Vegetation ecological water demand monitoring method and device, storage medium and electronic equipment
Through the DEMC algorithm and enhanced vegetation index, the target monitoring model is fitted, and the accuracy and sensitivity of estimation of vegetation water demand in a large area of traditional remote sensing models is solved, and the accurate prediction of vegetation water demand is achieved.
Patent Information
- Application Number
- CN202411003660.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2024-11-15
AI Technical Summary
Traditional remote sensing model methods are difficult to achieve accurate and rapid estimation of ecological water demand in large areas, and the model parameters are highly sensitive, resulting in poor prediction results in different vegetation types areas.
By obtaining the vegetation water demand in the monitoring area, model meteorological driving data and prior information, the differential evolution Markov chain DEMC algorithm is used to iterate the optimal value of the sensitivity parameters, fit the target monitoring model, and then predict the vegetation water demand. This method combines enhanced vegetation index to reduce uncertainty during model simulation and adapt to different vegetation types.
Accurate prediction of vegetation water demand is achieved, the complexity and uncertainty of model calculation is reduced, and it is suitable for monitoring vegetation ecological water demand in large areas.
Smart Images

Figure CN118965976A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of ecological monitoring, and specifically, to a method, device, storage medium and electronic device for monitoring the ecological water demand of vegetation. Background Art
[0002] Plants regulate the water balance and energy balance of ecosystems through transpiration, affecting regional climate and environmental changes. Therefore, accurate estimation of vegetation ecological water demand is an important basis for scientific management of regional water resources, optimal allocation of water resources and formulation of ecological protection measures. Vegetation ecological water demand refers to the amount of water required for vegetation to maintain its normal growth, development, physiological processes and its environment. Vegetation ecological water demand includes water used by plant physiological processes such as vegetation transpiration and photosynthesis, and water used by vegetation growth environment such as soil evaporation and seepage. Among them, photosynthesis water demand and seepage water demand account for a relatively small proportion in arid ecosystems. Therefore, in actual research, evapotranspiration (i.e., vegetation transpiration and soil evaporation) is often used to approximate vegetation ecological water demand.
[0003] Scholars at home and abroad have conducted a lot of research on ecological water demand for different scales and research objects. Commonly used methods for estimating vegetation water demand include direct calculation method, area quota method, water balance method, phreatic evaporation method and remote sensing model method. Traditional direct estimation methods have high parameter requirements, require a large amount of ground experimental data support, and have a large workload. Some methods (such as water balance method) are only applicable to the study of closed watersheds and cannot reflect the actual needs of the ecosystem. Although remote sensing methods can be used for large-scale estimation, the model is portable and does not require a large amount of ground survey data support, and thus has gradually been used by some scholars to calculate vegetation ecological water demand; however, traditional remote sensing model methods require a large number of model parameters, the calculation is relatively complex, and the model uncertainty is high, which makes it difficult to achieve large-scale accurate and rapid estimation of vegetation ecological water demand in large-scale regional estimation. Summary of the invention
[0004] In order to overcome at least one of the deficiencies in the prior art, the present application provides a vegetation ecological water demand monitoring method, device, storage medium and electronic device, specifically including:
[0005] In a first aspect, the present application provides a method for monitoring vegetation ecological water demand, the method comprising:
[0006] Obtain the observed vegetation water demand in the monitoring area, the corresponding model meteorological driving data and the prior information of the model parameters; and obtain the sensitivity parameters of the model based on the parameter sensitivity analysis;
[0007] Fitting the optimal parameter value of the sensitivity parameter according to the vegetation water demand, the corresponding model meteorological driving data and the prior information of the model parameters;
[0008] According to the optimal parameter value, a target monitoring model adapted to the monitoring area is obtained;
[0009] The target monitoring model is used to predict the water demand of vegetation in the monitoring area.
[0010] In combination with the optional implementation manner of the first aspect, fitting the optimal parameter value of the sensitivity parameter according to the vegetation water demand, the corresponding model meteorological driving data and the prior information of the model parameters includes:
[0011] According to the vegetation water demand, the corresponding model meteorological driving data and the prior information of the model parameters, the optimal parameter value of the sensitivity parameter is iterated through the differential evolution Markov chain DEMC algorithm.
[0012] In combination with the optional implementation manner of the first aspect, the optimal parameter value of the sensitivity parameter is iterated through a differential evolution Markov chain DEMC algorithm according to the vegetation water demand, the corresponding model meteorological driving data and the prior information of the model parameters, including:
[0013] Initializing a parameter value of the sensitivity parameter and a parameter range of the sensitivity parameter;
[0014] Within the parameter range, a new parameter value is obtained by performing a differential evolution mutation optimization process on the parameter value of the sensitivity parameter;
[0015] The iterative model uses the prior information of the model parameters and the model meteorological driving data to obtain the prediction result of the vegetation water demand in the monitoring area, and calculates the difference between the prediction result and the vegetation water demand, wherein the iterative model is obtained by assigning the sensitivity parameters in the model through the new parameter values;
[0016] According to the difference, determining whether to accept the new parameter value;
[0017] If not, returning to the step of performing a differential evolution mutation optimization process on the parameter value of the sensitivity parameter within the parameter range to obtain a new parameter value;
[0018] If so, the optimal parameter value of the sensitivity parameter in the model is obtained according to the new parameter value.
[0019] In conjunction with an optional implementation manner of the first aspect, the model is a PT-JPL model, and predicting the vegetation water demand in the monitoring area by using the target monitoring model includes:
[0020] Obtaining current evapotranspiration information of the monitoring area;
[0021] Processing the current evapotranspiration information through the target monitoring model to predict vegetation transpiration, soil evaporation, and canopy interception evaporation in the monitoring area;
[0022] The prediction result of the vegetation water demand in the monitoring area is obtained based on the vegetation transpiration, soil evaporation and canopy interception evaporation.
[0023] In combination with the optional implementation manner of the first aspect, in the process of processing the environmental information, vegetation information and remote sensing information by the target monitoring model to predict the vegetation transpiration, soil evaporation and canopy interception evaporation in the monitoring area, it is necessary to calculate the green canopy limiting factor, and the expression of the green canopy limiting factor is:
[0024]
[0025] In the formula, f g represents the green canopy limiting factor, f apar represents the proportion of photosynthetically active radiation absorbed by the vegetation canopy, f Ipar represents the proportion of photosynthetically active radiation intercepted by the vegetation canopy; f apar The expression is:
[0026] f apar =m1*EVI+b1;
[0027] Where EVI represents the enhanced vegetation index, and m1 and b1 represent the preset parameters.
[0028] In combination with the optional implementation manner of the first aspect, multiple groups of optimal parameter values of the sensitivity parameters are preset, and multiple target monitoring models corresponding to the multiple groups of optimal parameter values are used to monitor monitoring areas of different vegetation types. The method further includes:
[0029] Acquire an image of the monitoring area at intervals of a preset time length;
[0030] Determining the current vegetation type of the monitoring area according to the image of the monitoring area;
[0031] Selecting a target optimal parameter from a plurality of groups of optimal parameter values according to the current vegetation type in the monitoring area;
[0032] A new target monitoring model of the monitoring area is generated according to the target optimal parameters.
[0033] In a second aspect, the present application also provides a vegetation ecological water demand monitoring device, the device comprising:
[0034] The data acquisition module is used to obtain the vegetation water demand observed in the monitoring area, the corresponding model meteorological driving data and the prior information of the model parameters; and obtain the sensitivity parameters of the model based on the parameter sensitivity analysis;
[0035] A model optimization module, used for fitting the optimal parameter value of the sensitivity parameter according to the vegetation water demand, the corresponding model meteorological driving data and the prior information of the model parameters;
[0036] The model optimization module is further used to obtain a target monitoring model adapted to the monitoring area according to the optimal parameter value;
[0037] The evaporation prediction module is used to predict the water demand of vegetation in the monitoring area through the target monitoring model.
[0038] In conjunction with the optional implementation manner of the second aspect, the model optimization module is further specifically used for:
[0039] According to the vegetation water demand, the corresponding model meteorological driving data and the prior information of the model parameters, the optimal parameter value of the sensitivity parameter is iterated through the differential evolution Markov chain DEMC algorithm.
[0040] In conjunction with the optional implementation manner of the second aspect, the model optimization module is further specifically used for:
[0041] Initializing a parameter value of the sensitivity parameter and a parameter range of the sensitivity parameter;
[0042] Within the parameter range, a new parameter value is obtained by performing a differential evolution mutation optimization process on the parameter value of the sensitivity parameter;
[0043] The iterative model uses the prior information of the model parameters and the model meteorological driving data to obtain the prediction result of the vegetation water demand in the monitoring area, and calculates the difference between the prediction result and the vegetation water demand, wherein the iterative model is obtained by assigning the sensitivity parameters in the model through the new parameter values;
[0044] According to the difference, determining whether to accept the new parameter value;
[0045] If not, returning to the step of performing a differential evolution mutation optimization process on the parameter value of the sensitivity parameter within the parameter range to obtain a new parameter value;
[0046] If so, the optimal parameter value of the sensitivity parameter in the model is obtained according to the new parameter value.
[0047] In conjunction with the optional implementation manner of the second aspect, the model is a PT-JPL model, and the evaporation prediction module is further specifically used for:
[0048] Obtaining current evapotranspiration information of the monitoring area;
[0049] Processing the current evapotranspiration information through the target monitoring model to predict vegetation transpiration, soil evaporation, and canopy interception evaporation in the monitoring area;
[0050] The prediction result of the vegetation water demand in the monitoring area is obtained based on the vegetation transpiration, soil evaporation and canopy interception evaporation.
[0051] In conjunction with the optional implementation manner of the second aspect, in the process of processing the current evapotranspiration information through the target monitoring model and predicting the vegetation transpiration, soil evaporation, and canopy interception evaporation in the monitoring area, it is necessary to calculate the green canopy limiting factor, and the expression of the green canopy limiting factor is:
[0052]
[0053] In the formula, f g represents the green canopy limiting factor, f apar represents the proportion of photosynthetically active radiation absorbed by the vegetation canopy, f Ipar represents the proportion of photosynthetically active radiation intercepted by the vegetation canopy; f apar The expression is:
[0054] f apar =m1*EVI+b1;
[0055] Where EVI represents the enhanced vegetation index, and m1 and b1 represent the preset parameters.
[0056] In conjunction with the optional implementation manner of the second aspect, multiple groups of optimal parameter values of the sensitivity parameters are preset, and multiple target monitoring models corresponding to the multiple groups of optimal parameter values are used to monitor different types of monitoring areas. The evaporation prediction module is further used to:
[0057] Acquire an image of the monitoring area at intervals of a preset time length;
[0058] Determining the current target type in the monitoring area according to the image of the monitoring area;
[0059] Selecting target optimal parameters from a plurality of groups of optimal parameter values according to the current target type in the monitoring area;
[0060] A new target monitoring model of the monitoring area is generated according to the target optimal parameters.
[0061] In a third aspect, the present application also provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the vegetation ecological water demand monitoring method is implemented.
[0062] In a fourth aspect, the present application also provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for monitoring the ecological water demand of vegetation is implemented.
[0063] In a fifth aspect, the present application also provides a program instruction, which, when executed by a processor, implements the vegetation ecological water demand monitoring method.
[0064] Compared with the prior art, this application has the following beneficial effects:
[0065] The present application provides a method, device, storage medium and electronic device for monitoring the ecological water demand of vegetation applied to electronic devices. Among them, the electronic device obtains the vegetation water demand observed in the monitoring area, the corresponding model meteorological drive and the prior information of the model parameters, and obtains the sensitivity parameters of the model based on the parameter sensitivity analysis, wherein the prior information of the model meteorological drive and the model parameters determines the accuracy of the simulation of the vegetation's water demand; according to the vegetation water demand, the corresponding model meteorological drive and the prior information of the model parameters, the optimal parameter value of the sensitivity parameter in the model is fitted; according to the optimal parameter value, a target monitoring model adapted to the monitoring area is obtained; and the vegetation water demand in the monitoring area is predicted by the target monitoring model. In this way, for the sensitivity parameters in the model, the best matching optimal parameter value is fitted through the vegetation water demand observation, the corresponding model meteorological drive data and the prior information of the model parameters, so that the target monitoring model obtained based on the optimal parameter value can realize the accurate prediction of the vegetation water demand in the monitoring area. BRIEF DESCRIPTION OF THE DRAWINGS
[0066] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0067] Figure 1 A flow chart of a method for monitoring vegetation ecological water demand provided in an embodiment of the present application;
[0068] Figure 2 A schematic diagram of the principle of the DEMC algorithm provided in the embodiment of the present application;
[0069] Figure 3A schematic diagram of the structure of a vegetation ecological water demand monitoring device provided in an embodiment of the present application;
[0070] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.
[0071] Icons: 11 - data acquisition module; 12 - model optimization module; 13 - evaporation prediction module; 21 - memory; 22 - processor; 23 - communication unit; 24 - system bus. DETAILED DESCRIPTION
[0072] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.
[0073] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.
[0074] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.
[0075] In the description of the present application, it should be noted that the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance. In addition, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.
[0076] Based on the above statement, as introduced in the background technology, the traditional remote sensing model method requires a large number of model parameters, the calculation is relatively complex, and the model uncertainty is high, which makes it difficult to achieve large-scale accurate estimation of vegetation ecological water demand when estimating in a large area. After a lot of research, it was found that some parameters in the traditional remote sensing model method are more sensitive to regional types. When predicting the water demand of vegetation in the monitored area by remote sensing model methods, it is necessary to adaptively adjust these parameters according to the type of monitored area, otherwise it is difficult to obtain better prediction results. The regional types here include forest areas, grassland areas, farmland areas, wetland areas, urban areas, deserts or semi-arid areas, etc.
[0077] Based on the discovery of the above technical problems, the inventors have proposed the following technical solutions to solve or improve the above problems through creative work. It should be noted that the defects in the solutions in the above prior art are the results obtained by the inventors after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed in the embodiments of the present application for the above problems below should all be the contributions made by the inventors to the present application in the process of invention and creation, and should not be understood as technical contents known to those skilled in the art.
[0078] In view of the above problems, this embodiment provides a vegetation ecological water demand monitoring method applied to electronic devices. In this method, the electronic device obtains the vegetation water demand observed in the monitoring area, the corresponding model meteorological drive and the prior information of the model parameters, and obtains the sensitivity parameters of the model based on the parameter sensitivity analysis, wherein the prior information of the model meteorological drive and the model parameters determines the accuracy of the simulation of the vegetation's water demand; according to the vegetation water demand, the corresponding model meteorological drive and the prior information of the model parameters, the optimal parameter value of the sensitivity parameter in the model is fitted; according to the optimal parameter value, a target monitoring model adapted to the monitoring area is obtained; and the vegetation water demand in the monitoring area is predicted by the target monitoring model. In this way, for the sensitivity parameters in the model, the best matching optimal parameter value is fitted through the vegetation water demand observation, the corresponding model meteorological drive data and the prior information of the model parameters, so that the target monitoring model obtained based on the optimal parameter value can realize the accurate prediction of the vegetation water demand in the monitoring area.
[0079] It should be noted that the electronic device implementing the vegetation ecological water demand monitoring method may be, but is not limited to, a mobile terminal, a tablet computer, a laptop computer, a desktop computer, and a server, etc. When it is a server, the server may be a single server or a server group. The server group may be centralized or distributed (for example, the server may be a distributed system). In some embodiments, the server may be local or remote relative to the user terminal. In some embodiments, the server may be implemented on a cloud platform; as an example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud (Community Cloud), a distributed cloud, an inter-cloud (Inter-Cloud), a multi-cloud (Multi-Cloud), etc., or any combination thereof. In some embodiments, the server may be implemented on an electronic device having one or more components.
[0080] To make the solution provided by this embodiment clearer, the following uses a server as an electronic device and combines Figure 1 Each step of the method is described in detail. However, it should be understood that the operations of the flowchart may not be implemented in order, and steps without logical contextual relationships may be reversed in order or implemented simultaneously. In addition, those skilled in the art may add one or more other operations to the flowchart, or remove one or more operations from the flowchart under the guidance of the content of this application. Figure 1 As shown, the method includes:
[0081] S1, obtain the observed vegetation water demand in the monitoring area, the corresponding model meteorological driving data and the prior information of the model parameters, and obtain the sensitivity parameters of the model based on the parameter sensitivity analysis.
[0082] Among them, the model meteorological driving data and the prior information of model parameters determine the simulation accuracy of vegetation water demand. Among them, the model meteorological driving data and the prior information of model parameters include the meteorological information and vegetation information required by the model. The meteorological information includes the remote sensing data such as temperature, relative humidity, net radiation, saturated water vapor pressure difference and NDVI monitored when the vegetation water demand in the monitoring area is observed.
[0083] S2, according to the vegetation water demand, the corresponding model meteorological driving data and the prior information of model parameters, the optimal parameter values of the sensitivity parameters are fitted.
[0084] In an optional implementation, the server can iterate the optimal parameter values of the sensitivity parameters in the model through the differential evolution Markov chain DEMC (Differential Evolution Markov Chain) algorithm based on the observed vegetation water demand, the corresponding model meteorological driving data and the prior information of the model parameters. Among them, the DEMC algorithm is an optimization algorithm based on swarm intelligence, which combines the characteristics of the differential evolution algorithm and the Markov chain Monte Carlo method. In the DEMC algorithm, multiple populations are used to search the solution space in parallel. Each population uses the differential evolution algorithm for local search, and the migration between populations uses the Markov chain Monte Carlo method. This algorithm enhances the global search capability through the migration of populations while maintaining population diversity, and is suitable for solving high-dimensional, multi-modal optimization problems. Therefore, it is widely used in fields such as data mining and machine learning.
[0085] Different from the conventional usage scenario, this embodiment uses the DEMC algorithm to iterate the sensitivity parameters in the model to obtain the optimal parameter value of the sensitivity parameter. In a specific implementation, the server can iterate the sensitivity parameters through the following steps:
[0086] Step 1, initializing the parameter value of the sensitivity parameter and the parameter range of the sensitivity parameter;
[0087] Step 2: within the parameter range, obtain new parameter values by performing differential evolution mutation optimization on the parameter values of the sensitivity parameters;
[0088] Step 3, the iterative model uses the model meteorological driving data and the prior information of the model parameters to obtain the prediction results of the vegetation water demand in the monitoring area, and calculates the difference between the prediction results and the vegetation water demand, wherein the iterative model assigns the sensitivity parameters in the model with new parameter values;
[0089] Step 4: determine whether to accept a new parameter value based on the difference; if not, return to step 2; otherwise, execute step 5.
[0090] In step 5, the optimal parameter values of the sensitivity parameters in the model are obtained according to the new parameter values.
[0091] Exemplarily, it is assumed that the model in this embodiment is the Priestley-Taylor Jet Propulsion Laboratory model of Fisher et al. (2008), hereinafter referred to as the PT-JPL model. This model is based on the Priestley-Taylor model, comprehensively considers a variety of biophysical stress factors, and constrains potential evapotranspiration to actual evapotranspiration. Compared with the traditional Penman model, this method avoids the calculation of aerodynamics and surface impedance, and reduces the uncertainty of model calculation. This model divides vegetation water demand ET into vegetation transpiration ET c , soil evaporation ET s and canopy interception evaporation ET i The water demand of vegetation is simulated by three parts and energy balance allocation. The calculation process is as follows:
[0092] ET=ET c +ET s +ET i ;
[0093] Among them, vegetation evapotranspiration ET c The calculation expression is:
[0094]
[0095] Soil evaporation ET s The calculation expression is:
[0096]
[0097] Canopy interception evaporation ET i The calculation method is:
[0098]
[0099] In the formula, f wet represents the relative surface humidity limiting factor, f wet =RH 4 , RH is relative humidity; f g represents the green canopy limiting factor, f apar represents the proportion of photosynthetically active radiation absorbed by the vegetation canopy, f Ipar represents the proportion of photosynthetically active radiation intercepted by the vegetation canopy; f t represents the temperature limiting factor, T a Indicates the air temperature, T opt represents the optimum temperature for vegetation growth; f m represents the water limiting factor, f smrepresents the soil moisture limiting factor, VPD represents the saturated vapor pressure difference, β represents the sensitivity of the water limiting factor to VPD; R nc is the net radiation intercepted by the vegetation canopy, R ns represents the net radiation of the soil surface; G represents the soil heat flux; α represents the PriestleyTaylor coefficient; Δ represents the slope of the temperature-saturated water vapor pressure curve; and γ represents the psychrometer constant.
[0100] The calculation expressions of some of the above parameters are as follows:
[0101] R nc =R n -R ns
[0102] R ns =R n exp(-k Rn ×LAI)
[0103] f apar =m1×EVI+b1
[0104] f Ipar =m2×NDVI+b2
[0105]
[0106]
[0107] e a =RH×e s
[0108] VPD=e s -e a
[0109] In the formula, R n represents the total net radiation, EVI represents the enhanced vegetation index, NDVI represents the normalized difference vegetation index, and LAI represents the leaf area index. k par =0.5, k Rn represents the extinction coefficient, which is 0.6 in this implementation, e s represents the saturated water vapor pressure, e a It represents actual vapor pressure and VPD represents saturated vapor pressure difference.
[0110] It is worth noting here that the proportion of photosynthetically active radiation absorbed by the vegetation canopy in the above expression is f apar In the original model of PT-JPL, the soil-adjusted vegetation index SAVI (Soil-Adjusted Vegetation Index) is used to calculate it, that is, fapar =m1×SAVI+b1. However, it was found in practice that, compared with traditional vegetation indices, such as the Normalized Difference Vegetation Index (NDVI), SAVI only reduces the impact of soil background on the vegetation index, but has lower sensitivity to high biomass areas, while the vegetation water demand in this embodiment is precisely the area with high biomass sensitivity. The study further found that the Enhanced Vegetation Index (EVI) adds a blue light band and an atmospheric correction term to the NDVI to improve the performance of the index. Therefore, a more complex atmospheric correction is used to reduce atmospheric influences such as aerosols and water vapor, which is particularly suitable for areas with dense vegetation. Therefore, this embodiment calculates the proportion of photosynthetically active radiation absorbed by the vegetation canopy f apar The soil-adjusted vegetation index (SAVI) in the original PT-JPL model was replaced by the enhanced vegetation index. It should be noted that this discovery was made by the inventor based on the research results summarized in the long-term practice process.
[0111] In order to reduce the uncertainty in model simulation, the parameters β, m1, b1 in the above expression are regarded as more sensitive parameters, that is, the sensitivity parameters in the PT-JPL model. Figure 2 As shown, for these three parameters, the following method is used to iterate them and obtain the optimal parameter value:
[0112] (1) Initialization (range, parameter value, storage array)
[0113] First, initialize the parameter range, mainly by setting the parameter c min and c max Limit the upper and lower limits of each parameter range. Then, initialize the parameter values, including the parameter d used to limit the number of parameters, the parameter b as the perturbation factor, and the i-th parameter x of the j-th chain o(j,i) , randomly initialized to c min(i) and c max(i) Finally, initialize the parameter storage array, including the array pa for storing the best parameters for each cycle, and the parameter J for storing the current error of each chain. old , initially N ss .
[0114] (2) Entering the main loop
[0115] Every 10 cycles, the scaling factor c is set to 1, otherwise it is set to Then, we randomly select two different chains from the N chains, denoted as R1 and R2, and calculate the new parameter value x p (j), the formula is as follows:
[0116]
[0117] In the formula, N(0,1) represents a normally distributed random number, and ensures that x p (j) in c min(j) and c max(j) between.
[0118] (3) Call the iterative model of the PT-JPL model and the observed vegetation water demand to calculate the error
[0119] The new parameters are assigned to the sensitivity parameters in the PT-JPL model to obtain the iterative model. The result of the iterative model simulation based on the model meteorological driving data and the prior information of the model parameters is expressed as result_ET, which is compared with the observed vegetation water demand to obtain the difference between the two. The expression is as follows:
[0120] e ET =||result_ET-obs ET || 2
[0121] DJ ET =2(std(obs ET )) 2
[0122]
[0123] Therefore, the difference between the two can be expressed as ΔJ = J new -J old (i,1) and accept or reject the new parameters according to the MH criterion. In the MH criterion, if min(1,exp(-ΔJ))>rand, the new parameters are accepted.
[0124] (4) Storing parameter values
[0125] The parameters of each loop are stored in the array pa, and the final optimized parameters are calculated. Specifically, by rearranging the parameters in the array pa into newpa, the median of each parameter is used as the final optimized parameter optpara, that is:
[0126] optpara(ii)=median(reshape(nepa((Nss*0.5+1):Nss,:,ii),0.5*Nss*N,1))
[0127] In this way, after a certain number of iterations, the optimal parameter values of the parameters β, m1, and b1 are obtained. Of course, the sensitivity parameters in the above examples are only for the convenience of understanding the examples listed and should not be regarded as limitations on the present application. In other words, when the present solution is actually implemented, other parameters can be selected as sensitivity parameters as needed, or, when the model changes, the sensitivity parameters will also change with the changes in the model.
[0128] Based on the optimal parameter values obtained in the above embodiment, continue to refer to Figure 1 The vegetation ecological water demand monitoring method provided in this embodiment also includes:
[0129] S3, obtaining a target monitoring model adapted to the monitoring area according to the optimal parameter values.
[0130] In this embodiment, the optimal parameter value is assigned to the corresponding sensitivity parameter to obtain a target monitoring model that is compatible with the monitoring area. It should be noted that this embodiment does not limit the number of sensitivity parameters. There can be one or more sensitivity parameters, and correspondingly, there can be one or more optimal parameter values. Therefore, it can be understood that the target monitoring model obtained in this embodiment is a customized model for the monitoring area, and when predicting the vegetation water demand in the monitoring area, a relatively accurate prediction result can be obtained.
[0131] S4, predicting the water demand of vegetation in the monitoring area through the target monitoring model.
[0132] In an optional implementation, the server can obtain the current evapotranspiration information; process the current evapotranspiration information through the target monitoring model to predict the vegetation evaporation, soil evaporation, and canopy interception evaporation in the monitoring area; and obtain the prediction result of the vegetation water demand in the monitoring area based on the vegetation evaporation, soil evaporation, and canopy interception evaporation. Among them, the evapotranspiration information includes the current meteorological information and vegetation information. The meteorological information includes the temperature, relative humidity, net radiation, saturated water vapor pressure difference obtained from the meteorological station, and the NDVI and other remote sensing data obtained from the research site.
[0133] As Figure 2 In the example shown, in this embodiment, the server processes the current evapotranspiration information through the target monitoring model, and in the process of predicting the vegetation evaporation, soil evaporation, and canopy interception evaporation in the monitoring area, it is necessary to calculate the green canopy limiting factor. The expression of the green canopy limiting factor is:
[0134]
[0135] In the formula, f g represents the green canopy limiting factor, f aparrepresents the proportion of photosynthetically active radiation absorbed by the vegetation canopy, f Ipar represents the proportion of photosynthetically active radiation intercepted by the vegetation canopy; f apar The expression is:
[0136] f apar =m1*EVI+b1;
[0137] In the formula, EVI represents the enhanced vegetation index, and m1 and b1 represent preset parameters. In this way, the enhanced vegetation index replaces the soil-adjusted vegetation index SAVI in the original PT-JPL model, improving the accuracy of predicting vegetation water demand in the target monitoring area.
[0138] In order to monitor the vegetation water demand in the monitoring area in real time, this embodiment also deploys the target monitoring model to the cloud platform, so as to use the real-time data of the cloud platform to monitor the vegetation water demand in the monitoring area in real time. Specifically, the target monitoring model can be deployed to the cloud computing platform of Google Earth Engine (GEE) through legal means, and the meteorological information and vegetation information required for the operation of the target monitoring model can be obtained through the GEE platform as the input data of the model, so as to estimate the ecological water demand within the scale of the monitoring area, and store the predicted results of the vegetation water demand within the scale of the monitoring area, or download the predicted results to the local storage device. Among them, the vegetation information is obtained through the MODIS land cover classification data MCD12Q1 in the GEE platform, and the meteorological information is obtained through the ERA5-Land in the GEE platform.
[0139] The study found that for the same monitoring area, the vegetation information in the monitoring area will change with the change of years or seasons. For example, assuming that the monitoring area is farmland, different crops will be planted in the farmland with the change of seasons, and different crops will produce different vegetation water requirements. Therefore, in order to adapt to the vegetation changes in the monitoring area, multiple sets of optimal parameter values of sensitivity parameters are preset in the server, and multiple target monitoring models corresponding to the multiple sets of optimal parameter values are used to monitor monitoring areas with different vegetation types. Then, the server obtains an image of the monitoring area at a preset time interval; determines the current vegetation type of the monitoring area based on the image of the monitoring area; selects the target optimal parameter from multiple sets of optimal parameter values based on the current vegetation type of the monitoring area; and generates a new target monitoring model for the monitoring area based on the target optimal parameter.
[0140] Therefore, in this embodiment, the server monitors the vegetation changes in the monitoring area by means of image recognition. When the vegetation changes are detected, the sensitivity parameters in the model are adaptively adjusted to adapt to the vegetation changes in the monitoring area.
[0141] Based on the same inventive concept as the vegetation ecological water demand monitoring method provided in this embodiment, this embodiment also provides a vegetation ecological water demand monitoring device, which includes at least one software function module that can be stored in an electronic device in the form of software. The processor in the electronic device is used to execute the executable module stored in the memory. For example, the software function module and computer program included in the device. Please refer to Figure 3 , functionally speaking, the device may include:
[0142] The data acquisition module 11 is used to obtain the observed vegetation water demand in the monitoring area, the corresponding model meteorological driving data and the prior information of the model parameters; and obtain the sensitivity parameters of the model based on the parameter sensitivity analysis.
[0143] The model optimization module 12 is used to fit the optimal parameter value of the sensitivity parameter according to the vegetation water demand, the corresponding model meteorological driving data and the prior information of the model parameters;
[0144] The model optimization module 12 is also used to obtain a target monitoring model adapted to the monitoring area according to the optimal parameter values;
[0145] The evaporation prediction module 13 is used to predict the water demand of vegetation in the monitoring area through the target monitoring model.
[0146] In this embodiment, the data acquisition module 11 is used to implement Figure 1 In step S1, the model optimization module 12 is used to implement Figure 1 In steps S2 and S3, the evaporation prediction module 13 is used to implement Figure 1 Therefore, for the detailed description of each of the above modules, please refer to the specific implementation of the corresponding step. In addition, in view of the same inventive concept as the vegetation ecological water demand monitoring method provided in this embodiment, the above modules can also be used to implement other steps or sub-steps of the method, which will not be repeated in this embodiment.
[0147] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
[0148] It should also be understood that if the above implementation is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.
[0149] Therefore, this embodiment further provides a storage medium, which stores a computer program. When the computer program is executed by a processor, the vegetation ecological water demand monitoring method provided in this embodiment is implemented. The storage medium can be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes.
[0150] This embodiment provides an electronic device for implementing a method for monitoring the ecological water demand of vegetation. Figure 4 As shown, the electronic device may include a processor 22 and a memory 21. In addition, the memory 21 stores a computer program, and the processor implements the vegetation ecological water demand monitoring method provided in this embodiment by reading and executing the computer program corresponding to the above implementation in the memory 21.
[0151] Continue to see Figure 4 The electronic device further includes a communication unit 23. The memory 21, the processor 22 and the communication unit 23 are electrically connected to each other directly or indirectly through a system bus 24 to achieve data transmission or interaction.
[0152] The memory 21 may be an information recording device based on any electronic, magnetic, optical or other physical principle, used to record execution instructions, data, etc. In some embodiments, the memory 21 may be, but is not limited to, a volatile memory, a non-volatile memory, a storage drive, etc.
[0153] In some embodiments, the volatile memory may be a random access memory (RAM); in some embodiments, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), a flash memory, etc.; in some embodiments, the storage drive may be a disk drive, a solid-state drive, any type of storage disk (such as a CD, a DVD, etc.), or a similar storage medium, or a combination thereof, etc.
[0154] The communication unit 23 is used to send and receive data through a network. In some embodiments, the network may include a wired network, a wireless network, a fiber optic network, a telecommunication network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a wide area network (WAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, or a near field communication (NFC) network, or any combination thereof. In some embodiments, the network may include one or more network access points. For example, the network may include a wired or wireless network access point, such as a base station and / or a network switching node, through which one or more components of the service request processing system may be connected to the network to exchange data and / or information.
[0155] The processor 22 may be an integrated circuit chip having a signal processing capability, and the processor may include one or more processing cores (e.g., a single-core processor or a multi-core processor). By way of example only, the processor may include a central processing unit (CPU), an application specific integrated circuit (ASIC), an application specific instruction set processor (ASIP), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), or a microprocessor, or any combination thereof.
[0156] Understandably, Figure 4 The structure shown is for illustration only. The electronic device may also have Figure 4 More or fewer components than shown, or with Figure 4 Different configurations are shown. Figure 4 The components shown may be implemented in hardware, software or a combination thereof.
[0157] In addition, this embodiment also provides a program instruction, which implements the vegetation ecological water demand monitoring method when executed by the processor.
[0158] It should be understood that the apparatus and method disclosed in the above-mentioned embodiments can also be implemented in other ways. The apparatus embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the apparatus, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.
[0159] The above are only various implementations of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A method for monitoring vegetation ecological water demand, characterized in that: The method comprises: Obtain the observed vegetation water demand in the monitoring area, the corresponding model meteorological driving data and the prior information of the model parameters; and obtain the sensitivity parameters of the model based on the parameter sensitivity analysis; Fitting the optimal parameter value of the sensitivity parameter according to the vegetation water demand, the corresponding model meteorological driving data and the prior information of the model parameters; According to the optimal parameter value, a target monitoring model adapted to the monitoring area is obtained; The target monitoring model is used to predict the water demand of vegetation in the monitoring area.
2. The method for monitoring vegetation ecological water demand according to claim 1, characterized in that: According to the vegetation water demand, the corresponding model meteorological driving data and the prior information of the model parameters, the optimal parameter value of the sensitivity parameter is fitted, including: According to the vegetation water demand, the corresponding model meteorological driving data and the prior information of the model parameters, the optimal parameter value of the sensitivity parameter is iterated through the differential evolution Markov chain DEMC algorithm.
3. The method for monitoring vegetation ecological water demand according to claim 2, characterized in that: According to the vegetation water demand, the corresponding model meteorological driving data and the prior information of the model parameters, the optimal parameter value of the sensitivity parameter is iterated through the differential evolution Markov chain DEMC algorithm, including: Initializing a parameter value of the sensitivity parameter and a parameter range of the sensitivity parameter; Within the parameter range, a new parameter value is obtained by performing a differential evolution mutation optimization process on the parameter value of the sensitivity parameter; The iterative model uses the prior information of the model parameters and the model meteorological driving data to obtain the prediction result of the vegetation water demand in the monitoring area, and calculates the difference between the prediction result and the vegetation water demand, wherein the iterative model is obtained by assigning the sensitivity parameters in the model through the new parameter values; According to the difference, determining whether to accept the new parameter value; If not, returning to the step of performing a differential evolution mutation optimization process on the parameter value of the sensitivity parameter within the parameter range to obtain a new parameter value; If so, the optimal parameter value of the sensitivity parameter in the model is obtained according to the new parameter value.
4. The method for monitoring vegetation ecological water demand according to claim 1, characterized in that: The model is a PT-JPL model, and the prediction of the vegetation water demand in the monitoring area by using the target monitoring model includes: Obtaining current evapotranspiration information of the monitoring area; Processing the current evapotranspiration information through the target monitoring model to predict vegetation transpiration, soil evaporation, and canopy interception evaporation in the monitoring area; The prediction result of the vegetation water demand in the monitoring area is obtained based on the vegetation transpiration, soil evaporation and canopy interception evaporation.
5. The method for monitoring vegetation ecological water demand according to claim 4, characterized in that: In the process of processing the current evapotranspiration information through the target monitoring model and predicting the vegetation evaporation, soil evaporation, and canopy interception evaporation in the monitoring area, it is necessary to calculate the green canopy limiting factor. The expression of the green canopy limiting factor is: In the formula, f g represents the green canopy limiting factor, f apar represents the proportion of photosynthetically active radiation absorbed by the vegetation canopy, f Ipar represents the proportion of photosynthetically active radiation intercepted by the vegetation canopy; f apar The expression is: f apar =m1*EVI+b1; Where EVI represents the enhanced vegetation index, and m1 and b1 represent the preset parameters.
6. The method for monitoring vegetation ecological water demand according to claim 1, characterized in that: A plurality of groups of optimal parameter values of the sensitivity parameters are preset, and a plurality of target monitoring models corresponding to the plurality of groups of the optimal parameter values are used to monitor monitoring areas of different vegetation types. The method further comprises: Acquire an image of the monitoring area at intervals of a preset time length; Determining the current vegetation type of the monitoring area according to the image of the monitoring area; Selecting a target optimal parameter from a plurality of groups of optimal parameter values according to the current vegetation type in the monitoring area; A new target monitoring model of the monitoring area is generated according to the target optimal parameters.
7. A vegetation ecological water demand monitoring device, characterized in that: The device comprises: The data acquisition module is used to obtain the vegetation water demand observed in the monitoring area, the corresponding model meteorological driving data and the prior information of the model parameters; and obtain the sensitivity parameters of the model based on the parameter sensitivity analysis; A model optimization module, used for fitting the optimal parameter value of the sensitivity parameter according to the vegetation water demand, the corresponding model meteorological driving data and the prior information of the model parameters; The model optimization module is further used to obtain a target monitoring model adapted to the monitoring area according to the optimal parameter value; The evaporation prediction module is used to predict the water demand of vegetation in the monitoring area through the target monitoring model.
8. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the vegetation ecological water demand monitoring method described in any one of claims 1-6 is implemented.
9. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the vegetation ecological water demand monitoring method described in any one of claims 1-6 is implemented.
10. A program instruction, characterized in that: When the program instructions are executed by the processor, the vegetation ecological water demand monitoring method as described in any one of claims 1-6 is implemented.
Citation Information
Cited By
Vegetation water demand prediction method and system for seawall ecological protection
CN120525302A
