Karst mountainous area water resource management method and system based on intelligent algorithm

Abstract

The invention discloses a karst mountain area water resource management method and system based on an intelligent algorithm, and belongs to the technical field of water resource management. By integrating the three-dimensional model, the intelligent algorithm and multi-objective optimization, accurate prediction and efficient management of water resources in the karst mountainous area are realized, multi-dimensional information such as terrain, water areas and historical data can be comprehensively considered, the intelligent algorithm is used for prediction, water resource distribution is optimized through a multi-objective function, and the water resources in the karst mountainous area can be efficiently managed. Constraint conditions such as water balance and social economy are met while ecological benefits, water deficit and water resource utilization benefits are ensured to be met, and therefore scientificity and sustainability of water resource management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of water resource management, and more specifically to a method and system for water resource management in karst mountainous areas based on intelligent algorithms. Background Art

[0002] As a unique natural geographical environment on the earth, the water resources in karst mountainous areas have significant regional characteristics and complexity. Research on water resource management in karst mountainous areas is not only an urgent need to solve the contradiction between regional water resource supply and demand and protect the ecological environment, but also an important way to promote scientific and technological progress and sustainable economic and social development.

[0003] However, due to its special geological structure, the distribution of water resources in space and time in karst mountainous areas is extremely uneven, and traditional management methods are difficult to accurately capture these dynamic changes. At the same time, existing monitoring methods are often limited by geographical location and technical conditions, making it difficult to achieve comprehensive and real-time perception of water resources, resulting in incomplete and untimely data collection. In terms of prediction, due to the complexity of hydrogeological conditions in karst mountainous areas, traditional prediction models are difficult to accurately reflect the changing laws of water resources, and the prediction accuracy is limited. In the scheduling link, due to the lack of efficient decision support systems and intelligent scheduling algorithms, the allocation and utilization of water resources are often not scientific and reasonable, resulting in a waste of resources.

[0004] Therefore, it is an urgent problem to be solved by technical personnel in this field to propose a water resources management method and system in karst mountainous areas based on intelligent algorithms to improve the utilization efficiency and management level of water resources in karst mountainous areas. Summary of the invention

[0005] In view of this, the present invention provides a water resources management method and system for karst mountain areas based on intelligent algorithms, which uses three-dimensional digital twin technology to create a virtual water resources management model to reflect the status and changes of water resources in real time, helping decision makers to manage more effectively.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] On the one hand, the present invention discloses a method for water resource management in karst mountainous areas based on an intelligent algorithm, comprising the following steps:

[0008] Constructing a terrain model according to the terrain data of the target karst mountain area, and combining the terrain model with the water area model of the target karst mountain area to obtain a three-dimensional model of the karst mountain area;

[0009] Constructing a water resource management model, and integrating the water resource management model into the three-dimensional model of the karst mountain area;

[0010] Acquire historical hydrological and meteorological data of the target karst mountain area and screen the historical hydrological and meteorological data to determine factors affecting available water resources;

[0011] Using historical data on available water resources and factors influencing available water resources to train the water resources management model, and obtain an optimized prediction model;

[0012] Acquire the available amount of water resources and the data of factors affecting available water resources in the target karst mountain area in real time, and output the available amount of water resources according to the optimization prediction model;

[0013] The available water resources are combined with a multi-objective function to output an optimal water resources management plan.

[0014] Preferably, the water resource management model is constructed based on the MGRU model.

[0015] Preferably, the water resource management model is trained using historical water resource availability and historical data on factors affecting available water resources, including:

[0016] Conduct wavelet analysis and coefficient reconstruction on the historical available water resources to obtain the available water resources data component;

[0017] Reconstructing the phase space by combining the available water resources data component and the available water resources influencing factor data to construct a training set;

[0018] Using a particle swarm optimization algorithm to find the optimal hyperparameters of the MGRU model;

[0019] Based on the optimal hyperparameters, the MGRU model is trained using the training set to obtain an optimized prediction model.

[0020] Preferably, the multi-objective function L is constructed based on ecological benefits, water shortage, and water resource utilization benefits, and the formula is as follows:

[0021] L=min(-λ1L1+λ2L2-λ3L3)

[0022] Where L1 is the ecological benefit objective function, L2 is the water shortage objective function, L3 is the water resource utilization benefit objective function, λ1, λ2, and λ3 are the weight coefficients of the ecological benefit objective function, the water shortage objective function, and the water resource utilization benefit objective function, respectively.

[0023] Preferably, the ecological benefit objective function L1 formula is as follows:

[0024]

[0025] Where n is the total number of ecological areas in the target karst mountain area; is the minimum water requirement of the ith ecological region; is the actual amount of water obtained by the i-th ecological region; W i is the weight of the ith ecological region.

[0026] Preferably, the water shortage objective function L2 is:

[0027]

[0028] Where, P is the number of water use types, which in this embodiment includes industrial water, agricultural water, domestic water, etc., Q is the number of regions of the pth water use type, and D p,q is the water demand of the qth area of ​​the pth water use type, S p,q The actual amount of water obtained in the qth area of ​​the pth water use type.

[0029] Preferably, the water resource utilization benefit objective function L3 is:

[0030]

[0031] Where M is the number of water resources management options, R m is the economic benefit of the mth water resources management plan; C m is the cost of the mth water resources management option.

[0032] Preferably, under the condition that the constraints are met, an optimization algorithm is used to solve the multi-objective function to output an optimal water resources management plan;

[0033] The constraints include water balance constraints, ecological benefit constraints, water demand constraints, water resource utilization efficiency constraints and socio-economic constraints.

[0034] On the other hand, the present invention proposes a karst mountain water resource management system based on an intelligent algorithm, which is used to implement the above-mentioned karst mountain water resource management method based on an intelligent algorithm. The system comprises:

[0035] A three-dimensional model building module, used to build a terrain model according to the terrain data of the target karst mountain area, wherein the terrain model is combined with the water area model of the target karst mountain area to obtain a three-dimensional model of the karst mountain area;

[0036] A model integration module, used to construct a water resource management model and integrate the water resource management model into the three-dimensional model of the karst mountain area;

[0037] An influencing factor screening module is used to obtain the historical hydrological and meteorological data of the target karst mountain area and screen the historical hydrological and meteorological data to determine the influencing factors of available water resources;

[0038] A model training module is used to train the water resource management model using historical water resource availability and historical data on factors affecting available water resources to obtain an optimized prediction model;

[0039] A water resource availability output module is used to obtain the water resource availability and the data of the factors affecting the available water resources in the target karst mountain area in real time, and output the water resource availability according to the optimization prediction model;

[0040] The management plan output module is used to output the optimal water resource management plan according to the available water resources in combination with a multi-objective function.

[0041] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a method and system for water resource management in karst mountainous areas based on intelligent algorithms, which constructs a three-dimensional terrain and water area model, combines historical hydrological and meteorological data, and applies optimization algorithms to solve multi-objective functions, thereby achieving accurate prediction of available water resources and output of optimal management solutions. The present invention not only improves the scientificity and efficiency of water resource management, but also comprehensively considers ecological, economic and social factors, and can effectively respond to special water resource challenges in karst mountainous areas, ultimately promoting sustainable development and ecological protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0043] Figure 1 A schematic diagram of the method provided by the present invention;

[0044] Figure 2 A schematic diagram of the system architecture provided by the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] The embodiment of the present invention discloses a method for managing water resources in karst mountainous areas based on an intelligent algorithm. Figure 1 , the method comprises the following steps:

[0047] S1. A terrain model is constructed according to the terrain data of the target karst mountain area, and the terrain model is combined with the water area model of the target karst mountain area to obtain a three-dimensional model of the karst mountain area.

[0048] The terrain data of the target karst mountain area, including contour lines, point cloud data, etc., are obtained through UAV aerial surveys and ground measurements.

[0049] Use professional 3D modeling software, such as SketchUp, 3DMAX, etc., to build terrain models based on terrain data.

[0050] At the same time, through field surveys and remote sensing image interpretation, information on the water areas (rivers, lakes, reservoirs, etc.) in the mountainous area is obtained, including the location, shape and size of the water areas. A water area model is constructed using GIS software, and the terrain model and water area model are fused using the fusion function of GIS software or 3D modeling software to obtain a 3D model of the karst mountain area.

[0051] S2. Construct a water resource management model and integrate the water resource management model into the karst mountain three-dimensional model. Specifically, the water resource management model is constructed based on the MGRU model.

[0052] In this embodiment, the structure of the determined model is a three-layer MGRU network, each layer includes 64 neurons. The loss function adopts the mean square error (MSE) function.

[0053] The water resource management model was integrated into the 3D model of the karst mountain area using a software development kit (SDK). In the 3D model of the karst mountain area, the operation results and predictions of the water resource management model can be displayed through a visual interface.

[0054] S3. Obtain and screen the historical hydrological and meteorological data of the target karst mountain area to determine the factors affecting available water resources.

[0055] Collect historical hydrological and meteorological data of the target karst mountain area, including rainfall, evaporation, temperature, humidity, river flow, groundwater level, etc. These data can be obtained from meteorological stations, hydrological stations, geological departments and other channels, and can also be collected through remote sensing technology and data mining.

[0056] The collected historical hydrological and meteorological data are processed to remove outliers and noise data to ensure the accuracy and reliability of the data.

[0057] This embodiment performs correlation coefficient analysis on the above historical hydrological and meteorological data to determine the factors affecting available water resources.

[0058] S4. Use the historical data on available water resources and factors affecting available water resources to train the water resources management model and obtain an optimized prediction model, including:

[0059] S41. Perform wavelet analysis and coefficient reconstruction on the historical available water resources to obtain the available water resources data component.

[0060] The wavelet analysis of historical water resources availability is carried out, and Daubechies wavelet basis function is used to decompose it into components of different frequencies. Wavelet analysis can effectively extract the characteristics of time series data and remove noise and trends.

[0061] Then, the wavelet coefficients are reconstructed to obtain the available water resources data components, which can better reflect the changing characteristics of the available water resources.

[0062] S42. Reconstruct the phase space by combining the available water resources data component and the available water resources influencing factors data to construct a training set.

[0063] The available water resources data components and influencing factor data are reconstructed in phase space as the input of the MGRU model. Phase space reconstruction can reveal the intrinsic structure and dynamic characteristics of time series data.

[0064] A training set is constructed based on the data after phase space reconstruction for training water resources management models.

[0065] S43. Use particle swarm optimization algorithm to find the optimal hyperparameters of the MGRU model.

[0066] Determine the hyperparameter ranges for the MGRU model, such as learning rate, number of hidden layer neurons, batch size, etc.

[0067] The particle swarm optimization algorithm is used to find the optimal hyperparameter combination within the hyperparameter range. The particle swarm optimization algorithm is an optimization algorithm based on swarm intelligence, which finds the optimal solution by simulating the foraging behavior of bird flocks.

[0068] Evaluate the performance of the MGRU model under different hyperparameter combinations, and select the hyperparameter combination with the best performance as the optimal hyperparameter.

[0069] S44. Based on the optimal hyperparameters, the MGRU model is trained using the training set to obtain an optimized prediction model.

[0070] Initialize the MGRU model using the optimal hyperparameters.

[0071] The constructed training set is input into the MGRU model for training. During the training process, the back propagation algorithm is used to adjust the weights and biases of the model so that the model can better fit the training data.

[0072] The training process is iterated continuously until the model converges or the preset number of training times is reached.

[0073] Finally, an optimized water resources management prediction model is obtained.

[0074] S5. Obtain data on available water resources and factors affecting available water resources in the target karst mountain area in real time, and output available water resources according to the optimized prediction model.

[0075] S6. The available water resources are combined with multi-objective functions to output the optimal water resources management plan.

[0076] A multi-objective function L is constructed based on ecological benefits, water shortage, and water resource utilization benefits. The formula is as follows:

[0077] L=min(-λ1L1+λ2L2-λ3L3)

[0078] Where L1 is the ecological benefit objective function, L2 is the water shortage objective function, L3 is the water resource utilization benefit objective function, λ1, λ2, and λ3 are the weight coefficients of the ecological benefit objective function, the water shortage objective function, and the water resource utilization benefit objective function, respectively.

[0079] Among them, the formula of ecological benefit objective function L1 is as follows:

[0080]

[0081] Where n is the total number of ecological areas in the target karst mountain area; is the minimum water requirement of the ith ecological region; is the actual amount of water obtained by the i-th ecological region; W i is the weight of the ith ecological region.

[0082] The water shortage objective function L2 is:

[0083]

[0084] Where P is the number of water use types, Q is the number of regions with the pth water use type, and D p,q is the water demand of the qth area of ​​the pth water use type, S p,q The actual amount of water obtained in the qth area of ​​the pth water use type.

[0085] The objective function L3 of water resource utilization benefit is:

[0086]

[0087] Where M is the number of water resources management options, R m is the economic benefit of the mth water resources management plan; C m is the cost of the mth water resources management option.

[0088] Under the condition of satisfying the constraints, optimization algorithms such as genetic algorithms are used to solve the multi-objective function and output the optimal water resources management plan.

[0089] The constraints include:

[0090] Water balance constraint: HEO ≥ 0; where H is the available water resources output by the optimization prediction model, E is the evaporation, and O is the total water demand, including the water demand of ecological regions and different types of water demand such as industry, agriculture, and life.

[0091] Ecological benefit constraint: L1 ≥ E min

[0092] Among them, E min It is the minimum threshold of ecological benefits to ensure the sustainability of the ecological environment.

[0093] Water demand constraint: D≤D max

[0094] Among them, D max The maximum water shortage that the target karst mountain area can bear is set to ensure that the basic water needs in various fields are met.

[0095] Constraints on water resource utilization efficiency:

[0096] Where W is the water consumption in the area; I is the rainfall; R in represents the amount of water flowing into the area, U th It is the lower limit of water resource utilization efficiency, thereby ensuring the effective use of water resources.

[0097] Socioeconomic constraints: C total ≤B.

[0098] In the formula, C total represents the total cost of the water resources management plan; B represents the maximum affordable cost budget.

[0099] On the other hand, the present invention proposes a karst mountain water resource management system based on an intelligent algorithm, which is used to implement the above-mentioned karst mountain water resource management method based on an intelligent algorithm, such as Figure 2 As shown, the system includes:

[0100] A three-dimensional model building module is used to build a terrain model according to the terrain data of the target karst mountain area, and the terrain model is combined with the water area model of the target karst mountain area to obtain a three-dimensional model of the karst mountain area;

[0101] Model integration module, used to build a water resource management model and integrate the water resource management model into the 3D model of the karst mountain area;

[0102] The influencing factor screening module is used to obtain and screen the historical hydrological and meteorological data of the target karst mountain area to determine the influencing factors of available water resources;

[0103] A model training module is used to train a water resource management model using historical water resource availability and historical data on factors affecting available water resources to obtain an optimized prediction model;

[0104] The water resource availability output module is used to obtain the data on the water resource availability and influencing factors of available water resources in the target karst mountain area in real time, and output the water resource availability according to the optimization prediction model;

[0105] The management plan output module is used to output the optimal water resources management plan based on the available water resources combined with the multi-objective function.

[0106] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0107] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for water resource management in karst mountainous areas based on intelligent algorithm, characterized in that: The following steps are involved: Constructing a terrain model according to the terrain data of the target karst mountain area, and combining the terrain model with the water area model of the target karst mountain area to obtain a three-dimensional model of the karst mountain area; Constructing a water resource management model, and integrating the water resource management model into the three-dimensional model of the karst mountain area; Acquire historical hydrological and meteorological data of the target karst mountain area and screen the historical hydrological and meteorological data to determine factors affecting available water resources; Using historical data on available water resources and factors influencing available water resources to train the water resources management model, and obtain an optimized prediction model; Acquire the available amount of water resources and the data of factors affecting available water resources in the target karst mountain area in real time, and output the available amount of water resources according to the optimization prediction model; The available water resources are combined with a multi-objective function to output an optimal water resources management plan.

2. The method for water resource management in karst mountainous areas based on intelligent algorithm according to claim 1 is characterized in that: The water resources management model is constructed based on the MGRU model.

3. The method for water resource management in karst mountainous areas based on intelligent algorithm according to claim 2 is characterized in that: Use historical data on water availability and factors affecting water availability to train water resource management models, including: Conduct wavelet analysis and coefficient reconstruction on the historical available water resources to obtain the available water resources data component; Reconstructing the phase space by combining the available water resources data component and the available water resources influencing factor data to construct a training set; Using a particle swarm optimization algorithm to find the optimal hyperparameters of the MGRU model; Based on the optimal hyperparameters, the MGRU model is trained using the training set to obtain an optimized prediction model.

4. The method for water resource management in karst mountainous areas based on intelligent algorithm according to claim 1 is characterized in that: The multi-objective function L is constructed based on ecological benefits, water shortage, and water resource utilization benefits. The formula is as follows: L=min(-λ1L1+λ2L2-λ3L3) Where L1 is the ecological benefit objective function, L2 is the water shortage objective function, L3 is the water resource utilization benefit objective function, λ1, λ2, and λ3 are the weight coefficients of the ecological benefit objective function, the water shortage objective function, and the water resource utilization benefit objective function, respectively.

5. The method for water resource management in karst mountainous areas based on intelligent algorithm according to claim 4 is characterized in that: The formula of the ecological benefit objective function L1 is as follows: Where n is the total number of ecological areas in the target karst mountain area; is the minimum water requirement of the ith ecological region; is the actual amount of water obtained by the i-th ecological region; W i is the weight of the ith ecological region.

6. The method for water resource management in karst mountainous areas based on intelligent algorithm according to claim 4 is characterized in that: The water shortage objective function L2 is: Where P is the number of water use types, Q is the number of regions with the pth water use type, and D p，q is the water demand of the qth area of ​​the pth water use type, S p，q The actual amount of water obtained in the qth area of ​​the pth water use type.

7. The method for water resource management in karst mountainous areas based on intelligent algorithm according to claim 4 is characterized in that: The water resource utilization benefit objective function L3 is: Where M is the number of water resources management options, R m is the economic benefit of the mth water resources management plan; C m is the cost of the mth water resources management option.

8. The method for water resource management in karst mountainous areas based on intelligent algorithm according to claim 4 is characterized in that: Under the condition that the constraints are met, the optimization algorithm is used to solve the multi-objective function and output the optimal water resources management plan; The constraints include water balance constraints, ecological benefit constraints, water demand constraints, water resource utilization efficiency constraints and socio-economic constraints.

9. A karst mountain water resources management system based on intelligent algorithm, characterized in that: include: A three-dimensional model building module, used to build a terrain model according to the terrain data of the target karst mountain area, wherein the terrain model is combined with the water area model of the target karst mountain area to obtain a three-dimensional model of the karst mountain area; A model integration module, used to construct a water resource management model and integrate the water resource management model into the three-dimensional model of the karst mountain area; An influencing factor screening module is used to obtain the historical hydrological and meteorological data of the target karst mountain area and screen the historical hydrological and meteorological data to determine the influencing factors of available water resources; A model training module is used to train the water resource management model using historical water resource availability and historical data on factors affecting available water resources to obtain an optimized prediction model; A water resource availability output module is used to obtain the water resource availability and the data of the factors affecting the available water resources in the target karst mountain area in real time, and output the water resource availability according to the optimization prediction model; The management plan output module is used to output the optimal water resource management plan according to the available water resources in combination with a multi-objective function.

Images