Water ecological environment health state evaluation and prediction method and system

Abstract

The invention relates to the field of environment assessment, and discloses a water ecological environment health state assessment and prediction method and system, and the method comprises the following steps: obtaining and preprocessing water ecological environment basic data; constructing a water quality change model and an emergency influence model; calculating time sequence data of each water quality parameter concentration and each species quantity; constructing a multi-objective optimization model and solving to obtain an optimal management strategy parameter; according to the method, the influence of water ecological environment emergencies can be accurately simulated, evaluation indexes are optimized, multiple key factors such as microcosmic biocenosis interaction, spatial heterogeneity and emergencies uncertainty are considered at the same time, and the method has high practicability and adaptability.

Description

Technical Field

[0001] The present invention relates to the field of environmental assessment, and more specifically, to a method and system for assessing and predicting the health status of aquatic ecological environment. Background Art

[0002] The assessment and prediction of the health status of the water ecological environment is of great significance for water resources management and ecological protection. Traditional water ecological environment assessment methods mainly rely on manual sampling and laboratory analysis, which have problems such as long assessment cycle, poor timeliness, and weak prediction ability. In particular, when a sudden pollution incident occurs in the water ecological environment, how to quickly assess the impact of the pollution incident on the water ecosystem and timely predict the changing trend of the ecological health status is crucial for emergency response and decision-making, but it is difficult to achieve with existing technical means.

[0003] Therefore, there is an urgent need for a new method that can realize the rapid assessment and dynamic prediction of the health status of the water ecological environment, so as to improve the timeliness and scientificity of water ecological environment supervision and provide strong support for the emergency management of sudden events. Summary of the invention

[0004] The present invention provides a method and system for assessing and predicting the health status of aquatic ecological environment. By introducing machine learning algorithms and data-driven models, rapid assessment and dynamic prediction of the health status of water ecology can be achieved, and a real-time early warning and decision-making optimization mechanism can be established to improve the level of water ecological environment supervision and emergency management.

[0005] A method for assessing and predicting the health status of aquatic ecological environment comprises the following steps: Acquire and preprocess basic data of water ecological environment, including water quality parameters, hydrological parameters and aquatic biological data; Among them, water quality parameters include dissolved oxygen content , Chemical Oxygen Demand , ammonia nitrogen content ; Hydrological parameters include water velocity , water area ; Aquatic data including the number of species ; Modeling water quality changes: ; in for Water concentration at all times, is the initial concentration, is the reaction rate constant, is the equilibrium concentration; Constructing the impact model of emergencies:

[0006] in is the amount of pollutant released, is the mapping function between event type and pollutant release amount; Simulate and run, set simulation time interval and time step , calculate the time series data of each water quality parameter concentration and the number of each species for each time step; Indicator optimization, define management strategy parameter vector , construct water quality objective function and biodiversity objective function, and use multi-objective optimization algorithm to solve the optimal management strategy parameters.

[0007] Preferred: In the emergency impact model: In case of chemical spills, ;when When biological invasion occurs, ;in is the initial release amount (mg / s), is the attenuation coefficient (1 / s), is the base of natural logarithms, Represents an exponential function.

[0008] Preferred: Also includes microbial community interaction models: ; in For biological The intrinsic growth rate, is the environmental carrying capacity, For biological and Biological The interaction coefficient between and Biological and Biological The number of Indicates that except for species All other species The sum is calculated, where is the total number of species.

[0009] Preferred: Divide the water body into Space units, for space units , the water quality concentration change model is: ; in For unit and unit The material exchange coefficient between is the total number of spatial units, Indicates that except for the unit All adjacent units except The sum is used to calculate the total amount of material exchange between spatial units.

[0010] Preferred: Pollutant release Normal distribution , Monte Carlo method is used for multiple simulations, and the optimization goal is: ; in is the mathematical expectation of the objective function, is the variance of the objective function, is the trade-off coefficient.

[0011] Preferably: it also includes a real-time data updating step: Use dynamic update algorithm to update water quality concentration data: ; in is the updated water quality concentration, is the water quality concentration before updating, is the newly measured water quality concentration, To update the weights.

[0012] A water ecological environment health status assessment and prediction system includes: a data acquisition module for acquiring basic water ecological environment data; a model building module for building a water quality change model and an emergency impact model; a simulation calculation module for calculating time series data; and an optimization analysis module for solving optimal management strategy parameters.

[0013] Also includes: The real-time monitoring module is used to collect real-time water quality data; the data update module is used to dynamically update model parameters; and the early warning decision module is used to generate early warning information and management recommendations.

[0014] The simulation calculation module also includes: a Monte Carlo simulation unit for performing multiple random simulations; a spatial analysis unit for calculating water quality changes in different spatial units; and a biological interaction unit for simulating the dynamics of microscopic biological communities.

[0015] The optimization analysis module uses the non-dominated sorting genetic algorithm (NSGA-II) to solve multi-objective optimization problems.

[0016] The beneficial effects of the present invention are that the present invention can accurately simulate the impact of sudden events on the water ecological environment and optimize the evaluation indicators, while taking into account multiple key factors such as the interaction of microscopic biological communities, spatial heterogeneity, and uncertainty of sudden events, and has strong practicality and adaptability.

[0017] The present invention proposes a method for assessing and predicting the health status of water ecological environment based on machine learning and data-driven models, which overcomes the limitations of traditional methods such as long assessment cycle and weak prediction ability, and realizes rapid diagnosis and trend prediction of water ecological health status.

[0018] An ecological health assessment model driven by multi-source heterogeneous data fusion was constructed, and new assessment indicators such as the plankton biodiversity index were introduced to expand the assessment dimension and improve the comprehensiveness and accuracy of the health status characterization.

[0019] A water ecological health prediction model for emergencies has been developed, which can simulate dynamic processes such as pollutant diffusion and biological damage, realize rolling prediction of health status after an incident, and provide a scientific basis for emergency decision-making.

[0020] It integrates functions such as real-time early warning, scenario analysis, and countermeasure optimization, which enhances the practicality of the system. It can provide intelligent technical means for river basin water ecological environment management and improve management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flow chart of a method for assessing and predicting the health status of aquatic ecological environment proposed by the present invention; Figure 2 This is an example diagram of basic water ecological environment data in Example 1 of the present invention; Figure 3 is an example diagram of emergency event parameters in Embodiment 1 of the present invention; Figure 4 is an example diagram of model parameter settings in Embodiment 1 of the present invention; Figure 5 is an example diagram of the simulation results in Example 1 of the present invention; Figure 6 This is an example diagram of the optimization results in Example 1 of the present invention. DETAILED DESCRIPTION

[0022] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the contents of this specification. Each example may omit, replace or add various processes or components as needed. In addition, the features described relative to some examples may also be combined in other examples.

[0023] Example 1 This embodiment provides a method for assessing and predicting the health status of aquatic ecological environment, including the following steps: Step 100: Obtain and pre-process basic water ecological environment data: (1) Basic data on water ecological environment, including: Water quality parameters: dissolved oxygen content (mg / L), chemical oxygen demand ( ), ammonia nitrogen content (mg / L); Hydrological parameters: water flow velocity (m / s), water area (m²); Aquatic data: Number of species (pcs / m³), among which Indicates the species number; (2) Historical data of emergencies, including event types , Occurrence time Scope of influence (m).

[0024] Step 200: Construct a water quality change model and an emergency impact model: (1) Constructing a water quality change model: ; in: In the water quality change model Water quality concentration at each moment (mg / L); is the initial concentration (mg / L); is the reaction rate constant (1 / s); is the equilibrium concentration (mg / L); represents the definite integral from 0 to time t; for Water quality concentration at the time (mg / L), is the integral variable, representing any time between 0 and t; is the differential of the integrated variable.

[0025] (2) Constructing an emergency impact model:

[0026] in: is the pollutant release amount (mg / s); is the mapping function between event type and pollutant release amount, specifically: when In case of chemical spills, ; when When biological invasion occurs, ; in is the base of natural logarithms, represents the exponential function; in is the initial release amount (mg / s), is the attenuation coefficient (1 / s).

[0027] Step 300: Set the simulation time interval and time step, and calculate the time series data of each water quality parameter concentration and the number of each species for each time step: Set simulation time interval , time step ; in: is the simulation termination time (s), is the time step (s).

[0028] For the i-th time step , the dissolved oxygen content, chemical oxygen demand, and ammonia nitrogen content at the i-th time step are calculated as , , , the number of species at the i-th time step, the number of the i-th species is ; The time series data of the above parameters are recorded as the response data of the evaluation indicators.

[0029] Step 400: define the management strategy parameter vector, construct the water quality objective function and the biodiversity objective function, and use a multi-objective optimization algorithm to solve the optimal management strategy parameters: (1) Define the management strategy parameter vector: ; in: is the pollutant emission limit (mg / s); is the intensity of ecological restoration measures (dimensionless).

[0030] (2) Constructing the objective function: Water quality objective function: ; Biodiversity objective function: ; in: Indicates that all The sum is performed over the spatial units; represents the definite integral from 0 to T; is the differential of time; For unit Dissolved oxygen concentration (mg / L); is the standard value of dissolved oxygen (mg / L); For all species The sum is calculated, where is the total number of species; is the space unit at time T Medium Species The number of

[0031] (3) Establish a multi-objective optimization model: ; Constraints: ; .

[0032] in: is the maximum allowable pollutant emission limit (mg / s).

[0033] (4) Use the non-dominated sorting genetic algorithm (NSGA-II) to solve and obtain the optimal management strategy parameters .

[0034] in: represents the optimal management strategy parameter vector, represents the optimal pollutant emission limit (mg / s), represents the intensity of the optimal ecological restoration measure (dimensionless), with superscript Indicates the optimal solution.

[0035] To further illustrate the specific application effect of this embodiment, a practical application example of a chemical leakage incident in a certain river section is given below: See attached Figure 2 -Attached Figure 6 , it can be seen from the actual application data: 1. The chemical leak caused a significant drop in dissolved oxygen in the water, with the lowest level dropping to 3.5 mg / L, while chemical oxygen demand and ammonia nitrogen content increased significantly; 2. The number of aquatic organisms (for example, carp) showed a clear downward trend under the influence of the incident; 3. Through the optimization method of the present invention, the pollutant emission limit is reduced from 60 mg / s to 35 mg / s, and the intensity of ecological restoration measures is increased to 0.7, so that the water quality and biological survival rate after 24 hours are significantly improved.

[0036] Example 2 Based on Example 1, this example adds consideration to the interaction between microscopic biological communities and makes improvements. The main improvements are as follows: In step 100, data preprocessing, add the interaction coefficient between species , intrinsic growth rate and environmental carrying capacity .

[0037] In step 200, when constructing the model, a microbial community interaction model and a coupled water quality change model are added.

[0038] The microbial community interaction model is: ; in: For biological the number of For biological The intrinsic growth rate, is the environmental carrying capacity, For biological and Biological The interaction coefficient between Indicates species The rate of change of the quantity over time; Indicates that except for species All other species The sum was used to calculate the total effect of all interactions among species; For biological the number of Represents biological and Biological The product of quantities is used to quantify the strength of the interaction between two species.

[0039] The coupled water quality change model is: ; in: For coupled water quality change models Water quality concentration at each moment (mg / L), is the initial concentration (mg / L), is the reaction rate constant (1 / s), is the equilibrium concentration (mg / L), For species The influence coefficient on water quality, is the total number of species, Indicates that all The sum is calculated for each species.

[0040] The remaining steps are the same as those in Example 1.

[0041] By introducing the microbial community interaction model, this embodiment has the following benefits: It more accurately reflects the complex relationships between biological populations in aquatic ecosystems, such as competition and symbiosis, and improves the ecological authenticity of the simulation; By coupling the water quality change model, the impact of biological communities on water quality and the feedback of water quality changes on biological communities can be considered simultaneously, thus achieving a two-way coupled simulation of water quality and organisms. It helps to better predict the chain reaction of emergencies on the entire ecosystem and provide a more comprehensive basis for the formulation of ecological restoration measures.

[0042] Example 3 This embodiment is based on the first embodiment, and further considers spatial heterogeneity, and makes improvements. The main improvements are as follows: Divide the water into space units, each unit area is ,satisfy .

[0043] in: For the The area of ​​a space unit (m²), is the total area of ​​the water body (m²), is the total number of spatial units, Indicates that all The sum is calculated for each spatial unit.

[0044] The model is improved to a spatially distributed model when it is built. , the water quality concentration change model is: ; in: For space unit exist Water quality concentration at the moment (mg / L); For space unit Initial concentration (mg / L); For space unit Reaction rate constant (1 / s); For space unit Equilibrium concentration (mg / L); represents the definite integral from 0 to time t; For space unit exist Water quality concentration at the time (mg / L), is the integration variable; is the differential of the integrated variable; For unit and unit Material exchange coefficient between Indicates that except for the unit All adjacent units except The sum is used to calculate the total amount of material exchange between space units, where is the total number of spatial units; For space unit exist Water quality concentration at the moment (mg / L); Represents spatial unit With space unit The concentration difference between them is used to calculate the driving force for the diffusion of substances.

[0045] When the simulation is running, each indicator is calculated for each spatial unit.

[0046] The optimization objective function is improved to: ; ; in: Indicates that all The sum is performed over the spatial units; represents the definite integral from 0 to T; is the differential of time; For unit Dissolved oxygen concentration (mg / L); is the standard value of dissolved oxygen (mg / L); For all species The sum is calculated, where is the total number of species; is the space unit at time T Medium Species The number of

[0047] By introducing spatial heterogeneity considerations, this embodiment has the following benefits: It overcomes the limitation of considering the entire water body as a homogeneous system and can reflect the differences in water quality and biological distribution at different spatial locations; By considering the material exchange between spatial units, the diffusion process of pollutants and the spatial variation characteristics of water quality are simulated more accurately; The optimization objective function takes into account the indicators of all spatial units, making the formulation of management strategies more spatially targeted and improving the governance effect.

[0048] Example 4 This embodiment is based on the first embodiment, and the uncertainty of the emergency event is considered, and the main improvements are as follows: Data preprocessing: determining pollutant releases The probability distribution parameters of are: ; in: Indicates that it obeys a certain distribution; It means the mean , the variance is The normal distribution of .

[0049] When the simulation is running, the Monte Carlo method is used to perform multiple simulations to obtain the statistical characteristics of the evaluation indicators.

[0050] The optimization objective is improved to a robust optimization model: ; in: represents the minimization objective function; Represents the objective function The mathematical expectation of , which is used to measure average performance; Represents the objective function The variance is used to measure the degree of performance fluctuation; is a trade-off coefficient used to balance the importance of expected value and variance.

[0051] By introducing uncertainty considerations for emergencies, this embodiment has the following benefits: It breaks away from the limitations of traditional deterministic models and can cope with random fluctuations in parameters of emergencies; Obtaining statistical characteristics of evaluation indicators through Monte Carlo simulation provides more comprehensive risk assessment information; The robust optimization method is adopted to make the optimized management strategy have stronger anti-interference ability and can cope with various uncertain situations.

[0052] Example 5 This embodiment adds a real-time data update function based on embodiment 1 and makes improvements. The main improvements are as follows: Add real-time data acquisition and preprocessing modules to obtain new measurement data .

[0053] in: It is a newly collected environmental monitoring data set, including the latest water quality parameters, hydrological parameters and aquatic biological data.

[0054] The dynamic update algorithm is used to update the model parameters. For water quality concentration data: ; in: is the updated water quality concentration (mg / L); is the water quality concentration before updating (mg / L); is the newly measured water quality concentration (mg / L); is the update weight (a real number between 0 and 1).

[0055] Rerun the simulation using the updated parameters.

[0056] Re-calculate the optimization based on the updated simulation results By introducing the real-time data update function, this embodiment has the following advantages: The dynamic adjustment of model parameters is realized, so that the simulation results can reflect the actual changes of the water ecological environment in a timely manner; The weighted update algorithm not only maintains the stability of the model but also ensures sensitive response to new data; The accuracy and timeliness of model predictions are improved, providing more reliable decision-making support for emergency response to emergencies.

[0057] Example 6 In this embodiment, a water ecological environment health status assessment and prediction system is proposed, which is used to implement the methods in Embodiments 1 to 5, including: The data acquisition module is used to obtain basic data on the water ecological environment; the model building module is used to build water quality change models and emergency impact models; the simulation calculation module is used to calculate time series data; and the optimization analysis module is used to solve the optimal management strategy parameters.

[0058] Also includes: The real-time monitoring module is used to collect real-time water quality data; the data update module is used to dynamically update model parameters; and the early warning decision module is used to generate early warning information and management recommendations.

[0059] The simulation calculation module also includes: a Monte Carlo simulation unit for performing multiple random simulations; a spatial analysis unit for calculating water quality changes in different spatial units; and a biological interaction unit for simulating the dynamics of microscopic biological communities.

[0060] The optimization analysis module uses the non-dominated sorting genetic algorithm (NSGA-II) to solve multi-objective optimization problems.

[0061] The above describes an embodiment of the present invention, but this embodiment is not limited to the above specific implementation methods. The above specific implementation methods are merely illustrative and not restrictive. Under the guidance of this embodiment, ordinary technicians in this field can also make many forms, all of which are protected by this embodiment.

Claims

1. A method for assessing and predicting the health status of aquatic ecological environment, characterized in that: The steps include: Acquire and preprocess basic data of water ecological environment, including water quality parameters, hydrological parameters and aquatic biological data; Modeling water quality changes: ； in for Water concentration at all times, is the initial concentration, is the reaction rate constant, is the equilibrium concentration, represents the definite integral from 0 to time t; for The water concentration at the time, is the integral variable, representing any time between 0 and t; Constructing the impact model of emergencies: ； in is the amount of pollutant released, is the mapping function between event type and pollutant release amount; Simulate and run, set simulation time interval and time step , calculate the time series data of each water quality parameter concentration and the number of each species for each time step; Indicator optimization, definition of management strategy parameter vector , construct water quality objective function and biodiversity objective function, and use multi-objective optimization algorithm to solve the optimal management strategy parameters.

2. A method for assessing and predicting the health status of aquatic ecological environment according to claim 1, characterized in that: In the emergency impact model: when In case of chemical spills, ; when When biological invasion occurs, ; in is the initial release amount, is the attenuation coefficient, is the base of natural logarithms, Represents an exponential function.

3. A method for assessing and predicting the health status of aquatic ecological environment according to claim 1, characterized in that: Also included are models for microbial community interactions: ； in: For Biology the number of For Biology The intrinsic growth rate, is the environmental carrying capacity, For Biology and Biological The interaction coefficient between Indicates species The rate of change of the quantity over time; Indicates that except for species All other species The sum was used to calculate the total effect of all interactions among species; For Biology the number of Represents biological and Biological The product of quantities is used to quantify the strength of the interaction between two species.

4. A method for assessing and predicting the health status of aquatic ecological environment according to claim 1, characterized in that: Divide the water into Space units, for space units , the water quality concentration change model is: ； in: For space unit exist Water concentration at the time; For space unit The initial concentration of For space unit The reaction rate constant; For space unit The equilibrium concentration of represents the definite integral from 0 to time t; For space unit exist The water concentration at the time, is the integral variable; is the differential of the integrated variable; For unit and unit Material exchange coefficient between Indicates that except for the unit All adjacent units except The sum is used to calculate the total amount of material exchange between space units, where is the total number of spatial units; For space unit exist Water concentration at the time; Represents spatial unit With space unit The concentration difference between them is used to calculate the driving force for the diffusion of substances.

5. A method for assessing and predicting the health status of aquatic ecological environment according to claim 1, characterized in that: Pollutant release Normal distribution , Monte Carlo method is used for multiple simulations, and the optimization goal is: ； in represents the minimization objective function; Represents the objective function The mathematical expectation of , which is used to measure average performance; Represents the objective function The variance is used to measure the degree of performance fluctuation; is a trade-off coefficient used to balance the importance of expected value and variance.

6. A method for assessing and predicting the health status of aquatic ecological environment according to claim 1, characterized in that: Also includes real-time data update steps: Use dynamic update algorithm to update water quality concentration data: ； in is the updated water quality concentration, is the water quality concentration before updating, is the newly measured water quality concentration, To update the weights.

7. A water ecological environment health status assessment and prediction system, characterized in that: It is used to execute a method for assessing and predicting the health status of a water ecological environment as claimed in any one of claims 1 to 6, including: a data acquisition module for acquiring basic data on the water ecological environment; a model building module for building a water quality change model and an emergency impact model; a simulation calculation module for calculating time series data; and an optimization analysis module for solving optimal management strategy parameters.

8. A water ecological environment health status assessment and prediction system according to claim 7, characterized in that: Also includes: Real-time monitoring module, used to collect real-time water quality data; Data update module, used to dynamically update model parameters; The early warning decision module is used to generate early warning information and management suggestions.

9. A water ecological environment health status assessment and prediction system according to claim 7, characterized in that: The simulation calculation module also includes: a Monte Carlo simulation unit for performing multiple random simulations; a spatial analysis unit for calculating water quality changes in different spatial units; and a biological interaction unit for simulating the dynamics of microscopic biological communities.

10. A water ecological environment health status assessment and prediction system according to claim 7, characterized in that: The optimization analysis module uses a non-dominated sorting genetic algorithm to solve multi-objective optimization problems.

Images