A Method for Assessing and Warning the Ecological Quality of Gulf Regions Based on Machine Learning

Abstract

The present invention discloses a method for ecological quality assessment and early warning in a bay area based on machine learning, which relates to the technical field of bay ecological assessment. Data related to the ecological quality of the target bay area is collected based on multiple data sources, including water quality parameters, air quality parameters, and environmental pressure parameters. Feature analysis is performed on the data related to the ecological quality of the bay area to clarify the changing trend of the ecological quality in the bay area. Among them, the changing trend of ecological quality includes the water quality deviation trend, the air quality deviation trend, and the negative environmental pressure trend. By collecting and processing water quality, air quality, and environmental pressure data and using the trained abnormal ecological quality identification model for dynamic assessment, the present invention can realize the real-time monitoring of the ecological quality in the bay area. Once an abnormal situation is detected, a warning notice can be immediately issued to help managers take actions quickly and avoid the further deterioration of the ecosystem.

Description

Technical Field

[0001] The present invention relates to the technical field of bay ecological assessment, and particularly relates to a method for assessing and warning the ecological quality of bay areas based on machine learning. Background Art

[0002] Bay areas are an important part of the marine ecosystem, with rich biodiversity and important ecological functions. With the continuous increase of human activities, the bay ecosystem faces serious threats, such as pollution, overfishing, habitat destruction, etc. These threats not only affect the ecological balance of the bay area, but may also have a negative impact on the economic development and residents' lives in the surrounding areas. Therefore, it is particularly important to assess and warn the ecological quality of the bay area for targeted protection and management.

[0003] In the prior art, the ecological quality of the bay area is affected by various factors, which affects the accuracy of the ecological quality assessment and warning of the bay area. Therefore, how to capture the dynamic changes of the bay ecosystem and improve the accuracy of the ecological quality assessment and warning in order to match corresponding governance measures is the problem we need to solve. For this reason, a method for assessing and warning the ecological quality of bay areas based on machine learning is proposed. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for assessing and warning the ecological quality of bay areas based on machine learning to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the technical solution adopted by the present invention is:

[0006] A method for assessing and warning the ecological quality of bay areas based on machine learning, comprising the following steps:

[0007] S1. Collect data related to the ecological quality of the target bay area based on multiple data sources, including water quality parameters, air quality parameters, and environmental pressure parameters;

[0008] S2. Analyze the characteristics of the data related to the ecological quality of the bay area to clarify the changing trend of the ecological quality of the bay area, wherein the changing trend of the ecological quality includes the water quality deviation trend, the air quality deviation trend, and the negative environmental pressure trend;

[0009] S3. Use historical data with known ecological quality states to train an abnormal ecological quality identification model to identify abnormal situations existing in the ecological quality of the target bay area;

[0010] S4. Combine the identification results of the abnormal ecological quality identification model and the changing trend of the ecological quality to conduct a dynamic assessment of the ecological quality of the bay area;

[0011] S5. Set the ecological quality threshold, conduct early warning analysis on the dynamic assessment results, and implement corresponding governance measures based on the early warning results.

[0012] A further improvement of the technical solution of the present invention lies in: in S1, the process of collecting ecological quality data of the target bay area is as follows:

[0013] S11. Select and determine the data sources for ecological quality assessment of the target bay area, which are water quality monitoring stations, air quality monitoring stations, and environmental pressure data sources respectively. Among them, select and determine multiple water quality monitoring stations to cover different areas of the target bay, including key locations such as the inshore area, deep sea area, and estuary. Determine multiple air quality monitoring stations to reflect the air quality status around the target bay. Use satellite remote sensing technology to monitor the environmental information of a large geographical area, and combine pollutant emission reports and meteorological stations to comprehensively obtain environmental pressure data;

[0014] S12. According to the characteristics of the target bay area, clarify the data types for ecological quality assessment of the bay area, including water quality parameters, air quality parameters, and environmental pressure parameters;

[0015] For water quality parameter data, use automatic water quality monitoring instruments to regularly collect data on pH value, suspended particulate matter, dissolved oxygen, chemical oxygen demand, and total nitrogen and phosphorus content; for air quality parameter data, install sensors at the selected air quality monitoring stations to monitor and obtain data on sulfur dioxide concentration, nitrogen oxide concentration, and inhalable particulate matter (PM2.5 and PM10) concentration; for environmental pressure parameters, based on satellite remote sensing monitoring, pollutant emission reports, and meteorological stations, obtain data on pollutant emissions and temperature change rates;

[0016] S14. Build a data warehouse, and perform preprocessing operations of data cleaning and data standardization on the relevant data of the obtained water quality parameters, air quality parameters, and environmental pressure parameters. Preprocess the original data to remove noise, fill in missing values, correct incorrect data, etc. Unify the formats of data from different sources through data standardization to facilitate subsequent analysis, and integrate the data from different data sources into the data warehouse for storage.

[0017] A further improvement of the technical solution of the present invention lies in: in S2, the process of analyzing the changing trend of the ecological quality of the bay area is as follows:

[0018] S21. Traverse the data warehouse to retrieve the preprocessed water quality parameters, air quality parameters, and environmental pressure parameter data, and perform feature analysis on each parameter data to extract indicators reflecting the ecological quality of the bay area;

[0019] S22. Based on the preprocessed water quality data, extract the evaluation indicators of pH value, suspended particulate matter, dissolved oxygen, chemical oxygen demand, and total nitrogen and phosphorus content. Combine with the ecological quality requirements and historical database of the target area to determine the benchmark values of each water quality evaluation indicator, and then calculate the water quality deviation index to analyze the change trend of water quality parameters over time during the evaluation period;

[0020] S23. Based on the preprocessed air quality data, extract the evaluation indicators of sulfur dioxide concentration, nitrogen oxide concentration, and inhalable particulate matter (PM2.5 and PM10) concentration. Combine with the ecological quality requirements and historical database of the target area to determine the benchmark values of each air quality evaluation indicator, and then calculate the air quality deviation index to analyze the change trend of air quality parameters over time during the evaluation period;

[0021] S24. Based on the preprocessed environmental pressure parameter data, extract the evaluation indicators of pollutant emissions and temperature change rate. Combine with the ecological quality requirements and historical database of the target area to determine the benchmark values of each environmental pressure evaluation indicator, and then calculate the environmental pressure trend index to analyze the negative trend of environmental pressure.

[0022] A further improvement of the technical solution of the present invention lies in: the calculation formula of the water quality deviation index is as follows:

[0023] ;

[0024] In the formula, W is the water quality deviation index, is the actual measured value of the i-th water quality parameter evaluation indicator, is the benchmark value of the i-th water quality parameter evaluation indicator, which is the standard value determined based on the ecological quality requirements and historical database of the target area, is the weight of the i-th water quality parameter evaluation indicator, used to reflect its importance in the comprehensive evaluation, p is the adjustment factor, used to control the sensitivity of the exponential function, default set to 2, n is the number of water quality parameter evaluation indicators, i is the index of the water quality parameter evaluation indicator, i = 1, 2, 3, 4, 5, corresponding to pH value, suspended particulate matter, dissolved oxygen, chemical oxygen demand, and total nitrogen and phosphorus content respectively. The value range of W is between 0 and 1. When all water quality parameter evaluation indicators are exactly the same as the benchmark values, W is 0. When one or more water quality parameter evaluation indicators deviate from the benchmark values more, W is closer to 1; W approaching 0 indicates that the water quality parameters are close to the benchmark values and the water quality condition is good, and W approaching 1 indicates that the water quality parameters seriously deviate from the benchmark values and the water quality condition is poor;

[0025] The calculation formula of the air quality deviation index is as follows:

[0026] ;

[0027] Wherein, R is the air quality deviation index, is the actual measured value of the j-th air quality parameter evaluation index, is the reference value of the j-th air quality parameter evaluation index, which is a standard value determined based on the ecological quality requirements and historical database of the target area, is the weight of the j-th air quality parameter evaluation index, which is used to reflect its importance in the comprehensive evaluation. m is the number of air quality parameter evaluation indexes, and j is the index of the air quality parameter evaluation index. j = 1, 2, 3, corresponding to sulfur dioxide concentration, nitrogen oxide concentration, and inhalable particulate matter concentration respectively. The value range of R is between 0 and 1. When all air quality parameter evaluation indexes are exactly the same as the reference value, R is 0. When one or more air quality parameter evaluation indexes deviate from the reference value more, R is closer to 1. R approaching 0 indicates that the air quality parameter is close to the reference value and the air quality condition is good. R approaching 1 indicates that the air quality parameter seriously deviates from the reference value and the air quality condition is poor;

[0028] The calculation formula of the environmental pressure trend index is as follows:

[0029] ;

[0030] Wherein, E is the environmental pressure trend index, is the actual measured value of the k-th environmental pressure parameter evaluation index, is the reference value of the k-th environmental pressure parameter evaluation index, which is a standard value determined based on the ecological quality requirements and historical database of the target area, is the weight of the k-th environmental pressure parameter evaluation index, which is used to reflect its importance in the comprehensive evaluation. h is the number of environmental pressure parameter evaluation indexes, and k is the index of the environmental pressure parameter evaluation index. k = 1, 2, corresponding to pollutant emissions and temperature change rate respectively. The value range of E is between 0 and 1. When all environmental pressure parameter evaluation indexes are exactly the same as the reference value, E is 0. When one or more environmental pressure parameter evaluation indexes deviate from the reference value more, E is closer to 1. E approaching 0 indicates that the environmental pressure parameter is close to the reference value and the environmental condition is good. E approaching 1 indicates that the environmental pressure parameter seriously deviates from the reference value and the environmental condition is poor.

[0031] A further improvement of the technical solution of the present invention lies in: in S3, the identification process of abnormal situations is as follows:

[0032] S31. Collect historical data of the target bay area containing known ecological quality states, and mark abnormal water quality parameters, abnormal air quality parameters, and abnormal environmental pressure parameters in the historical data;

[0033] S32. Integrate the evaluation indicators of water quality parameters, air quality parameters, and environmental pressure parameters to obtain a comprehensive dataset, and divide it into a training set and a test set, ensuring that each sample contains all relevant parameters and their corresponding normal or abnormal labels;

[0034] S33. Based on the evaluation indicator data of the training set and combined with a neural network model, use the water quality parameters, air quality parameters, and environmental pressure parameters in the training set as input features, and the normal or abnormal labels as output. Train the abnormal ecological quality recognition model, adjust the model parameters to enable it to identify abnormal situations of ecological quality, and evaluate the performance of the model by calculating indicators such as accuracy, recall rate, F1-score, and AUC in combination with the test set data, and then optimize the model according to the evaluation results;

[0035] S34. Apply the trained model to the real-time ecological quality data of the target bay area, and calculate the abnormal recognition index according to the probability output by the model. Set the abnormal threshold Y to determine whether there is an abnormality.

[0036] A further improvement of the technical solution of the present invention lies in: The calculation formula of the abnormal recognition index is as follows:

[0037] ;

[0038] In the formula, T is the abnormal recognition index, is the actual measured value of the t-th real-time ecological quality parameter, is the weight of the t-th parameter, which is used to reflect its importance in the comprehensive evaluation. N is the number of ecological quality parameters, that is, the sum of the evaluation indicators of water quality parameters, air quality parameters, and environmental pressure parameters, is an adjustment factor, which is used to control the influence degree of the parameter average value on the threshold, is an adjustment factor, which is used to introduce randomness so that the threshold has a certain fluctuation range, represents a number randomly generated within the interval [0,1]. If , it is determined that there is an abnormality.

[0039] A further improvement of the technical solution of the present invention lies in: In the above S4, the process of dynamic evaluation of the ecological quality of the bay area is as follows:

[0040] S41. Input the parameter data of water quality, air quality, and environmental pressure in the target area into the trained abnormal ecological quality recognition model for abnormal detection of the target area. The model outputs the probability of normal or abnormal. According to the set abnormal threshold, obtain the recognition result of the abnormal state;

[0041] S42. Calculate the water quality deviation index, air quality deviation index, and environmental pressure trend index of the target area, analyze the variation trends of each parameter over time, and assign corresponding weights according to the importance of each parameter in the ecosystem;

[0042] S43. Based on the weights assigned to each parameter, combined with the calculation results of the water quality deviation index, air quality deviation index, and environmental pressure trend index of the target area, comprehensively calculate the ecological quality assessment coefficient, and analyze the ecological quality status of the target bay area according to the magnitude of the comprehensive ecological quality assessment coefficient.

[0043] A further improvement of the technical solution of the present invention is that the calculation formula of the ecological quality assessment coefficient is as follows:

[0044] ;

[0045] In the formula, SC is the ecological quality assessment coefficient, W is the water quality deviation index, R is the air quality deviation index, E is the environmental pressure trend index, is the weight of the water quality deviation index, is the weight of the air quality deviation index, is the weight of the environmental pressure trend index. It should be noted that when SC approaches 1, it indicates that the water quality, air quality, and environmental pressure parameters are all close to the reference values, and the ecological quality status is good.

[0046] A further improvement of the technical solution of the present invention is that in the above S5, the process of early warning analysis is as follows:

[0047] S51. According to the requirements of the ecological quality of the bay area and the historical ecological quality data of the bay area, classify the ecological quality of the bay area into excellent ecological quality grade, good ecological quality grade, and poor ecological quality grade;

[0048] S52. Combine the calculation results of the ecological quality assessment coefficient, match them with each ecological quality grade, and set corresponding ecological quality thresholds for each ecological quality grade;

[0049] S53. Based on the value of the ecological quality assessment coefficient, judge the current ecological quality grade and mark it with different status colors. Mark the excellent ecological quality grade with a green status color, mark the good ecological quality grade with a yellow status color, and mark the poor ecological quality grade with a red status color;

[0050] S54. When in the good ecological quality grade, issue a warning notice and recommend taking preventive measures. When in the poor ecological quality grade, issue an emergency warning notice, immediately activate the emergency response mechanism, and analyze the reasons for the warning, including water quality deterioration, increased air pollution, and increased environmental pressure;

[0051] S55. According to the early warning analysis results, formulate targeted treatment plans, implement corresponding treatment measures, strengthen water quality monitoring and treatment, improve air quality, relieve environmental pressure. At the same time, supervise the implementation of the treatment measures to ensure the effective execution of the measures, regularly evaluate the treatment effect, and adjust the treatment plan according to the evaluation results.

[0052] A further improvement of the technical solution of the present invention lies in that: multiple ecological quality grades correspond to multiple ecological quality thresholds, wherein the ecological quality thresholds include an upper threshold and a lower threshold;

[0053] Multiple ecological quality grades and multiple ecological quality thresholds satisfy the following relationship:

[0054] The ecological quality threshold for the excellent ecological quality grade is: ;

[0055] The ecological quality threshold for the good ecological quality grade is: ;

[0056] The ecological quality threshold for the poor ecological quality grade is: ;

[0057] Wherein, SC is the ecological quality evaluation coefficient, is the lower threshold corresponding to the excellent ecological quality grade and the upper threshold corresponding to the good ecological quality grade, is the lower threshold corresponding to the good ecological quality grade and the upper threshold corresponding to the poor ecological quality grade, , .

[0058] Due to the adoption of the above technical solution, the technical progress achieved by the present invention compared with the prior art is:

[0059] The present invention provides a method for evaluating and warning the ecological quality of a bay area based on machine learning. By collecting and processing water quality, air quality and environmental pressure data, and using a trained abnormal ecological quality identification model for dynamic evaluation, it can realize the real-time monitoring of the ecological quality of the bay area. Once an abnormal situation is detected, a warning notice can be immediately issued to help managers take prompt actions to avoid the further deterioration of the ecosystem.

[0060] The present invention provides a method for evaluating and warning the ecological quality of a bay area based on machine learning. By integrating the water quality deviation index, air quality deviation index and environmental pressure trend index, it comprehensively evaluates the ecological quality of the bay area from multiple dimensions, more accurately reflects the overall ecological situation, avoids the deviation caused by a single index, and moreover, according to the early warning analysis results, a targeted treatment plan can be formulated to ensure the long-term health and sustainable development of the ecosystem. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0062] Figure 1 is a flowchart of the method of the present invention;

[0063] Figure 2 is an analysis flowchart of the changing trend of the ecological quality in the bay area of the present invention;

[0064] Figure 3 is a flowchart of the dynamic assessment of the ecological quality in the bay area of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0065] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0066] Embodiment 1, as Figure 1 、 Figure 2 shown, the present invention provides a method for evaluating and warning the ecological quality of a bay area based on machine learning, including the following steps:

[0067] S1. Collect data related to the ecological quality of the target bay area from multiple data sources, including water quality parameters, air quality parameters, and environmental pressure parameters. Among them, the water quality parameters include pH value, suspended particulate matter, dissolved oxygen, chemical oxygen demand, and total nitrogen and phosphorus content; the air quality parameters include sulfur dioxide concentration, nitrogen oxide concentration, and inhalable particulate matter (PM2.5 and PM10) concentration; the environmental pressure parameters include pollutant emissions and temperature change rate. Select and determine the data sources for ecological quality assessment in the target bay area, namely water quality monitoring stations, air quality monitoring stations, and environmental pressure data sources. Among them, select and determine multiple water quality monitoring sites covering different areas of the target bay, including key locations such as the inshore area, deep sea, and estuary; determine multiple air quality monitoring stations to reflect the air quality status around the target bay; use satellite remote sensing technology to monitor environmental information in a large geographical area, and combine pollutant emission reports and meteorological stations to comprehensively obtain environmental pressure data. According to the characteristics of the target bay area, clarify the data types for ecological quality assessment in the bay area, including water quality parameters, air quality parameters, and environmental pressure parameters. For water quality parameter data, use automatic water quality monitoring instruments to regularly collect data on pH value, suspended particulate matter, dissolved oxygen, chemical oxygen demand, and total nitrogen and phosphorus content; for air quality parameter data, install sensors at the selected air quality monitoring stations to monitor and obtain data on sulfur dioxide concentration, nitrogen oxide concentration, and inhalable particulate matter (PM2.5 and PM10) concentration; for environmental pressure parameters, obtain data on pollutant emissions and temperature change rate based on satellite remote sensing monitoring, pollutant emission reports, and meteorological stations. Among them, the pH value reflects the acid-base balance of the water body, suspended particulate matter indicates the turbidity of the water body, dissolved oxygen reflects the self-purification ability and biological activity of the water body, chemical oxygen demand measures the degree of organic pollution in the water body, total nitrogen and phosphorus content indicates the risk of water eutrophication, sulfur dioxide concentration is one of the harmful gases, nitrogen oxide concentration includes NO and NO2, inhalable particulate matter includes PM2.5 and PM10, pollutant emissions measure the pressure of human activities on the environment, and temperature change rate reflects the impact of climate change on the ecosystem. Build a data warehouse and perform preprocessing operations of data cleaning and data standardization on the relevant data of the obtained water quality parameters, air quality parameters, and environmental pressure parameters. Preprocess the original data, remove noise, fill in missing values, correct incorrect data, etc. Unify the formats of data from different sources through data standardization to facilitate subsequent analysis, and integrate the data from different data sources into the data warehouse for storage;

[0068] S2. Analyze the characteristics of the data related to the ecological quality of the bay area to clarify the changing trend of the ecological quality of the bay area. Among them, the changing trend of ecological quality includes the water quality deviation trend, the air quality deviation trend, and the negative trend of environmental pressure. Traverse the data warehouse to retrieve the preprocessed water quality parameters, air quality parameters, and environmental pressure parameter data, and analyze the characteristics of each parameter data to extract the indicators reflecting the ecological quality of the bay area. Based on the preprocessed water quality data, extract the evaluation indicators of pH value, suspended particulate matter, dissolved oxygen, chemical oxygen demand, and total nitrogen and phosphorus content, and combine the ecological quality requirements of the target area and the historical database to determine the benchmark values of each water quality evaluation indicator. Then calculate the water quality deviation index and analyze the changing trend of water quality parameters over time during the evaluation period. Based on the preprocessed air quality data, extract the evaluation indicators of sulfur dioxide concentration, nitrogen oxide concentration, and inhalable particulate matter (PM2.5 and PM10) concentration, and combine the ecological quality requirements of the target area and the historical database to determine the benchmark values of each air quality evaluation indicator. Then calculate the air quality deviation index and analyze the changing trend of air quality parameters over time during the evaluation period. Based on the preprocessed environmental pressure parameter data, extract the evaluation indicators of pollutant emissions and temperature change rate, and combine the ecological quality requirements of the target area and the historical database to determine the benchmark values of each environmental pressure evaluation indicator. Then calculate the environmental pressure tendency index and analyze the negative trend of environmental pressure;

[0069] Further, the calculation formula of the water quality deviation index is as follows:

[0070] ;

[0071] In the formula, W is the water quality deviation index, is the actual measured value of the i-th water quality parameter evaluation indicator, is the benchmark value of the i-th water quality parameter evaluation indicator, which is the standard value determined based on the ecological quality requirements of the target area and the historical database, is the weight of the i-th water quality parameter evaluation indicator, which is used to reflect its importance in the comprehensive evaluation. p is the adjustment factor, which is used to control the sensitivity of the exponential function and is default set to 2. n is the number of water quality parameter evaluation indicators. i is the index of the water quality parameter evaluation indicator, i = 1, 2, 3, 4, 5, corresponding to pH value, suspended particulate matter, dissolved oxygen, chemical oxygen demand, and total nitrogen and phosphorus content respectively. The value range of W is between 0 and 1. When all water quality parameter evaluation indicators are exactly the same as the benchmark values, W is 0. When one or more water quality parameter evaluation indicators deviate from the benchmark values more, W is closer to 1; W approaching 0 indicates that the water quality parameters are close to the benchmark values and the water quality condition is good. W approaching 1 indicates that the water quality parameters seriously deviate from the benchmark values and the water quality condition is poor;

[0072] The calculation formula of the air quality deviation index is as follows:

[0073] ;

[0074] Wherein, R is the air quality deviation index, is the actual measured value of the jth air quality parameter evaluation index, is the reference value of the jth air quality parameter evaluation index, which is a standard value determined based on the ecological quality requirements of the target area and the historical database, is the weight of the jth air quality parameter evaluation index, used to reflect its importance in the comprehensive evaluation, m is the number of air quality parameter evaluation indexes, j is the index of the air quality parameter evaluation index, j = 1, 2, 3, corresponding to the sulfur dioxide concentration, nitrogen oxide concentration and inhalable particulate matter concentration respectively. The value range of R is between 0 and 1. When all air quality parameter evaluation indexes are exactly the same as the reference value, R is 0. When one or more air quality parameter evaluation indexes deviate from the reference value more, R is closer to 1; R approaching 0 indicates that the air quality parameter is close to the reference value and the air quality condition is good, and R approaching 1 indicates that the air quality parameter seriously deviates from the reference value and the air quality condition is poor;

[0075] The calculation formula of the environmental pressure trend index is as follows:

[0076] ;

[0077] Wherein, E is the environmental pressure trend index, is the actual measured value of the kth environmental pressure parameter evaluation index, is the reference value of the kth environmental pressure parameter evaluation index, which is a standard value determined based on the ecological quality requirements of the target area and the historical database, is the weight of the kth environmental pressure parameter evaluation index, used to reflect its importance in the comprehensive evaluation, h is the number of environmental pressure parameter evaluation indexes, k is the index of the environmental pressure parameter evaluation index, k = 1, 2, corresponding to the pollutant emission amount and the temperature change rate respectively. The value range of E is between 0 and 1. When all environmental pressure parameter evaluation indexes are exactly the same as the reference value, E is 0. When one or more environmental pressure parameter evaluation indexes deviate from the reference value more, E is closer to 1; E approaching 0 indicates that the environmental pressure parameter is close to the reference value and the environmental condition is good, and E approaching 1 indicates that the environmental pressure parameter seriously deviates from the reference value and the environmental condition is poor;

[0078] S3. Use the historical data of known ecological quality status to train an abnormal ecological quality recognition model to identify the abnormal conditions existing in the ecological quality of the target bay area. Collect the historical data of the target bay area containing known ecological quality status, mark the abnormal water quality parameters, abnormal air quality parameters, and abnormal environmental pressure parameters in the historical data, integrate the evaluation indicators of water quality parameters, air quality parameters, and environmental pressure parameters to obtain a comprehensive data set, and divide it into a training set and a test set to ensure that each sample contains all relevant parameters and their corresponding normal or abnormal labels. Based on the evaluation index data of the training set combined with the neural network model, use the water quality parameters, air quality parameters, and environmental pressure parameters in the training set as input features and the normal or abnormal labels as output to train the abnormal ecological quality recognition model, adjust the model parameters to enable it to identify the abnormal conditions of ecological quality, and evaluate the performance of the model by calculating indicators such as accuracy, recall rate, F1-score, and AUC in combination with the test set data. Then optimize the model according to the evaluation results, apply the trained model to the real-time ecological quality data of the target bay area, and calculate the abnormal recognition index according to the probability output by the model. Set an abnormal threshold Y to determine whether there is an abnormality;

[0079] Further, the calculation formula of the abnormal recognition index is as follows:

[0080] ;

[0081] In the formula, T is the abnormal recognition index, is the actual measured value of the t-th real-time ecological quality parameter, is the weight of the t-th parameter, which is used to reflect its importance in the comprehensive evaluation. N is the number of ecological quality parameters, that is, the sum of the evaluation indicators of water quality parameters, air quality parameters, and environmental pressure parameters, is an adjustment factor, which is used to control the influence degree of the parameter average value on the threshold, is an adjustment factor, which is used to introduce randomness to make the threshold have a certain fluctuation range, represents a number randomly generated in the interval [0, 1], which is used to introduce randomness. When the parameter value deviates significantly from the reference value, is larger, and the threshold will decrease, making it easier to determine as abnormal. When the parameter value is very close to the reference value, the threshold will be close to 0.5 or higher, making the standard for determining as abnormal more strict. If , it is determined that there is an abnormality;

[0082] S4. Combine the recognition results of the abnormal ecological quality recognition model and the ecological quality change trend to conduct a dynamic evaluation of the ecological quality of the bay area;

[0083] S5. Set the ecological quality threshold, conduct early warning analysis on the dynamic assessment results, and implement corresponding governance measures based on the early warning results.

[0084] Example 2. As Figure 3 shown, based on Example 1, the present invention provides a technical solution: Preferably, in S4, the process of dynamic assessment of the ecological quality in the bay area is as follows:

[0085] Input the parameter data of water quality, air quality, and environmental pressure in the target area into the trained abnormal ecological quality identification model for abnormal detection of the target area. The model outputs the probability of normal or abnormal. According to the set abnormal threshold, obtain the identification result of the abnormal state, calculate the water quality deviation index, air quality deviation index, and environmental pressure trend index of the target area, analyze the change trend of each parameter over time, and assign corresponding weights according to the importance of each parameter in the ecosystem. Based on the weights assigned to each parameter, combined with the calculation results of the water quality deviation index, air quality deviation index, and environmental pressure trend index of the target area, comprehensively calculate the ecological quality assessment coefficient, and analyze the ecological quality status of the target bay area according to the magnitude of the comprehensive ecological quality assessment coefficient.

[0086] Furthermore, the calculation formula of the ecological quality assessment coefficient is as follows:

[0087] ;

[0088] In the formula, SC is the ecological quality assessment coefficient, W is the water quality deviation index, R is the air quality deviation index, E is the environmental pressure trend index, is the weight of the water quality deviation index, is the weight of the air quality deviation index, is the weight of the environmental pressure trend index. It should be noted that when all deviation indexes are 0, SC is 1. When one or more deviation indexes increase, SC approaches 0; SC approaching 1 indicates that the water quality, air quality, and environmental pressure parameters are all close to the reference values, and the ecological quality status is good. SC approaching 0 indicates that some or all parameters seriously deviate from the reference values, and the ecological quality status is poor.

[0089] In S5, the process of early warning analysis is as follows:

[0090] According to the requirements of the ecological quality in the bay area and historical ecological quality data of the bay area, the ecological quality of the bay area is classified into excellent ecological quality level, good ecological quality level and poor ecological quality level. Combining the calculation results of the ecological quality assessment coefficient, it is matched with each ecological quality level, and corresponding ecological quality thresholds are set for each ecological quality level. Based on the value of the ecological quality assessment coefficient, the current ecological quality level is judged and marked with different status colors. The excellent ecological quality level is marked with a green status color, the good ecological quality level is marked with a yellow status color, and the poor ecological quality level is marked with a red status color. When in the good ecological quality level, a warning notice is issued, and preventive measures are recommended. When in the poor ecological quality level, an emergency warning notice is issued, the emergency response mechanism is immediately activated, and the warning reasons are analyzed, including water quality deterioration, aggravated air pollution and increased environmental pressure. According to the warning analysis results, a targeted treatment plan is formulated and corresponding treatment measures are implemented. Water quality monitoring and treatment are strengthened, air quality is improved, and environmental pressure is reduced. At the same time, the implementation of the treatment measures is supervised to ensure that the measures are effectively implemented, and the treatment effect is regularly evaluated. According to the evaluation results, the treatment plan is adjusted;

[0091] Furthermore, multiple ecological quality levels correspond to multiple ecological quality thresholds, where the ecological quality thresholds include upper threshold and lower threshold;

[0092] The relationships between multiple ecological quality levels and multiple ecological quality thresholds are as follows:

[0093] The ecological quality threshold for the excellent ecological quality level is: ; indicating that the ecological quality is extremely good, the ecosystem function is strong, the biodiversity is rich, and the health status of the ecosystem is good, and no immediate emergency measures are required;

[0094] The ecological quality threshold for the good ecological quality level is: ; indicating that the ecological quality is good, the ecosystem function is basically stable, the biodiversity is relatively rich, but there are certain problems in the health status of the ecosystem, and preventive measures need to be closely monitored and taken;

[0095] The ecological quality threshold for the poor ecological quality level is: ; indicating that the ecological quality is poor, the ecosystem function is damaged, the biodiversity is reduced, and the health status of the ecosystem is poor, and immediate emergency treatment measures are required;

[0096] Among them, SC is the ecological quality assessment coefficient, is the lower threshold corresponding to the excellent ecological quality level and the upper threshold corresponding to the good ecological quality level, is the lower threshold corresponding to the good ecological quality level and the upper threshold corresponding to the poor ecological quality level, , 。

[0097] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims described above.

Claims

1. A method for evaluating and warning the ecological quality of the bay area based on machine learning, characterized in that, Including the following steps: S1. Collect data related to the ecological quality of the target bay area from multiple data sources, including water quality parameters, air quality parameters, and environmental pressure parameters; S2. Conduct a feature analysis of the data related to the ecological quality of the bay area to clarify the changing trend of the ecological quality of the bay area. Among them, the changing trend of ecological quality includes the water quality deviation trend, the air quality deviation trend, and the negative environmental pressure trend; S3. Use the historical data with known ecological quality status to train the abnormal ecological quality identification model to identify the abnormal conditions existing in the ecological quality of the target bay area. The identification process of the abnormal conditions is as follows: S31. Collect the historical data of the target bay area containing the known ecological quality status, and mark the abnormal water quality parameters, abnormal air quality parameters, and abnormal environmental pressure parameters in the historical data; S32. Integrate the evaluation indicators of water quality parameters, air quality parameters, and environmental pressure parameters to obtain a comprehensive data set, and divide it into a training set and a test set; S33. Based on the evaluation index data of the training set and combined with the neural network model, use the water quality parameters, air quality parameters, and environmental pressure parameters in the training set as input features, and the normal or abnormal labels as output to train the abnormal ecological quality identification model, adjust the model parameters to make it identify the abnormal conditions of the ecological quality, and evaluate the performance of the model combined with the test set data, and then optimize the model according to the evaluation results; S34. Apply the trained model to the real-time ecological quality data of the target bay area, calculate the abnormal identification index according to the probability output by the model, and set the abnormal threshold Y to judge whether there is an abnormality; S4. Combine the identification results of the abnormal ecological quality identification model and the changing trend of the ecological quality to conduct a dynamic evaluation of the ecological quality of the bay area; S5. Set the ecological quality threshold, conduct a warning analysis on the dynamic evaluation results, and implement corresponding treatment measures based on the warning results.

2. The method for evaluating and warning the ecological quality of a bay area based on machine learning according to claim 1, wherein: In the above S1, the process of collecting the ecological quality data of the target bay area is as follows: S11. Select and determine the data sources for the ecological quality assessment of the target bay area, namely the water quality monitoring station, the air quality monitoring station, and the environmental pressure data source; S12. According to the characteristics of the target bay area, clarify the data types for the ecological quality assessment of the bay area, including water quality parameters, air quality parameters, and environmental pressure parameters; S13. For the water quality parameter data, use an automatic water quality monitoring instrument to regularly collect data on pH value, suspended particulate matter, dissolved oxygen, chemical oxygen demand, and total nitrogen and phosphorus content; for the air quality parameter data, install sensors at the selected air quality monitoring sites to monitor and obtain data on sulfur dioxide concentration, nitrogen oxide concentration, and inhalable particulate matter concentration; for the environmental pressure parameters, based on satellite remote sensing monitoring, pollutant emission reports, and meteorological stations, obtain data on pollutant emissions and temperature change rates; S14. Build a data warehouse, perform preprocessing operations of data cleaning and data standardization on the relevant data of the obtained water quality parameters, air quality parameters, and environmental pressure parameters, and integrate the data from different data sources into the data warehouse for storage.

3. The method for evaluating and warning the ecological quality of a bay area based on machine learning according to claim 2, characterized in that: In S2, the analysis process of the ecological quality change trend in the bay area is as follows: S21. Traverse the data warehouse to retrieve the preprocessed water quality parameters, air quality parameters, and environmental pressure parameter data, and conduct feature analysis on each parameter data to extract the indicators reflecting the ecological quality of the bay area; S22. Based on the preprocessed water quality data, extract the evaluation indicators of pH, suspended particulate matter, dissolved oxygen, chemical oxygen demand, and total nitrogen and phosphorus content, and combine the ecological quality requirements of the target area and the historical database to determine the benchmark values of each water quality evaluation indicator, and then calculate the water quality deviation index to analyze the change trend of water quality parameters over time during the evaluation period; S23. Based on the preprocessed air quality data, extract the evaluation indicators of sulfur dioxide concentration, nitrogen oxide concentration, and inhalable particulate matter concentration, and combine the ecological quality requirements of the target area and the historical database to determine the benchmark values of each air quality evaluation indicator, and then calculate the air quality deviation index to analyze the change trend of air quality parameters over time during the evaluation period; S24. Based on the preprocessed environmental pressure parameter data, extract the evaluation indicators of pollutant emissions and temperature change rate, and combine the ecological quality requirements of the target area and the historical database to determine the benchmark values of each environmental pressure evaluation indicator, and then calculate the environmental pressure tendency index to analyze the negative trend of environmental pressure.

4. The method for evaluating and warning the ecological quality of the bay area based on machine learning according to claim 3, wherein: The calculation formula of the water quality deviation index is as follows: Where W is the water quality deviation index, and x i is the actual measured value of the i-th water quality parameter evaluation index, and b i is the reference value of the i-th water quality parameter evaluation index, and w i is the weight of the i-th water quality parameter evaluation index, p is the adjustment factor, n is the number of water quality parameter evaluation indexes, i is the index of the water quality parameter evaluation index, and i = 1, 2, 3, 4, 5, corresponding to pH, suspended particulate matter, dissolved oxygen, chemical oxygen demand, and total nitrogen and phosphorus content respectively. The value range of W is between 0 and 1. When W approaches 0, it indicates that the water quality parameter is close to the reference value and the water quality condition is good. When W approaches 1, it indicates that the water quality parameter seriously deviates from the reference value and the water quality condition is poor; The calculation formula of the air quality deviation index is as follows: where R is the air quality deviation index, x j is the actual measured value of the j-th air quality parameter evaluation index, b j is the reference value of the j-th air quality parameter evaluation index, w j is the weight of the j-th air quality parameter evaluation index, m is the number of air quality parameter evaluation indexes, j is the index of the air quality parameter evaluation index, j = 1, 2, 3, corresponding to sulfur dioxide concentration, nitrogen oxide concentration and inhalable particulate matter concentration respectively. The value range of R is between 0 and 1. When R approaches 0, it means that the air quality parameter is close to the reference value and the air quality condition is good. When R approaches 1, it means that the air quality parameter seriously deviates from the reference value and the air quality condition is poor; The calculation formula of the environmental pressure tendency index is as follows: where E is the environmental pressure trend index, x k is the actual measured value of the k-th environmental pressure parameter evaluation index, b k is the reference value of the k-th environmental pressure parameter evaluation index, w k is the weight of the k-th environmental pressure parameter evaluation index, h is the number of environmental pressure parameter evaluation indexes, k is the index of the environmental pressure parameter evaluation index, k = 1, 2, corresponding to the pollutant emission and the temperature change rate respectively. The value range of E is between 0 and 1. When E approaches 0, it means that the environmental pressure parameter is close to the reference value and the environmental condition is good. When E approaches 1, it means that the environmental pressure parameter seriously deviates from the reference value and the environmental condition is poor.

5. The method for evaluating and warning the ecological quality of the bay area based on machine learning according to claim 4, characterized in that: The calculation formula of the anomaly identification index is as follows: where T is the anomaly recognition index, and X t is the actual measured value of the t-th real-time ecological quality parameter, w t is the weight of the t-th parameter, N is the number of ecological quality parameters, α is the adjustment factor, β is the adjustment factor, rand(0,1) represents a number randomly generated within the interval [0,1], and if T ≤ Y, it is determined that an anomaly exists.

6. The method for evaluating and warning the ecological quality of the bay area based on machine learning according to claim 5, characterized in that: In S4, the process of dynamic evaluation of the ecological quality in the bay area is as follows: S41. Input the parameter data of water quality, air quality, and environmental pressure in the target area into the trained abnormal ecological quality identification model for anomaly detection in the target area. The model outputs the probability of normal or abnormal, and according to the set anomaly threshold, the identification result of the abnormal state is obtained; S42. Calculate the water quality deviation index, air quality deviation index, and environmental pressure tendency index of the target area, analyze the change trend of each parameter over time, and assign corresponding weights according to the importance of each parameter in the ecosystem; S43. Based on the weights assigned to each parameter, combined with the calculation results of the water quality deviation index, air quality deviation index, and environmental pressure tendency index in the target area, comprehensively calculate the ecological quality evaluation coefficient, and analyze the ecological quality status of the target bay area according to the size of the comprehensive ecological quality evaluation coefficient.

7. A method for evaluating and warning the ecological quality of a bay area based on machine learning according to claim 6, characterized in that: The calculation formula of the ecological quality evaluation coefficient is as follows: In the formula, SC is the ecological quality assessment coefficient, W is the water quality deviation index, R is the air quality deviation index, E is the environmental pressure trend index, and ω W is the weight of the water quality deviation index, ω R is the weight of the air quality deviation index, ω E is the weight of the environmental pressure trend index. It should be noted that when SC approaches 1, it indicates that the water quality, air quality, and environmental pressure parameters are all close to the reference values, and the ecological quality status is good.

8. The method for evaluating and warning the ecological quality of the bay area based on machine learning according to claim 7, characterized in that: In S5, the process of early warning analysis is as follows: S51. According to the requirements of the ecological quality in the bay area and the historical ecological quality data of the bay area, classify the ecological quality of the bay area into excellent ecological quality level, good ecological quality level, and poor ecological quality level; S52. Combine the calculation results of the ecological quality evaluation coefficient, match them with each ecological quality level, and set corresponding ecological quality thresholds for each ecological quality level; S53. Determine the current ecological quality level based on the value of the ecological quality assessment coefficient, and mark it with different status colors. Mark the excellent ecological quality level with a green status color, the good ecological quality level with a yellow status color, and the poor ecological quality level with a red status color; S54. When in the good ecological quality level, issue a warning notice and recommend taking preventive measures. When in the poor ecological quality level, issue an emergency warning notice, immediately activate the emergency response mechanism, and analyze the warning reasons, including water quality deterioration, increased air pollution, and increased environmental pressure; S55. According to the warning analysis results, formulate a targeted treatment plan and implement corresponding treatment measures. At the same time, supervise the implementation of the treatment measures, regularly evaluate the treatment effect, and adjust the treatment plan according to the evaluation results.

9. A method for evaluating and warning the ecological quality of a bay area based on machine learning according to claim 8, characterized in that: Multiple said ecological quality levels correspond to multiple said ecological quality thresholds, wherein, said ecological quality thresholds include upper threshold values and lower threshold values; Multiple said ecological quality levels and multiple said ecological quality thresholds satisfy the following relationship: The ecological quality threshold for the high-quality ecological quality level is: SC ys ≤ SC < 1; The ecological quality threshold for the good ecological quality level is: SC ls ≤ SC < SC ys ; The ecological quality threshold for the differential ecological quality level is: 0 < SC < SC ls ; Among them, SC is the ecological quality assessment coefficient, SC ys is the lower threshold corresponding to the excellent ecological quality level and the upper threshold corresponding to the good ecological quality level, SC ls is the lower threshold corresponding to the good ecological quality level and the upper threshold corresponding to the poor ecological quality level, SC ys = 0.8, SC ls = 0.5.

Images