A system and method for assessing the value of a gulf ecosystem
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- DALIAN UNIV OF TECH
- Filing Date
- 2026-01-23
- Publication Date
- 2026-05-26
Smart Images
Figure CN121581583B_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of ecosystem service valuation technology, and specifically relates to a system and method for valuing a bay ecosystem. Background Technology
[0002] As a crucial zone for land-sea interaction, the accurate assessment of the service value of the Gulf ecosystem is essential for implementing ecological compensation and optimizing coastal zone management. Current assessment practices typically rely on comprehensive analysis of historical monitoring and statistical data. In practice, the time frame and phases of the assessment are usually predetermined based on external events or natural cycles, and then appropriate models are selected to calculate the service value for each period.
[0003] However, the evolution of the Gulf ecosystem is influenced by the complex interplay of natural fluctuations and human activities. Changes in its internal state often exhibit non-uniform temporal characteristics, with some critical periods of dynamic transition. If the pre-set assessment period fails to fully coincide with these intrinsic nodes that characterize the qualitative changes in the system, it may lead to deviations in the portrayal of the system's behavior, thereby affecting the accuracy of the final value assessment results. Summary of the Invention
[0004] This application provides a system and method for assessing the value of a bay ecosystem, which effectively solves the problem of inaccurate value assessment caused by the mismatch between the preset assessment period and the inherent nodes of qualitative change in the system in the prior art. It achieves precise matching between the assessment period and the key nodes of the evolution of the bay ecosystem, thereby improving the accuracy of the value assessment of the bay ecosystem.
[0005] To achieve the above objectives, this application adopts the following technical solution:
[0006] Firstly, this application provides a method for assessing the value of a Gulf ecosystem, including:
[0007] Obtain raw data on the Gulf ecosystem;
[0008] Based on the raw data, time periods are divided to obtain a preliminary time period division scheme;
[0009] The first time period characteristic data is extracted from the preliminary time period division scheme, and the first time period characteristic data is input into the system dynamics model for the first simulation to obtain the first process state data.
[0010] Set mutation threshold and event tolerance threshold; filter candidate mutation events based on the first process state data, mutation threshold, and event tolerance threshold, and calculate the significance score of the candidate mutation events;
[0011] The distribution dispersion index of the significance score is calculated and compared with a preset stability threshold. If the distribution dispersion index is not greater than the stability threshold, the mutation time point is identified from the first process state data; otherwise, the mutation threshold and event tolerance threshold are adjusted according to the dispersion index, and the process returns to the step of calculating the significance score.
[0012] The initial time period division scheme was adjusted based on the time point of the mutation to obtain an optimized time period division scheme;
[0013] The second time period feature data is extracted from the optimized time period division scheme, and the second time period feature data is input into the system dynamics model for a second simulation to obtain the second process state data.
[0014] The value assessment results of the Gulf ecosystem were calculated based on the second process state data.
[0015] Secondly, this application provides a system for assessing the value of a Gulf ecosystem, comprising:
[0016] Data standardization module: used to obtain raw data on the Gulf ecosystem;
[0017] Preliminary Time Period Division Module: Used to divide time periods based on raw data to obtain a preliminary time period division scheme;
[0018] Initial simulation module: used to extract the first time period feature data from the preliminary time period division scheme, input the first time period feature data into the system dynamics model for the first simulation, and obtain the first process state data;
[0019] Significance score calculation module: used to set the mutation threshold and event tolerance threshold; to filter candidate mutation events based on the first process state data, mutation threshold, and event tolerance threshold, and to calculate the significance score of the candidate mutation events;
[0020] Adjustment module: Used to calculate the distribution dispersion index of significance score, compare the distribution dispersion index with the preset stability threshold: if the distribution dispersion index is not greater than the stability threshold, then identify the mutation time point from the first process state data; otherwise, adjust the mutation threshold and event tolerance threshold according to the dispersion index, and return to the step of calculating significance score.
[0021] The scheme optimization module is used to adjust the initial time period division scheme based on the time point of the sudden change, so as to obtain an optimized time period division scheme.
[0022] Secondary simulation module: used to extract the second time period feature data from the optimized time period division scheme, input the second time period feature data into the system dynamics model for a second simulation, and obtain the second process state data;
[0023] Valuation module: Used to calculate the valuation results of the Gulf ecosystem based on the second process state data.
[0024] Thirdly, this application provides a Gulf ecosystem valuation apparatus, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program to implement the steps of the Gulf ecosystem valuation method.
[0025] Fourthly, this application provides a readable storage medium storing computer program instructions, which are read and executed by a processor to perform the steps of a Gulf ecosystem valuation method.
[0026] Fifthly, this application provides a computer program product, including a computer program or instructions that, when executed by a processor, implement the steps of a method for assessing the value of a Gulf ecosystem.
[0027] The beneficial effects of this application are:
[0028] This application adopts a method of first standardizing the original data of the bay ecosystem and initially dividing it into time periods. Then, it uses a system dynamics model to initially simulate and identify abrupt change time points to optimize the time periods. After a second simulation, it calculates the dynamic value and generates the evaluation results. This effectively solves the problem in the existing technology where the preset evaluation time period does not match the inherent nodes of the system's qualitative changes, resulting in inaccurate value evaluation. It achieves a precise match between the evaluation time period and the key nodes of the bay ecosystem's evolution, thereby improving the accuracy of the bay ecosystem's value evaluation.
[0029] Other features and advantages of this application will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures pointed out in the description and the accompanying drawings. Attached Figure Description
[0030] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0031] Figure 1 A schematic diagram of the modules of a bay ecosystem valuation system according to this application is shown;
[0032] Figure 2 A flowchart illustrating the preliminary time-segmentation scheme obtained in this application is shown;
[0033] Figure 3 A flowchart illustrating the calculation of significance scores for candidate mutation events in this application is shown.
[0034] Figure 4 A flowchart illustrating the dynamic value calculation process in this application is shown. Detailed Implementation
[0035] To address the problems raised in the background technology, this application first standardizes the original data of the bay ecosystem and preliminarily divides the time periods. Then, it uses a system dynamics model to initially simulate and identify abrupt change time points to optimize the time periods. After a second simulation, it calculates the dynamic value and generates the assessment results, thereby improving the accuracy of the bay ecosystem value assessment.
[0036] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0037] In some embodiments, such as Figure 1 As shown, this application provides a method for assessing the value of a bay ecosystem, including:
[0038] S1. Obtain raw data on the Gulf ecosystem.
[0039] S2. Map the original data into a dimensionless, comparable data format to obtain standardized indicator data. Divide the standardized indicator data into time periods according to preset rules to obtain a preliminary time period division scheme.
[0040] S3. Extract the first time period characteristic data from the preliminary time period division scheme, input the first time period characteristic data into the system dynamics model for the first simulation, and obtain the first process state data.
[0041] S4. Set the mutation threshold and event tolerance threshold; filter candidate mutation events based on the first process state data, mutation threshold, and event tolerance threshold, and calculate the significance score of the candidate mutation events.
[0042] S5. Calculate the distribution dispersion index of the significance score, and compare the distribution dispersion index with the preset stability threshold: if the distribution dispersion index is not greater than the stability threshold, identify the mutation time point from the first process state data; otherwise, adjust the mutation threshold and event tolerance threshold according to the dispersion index, and return to the step of calculating the significance score.
[0043] S6. Adjust the initial time period division scheme according to the mutation time point to obtain the optimized time period division scheme.
[0044] S7. Extract the second time period feature data from the optimized time period division scheme, input the second time period feature data into the system dynamics model for a second simulation, and obtain the second process state data.
[0045] S8. The value assessment results of the Gulf ecosystem are calculated based on the second process state data.
[0046] In some embodiments, such as Figure 2 As shown, the raw data for obtaining the Gulf ecosystem includes:
[0047] S1.1. Obtain raw data including biophysical monitoring data and environmental status monitoring data.
[0048] Biophysical monitoring data represent quantitative data describing the status of biological resources. For example, the annual catch of a specific economically important fish species reflects the potential for fisheries output, while the population density of a certain indicator shellfish in the intertidal zone serves as an indicator for assessing the health of benthic ecosystems.
[0049] Environmental status monitoring data represent data describing the physical and chemical state of the natural environment. For example, the dissolved oxygen concentration in seawater directly affects the survival of aquatic organisms; chlorophyll a concentration characterizes phytoplankton biomass and is related to the degree of eutrophication in water bodies.
[0050] All acquired data were converted into a unified timestamp format and arranged in chronological order to form a list of biophysical monitoring data and an environmental status monitoring data list with timestamps.
[0051] In some embodiments, such as Figure 2 As shown, the original data is mapped to standardized indicator data, and the standardized indicator data is divided into time periods according to preset rules to obtain a preliminary time period division scheme, including:
[0052] S2.1. Based on the preset scenario and dimension mapping rules, the biophysical monitoring data and environmental state monitoring data are mapped to standardized indicator data under the biophysical supply dimension and the environmental state regulation dimension, respectively.
[0053] The scenario and dimension mapping rules specify which standardized evaluation dimension each type of raw data should be assigned to. For example, a rule might specify that "annual fish catch" data should be mapped to the "biophysical supply dimension"; and "seawater dissolved oxygen concentration" data should be mapped to the "environmental condition regulation dimension".
[0054] For original data of the same type that are mapped to the same evaluation dimension, the Z-Score standardization method can be used to eliminate dimensional differences.
[0055] The final standardized indicator data includes standardized time series of each indicator under the "biophysical supply dimension" and standardized time series of each indicator under the "environmental state regulation dimension". For example, the standardized fishery production index series under the "biophysical supply dimension" and the standardized dissolved oxygen index series under the "environmental state regulation dimension".
[0056] S2.2. Identify key mutation points in the standardized indicator data sequence.
[0057] Specifically, a sliding time window of fixed length is set for the standardized indicator data to be analyzed. This window starts from the beginning of the time series and slides forward at fixed time steps.
[0058] For each position of the window in the sequence, calculate the variance of the data within the window. Calculate the global variance of the entire time series of this data. ,Will and Multiply by a preset threshold factor Compare the values after, if they satisfy... If the data fluctuations within the current sliding time window are deemed abnormally drastic, the time corresponding to the center point of that sliding time window is recorded as a critical abrupt change point. The threshold multiple is also considered. This represents an adjustable parameter used to control the tightness of the judgment on significant changes, such as 2.0.
[0059] After traversing the entire standardized metric data, a list containing all key mutation points is obtained.
[0060] S2.3. Match key mutation points with preset natural cycle nodes and socio-economic event nodes to obtain successfully matched nodes.
[0061] Natural cycle nodes include the time points when periodic natural phenomena occur, such as the spring equinox, autumn equinox, and the local historical average start date of the rainy season.
[0062] Socioeconomic event milestones include the time points of human activities or policy events that occur within the assessment timeframe and may have a significant impact on the Gulf ecosystem, such as the official effective date of an environmental protection regulation or the commencement date of a large-scale marine engineering project.
[0063] Set a time tolerance threshold; for example, the time tolerance threshold could be half the length of the sliding window.
[0064] For each key mutation point, determine whether there is a node in the natural cycle node or socio-economic event node whose absolute time difference with the current key mutation point is less than a preset time matching tolerance, such as half the duration of the sliding time window. If so, the key mutation point is considered to have successfully matched with the natural cycle node or socio-economic event node.
[0065] S2.4. Divide the standardized indicator data into time periods based on the successfully matched nodes to form a preliminary time period division scheme.
[0066] The start and end times of this assessment, as well as all successfully matched nodes, are sorted in chronological order. Each two adjacent time points are defined as an assessment period, thus obtaining a preliminary period division scheme.
[0067] In some embodiments, extracting first time period feature data from the preliminary time period division scheme includes:
[0068] S3.1. Extract the time periods from the initial time period division scheme, and perform time alignment on standardized indicator data that are collected at different frequencies within the same time period to obtain the indicator sequence for that time period. For example, linear interpolation can be used for alignment.
[0069] S3.2. Extract statistical features from the indicator sequences of each time period to obtain the feature data of the first time period.
[0070] Statistical characteristics include mean, standard deviation, and linear trend slope. The mean reflects the average level of the standardized indicator data within a given period; the standard deviation reflects the numerical fluctuation or dispersion of the standardized indicator data within that period; and the linear trend slope reflects the direction and average rate of change of the standardized indicator data within that period.
[0071] The first time period feature data is a two-dimensional matrix, with each row corresponding to a time period and each column corresponding to a specific statistical feature.
[0072] Using the characteristic data of the first time period as input, a pre-built system dynamics model for simulating the causal and feedback relationships among various elements in the Gulf ecosystem is driven to perform its first simulation operation. For example, the EcosystemValuation and Ecosystem Services model. After the system dynamics model runs, it outputs data describing the changes of key states within the ecosystem over time, i.e., the first process state data.
[0073] For example, the first process state data includes time series of fish resource quantity and time series of dissolved oxygen concentration in water. The time series of fish resource quantity simulates the dynamic changes in fish population biomass, and the time series of dissolved oxygen concentration in water simulates the dynamic changes in dissolved oxygen content in seawater.
[0074] In some embodiments, such as Figure 3 As shown, candidate mutation events are screened based on the first process state data, mutation threshold, and event tolerance threshold, and the significance score of the candidate mutation events is calculated, including:
[0075] S4.1. Extract at least two key state variable sequences from the first process state data.
[0076] From the first-process state data, select one or more predefined state variable sequences that best comprehensively reflect the overall dynamics and health status of the bay ecosystem as key state variable sequences. For example, extract time series of fish resources and time series of dissolved oxygen concentration in the water.
[0077] S4.2. Calculate the characteristic values of the changes in each key state variable sequence within the sliding time window.
[0078] The change characteristic value represents the degree of local drastic change in the sequence of key state variables, and the sliding window analysis method can be used to calculate the change characteristic value.
[0079] Specifically, for each window position, the maximum absolute value of the instantaneous rate of change of the state variable within the window is calculated and used as the change characteristic value of that window.
[0080] S4.3. Compare the changing characteristic value with the mutation threshold. When the changing characteristic value exceeds the mutation threshold, determine the center point of the sliding window as the initial mutation time point.
[0081] Mutation threshold Used to distinguish between normal fluctuations and drastic changes; if the change characteristic value is greater than the mutation threshold. If a state change occurs within that window, it is determined that a state change has occurred. Change threshold. The initial value can be set to a high-order statistical quantile in the set of historical change characteristic values, such as the 90th percentile.
[0082] The event tolerance threshold is used to determine whether multiple preliminary mutation time points that are close in time can be grouped into a single candidate mutation event. The initial value of the event tolerance threshold can be half the length of the sliding window.
[0083] S4.4. Cluster adjacent preliminary mutation time points with a time difference less than the event tolerance threshold to obtain candidate mutation events.
[0084] Specifically, the initial mutation time points of all key state variable sequences are sorted in chronological order, and events with time differences less than the tolerance threshold are selected. The initial mutation time points were grouped into the same candidate mutation event.
[0085] For example, if the abrupt change time points come from different key state variable sequences and satisfy Then the mutation time point and For events belonging to the same candidate mutation event, the mutation time can be the average of the mutation time points of all key state variable sequences.
[0086] S4.5. Calculate the synergy and overall strength of each candidate mutation event.
[0087] Synergy represents the proportion of key state variable sequences that mutate in a candidate mutation event, reflecting the degree of temporal synergy between state changes in different dimensions within the Gulf ecosystem. (Refer to the formula:) Where m represents the number of key state variable sequences contained in the candidate mutation event, and n represents the total number of key state variable sequences extracted from the first process state data.
[0088] The overall intensity represents the average severity of the changes in characteristic values at all initial mutation time points within a candidate mutation event, reflecting the overall magnitude of the system state change triggered by the event. (Refer to the formula:) ;in, Represents overall strength. This represents the number of initial mutation time points included in the candidate mutation event. This represents the change characteristic value corresponding to the j-th initial mutation time point.
[0089] S4.6. Multiply the degree of synergy as a weighting factor by the overall strength to obtain the significance score of the candidate mutation event.
[0090] The significance score can comprehensively reflect the importance of candidate mutation events by taking into account both dimensional coherence and the intensity of change. See the formula below: ;in, The significance score represents the score.
[0091] In some embodiments, calculating the distribution dispersion index of the significance score in S5 includes: obtaining a set of significance scores of all candidate mutation events in the current loop, and calculating the distribution dispersion index of the set. The standard deviation of this set can be used as an index of distribution dispersion. The larger the value, the more dispersed the distribution of the significance score, meaning the worse the consistency of the identification results.
[0092] Stability threshold To assess the consistency of the identification results at the mutation time point, the stability threshold can be set as a low statistical quantile of the set of saliency score dispersions generated by successful identification processes in similar historical projects, such as the 10th quantile.
[0093] Otherwise, it indicates that the importance scores of the currently identified candidate events fluctuate too much, making the results unreliable. The current dispersion index needs to be considered. With stability threshold To mitigate the deviation, adjust the mutation threshold θ and the event tolerance threshold. ,For example: , ;in, , These represent the adjusted mutation threshold and event tolerance threshold, respectively. , These represent the mutation threshold and event tolerance threshold before adjustment, respectively. , This represents the preset adjustment coefficient, used to control the adjustment range; for example, it can be 0.1.
[0094] If the comparison result is the dispersion index Not greater than the stability threshold If the score is positive, it indicates that the recognition result of the current loop meets the requirements. Candidate mutation events with a significance score greater than the preset significance threshold are identified as target mutation events, and the time point of the target mutation event is identified as the mutation time point.
[0095] A significance threshold is used to ensure that the identified mutation time points are highly correlated with significant changes in ecosystem service value. The significance scores of all candidate mutation events can be calculated to form a historical significance score sequence. A high statistical quantile in this historical significance score sequence is used as the significance threshold, for example, the 90th percentile.
[0096] For example, the mutation threshold θ and the event tolerance threshold The initial values were 2.0 and 12 days, respectively, and the stability threshold was... If the value is 0.5, and four candidate mutation events are obtained. , , , The significance scores were 0.9, 1.5, 2.8, and 1.7, respectively. The set distribution dispersion index composed of these significance scores... , Adjusted mutation threshold θ and event tolerance threshold Three candidate mutation events were obtained from time intervals of 2.2 and 11 days, respectively. , , The significance scores were 1.6, 2.7, and 1.8, respectively. The set distribution dispersion index composed of these significance scores... , The results showed that the consistency requirement was met, and the significance scores of the candidate mutation events were optimized from discrete {0.9,1.5,1.7,2.8} to more concentrated {1.6,1.8,2.7}, thereby identifying more reliable mutation events.
[0097] In some embodiments, the initial time period division scheme is adjusted according to the mutation time point to obtain an optimized time period division scheme, including:
[0098] S6.1 Calculate the time distance between the mutation time point of each target mutation event and the existing segmentation point in the preliminary time period division scheme, take the minimum value as the minimum time distance, and calculate the adaptive tolerance threshold of the target mutation event based on the significance score.
[0099] Adaptive tolerance threshold reference formula: ,in, This represents a preset constant, representing a baseline tolerance threshold; for example, it can be taken as... sky.
[0100] S6.2. If the minimum time distance between the mutation time point of the target mutation event and any existing segmentation point is greater than the adaptive tolerance threshold, then the mutation time point is determined as a new segmentation point, which increases the possibility of important target mutation events being identified as segmentation points.
[0101] S6.3. Add new dividing points to the initial time period division scheme to obtain an optimized time period division scheme.
[0102] In the optimized time period division scheme, a new evaluation time period is defined between every two adjacent dividing points.
[0103] The second time period feature data is extracted from the optimized time period division scheme, and then input into the system dynamics model for a second simulation to simulate the internal dynamic changes of the ecosystem within the time range defined by the optimized time period division scheme, thus obtaining the second process state data.
[0104] The content and structure of the second process state data are the same as those of the first process state data, containing the same state variables, such as the time series of fish resources and the time series of dissolved oxygen concentration in the water. However, the second simulation is based on a time period division that is more consistent with the dynamics of the bay ecosystem. Therefore, the second process state data can more accurately reflect the typical behavior and state of the ecosystem in each optimization period.
[0105] In some embodiments, the valuation result of the Gulf ecosystem is calculated based on the second process state data, including:
[0106] S8.1. Input the second process state data into the preset value mapping function library for calculation to obtain the basic value data of each dimension; obtain the time series data of the external driving factors, and calculate the time adjustment factors of each dimension based on the time series data of the external driving factors.
[0107] The value mapping function library is a predefined set of mathematical functions, each of which maps a specific ecological state quantity to an economic value. The value mapping function library includes value mapping functions corresponding to the biophysical supply dimension and value mapping functions corresponding to the environmental state regulation dimension.
[0108] For example, the time series of fish resource quantities in the second process state data. Using this as input, the fishery supply value sequence from the basic value data is obtained. : ;in, The benchmark market price representing a unit weight of fish.
[0109] Time series of dissolved oxygen concentration in water body from the second process state data As input, it is processed through a function that reflects the relationship between dissolved oxygen concentration and purification service volume. The water purification value sequence in the basic value data was calculated. : , ;in, This represents the average marginal cost required to increase the dissolved oxygen concentration per unit volume of water by one unit through artificial means. This represents the water quality benchmark concentration; for example, the dissolved oxygen standard for Class III water is... It is acceptable .
[0110] Time-series data of external drivers represent socioeconomic variables that are not related to Gulf ecosystem processes but affect the value of their services. Examples include seafood market price indices that affect fisheries value and wastewater treatment cost indices that affect environmental governance value.
[0111] The time adjustment factor represents the real-time scaling factor used to linearly map the time-series data of external driving factors to dynamically scale the underlying value data.
[0112] S8.2. Combine the basic value data with the time adjustment factor to calculate the dynamic value data.
[0113] S8.3. Dynamic value data includes value time series of each dimension. For each time point, the dynamic value data of each dimension at the same time point are summed to obtain the total value time series data.
[0114] S8.4. Generate a value evolution curve based on total value time series data.
[0115] By plotting time on the horizontal axis and total value time series data on the vertical axis, a value evolution curve is obtained, which can show the changing trend of the total service value of the Gulf ecosystem over time.
[0116] In some embodiments, such as Figure 4 As shown, by combining the basic value data with the time adjustment factor, dynamic value data is obtained, including:
[0117] S8.2.1. Configure a time adjustment function for each dimension.
[0118] For example, linear functions: ;in, Represents the time adjustment factor. Time series data representing external driving factors, and The scaling factor and offset are determined based on the baseline conditions and the target adjustment range.
[0119] parameter and The setting must satisfy the requirement that, within the set baseline period, the time adjustment factor... The value is equal to or close to 1, indicating that the socio-economic conditions during that period are at the baseline state, without amplifying or discounting the basic value.
[0120] Time series data of external driving factors in historical data can be used The fluctuation range and the preset target for the value adjustment are directly calculated.
[0121] Specifically, calculating time series data of external driving factors Maximum value within a historical period and minimum value The objective is set as follows: when the time series data of external driving factors... From historical average to maximum value or minimum value Time adjustment factor The corresponding change range of 1 is ,but .
[0122] A baseline period is selected, and the time series data of the external driving factors corresponding to this baseline period are: , The historical average can be used, and the baseline conditions must be met during this baseline period. Substituting into a linear function, we get Calculations yielded .
[0123] For example, using historical data from 2013 to 2022, the price index was calculated. maximum value minimum value The average value is taken during the baseline period. When the price index reaches its historical high or low, the time adjustment factor... Variation relative to 1 The calculated result , .
[0124] S8.2.2. Input the time series data of the external driving factor into the time adjustment function to calculate the time adjustment factor sequence that changes with time.
[0125] For example, when hour, , is the baseline value; when hour, The value was increased by 15% compared to the baseline; when hour, This represents a 15% reduction compared to the baseline value.
[0126] S8.2.3. At each point in time, the basic value data is multiplied by the corresponding time adjustment factor to obtain the time-varying dynamic value data.
[0127] In some embodiments, this application provides a system for assessing the value of a bay ecosystem, comprising:
[0128] Data standardization module: used to obtain raw data on the Gulf ecosystem;
[0129] Preliminary Time Period Division Module: Used to divide time periods based on raw data to obtain a preliminary time period division scheme;
[0130] Initial simulation module: used to extract the first time period feature data from the preliminary time period division scheme, input the first time period feature data into the system dynamics model for the first simulation, and obtain the first process state data;
[0131] Significance score calculation module: used to set the mutation threshold and event tolerance threshold; to filter candidate mutation events based on the first process state data, mutation threshold, and event tolerance threshold, and to calculate the significance score of the candidate mutation events;
[0132] Adjustment module: Used to calculate the distribution dispersion index of significance score, compare the distribution dispersion index with the preset stability threshold: if the distribution dispersion index is not greater than the stability threshold, then identify the mutation time point from the first process state data; otherwise, adjust the mutation threshold and event tolerance threshold according to the dispersion index, and return to the step of calculating significance score.
[0133] The scheme optimization module is used to adjust the initial time period division scheme based on the time point of the sudden change, so as to obtain an optimized time period division scheme.
[0134] Secondary simulation module: used to extract the second time period feature data from the optimized time period division scheme, input the second time period feature data into the system dynamics model for a second simulation, and obtain the second process state data;
[0135] Valuation module: Used to calculate the valuation results of the Gulf ecosystem based on the second process state data.
[0136] In some embodiments, this application provides a Gulf ecosystem valuation apparatus, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program to implement the steps of the Gulf ecosystem valuation method.
[0137] In some embodiments, this application provides a readable storage medium storing computer program instructions that are read and executed by a processor to perform steps of a Gulf ecosystem valuation method.
[0138] In some embodiments, this application provides a computer program product, including a computer program or instructions that, when executed by a processor, implement the steps of a Gulf ecosystem valuation method.
[0139] It should be noted that, in this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0140] Any references to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory.
[0141] Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.
Claims
1. A method for assessing the value of a bay ecosystem, characterized in that, include: Obtain raw data including biophysical monitoring data and environmental status monitoring data. The biophysical monitoring data includes the annual catch of specific economic fish species, and the environmental status monitoring data includes the dissolved oxygen concentration of seawater. According to preset scenario and dimension mapping rules, the biophysical monitoring data and environmental state monitoring data are mapped to standardized indicator data under the biophysical supply dimension and environmental state regulation dimension, respectively; key mutation points in the standardized indicator data sequence are identified; the key mutation points are matched with preset natural cycle nodes and socio-economic event nodes to obtain successfully matched nodes; wherein, if the absolute value of the time difference between the key mutation point and the natural cycle node or socio-economic event node is less than a preset time matching tolerance, the match is successful; the standardized indicator data is divided into time periods according to the successfully matched nodes to form the preliminary time period division scheme. The time periods are extracted from the preliminary time period division scheme, and the standardized index data with different collection frequencies in the same time period are time-aligned to obtain the index sequence of that time period; statistical features are extracted from the index sequence of each time period to obtain the first time period feature data, and the first time period feature data is input into the system dynamics model for the first simulation to obtain the first process state data; Setting a mutation threshold and an event tolerance threshold; filtering candidate mutation events based on the first process state data, the mutation threshold, and the event tolerance threshold, including: extracting at least two key state variable sequences from the first process state data; calculating the change feature value of each key state variable sequence within a sliding time window; comparing the change feature value with the mutation threshold, and when the change feature value exceeds the mutation threshold, determining the center point of the sliding window as the initial mutation time point; clustering adjacent initial mutation time points with a time difference less than the event tolerance threshold to obtain candidate mutation events; and calculating the significance score of the candidate mutation events. Calculate the distribution dispersion index of the significance score, and compare the distribution dispersion index with a preset stability threshold: if the distribution dispersion index is not greater than the stability threshold, then identify the mutation time point from the first process state data; otherwise, adjust the mutation threshold and event tolerance threshold according to the dispersion index, and return to the step of calculating the significance score. The initial time period division scheme is adjusted based on the abrupt change time point to obtain an optimized time period division scheme; The second time period feature data is extracted from the optimized time period division scheme, and the second time period feature data is input into the system dynamics model for a second simulation to obtain the second process state data. The value assessment results of the Gulf ecosystem were calculated based on the second process state data.
2. The method according to claim 1, characterized in that, Candidate mutation events are screened based on the first process state data, mutation threshold, and event tolerance threshold, and significance scores of the candidate mutation events are calculated, including: Calculate the synergy and overall strength of each of the candidate mutation events; The significance score of the candidate mutation event is obtained by multiplying the degree of synergy as a weighting factor by the overall strength.
3. The method according to claim 2, characterized in that, Identifying abrupt change points from the first process state data includes: Candidate mutation events with a significance score greater than a preset significance threshold are identified as target mutation events, and the time point of the target mutation event is identified as the mutation time point.
4. The method according to claim 1, characterized in that, The initial time period division scheme is adjusted based on the abrupt change time point to obtain an optimized time period division scheme, including: Calculate the time distance between the mutation time point of each target mutation event and the existing segmentation point in the preliminary time period division scheme, take the minimum value as the minimum time distance, and calculate the adaptive tolerance threshold of the target mutation event based on the significance score. If the minimum time distance between the mutation time point of the target mutation event and any existing segmentation point is greater than the adaptive tolerance threshold, then the mutation time point is determined as a new segmentation point. By adding new segmentation points to the initial time period division scheme, an optimized time period division scheme is obtained.
5. The method according to claim 1, characterized in that, The valuation results of the Gulf ecosystem were calculated based on the second process state data, including: The second process state data is input into a preset value mapping function library for calculation to obtain the basic value data of each dimension; the time series data of the external driving factors are obtained, and the time adjustment factors of each dimension are calculated based on the time series data of the external driving factors. The dynamic value data is obtained by combining the basic value data with the time adjustment factor. The total value time series data is obtained by summing the dynamic value data of each dimension at the same point in time. A value evolution curve is generated based on the total value time series data.
6. The method according to claim 5, characterized in that, The dynamic value data is obtained by combining the basic value data with the time adjustment factor, including: Configure a time adjustment function for each dimension; The time series data of the external driving factor is input into the time adjustment function to calculate the time adjustment factor sequence that changes with time. At each point in time, the basic value data is multiplied by the corresponding time adjustment factor to obtain the time-varying dynamic value data.
7. A system for assessing the value of a bay ecosystem, characterized in that, include: Data standardization module: used to acquire raw data including biophysical monitoring data and environmental status monitoring data. Biophysical monitoring data includes the annual catch of specific economic fish species, and environmental status monitoring data includes the dissolved oxygen concentration of seawater. The preliminary time period segmentation module is used to map the biophysical monitoring data and environmental state monitoring data into standardized indicator data under the biophysical supply dimension and environmental state regulation dimension, respectively, according to preset scenario and dimension mapping rules; identify key mutation points in the standardized indicator data sequence; match the key mutation points with preset natural cycle nodes and socio-economic event nodes to obtain successfully matched nodes; wherein, if the absolute value of the time difference between the key mutation point and the natural cycle node or socio-economic event node is less than a preset time matching tolerance, the match is successful; and divide the standardized indicator data into time periods according to the successfully matched nodes to form the preliminary time period segmentation scheme. Initial simulation module: used to extract the time periods from the initial time period division scheme, time-align standardized indicator data with different collection frequencies in the same time period to obtain the indicator sequence of that time period; extract statistical features from the indicator sequences of each time period to obtain the first time period feature data, and input the first time period feature data into the system dynamics model for the first simulation to obtain the first process state data; The significance score calculation module is used to set the mutation threshold and event tolerance threshold; and to filter candidate mutation events based on the first process state data, the mutation threshold, and the event tolerance threshold, including: extracting at least two key state variable sequences from the first process state data; calculating the change feature value of each key state variable sequence within a sliding time window; comparing the change feature value with the mutation threshold, and when the change feature value exceeds the mutation threshold, determining the center point of the sliding window as the initial mutation time point; clustering adjacent initial mutation time points with a time difference less than the event tolerance threshold to obtain candidate mutation events; and calculating the significance score of the candidate mutation events. Adjustment module: used to calculate the distribution dispersion index of the significance score, compare the distribution dispersion index with a preset stability threshold: if the distribution dispersion index is not greater than the stability threshold, then identify the mutation time point from the first process state data; otherwise, adjust the mutation threshold and event tolerance threshold according to the dispersion index, and return to the step of calculating the significance score; Scheme optimization module: used to adjust the initial time period division scheme according to the abrupt change time point to obtain an optimized time period division scheme; Secondary simulation module: used to extract second time period feature data from the optimized time period division scheme, input the second time period feature data into the system dynamics model for a second simulation, and obtain second process state data; Valuation module: used to calculate the valuation results of the Gulf ecosystem based on the second process status data.