Wetland group dynamic water distribution method, device and equipment based on multi-modal perception

Abstract

The application provides a kind of wetland group dynamic water distribution method, device and equipment based on multi-modal perception, relating to dynamic water distribution technical field, comprising: through the real-time collection of wetland group environmental data by pre-layout optimized multi-source sensor network;The standardized environmental data is obtained by preprocessing the environmental data;Based on the pre-trained federated learning model, the standardized environmental data is processed, and the water demand prediction value of each wetland is output;The water demand prediction value and real-time data are fused into a multi-dimensional feature vector and the feature weight is dynamically adjusted to obtain the fused data;Based on the fused data, a water distribution scheme is generated, and is executed after simulation and verification by a digital twin platform.The way improves the ecological relevance, ensures the ecological balance and saves resources.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of dynamic water distribution, in particular to a wetland group dynamic water distribution method, device and equipment based on multi-modal perception. BACKGROUND

[0002] Artificial wetlands are ecological engineering systems constructed by simulating natural wetlands, which use plants, microorganisms and substrates to cooperatively purify water bodies, and have the functions of water quality improvement, ecological restoration and water resource regulation. Artificial wetland management has an important influence on improving water purification efficiency, optimizing resource utilization and ensuring flood control and drought resistance. The core of artificial wetland management lies in dynamic water distribution, ensuring ecological balance, water purification and flood control and drought resistance, improving resource efficiency and responding to environmental mutations.

[0003] In the related art water distribution, a single wetland independent management mode is usually adopted, ignoring the ecological correlation between wetland groups, resulting in local ecological degradation or resource waste. SUMMARY

[0004] Therefore, the present application aims to provide a wetland group dynamic water distribution method, device and equipment based on multi-modal perception to improve ecological correlation, ensure ecological balance and save resources.

[0005] In the first aspect, the present application provides a wetland group dynamic water distribution method based on multi-modal perception, which collects environmental data of the wetland group in real time through a multi-source sensor network with pre-optimized layout; pre-processes the environmental data to obtain standardized environmental data; processes the standardized environmental data based on a pre-trained federated learning model to output water demand prediction values of each wetland; fuses the water demand prediction values with real-time data into a multi-dimensional feature vector and dynamically adjusts the feature weights to obtain fused data; generates a water distribution scheme based on the fused data, and executes after simulation and verification through a digital twin platform.

[0006] In a preferred embodiment of the present application, the layout optimization method of the multi-source sensor network includes: obtaining geographic coordinates of the wetland area to form a wetland plane; randomly selecting a preset number of initial cluster centers within the range of the wetland plane; the preset number is the number of sensor nodes in the multi-source sensor network; assigning each wetland area geographic coordinate to the nearest cluster center to form multiple clusters, and determining the mean of the geographic coordinates of each point in each cluster as the target cluster center; determining the center change between the target cluster center and the cluster center; when the center change is less than a pre-set change threshold or reaches a maximum iteration number, outputting the optimal arrangement position of the preset number of sensor nodes.

[0007] In the preferred embodiment of the present application, the above-mentioned step of assigning each wetland region geographic coordinate to the nearest cluster center to form multiple clusters and determining the mean of the geographic coordinates of each point in each cluster as the target cluster center comprises: determining, for each wetland region geographic coordinate, the Euclidean distance between the wetland region geographic coordinate and all cluster centers; assigning the wetland region geographic coordinate to the cluster corresponding to the cluster center with the smallest distance based on the Euclidean distance; and determining, for each cluster, the mean of the geographic coordinates of each point in the cluster as the target cluster center.

[0008] In the preferred embodiment of the present application, the above-mentioned step of determining the center change between the target cluster center and the cluster center comprises: re-determining the centroid coordinates of each cluster; and determining the center change between the target cluster center and the cluster center after each re-computation.

[0009] In the preferred embodiment of the present application, the above-mentioned step of preprocessing the environmental data to obtain standardized environmental data comprises:

[0010] In the preferred embodiment of the present application, the above-mentioned step of preprocessing the environmental data to obtain standardized environmental data comprises:

[0011] In the preferred embodiment of the present application, the above-mentioned step of fusing the water demand prediction value and the real-time data into a multi-dimensional feature vector and dynamically adjusting the feature weight to obtain fused data comprises: normalizing and combining the water demand prediction value and the real-time data into a multi-dimensional feature vector; and dynamically adjusting the feature weight based on the wetland type to obtain the fused data.

[0012] In a second aspect, the embodiments of the present application also provide a wetland group dynamic water distribution device based on multi-modal perception, comprising: an environmental data real-time acquisition module configured to collect environmental data of a wetland group in real time through a multi-source sensor network that is pre-optimized in layout; an environmental data preprocessing module configured to preprocess the environmental data to obtain standardized environmental data; a water demand prediction value output module configured to process the standardized environmental data based on a pre-trained federated learning model and output water demand prediction values of each wetland; a data fusion module configured to fuse the water demand prediction values and real-time data into a multi-dimensional feature vector, dynamically adjust the feature weight, and obtain fused data; and a water distribution scheme generation module configured to generate a water distribution scheme based on the fused data and execute the water distribution scheme after simulation and verification through a digital twin platform.

[0013] In a third aspect, the embodiments of the present application also provide an electronic device, comprising a processor and a memory, wherein the memory stores computer executable instructions capable of being executed by the processor, and the processor executes the computer executable instructions to implement the above-mentioned first aspect of the wetland group dynamic water distribution method based on multi-modal perception.

[0014] In a fourth aspect, the embodiments of the present application further provide a computer readable storage medium, which stores computer executable instructions. When the computer executable instructions are invoked and executed by a processor, the computer executable instructions cause the processor to implement the multi-modal perception based wetland group dynamic water distribution method of the first aspect.

[0015] The embodiments of the present application bring the following beneficial effects:

[0016] The embodiments of the present application provide a multi-modal perception based wetland group dynamic water distribution method, device and equipment. The multi-source sensor network with pre-optimized layout is used to collect the environmental data of the wetland group in real time. The environmental data is preprocessed to obtain standardized environmental data. The standardized environmental data is processed based on a pre-trained federated learning model to output the water demand prediction value of each wetland. The water demand prediction value and real-time data are fused into a multi-dimensional feature vector and the feature weight is dynamically adjusted to obtain the fused data. The water distribution scheme is generated based on the fused data, and is executed after being simulated and verified by a digital twin platform. In this way, the ecological correlation is improved, the ecological balance is ensured, and resources are saved.

[0017] Other features and advantages of the present disclosure will be described in the following description, or some features and advantages can be inferred from the description or determined without doubt, or can be known by implementing the above-mentioned technologies of the present disclosure.

[0018] In order to make the above-mentioned purposes, features and advantages of the present disclosure more obvious and easy to understand, the following preferred embodiments are described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or prior art description. Obviously, the drawings described below are some embodiments of the present application. For those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0020] Figure 1 A flowchart of a multi-modal perception based wetland group dynamic water distribution method provided by the embodiments of the present application;

[0021] Figure 2 A flowchart of another multi-modal perception based wetland group dynamic water distribution method provided by the embodiments of the present application;

[0022] Figure 3 A flowchart of another multi-modal perception based wetland group dynamic water distribution method provided by the embodiments of the present application;

[0023] Figure 4 A structural schematic diagram of a wetland group dynamic water distribution device based on multi-modal perception is provided for an embodiment of the present application.

[0024] Figure 5 A structural schematic diagram of an electronic device is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0025] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the present application will be described below in detail with reference to the drawings. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0026] Artificial wetlands are ecological engineering systems constructed by simulating natural wetlands, which use plants, microorganisms and substrates to cooperatively purify water bodies, and have the functions of water quality improvement, ecological restoration and water resource regulation. Artificial wetland management has important influence on improving water purification efficiency, optimizing resource utilization and ensuring flood control and drought resistance. The core of artificial wetland management is dynamic water distribution, which ensures ecological balance, water purification and flood control and drought resistance, improves resource efficiency and responds to environmental mutations.

[0027] In the related art water distribution, a single wetland independent management mode is usually adopted, and the ecological correlation between wetland groups is ignored, resulting in local ecological degradation or resource waste.

[0028] Based on this, the embodiments of the present application provide a wetland group dynamic water distribution method, device and equipment based on multi-modal perception, which can collect environmental data of the wetland group in real time through a multi-source sensor network optimized in advance, preprocess the environmental data to obtain standardized environmental data, process the standardized environmental data based on a pre-trained federated learning model, output the water demand prediction value of each wetland, fuse the water demand prediction value and real-time data into a multi-dimensional feature vector and dynamically adjust the feature weight to obtain fused data, generate a water distribution scheme based on the fused data, and execute after simulation and verification through a digital twin platform. In this way, the ecological correlation is improved, the ecological balance is ensured, and resources are saved.

[0029] To facilitate the understanding of the present embodiment, first, a wetland group dynamic water distribution method based on multi-modal perception disclosed by the present embodiment will be described in detail.

[0030] Embodiment 1

[0031] The embodiments of the present application provide a wetland group dynamic water distribution method based on multi-modal perception, Figure 1A flow chart of a wetland group dynamic water distribution method based on multi-modal perception is provided for an embodiment of the present application. As shown in Figure 1 , the wetland group dynamic water distribution method based on multi-modal perception can include the following steps:

[0032] Step S101, real-time collection of environment data of the wetland group by a multi-source sensor network with pre-optimized layout.

[0033] Among them, the multi-source sensor network can include soil moisture monitoring equipment, water quality monitoring equipment, meteorological monitoring equipment, etc.

[0034] Among them, the environment data can include soil moisture data, water quality data, meteorological data, etc.

[0035] Step S102, pre-processing of the environment data to obtain standardized environment data.

[0036] Specifically, the pre-processing of the environment data to obtain standardized environment data can include: removing high-frequency noise from the environment data using wavelet decomposition, reconstructing the denoising data; after reconstructing the denoising data, filling the missing data points by cubic polynomial interpolation to obtain standardized data.

[0037] Among them, in order to improve the data quality, the environment data can be pre-processed.

[0038] Among them, removing high-frequency noise from the environment data using wavelet decomposition, reconstructing the denoising data can include: removing high-frequency noise from the environment data using wavelet decomposition by the following formula: ; wherein, is the original signal, indicating the input data to be decomposed; k is the translation parameter, indicating the position of the wavelet function on the time axis; is the scale coefficient, generated by the scale function , reflecting the low-frequency component of the signal, ; is the detail coefficient, generated by the wavelet function , .

[0039] Among them, the soft threshold can be applied to remove high-frequency noise from the detail coefficient; wherein, is the noise standard deviation, and N is the number of data points. The reconstructed denoising data .

[0040] Specifically, filling the missing data points by cubic polynomial interpolation to obtain standardized data can include: for the missing data points , based on the data of adjacent time points and , , , construct a cubic polynomial: ; satisfy the boundary conditions and , and the first and second derivatives are continuous.

[0041] Therefore, for the missing point , the interpolation is calculated using the polynomial of the corresponding interval: . After supplementing the missing point, the standardized data is obtained.

[0042] Step S103, processing the standardized environmental data based on the pre-trained federated learning model, and outputting the water demand prediction value of each wetland.

[0043] Among them, the federated learning model (LSTM+FedAvg) can be used to predict the water demand of each wetland in the future target time according to the input historical water level, rainfall and evaporation.

[0044] Specifically, the overall structure of the local model can be: ; wherein, , , , are the weight matrices of the LSTM unit, respectively corresponding to the forget gate, the input gate, the output gate and the candidate memory unit; , , , are the bias terms of the LSTM unit; , , are the activation values of the forget gate, the input gate and the output gate, respectively; , is the candidate memory unit and the memory unit at the current time; is the hidden state at the current time.

[0045] Among them, the loss function is represented by the mean square error: , which is used to measure the deviation of the predicted water demand from the actual value .

[0046] Step S104, fuse the water demand prediction value and real-time data into a multi-dimensional feature vector and dynamically adjust the feature weight to obtain the fused data.

[0047] Specifically, the water demand prediction value and the real-time data are fused into a multi-dimensional feature vector and the feature weight is dynamically adjusted to obtain the fused data, which can include: normalizing and combining the water demand prediction value and the real-time data into a multi-dimensional feature vector; dynamically adjusting the feature weight based on the wetland type to obtain the fused data.

[0048] where each wetland node uploads local model parameters , the global model is weighted by data volume proportion to ensure that it reflects the data distribution of all wetlands: ; where, is the data volume of the kth node, .

[0049] By adding Gaussian noise differential privacy protection on the parameter , , the noise intensity is adjusted according to the privacy budget, such as = 1.

[0050] Specifically, the preprocessed environmental data is input into the global LSTM model, and the water demand sequence is output: ; the Monte Carlo Dropout method is used to calculate the confidence interval of the predicted value: ; where, is the mean of the predicted water demand, is the standard deviation of the predicted value, M is the number of Monte Carlo sampling, and z is the Z-score, for example: z = 1.96 corresponds to a 95% confidence level.

[0051] Specifically, the water demand prediction value, real-time water level, weather forecast and other data are normalized and combined into a multi-dimensional feature vector: , and then the feature weight is dynamically adjusted according to the wetland type, such as ecological zone / agricultural zone / flood control zone.

[0052] Step S105, based on the fused data to generate water distribution scheme, and through digital twin platform simulation verification and execution.

[0053] Wherein, the high-precision three-dimensional hydrological model of the wetland group can be constructed in real time through digital twin technology, integrating sensor network (water level, weather, water quality) and external data (weather forecast, remote sensing image), dynamically sensing the environmental state; based on the multi-objective optimization model to generate water distribution scheme, using digital twin platform to simulate the effect of the scheme, verify the feasibility and risk, and through intelligent gate (PID control) and solar water pump to accurately execute the water distribution instruction; combined with the isolation forest algorithm to detect anomalies (such as equipment failure or sudden heavy rain) in real time, trigger the emergency mode (start the standby water source, adjust the weight to give priority to protect the core ecological zone), at the same time, the closed-loop feedback mechanism continuously calibrates the model parameters, ensures that the system dynamically optimizes with the change of environment, realizes the precision, intelligence and high robustness of water resources allocation.

[0054] The multi-modal perception-based wetland group dynamic water distribution method provided by the embodiment of the present application can collect environmental data of the wetland group in real time through a multi-source sensor network with layout optimization, pre-process the environmental data to obtain standardized environmental data, process the standardized environmental data based on a pre-trained federated learning model, output water demand prediction values of each wetland, fuse the water demand prediction values and real-time data into a multi-dimensional feature vector and dynamically adjust the feature weight to obtain fused data, generate a water distribution scheme based on the fused data, and execute the water distribution scheme after simulation and verification through a digital twin platform. In this way, the ecological correlation is improved, the ecological balance is ensured, and resources are saved.

[0055] Embodiment 2

[0056] The embodiment of the present application also provides another multi-modal perception-based wetland group dynamic water distribution method; the method is implemented based on the method of the above embodiment; and the embodiment focuses on the specific implementation of the layout optimization mode of the multi-source sensor network.

[0057] Figure 2 The flowchart of another multi-modal perception-based wetland group dynamic water distribution method provided by the embodiment of the present application is shown in Figure 2 The layout optimization mode of the multi-source sensor network can include the following steps:

[0058] In step S201, the geographical coordinates of the wetland area are obtained to form a wetland plane.

[0059] The geographical coordinates of the wetland area can be longitude and latitude or two-dimensional plane coordinates.

[0060] In step S202, a preset number of initial cluster centers are randomly selected in the range of the wetland plane; the preset number is the number of sensor nodes in the multi-source sensor network.

[0061] The K initial cluster centers are randomly selected in the range of the wetland plane, and K is the number of sensor nodes, which can be determined according to the wetland area and resolution requirement.

[0062] In step S203, each wetland area geographical coordinate is assigned to the nearest cluster center to form multiple clusters, and the mean value of the geographical coordinates of each point in each cluster is determined as the target cluster center.

[0063] The geographical coordinates of each wetland area can be determined by the following formula: The Euclidean distance between the geographical coordinates of the wetland area and all cluster centers can be determined by the following formula: The wetland area geographical coordinates are assigned to the cluster corresponding to the cluster center with the smallest distance based on the Euclidean distance by the following formula: ​​For each cluster, determine the mean of the geographic coordinates of each point in each cluster as the target cluster center.

[0064] Step S204, determine the center change between the target cluster center and the cluster center.

[0065] Specifically, determining the center change between the target cluster center and the cluster center can include: re-determining the centroid coordinates of each cluster by the following formula: ; wherein, represents the data point set of the jth cluster, and represents the target cluster center; after each re-computation, the center change between the target cluster center and the cluster center is determined by the following formula: ; wherein, and represents the cluster center.

[0066] Step S205, when the center change is less than the pre-set change threshold or reaches the maximum number of iterations, output the optimal arrangement position of a preset number of sensor nodes.

[0067] Wherein, the change threshold can be set to 1-1.5m.

[0068] The wetland group dynamic water distribution method based on multi-modal perception provided by the embodiment of the application adopts the K-means clustering algorithm to optimize the sensor network, distributes the sensor nodes according to the optimal position by analyzing the geographic coordinates of the wetland area, maximizes the monitoring coverage and minimizes the data redundancy. By iteratively updating the cluster center, it ensures that the nodes evenly cover the key areas, improves the data collection efficiency, reduces the communication energy consumption and equipment redundancy, and meets the dynamic monitoring needs of the wetland.

[0069] Embodiment 3

[0070] The embodiment of the application also provides another wetland group dynamic water distribution method based on multi-modal perception; the method is realized on the basis of the above-mentioned embodiment method; the method focuses on the specific implementation mode of generating a water distribution scheme based on fused data and executing after simulation and verification by a digital twin platform.

[0071] Figure 3 The flowchart of another wetland group dynamic water distribution method based on multi-modal perception provided by the embodiment of the application is shown in Figure 3 , which generates a water distribution scheme based on fused data and executes after simulation and verification by a digital twin platform, which can include the following steps:

[0072] Step S301, generate a Pareto optimal solution set based on the fused data combined with the NSGA-III algorithm.

[0073] The fused data includes real-time data and prediction data. The real-time data can include current water level, soil moisture and water quality indicators, such as PH, dissolved oxygen, etc. The prediction data can include water demand in the future specified time output by the federated learning model, weather forecast, etc. The weather forecast can be rainfall, evaporation, etc. The future specified time can be 24 hours in the future, for example.

[0074] Specifically, population initialization is performed: N candidate solutions are randomly generated, for example, N = 100, and each solution includes: water distribution amount , gate opening , water distribution timing .

[0075] Non-dominated sorting is then performed: the solution set is layered based on the objective function value by the following formula: , , The first layer of non-dominated solutions is screened out: all candidate solutions are traversed, and each solution is compared with other solutions one by one. If solution A is not inferior to solution B in all objective functions, and is strictly superior in at least one objective, then solution A dominates solution B. The solution that is not dominated by any other solution is the non-dominated solution. All non-dominated solutions are classified into the first layer of Pareto front, forming the initial optimal solution set.

[0076] Reference points are then generated: reference points are uniformly distributed in a three-dimensional target space (ecology, economy, and society) to ensure solution set diversity. The number of reference points M is represented as: ; wherein H is the number of partitions in each target direction (i.e. the number of uniformly divided intervals), for example: H = 4 means that each target dimension is divided into 4 segments; D is the number of objective functions (dimension number) of the optimization problem, for example: D = 3 corresponds to three objectives of ecology, economy, and society; M is the total number of generated reference points.

[0077] Therefore, when H = 4 and D = 3, , a total of 20 uniformly distributed reference points are generated.

[0078] Finally, crossover and mutation are performed: crossover and mutation generate offspring by simulating binary crossover (SBX) combined with the excellent characteristics of the parent generation to ensure that the solution set inherits advantages; polynomial mutation introduces random disturbance to break through local optimality and explore new solution space. The two work together to maintain population diversity, avoid premature convergence, and ensure the universality and balanced distribution of Pareto front solutions. Simulated binary crossover (SBX) is used to generate offspring solutions.

[0079] Crossover probability refers to the probability of gene exchange between two parent individuals to generate offspring in genetic algorithms, which is usually between 0.5 and 1; a high probability is conducive to promoting the transmission of excellent characteristics and accelerating convergence.

[0080] The mutation probability refers to the probability of random change of individual genes, and the mutation probability (n is the variable dimension) is usually between 0.001 and 0.01; the low probability is beneficial to maintain the population diversity and avoid local optimum.

[0081] In step S302, the target weight is dynamically adjusted through deep reinforcement learning.

[0082] In the formula, the NSGA-III is used to generate a Pareto solution set, and the deep reinforcement learning (PPO) is used to adjust the ecological, economic and social target weights in real time, so as to solve the multi-dimensional demand conflict and improve the adaptability and balance of the water distribution strategy.

[0083] In the formula, the target weight can be dynamically optimized according to the real-time environmental changes. The deep reinforcement learning (PPO) can learn the optimal strategy in interaction by defining the state space (such as real-time water level and weather forecast), the action space (dynamically adjusting the ecological / economic / social target weight) and the reward function (vegetation coverage, energy consumption and other indicators).

[0084] In the formula, the target weight can be the ecological target weight, the economic target weight and the social target weight. Initially, the initial weights of the ecological target, the economic target and the social target are allocated, for example, the ecological target weight =0.6, the economic target weight =0.3, and the social target weight =0.1.

[0085] In the formula, the reward function involves ecological reward, economic penalty and social penalty. For the ecological reward: the reward is +10 for each 1% increase in vegetation coverage; for the economic penalty: the penalty is -5 for each 1kwh increase in energy consumption; for the social penalty: the penalty is -20 for each 1 yuan overspending in irrigation cost.

[0086] Specifically, the interaction data (dynamic-action-reward) can be collected based on the current strategy, and the generalized advantage estimation (GAE) is used to calculate the action advantage value .

[0087] Therefore, the objective function is maximized , which is represented by the following formula: .

[0088] In the formula, πθ(a|s) is the probability of selecting the action a under the state s by the current strategy (neural network); and πθold(a|s) is the probability of selecting the same action by the old strategy (the strategy before updating), which is used to constrain the updating range of the strategy. ​​​​​For the advantage function, measure the action The pros and cons of the average strategy (such as the comprehensive improvement of ecological, economic and social goals); For the shear threshold, limit the policy update step size to prevent training instability.

[0089] Finally, adjust the target weights based on the optimized strategy, for example, adjust the initial weights of ecological, economic and social goals to: ecological goal weight =0.65, economic goal weight =0.25, and social goal weight =0.1.

[0090] Step S303, determine the water distribution scheme based on the Pareto optimal solution set and the target weights.

[0091] In order to make the generated water distribution scheme meet the actual constraint conditions, constraint processing and scheme verification are required. For example, when the water volume is over the limit, a penalty is imposed on the solution that violates the constraint, and the penalty term is: ; Wherein, represents the penalty coefficient, .

[0092] Where, the scheme needs to be verified for feasibility, according to the channel length L and the flow rate v, the transmission time is calculated to ensure ; Check must be greater than the ecological water demand, that is, , for example, the ecological water demand of mangrove forest .

[0093] Specifically, select the solution with the highest comprehensive score from the Pareto frontier, for example, the ecological score accounts for 60%; Determine the water allocation for each wetland , for example, the mangrove area is 1200m 3 / d, and the agricultural area is 800m 3 / d; And determine the execution parameters, for example, the gate opening =75%, the water distribution timing is 6:00~8:00 every day; Pre-visualize the scheme effect in the digital twin platform, and verify the water level change and ecological impact.

[0094] Step S304, execute the water distribution scheme through the digital twin platform and monitor the execution results, and adjust the Pareto optimal solution set based on the execution results.

[0095] The dynamic feedback and iterative optimization aims to continuously optimize the model according to the actual execution results. By monitoring the water level, vegetation coverage, energy consumption and other indicators in real time after execution, the model is updated. If the actual effect deviates from the prediction (such as water level error ≥ 5%), the NSGA-III is triggered to regenerate the solution set, and the federal learning model parameters are updated to improve the accuracy of water demand prediction.

[0096] Among them, the digital twin modeling about the digital twin platform: can build a three-dimensional hydrological model of wetlands (resolution 1m x 1m) based on remote sensing and GIS, integrate soil permeability coefficient, vegetation transpiration rate and other parameters, real-time access to sensor, weather and satellite data, and calibrate the model accuracy (water level error ≤ 5%) through historical data, establish a virtual-real synchronous twin platform, and support dynamic monitoring and closed-loop control.

[0097] Specifically, three-dimensional hydrological modeling is performed: based on remote sensing images and geographic information system (GIS), a three-dimensional terrain model of wetland group is established (resolution 1m x 1m). Integration of hydrological parameters: soil permeability coefficient, vegetation transpiration rate, channel slope, etc.; data access: real-time access to sensor data (water level, soil moisture, water quality), weather forecast (rainfall, evaporation), satellite remote sensing data (NDVI vegetation index); model calibration: use historical data to verify the model accuracy (such as water level simulation error ≤ 5%), adjust parameters (such as Manning coefficient).

[0098] Specifically, real-time data monitoring and data synchronization are performed: data collection, sensor network uploads data (water level, soil moisture, equipment status) every 5 minutes; data cleaning, wavelet decomposition and cubic polynomial are used for denoising and filling processing; digital twin synchronization, real-time water level, vegetation coverage and other parameters in the three-dimensional model are updated, and a visual interface is generated.

[0099] Specifically, optimal control instructions can be generated based on the digital twin simulation results, which specifically include: scenario simulation: input the water distribution scheme generated by the multi-objective optimization model to simulate the water level change, vegetation response and energy consumption within the next 6 hours; risk assessment: detect potential risks (such as water level overrun or channel blockage); generate instructions: if the simulation results meet the constraint conditions, output the execution instructions (gate opening, pump flow); otherwise, trigger the optimization model to recalculate.

[0100] Specifically, the decision instructions can be converted into physical device actions, which specifically include: intelligent gate control, set the target water level , calculate the error by the following formula , control the output by the following formula: , wherein, , , , adjust the gate opening (accuracy 1cm), so as to make the actual water level approach the target value; solar water pump control, according to the water distribution amount Adjusting flow: , flow = Qitirrigation (such as = 1200 m 3 / d, t = 8 h, flow = 150 m 3 / h), dynamically adjusting the water pump speed (accuracy 5%), matching the water distribution time sequence.

[0101] Specifically, abnormality detection and emergency response can be performed, specifically including:

[0102] Regarding abnormality detection, an isolation forest algorithm is adopted: constructing an isolated tree (iTree): randomly selecting a feature and a split value, recursively dividing the data space into sub-regions until each sub-region contains only one sample or reaches the tree height limit; abnormal point characteristics: because of the large difference from most data, abnormal points are usually isolated at a shallow layer (shorter path); calculating path length: recording the average path length required for each sample to be isolated in all isolated trees ; the shorter the path length, the higher the sample abnormality probability; calculating abnormality score: analyzing the sensor data stream, calculating the abnormality score: , wherein, is the average path length of the data point in the isolated tree, is a path length normalization factor, and a score close to 1 is determined to be abnormal, and a score close to 0 is normal. Specifically, if the abnormality score is > 0.7, it is determined to be an abnormal event (such as affected by heavy rain, equipment failure, etc.).

[0103] Regarding emergency mode triggering: starting a backup water source, automatically starting a groundwater well or a water storage tank to ensure water supply for the core ecological area; conservative strategy switching, mangrove protection area: maintaining the minimum ecological water demand = 1000 m3 / d, agricultural area: reducing the water distribution amount to 50% (such as = 400 m3 / d); manual intervention notification: sending an alarm to the administrator, for example, through APP push and SMS sending.

[0104] Specifically, system parameters can be optimized according to actual execution effect:

[0105] Effect evaluation: comparing the deviation of the digital twin prediction value and the actual water level and vegetation coverage (allowable error ≤ 5%); parameter calibration: if the deviation is out of limit, adjusting the hydrological model parameters (such as the permeability coefficient) or the federal learning model weight; model retraining: collecting new data, updating the LSTM water demand prediction model (training once every 7 days).

[0106] Specifically, a man-machine interaction interface can be provided to support decision monitoring:

[0107] Cloud platform: WebGL three-dimensional interface displays real-time water level, water distribution scheme simulation, and equipment status; historical data backtracking (such as water level change curve in the past 30 days). Mobile APP: real-time receiving of early warning (such as "water level in mangrove area is lower than threshold"); remote manual regulation and control (such as forced closing of a gate).

[0108] The wetland group dynamic water distribution method based on multi-modal perception provided by the embodiment of the application adopts NSGA-III to generate a Pareto solution set, combines deep reinforcement learning (PPO) to adjust ecological, economic and social target weights in real time, solves multi-dimensional demand conflicts, improves the adaptability and balance of the water distribution strategy, constructs a high-precision three-dimensional hydrological model, integrates PID algorithm and solar equipment to accurately execute water distribution instructions, dynamically calibrates the model through real-time data feedback, realizes "perception-decision-execution-optimization" whole-process closed-loop management. Based on the isolated forest algorithm, real-time data anomalies (such as heavy rain and equipment failure) are detected, and standby water sources are automatically started and the water distribution strategy is adjusted to ensure water supply in the core ecological area and enhance the risk resistance and emergency response efficiency of the system.

[0109] Embodiment 4

[0110] Corresponding to the method embodiment described above, the embodiment of the application provides a wetland group dynamic water distribution device based on multi-modal perception, Figure 4 A structure diagram of the wetland group dynamic water distribution device based on multi-modal perception provided by the embodiment of the application is shown in Figure 4 As shown in the figure, the wetland group dynamic water distribution device based on multi-modal perception can include:

[0111] The environmental data real-time acquisition module 401 is used to acquire environmental data of the wetland group in real time through a multi-source sensor network optimized in advance.

[0112] The environmental data preprocessing module 402 is used to preprocess the environmental data to obtain standardized environmental data.

[0113] The water demand prediction value output module 403 is used to process the standardized environmental data based on a pre-trained federated learning model, and output water demand prediction values of each wetland.

[0114] The data fusion module 404 is used to fuse the water demand prediction values and real-time data into a multi-dimensional feature vector and dynamically adjust the feature weight to obtain fused data.

[0115] The water distribution scheme generation module 405 is used to generate a water distribution scheme based on the fused data, and execute after simulation and verification through a digital twin platform.

[0116] The wetland group dynamic water distribution device based on multi-modal perception provided by the embodiment of the present application can collect environmental data of the wetland group in real time through a multi-source sensor network that is pre-optimized in layout, pre-process the environmental data to obtain standardized environmental data, process the standardized environmental data based on a pre-trained federated learning model, output water demand prediction values of each wetland, fuse the water demand prediction values and real-time data into a multi-dimensional feature vector and dynamically adjust the feature weight to obtain fused data, generate a water distribution scheme based on the fused data, and execute the water distribution scheme after simulation and verification through a digital twin platform. In this way, the ecological correlation is improved, the ecological balance is ensured, and resources are saved.

[0117] In some embodiments, the environmental data real-time acquisition module is further configured to obtain geographical coordinates of the wetland areas to form a wetland plane, randomly select a preset number of initial cluster centers within the wetland plane, set the preset number as the number of sensor nodes in the multi-source sensor network, assign each wetland area geographical coordinate to the nearest cluster center to form a plurality of clusters, and determine the mean of the geographical coordinates of each point in each cluster as a target cluster center, determine the center change between the target cluster center and the cluster center, and output the optimal arrangement positions of the preset number of sensor nodes when the center change is less than a pre-set change threshold or a maximum iteration number is reached.

[0118] In some embodiments, the environmental data real-time acquisition module is further configured to determine, for each wetland area geographical coordinate, the Euclidean distance between the wetland area geographical coordinate and all cluster centers, assign the wetland area geographical coordinate to the cluster corresponding to the cluster center with the smallest distance based on the Euclidean distance, and determine, for each cluster, the mean of the geographical coordinates of each point in each cluster as a target cluster center.

[0119] In some embodiments, the environmental data real-time acquisition module is further configured to re-determine the centroid coordinates of each cluster, and determine the center change between the target cluster center and the cluster center after each re-computation.

[0120] In some embodiments, the environmental data preprocessing module is further configured to remove high-frequency noise by wavelet decomposition on the environmental data, and reconstruct the de-noised data, fill in missing data points by cubic polynomial interpolation after reconstructing the de-noised data, and obtain standardized data.

[0121] In some embodiments, the environmental data preprocessing module is further configured to construct a cubic polynomial based on the data of adjacent time points for the missing data points, determine the interpolation based on the cubic polynomial and a pre-set boundary condition, and fill in the missing data points by interpolation to obtain standardized data.

[0122] In some embodiments, the data fusion module is further configured to normalize and combine the water demand prediction value and real-time data into a multi-dimensional feature vector; dynamically adjust the feature weight based on the wetland type to obtain the fused data.

[0123] The device provided by the embodiments of the present application has the same implementation principle and technical effects as the foregoing method embodiments, and for brevity, the part not mentioned in the device embodiment can be referred to the corresponding content in the foregoing method embodiments.

[0124] Embodiment 5

[0125] The embodiments of the present application further provide an electronic device for running the wetland group dynamic water distribution method based on multi-modal perception. Figure 5 As shown in a structural schematic diagram of an electronic device, the electronic device comprises a memory 500 and a processor 501, wherein the memory 500 is configured to store one or more computer instructions, and the one or more computer instructions are executed by the processor 501 to implement the wetland group dynamic water distribution method based on multi-modal perception.

[0126] Further, Figure 5 The electronic device further comprises a bus 502 and a communication interface 503, and the processor 501, the communication interface 503 and the memory 500 are connected through the bus 502.

[0127] The memory 500 can include a high-speed random access memory (RAM) and can also include a non-volatile memory such as at least one disk memory. The communication between the system network element and at least one other network element is realized through at least one communication interface 503 (which can be wired or wireless), and the Internet, a wide area network, a local area network, a metropolitan area network, etc. can be used. The bus 502 can be an ISA bus, a PCI bus or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 5 Only one bidirectional arrow is used in the figure, but it does not mean that there is only one bus or only one type of bus.

[0128] The processor 501 can be an integrated circuit chip having a signal processing capability. In the implementation process, each step of the above method can be completed by the integrated logic circuit of hardware in the processor 501 or the instruction in the form of software. The processor 501 described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. Each method, step and logic block diagram disclosed in the embodiment of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiment of the present application can be directly embodied as a hardware code processor for execution, or a combination of hardware and software modules in the code processor for execution. The software module can be located in a random access memory, a flash memory, a read only memory, a programmable read only memory or an electrically erasable programmable memory, a register, etc. The storage medium in the storage 500 is read by the processor 501, and the hardware thereof is combined to complete the steps of the method of the above embodiment.

[0129] The embodiment of the present application also provides a computer readable storage medium, the computer readable storage medium stores computer executable instructions, when the computer executable instructions are called and executed by a processor, the computer executable instructions cause the processor to implement the wetland group dynamic water distribution method based on multi-modal perception described above. For specific implementation, please refer to the method embodiment, which will not be repeated here.

[0130] The computer program product for implementing the wetland group dynamic water distribution method based on multi-modal perception provided by the embodiment of the present application includes a computer readable storage medium storing non-volatile program codes executable by a processor. The instructions included in the program codes can be used to execute the method in the foregoing method embodiment. For specific implementation, please refer to the method embodiment, which will not be repeated here.

[0131] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

[0132] In several embodiments provided by the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. The described device embodiments are merely schematic, and for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation; for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, or the among different units, can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electric, mechanical or other forms.

[0133] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. In actual implementation, some or all of the units can be selected according to the actual needs to achieve the purposes of the embodiments of the present application.

[0134] In addition, each functional unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically as a separate unit, or two or more units can be integrated in one unit.

[0135] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer readable storage medium of a processor. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art, or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in the various embodiments of the present application. The foregoing storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, and various media that can store program codes.

[0136] Finally, it should be noted that the above examples are merely specific embodiments of the present application, and are used to illustrate the technical solutions of the present application, but are not intended to limit the present application. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that any person skilled in the art can still modify or easily think of changes to the technical solutions recorded in the foregoing examples, or make equivalent replacements to some of the technical features, within the technical range disclosed by the present application. These modifications, changes or replacements do not cause the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A multi-modal perception based dynamic water distribution method for wetland communities, characterized in that, The method comprises: A multi-source sensor network based on a K-means clustering algorithm is used to collect real-time environmental data of a wetland group, wherein the multi-source sensor network comprises soil moisture monitoring equipment, water quality monitoring equipment, and meteorological monitoring equipment; The environmental data is preprocessed to obtain standardized environmental data, wherein the preprocessing comprises removing high-frequency noise in the data by a wavelet decomposition algorithm and filling in missing values in the data by a cubic polynomial difference algorithm; The standardized environmental data is processed based on a pre-trained federated learning model, wherein the federated learning algorithm obtains a global model by weighted aggregation of local model parameters of each wetland node, the weight of the weighted aggregation is proportional to the data volume of each node, and Gaussian noise is added to the local model parameters to realize differential privacy protection, and a water demand prediction value and a confidence interval of each wetland are output; The water demand prediction value, real-time water level, and meteorological forecast data are fused into a multi-dimensional feature vector, and the weight of each feature in the feature vector is dynamically adjusted based on the type of the wetland, to obtain fused data, wherein the type of the wetland comprises an ecological zone, an agricultural zone, and a flood control zone; A NSGA-III multi-objective optimization algorithm is used to generate a Pareto optimal water distribution scheme based on the fused data, and a near-end strategy in deep reinforcement learning is used for decision-making, to obtain a final water distribution scheme; The final water distribution scheme is input into a digital twin platform, the final water distribution scheme is simulated and verified, control instructions are generated after verification, and an execution device is driven to complete water distribution; the digital twin platform integrates soil permeability coefficient, vegetation transpiration rate, and wetland hydrological parameters.

2. The method of claim 1, wherein, The layout optimization method of the multi-source sensor network comprises: Obtaining geographical coordinates of a wetland area to form a wetland plane; Randomly selecting a preset number of initial cluster centers within the range of the wetland plane; the preset number is the number of sensor nodes in the multi-source sensor network; Assigning each geographical coordinate of the wetland area to the nearest cluster center to form a plurality of clusters, and determining the mean value of the geographical coordinates of each point in each cluster as a target cluster center; Determining the center change amount between the target cluster center and the cluster center; When the center change amount is less than a pre-set change amount threshold or a maximum iteration number is reached, outputting the optimal arrangement positions of the preset number of sensor nodes.

3. The method of claim 2, wherein, The method of assigning each geographical coordinate of the wetland area to the nearest cluster center to form a plurality of clusters, and determining the mean value of the geographical coordinates of each point in each cluster as a target cluster center, comprises: For each geographical coordinate of the wetland area, determining the Euclidean distance between the geographical coordinate of the wetland area and all cluster centers; Based on the Euclidean distance, assigning the geographical coordinate of the wetland area to the cluster corresponding to the cluster center with the smallest distance; For each cluster, determining the mean value of the geographical coordinates of each point in the cluster as a target cluster center.

4. The method of claim 3, wherein, The method of determining the center change amount between the target cluster center and the cluster center comprises: Redetermining the centroid coordinates of each cluster; Determine the target cluster center and the center change between the cluster centers after each recalculation.

5. The method of claim 1, wherein, The pre-processing of the environment data obtains standardized environment data, including: Wavelet decomposition is used on the environment data to remove high-frequency noise, and the denoised data is reconstructed. After reconstructing the denoised data, the missing data points are filled by cubic polynomial interpolation to obtain standardized data.

6. The method of claim 5, wherein, The missing data points are filled by cubic polynomial interpolation to obtain standardized data, including: For the missing data points, a cubic polynomial is constructed based on the data of adjacent time points; Determine the interpolation based on the cubic polynomial and the pre-set boundary conditions; The standardized data is obtained by filling the interpolation.

7. The method of claim 1, wherein, The water demand prediction value and real-time data are fused into a multi-dimensional feature vector and the feature weight is dynamically adjusted to obtain fused data, including: The water demand prediction value and real-time data are normalized and combined into a multi-dimensional feature vector; Based on the wetland type, the feature weight is dynamically adjusted to obtain the fused data.

8. A multi-modal perception based dynamic water distribution device for wetland population, characterized in that, The device for implementing the multi-modal perception-based wetland group dynamic water distribution method of any one of claims 1 to 7, comprising: An environment data real-time acquisition module for real-time collection of environment data of the wetland group through a multi-source sensor network optimized in advance for layout; An environment data preprocessing module for preprocessing the environment data to obtain standardized environment data; A water demand prediction value output module for processing the standardized environment data based on a pre-trained federated learning model and outputting the water demand prediction value of each wetland; A data fusion module for fusing the water demand prediction value and real-time data into a multi-dimensional feature vector and dynamically adjusting the feature weight to obtain fused data; A water distribution scheme generation module for generating a water distribution scheme based on the fused data and executing after simulation verification through a digital twin platform.

9. An electronic device, comprising: A processor and a memory, the memory storing computer executable instructions executable by the processor, and the processor executing the computer executable instructions to implement the multi-modal perception-based wetland group dynamic water distribution method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer executable instructions, and when the computer executable instructions are called and executed by the processor, the computer executable instructions cause the processor to implement the multi-modal perception-based wetland group dynamic water distribution method of any one of claims 1 to 7.

Images