language model: constructing a multi-source real-time data acquisition system, synchronously acquiring and fusing environment and pig behavior data, and constructing the environment-behavior collaborative decision-making system based on the fine-tuned large language model for realizing multi-factor collaborative attribution and intelligent regulation and control. According to the method, the pre-trained large language model and the multi-source perception data are fused, and the method has the advantages that the processing efficiency can be guaranteed, and meanwhile accurate modeling and analysis of the complex environment-behavior relation can be achieved.

The invention relates to the technical field of jerusalem artichoke breeding and planting, and discloses a jerusalem artichoke variety breeding and planting method and system. The method comprises the following steps: collecting phenotype data of jerusalem artichoke plants at different growth stages Constructing a multi-dimensional growth model containing an incidence relation between environmental factors and phenotypic data, wherein the environmental factors are obtained by monitoring a planting area sensor array in real time; screening candidate jerusalem artichoke strains in the target environment parameter interval based on the phenotype-environment response curve; hybridizing and matching the candidate strains to obtain filial generation seeds, and sowing the filial generation seeds in a controllable environment test field; extracting gene expression profile data of offspring seeds, and establishing a genotype-phenotype incidence matrix in combination with the response curve; transplanting the dominant group to a field, and collecting growth dynamic data to update the multi-dimensional growth model; an environment control strategy is adjusted according to the updated model, and dominant groups are directionally cultivated; tubers are harvested and subjected to quality detection, and the result is fed back to the incidence matrix to optimize the next breeding process.

The invention relates to a probiotic product stability prediction model and a construction method and application thereof. The invention provides a new method capable of predicting the stability of the probiotic product earlier, faster and more accurately, 14 potential influence factors such as strain physiological characteristics, preparation processes and environmental factors are incorporated into a consideration system, and a machine learning algorithm is utilized to capture a complex nonlinear relationship between the potential influence factors and the stability, so that the stability of the probiotic product can be predicted more early, faster and more accurately. The accuracy and the reliability of the prediction model are greatly improved, the prediction timeliness is high, the universality and the guidance are high, and digital management can be realized.

The present application relates to the technical field of geomorphology prediction, in particular to a tidal flat evolution prediction method and system based on a geomorphology model. The method comprises the following steps: obtaining geomorphology data, environmental parameter data and biological membrane characteristic data of a target tidal flat area; the geomorphology data comprises water depth distribution and sediment porosity; the environmental parameter data comprises tidal current velocity, fluid shear force, light intensity and water temperature; the biological membrane characteristic data comprises biological membrane thickness obtained by in-situ sampling; a biological membrane dynamic viscosity coefficient model is constructed based on the biological membrane thickness and the water temperature; the dynamic viscosity coefficient model represents a nonlinear enhancement effect of the biological membrane on sediment viscosity; a biological membrane growth rate feedback model is established based on the water depth distribution and the light intensity; the feedback model quantifies the coupling relationship between biological membrane growth in a deposition area and microtopographic factors; the present application can solve the problem of inaccurate evolution prediction under dynamic interaction of environmental factors.

This invention discloses a method and system for determining the propagation conditions of wood-eating insect populations based on data modeling. Specifically, it relates to the field of computer data modeling and simulation optimization technology. The method addresses the problem that existing data modeling methods for establishing propagation conditions of wood-eating insect populations suffer from drift in model parameter mapping relationships and poor reproducibility of output propagation conditions in subsequent batches due to neglecting latent variables such as cross-interface microbial communities. The method establishes an initial mapping model by acquiring environmental parameters and population response data from multiple historical batches. For the data in the initial stage of the current batch, a residual sequence is calculated, and a non-random structure is determined based on the monotonic change trend of the residual fluctuation amplitude with the substrate fermentation process. When a non-random structure exists, the partial dependence relationship between the residual sequence and each environmental factor is extracted along the drift trajectory of the fermentation process as a characterization of the latent variable effect. After concentration screening, the initial mapping model is corrected, and the corrected mapping model is then used to simulate and optimize the output propagation conditions adapted to the latent variable environment.

The invention relates to the technical field of intelligent medicine, and discloses a microorganism and environmental factor association modeling method and system.The method comprises the steps that according to distribution data of features in a standardized data set, information entropy values of the features are determined; screening out features of which the feature weights are higher than a preset threshold in the feature entropy set to obtain a key feature set; taking the key feature set as a node, taking the interaction relationship as an edge, and taking the association strength as an edge weight to obtain an association model of the microorganisms and the environmental factors; performing performance evaluation on the association model by using the independent verification data set to obtain a model verification report of the association model; inputting the standardized data set of the target microorganisms and the target environmental factors, and obtaining an association network diagram of the target microorganisms and the target environmental factors, wherein the model verification report is a passed association model; according to the method, the accuracy of correlation modeling of microorganisms and environmental factors can be improved.

The invention discloses a fish egg hatching rate prediction optimization method based on deep learning, and belongs to the technical field of deep learning. Hatching environment parameters such as water temperature, dissolved oxygen and illumination intensity and roe physiological state parameters are collected, and a unified feature identifier is established; by introducing environment disturbance parameters such as temperature fluctuation, dissolved oxygen change and pollutant concentration and combining with a hatching rate index for correction, a dynamic response diagram under a real working condition is generated, and the robustness of a prediction model in a complex environment is improved; by constructing a multi-modal prediction strategy and a priority weighted multi-factor collaborative prediction mechanism, efficient collaboration and conflict arbitration among environmental factors are realized; and a real-time evaluation signal is generated in combination with sensor feedback, and the deep learning network is continuously updated, so that online optimization and adaptive adjustment of the prediction model are realized. The method can effectively improve the prediction precision of the roe hatching rate, improves the stability, energy efficiency and success rate of the hatching process, and has good agricultural applicability and expansibility.

The present application relates to the technical field of ecological environment, in particular to a water ecological system evaluation system and method based on a water habitat coupling mechanism model. The technical problem is to integrate key ecological mechanisms while maintaining high computational efficiency. The system includes: an input layer that receives measured data related to the water environment of the target water habitat; a configuration layer that selects several indicators from the geographic indicators, hydrological indicators, hydrodynamic indicators and meteorological indicators input by the input layer, and configures multiple different environmental factors; key ecological processes are integrated through selective mechanism coupling, and interspecific competition factors are configured for algae and biological interaction factors are configured for fish; the simulation layer uses a differential evolution algorithm to automatically calibrate and optimize the parameters configured by the configuration layer; obtain the spatial and temporal changes of aquatic plants, algae and fish; the output layer outputs the spatial distribution results of the three species of aquatic plants, algae and fish, and provides suggestions for scenario analysis results and environmental economic balance decision-making.

The application provides a soil environmental pollutant risk prediction method and system, which comprises the following steps: determining toxic substances having an influence on plants and animals of a species in a soil environment, and establishing a species sensitivity curve; obtaining environmental factors affecting the cumulative exposure of the toxic substances in an industrial park, and determining main environmental factors affecting the cumulative exposure of the toxic substances based on the environmental factors; based on the main environmental factors, a time series evolution prediction model is established by combining a time series and a multivariate autoregressive model; based on the species sensitivity curve and the cumulative exposure of the toxic substances in the future soil environment predicted by the time series evolution prediction model, a risk prediction model is established by combining a joint probability density model, the risk prediction model is used at least for predicting the probability of the soil environment of the industrial park being polluted by the toxic substances in the future; and the probability prediction value of the soil environment being polluted by the toxic substances in the future is predicted based on the prediction model.

The invention relates to the technical field of lobster breeding, and discloses a method for increasing the survival rate of lobster larvae in the floating period. The method comprises the following steps: dividing a larva density monitoring area according to physical structure parameters of a culture pond, and continuously collecting initial water environment parameters to obtain water environment time sequence data; on the basis of the time sequence data, key water quality fluctuation nodes are marked by adopting a dynamic time axis generation technology, and a water quality change map with time marks is obtained; performing multi-dimensional environmental factor mapping processing by combining the spatial distribution information of the larva density monitoring area and the water quality change map to generate a larva living environment pressure matrix; introducing an adaptive learning mechanism, carrying out pattern recognition processing on a dissolved oxygen fluctuation section and an ammonia nitrogen accumulation point in the pressure matrix, and establishing an environmental stress response rule base; and dynamically analyzing the operation instruction of the breeding equipment by using the rule base, and generating a feeding path optimization strategy and an oxygenation intensity adjustment strategy.

The utility model discloses a robinia pseudoacacia volumetric water content and environmental factor acquisition device. The device comprises an adjustable mounting rod; the environment factor acquisition part is arranged on the adjustable mounting rod and is used for acquiring environment factor data in real time; the plurality of robinia pseudoacacia data acquisition parts are used for respectively acquiring robinia pseudoacacia trunk data of the plurality of robinia pseudoacacia; and the electric appliance mechanism is arranged on the adjustable mounting rod, is electrically connected with the environment factor acquisition part and the robinia pseudoacacia data acquisition part, and is used for controlling the environment factor acquisition part and the robinia pseudoacacia data acquisition part to work and sending the acquired environment factor data and robinia pseudoacacia trunk data to an external monitoring terminal for processing and analysis. According to the utility model, the environmental factor data is acquired in real time through the environmental factor acquisition part, and the robinia pseudoacacia trunk data is acquired in real time through the robinia pseudoacacia data acquisition part and is sent to the external monitoring terminal for processing and analysis, so that the relationship between the volume water content of the robinia pseudoacacia and the environmental factors can be obtained; and real-time monitoring and continuous recording can be realized while the efficiency is high.

The application discloses a fruit tree load intelligent decision-making method based on pollen tube behavior and carbon accumulation balance, and belongs to the field of fruit tree growth management. The method collects physiological data such as fruit tree pollen tube growth and leaf photosynthesis in real time through multiple sensors, combines environmental factors and carbon balance parameters, constructs a multi-source data fusion model, and realizes fine perception and dynamic optimization and regulation and control of fruit load under different growth states of fruit trees. The system introduces an abnormal data detection and self-adaptive evolution mechanism to improve the adaptability and robustness of the model to complex field environments and various varieties. The application can effectively improve the yield and quality of fruit trees, optimize the utilization efficiency of carbon resources, and promote the intelligent and fine management of orchards.

The invention discloses a test device and method for researching physiological and ecological characteristics of disastrous periphytic algae and shellfish in a channel. The test device comprises a circulating water tank system, a multi-environmental factor coupling control system and an in-situ monitoring system, wherein the multi-environmental factor coupling control system is used for regulating and controlling one or more environmental factors of a water body in the circulating water tank system; the in-situ monitoring system is used for acquiring growth condition images of algae and / or activity condition images of shellfish in the circulating water tank system by adopting an AI behavior tracking camera, and extracting algae biomass data and / or shellfish movement behavior parameter data. According to the test method, algae biomass data and / or shellfish motion behavior parameter data are / is analyzed and processed to obtain a critical environment factor threshold value of algae and shellfish. According to the testing device, the environment of periphytic algae and shellfish can be simulated more truly, so that the physiological and ecological characteristics of the algae and shellfish can be researched more scientifically and more accurately.

The invention discloses a desertification restoration vegetation configuration optimization method and system based on microtopography regulation and control. The method comprises the following steps: dividing a research area into typical microtopography units according to surface morphological characteristics; measuring environmental factors in each microtopography; collecting functional character indexes and abundance of different microtopography unit species, calculating a community weighted mean value and a functional diversity index in combination with an environmental factor, calculating an ecological niche width and an optimal environmental parameter, and storing the ecological niche width and the optimal environmental parameter as a species ecological niche parameter table; constructing a three-dimensional adaptability matrix, calculating a comprehensive adaptability index of each species in each microtopographic unit through a adaptability deviation function, constructing a multi-objective optimization model by using the comprehensive adaptability index, a community weighted mean value and a functional diversity index, and setting space and ecological constraints; the model is solved to output the optimal plant combination and proportional relation under different micro-terrain units, and a spatialized vegetation configuration scheme is generated; according to the method, the problem that traditional ecological restoration is lack of a micro-topography zoning and quantitative configuration basis is solved.

The invention relates to the technical field of ecology and agronomy, in particular to a multi-environmental-factor coupled mosquito grass ecological adaptability prediction system and method, and the system comprises a data acquisition module, a data processing module, a coupling analysis modeling module, a dynamic prediction module and a space visualization module. Compared with the prior art in which a single environmental factor independent evaluation scheme is mainly adopted, serious limitation exists, complex interaction among various environmental factors cannot be accurately reflected, and an evaluation result often deviates from the actual situation, the method adopts a multi-factor dynamic coupling analysis scheme, and the evaluation result is more accurate. By comprehensively quantifying the weights and interaction effects of multi-dimensional environmental factors such as temperature, humidity, illumination and soil characteristics, an evaluation system comprehensively reflecting the comprehensive influence of the environment is established, the integrity and accuracy of ecological adaptability evaluation are remarkably improved, and a more scientific and reliable basis is provided for ecological system management.

This invention relates to a heat exchange model and detection method for pigs that integrates a mechanistic model and machine learning, belonging to the field of smart agriculture. First, a two-node heat exchange mechanism model for pigs based on environmental conditions is constructed, incorporating the physiological structural features of pigs into the modeling framework to realistically represent the heat exchange mechanism of pigs in actual farming environments. Second, a machine learning model is integrated, using environmental parameters and pig physiological data as inputs for model training. This deeply explores the intrinsic correlation between environmental factors and pig physiological responses, and the output feature values ​​of the machine learning model and the mechanistic model are fused through an attention mechanism. This method combines the simulation of physiological parameters by the mechanistic model with the dynamic correction of the machine learning model, compensating for deviations that occur in the mechanistic model during simulation. This provides a new solution for improving simulation accuracy, effectively enhancing the model's adaptive learning ability and improving its adaptability and robustness under complex and changing environmental conditions.

The application provides a kind of dynamic evaluation method for carbon storage of bivalve, which comprises the following steps: monitoring and collecting environmental data of typical aquaculture sea area, calculating a functional function, carrying out on-site flow experiment to determine physiological and biological parameters of bivalve, converting to obtain carbon parameters, based on dynamic energy budget theory, combining multiple environmental factors and carbon parameters to construct a carbon budget model integrating the whole physiological process, and finally simulating the carbon storage flux of bivalve in the growth cycle. The application solves the problems of static evaluation of bivalve carbon sink, insufficient consideration of environmental factor fluctuation, incomplete description of key physiological processes and insufficient precision of carbon budget quantification, and realizes the daily dynamic and accurate evaluation of bivalve carbon storage, quantifies the carbon storage contribution of shell formation and biogenic sedimentation.

The invention relates to the technical field of livestock breeding and feed nutrition, and discloses a low-protein diversified daily ration design method and system based on multi-source data fusion, and the method comprises the steps: constructing a formula-environment-effect directed causal diagram through a PC algorithm, estimating the effect deviation contribution proportion of an environment factor and a formula factor through anti-factual reasoning, and calculating the effect deviation contribution proportion of the environment factor and the formula factor; and inferring the target weight preference of the farm by using inverse reinforcement learning, and carrying out conditional weight updating according to a causal attribution result. Real reasons of growth effect deviation can be distinguished, effect deviation errors caused by environmental factors are prevented from being attributed to improper formula setting, and the accuracy and stability of formula recommendation are improved.

The invention provides a migrant bird habitat environment monitoring and protection method based on the Internet of Things, and relates to the technical field of environment monitoring and protection. Comprising the following steps: constructing a three-dimensional environment model of a target migrant bird habitat, and dividing the habitat into monitoring sub-regions; environment factor data of each monitoring sub-region are collected and preprocessed; constructing a habitat suitability evaluation model, and optimizing an environmental factor preference interval in the ecological niche factor analysis model by using kernel density estimation; deploying fixed Internet of Things monitoring nodes for the high-suitability level area; and dynamically monitoring the patrol path of the mobile monitoring equipment in the low-suitability-grade area according to seasonal periods. According to the method, the suitability is evaluated by applying a kernel density estimation and ecological niche factor analysis model, fixed and mobile monitoring nodes are deployed, and a patrol path is planned. The scientificity, the accuracy and the initiative of monitoring are improved, the ecological stability of the habitat of the migrant birds is powerfully guaranteed, and the long-term reproduction and inhabitation of the migrant birds are promoted.

This invention provides a method and apparatus for predicting the contents of fresh tea leaves at a regional scale. The method includes: analyzing the correlation between tea growth environmental factors and the contents of fresh tea leaves to determine target environmental factors; the growth environmental factors include at least one of temperature, precipitation, wind speed, and humidity during different growth stages of tea; using the target environmental factors to perform multi-level prediction of the contents of fresh tea leaves to obtain the prediction results. The method and apparatus of this invention can accurately identify core driving factors from complex ecological and environmental data, improving the prediction accuracy of subsequent models, and also revealing the specific influence mechanism of environmental factors on the formation of tea leaf contents, enhancing the theoretical depth and interpretability of the scheme; further, by using the target environmental factors to perform multi-level prediction of the contents of fresh tea leaves, the natural regional differences between different tea-producing areas are fully considered, improving the reliability and accuracy of the prediction of the contents of fresh tea leaves.

The invention belongs to the technical field of water body ecological risk assessment, relates to remote sensing image processing, environmental factor assessment and risk assessment, and aims to solve the problem that the prior art is short in remote sensing application, super-resolution fusion and risk diagnosis connection. The invention provides a large-scale aquatic vegetation imbalance risk differentiation diagnosis method based on super-resolution remote sensing. According to the method, a large-scale aquatic vegetation spatio-temporal information extraction method is constructed based on a remote sensing super-resolution reconstruction technology, that is, vegetation class groups, biomass and spatial distribution information are accurately extracted through super-resolution high-resolution remote sensing data. Meanwhile, a driving mechanism of multiple stress factors such as hydrological situation change, water quality pollution and habitat disturbance on aquatic vegetation under a large scale is disclosed by combining a multi-source data system. Finally, an evaluation system is constructed according to the evaluation indexes, systematic diagnosis of'classification-grading-zoning 'is achieved, and a global and differentiated treatment scheme is provided for water bodies of the whole key watershed, large lakes or cross-administrative districts.

The application relates to the technical field of data analysis, and provides a high and steep slope ecological restoration evaluation method and system based on multi-source data fusion. Embodiments of the application utilize multi-source observation data of a high and steep slope region to form a slope restoration observation data set with time sequence correlation, which contains surface coverage spectrum, soil environment monitoring, slope surface image and vegetation physiological characteristic data. According to the data set, a correlation mapping relationship between restoration indexes and environmental factors is generated, and a multi-dimensional evaluation model is constructed. A time sequence analysis algorithm is used to dynamically track the trend of key indexes, and a fuzzy comprehensive evaluation method is combined to obtain a comprehensive evaluation result. Based on the result, a visual evaluation report containing a time axis evolution trend graph, a spatial distribution heat map and a restoration grade division boundary line is generated, and is pushed to an ecological restoration management platform to support restoration strategy adjustment decision-making.

The invention belongs to the technical field of crop developmental stage diagnosis, and particularly relates to a crop developmental stage diagnosis method and system based on multi-modal data fusion. The method comprises the following steps: firstly, acquiring an image of a target crop, a shooting date of the image and environment factor data of the shooting date, and calculating a corresponding annual day according to the environment date; and inputting the acquired image, year date and environment factor data into a trained development period diagnosis model to obtain a development period diagnosis result of the target crop. According to the method, starting from three aspects of visual representation, a time process and an environmental factor for driving the process, the developmental stage diagnosis model can understand the internal mechanism of crop growth instead of only performing representation association, so that the model can still make accurate judgment when facing an abnormal climate annual scene, the generalization ability and robustness are remarkably improved, and the development stage diagnosis model can be widely applied to the field of crop growth. And the diagnosis precision of crop developmental stage diagnosis is improved.