Small watershed driving-obstacle double-diagnosis key index identification method and system

Abstract

The invention provides a small watershed driving-obstacle double-diagnosis key index identification method and system, and belongs to the technical field of hydraulic engineering based on computer data processing. The method comprises the following steps: firstly, selecting a target small watershed, analyzing water and sediment-ecological-economic system indexes of the small watershed, and constructing a small watershed basic data set; secondly, a key driving factor is obtained through grey correlation analysis; then, acquiring key obstacle factors by using an obstacle degree model; and finally, integrating the driving factor and the obstacle factor, determining a key influence factor of the target small watershed, and visually outputting a diagnosis result. The key index identification method based on driving-obstacle double diagnosis has the advantages of being comprehensive in diagnosis, high in applicability and high in decision support, and can provide scientific basis for small watershed water resource management, ecological protection and economic sustainable development.

Description

Technical Field

[0001] This invention belongs to the field of water conservancy engineering technology based on computer data processing, and particularly relates to a method and system for identifying key indicators of dual diagnosis of drive and obstacle in small watersheds. Background Technology

[0002] As the basic unit of the natural hydrological cycle, small watersheds bear important functions of water conservation, material transport, and ecosystem services, and are key supports for regional water security and ecological balance. However, affected by rapid industrialization, urbanization, agricultural intensification, and climate change, the water and soil resource balance, ecological structure, and coordination of economic and social development in small watershed systems face severe challenges, manifesting as a series of problems such as water and soil resource imbalance, water pollution, and ecological degradation, which continuously increases the complexity and urgency of small watershed management.

[0003] Small watershed systems encompass multiple aspects, including water and sediment resources, ecological environment, and socio-economic factors. Their harmonious development is the result of the synergistic effects of multiple elements. The healthy development of small watersheds is subject to interference and constraints from numerous factors. These factors include both positive driving forces that promote mutual and coordinated development among system elements, and negative forces that hinder harmonious development. The dynamic interplay between these two factors determines the direction and rate of system evolution. Current research, in identifying key influencing factors, mostly considers only a single effect, neglecting the interactions between multidimensional elements. This makes it difficult to fully reveal the evolutionary mechanisms of small watershed systems, thus affecting the scientific validity and effectiveness of governance measures.

[0004] Therefore, how to adopt effective technical means to accurately identify the key influencing factors of small watershed systems is a critical technical problem that urgently needs to be solved.

[0005] The information disclosed in this background section is only intended to enhance the understanding of the background technology of this application and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this invention provides a method and system for identifying key indicators for dual diagnosis of driving forces and obstacles in small watersheds. By integrating grey relational analysis and obstacle degree models, it achieves the collaborative identification of key driving forces and obstacle factors in small watershed systems. Combined with visualization analysis and intelligent decision-making modules, it provides highly operable technical support for small watershed governance.

[0007] The present invention proposes a method for identifying key indicators for dual diagnosis of drive and obstacle in small watersheds, comprising the following steps: S1. Data Acquisition: Select a target small watershed, analyze the water-sediment-ecology-economic system indicators of the small watershed, and construct a basic dataset for the small watershed. The dataset includes multi-source heterogeneous data on water and sediment resources, ecological environment, and socio-economic factors. S2. Key driving factors acquisition: Key driving factors are acquired using grey relational analysis. S3. Key Obstacle Factor Acquisition: Key obstacle factors are acquired using an obstacle degree model; S4. Construction of a dual-diagnostic model: Integrating driving factors and obstacle factors to identify key influencing factors in the target watershed; S5. Results Visualization and Evaluation: Visualize the diagnostic results to achieve an intuitive evaluation of the shortcomings and advantages of different small watersheds.

[0008] Preferably, the target small watershed is a typical small watershed in the Sanmenxia Reservoir area, including Hubin District, Shanzhou District and Lingbao City of Sanmenxia City.

[0009] Preferably, the small watershed water-sediment-ecology-economy system refers to the water and sediment resource subsystem, ecological environment subsystem, and socio-economic subsystem of the small watershed.

[0010] Preferably, the grey relational analysis calculation method is as follows: Standardize the indicators for each sequence: (1) Obtain the standardized matrix: (2) Calculate the correlation coefficient: (3) Calculate the correlation: (4) In the formula, These are the standardized values. These are the original values ​​of each sequence indicator. This represents the mean of the original values ​​of each sequence indicator. As a reference sequence, For comparison sequences, m is the number of indicators and n is the length of the time series. The resolution coefficient is set to 0.5. ; . The correlation coefficient, This represents the grey relational degree.

[0011] Preferably, the obstacle degree model calculation method is as follows: The indicators of each sequence were standardized using the same method as in grey relational analysis. Indicator Deviation: (5) The degree of obstacle to the system by the j-th indicator: (6) (7) System obstacle degree of each subsystem: (8) In the formula, yy ij As an indicator j The standardization results YY ij As an indicator j The degree of deviation SP j As an indicator j Obstacles U t For subsystem t The degree of system obstacle.

[0012] Preferably, the integration of driving factors and obstacle factors refers to taking the top 50% of the indicators obtained from grey relational analysis as key driving factors and the top 50% of the indicators obtained from the obstacle degree model as key obstacle factors, and merging these two factors to form the set of key influencing factors of the system.

[0013] Preferably, the indicators in the set of key influencing factors are screened by a threshold method to obtain the final key influencing factors. The evaluation criteria for the threshold method are a gray relational degree value greater than 0.90 and a barrier degree value greater than 10%.

[0014] This invention also provides a key indicator identification system for dual diagnosis of drive and obstacle in small watersheds, used to perform the above method, which includes the following modules: The data acquisition module is used to acquire and update multi-source heterogeneous data from small watersheds.

[0015] The data processing module is used to clean, imputate, and standardize the data.

[0016] The model calculation module is used to construct a driver-obstacle dual diagnostic model and calculate the correlation and obstacle degree of each indicator.

[0017] The indicator identification module is used to identify key driving factors and obstacle factors based on the model output.

[0018] The visualization analysis module is used to graphically display and compare diagnostic results.

[0019] The decision support module is used to output targeted governance suggestions or development path solutions.

[0020] Each module can be implemented using computer programs and their storage media.

[0021] Preferably, the decision support module is connected to the artificial intelligence model service platform through a programming interface.

[0022] Compared with the prior art, the present invention has the following beneficial effects: (1) The dual diagnostic identification method that combines grey relational analysis with obstacle degree model can not only reveal the positive driving effect of each indicator on the watershed system, but also identify the key obstacle factors that restrict the development of the system, thus forming a comprehensive diagnosis from the dual perspective of driving and obstacle, avoiding the one-sidedness of conclusions caused by a single method. (2) The grey relational degree and obstacle degree model is adopted, which requires less data and is particularly suitable for small watersheds with incomplete monitoring data and lack of long series of observation data. It can still achieve effective diagnosis, especially in areas with scarce data such as the Loess Plateau. (3) The key driving factors and obstacle factors calculated by the model can be transformed into management strategies and control schemes, achieving close integration with water conservancy engineering practices and providing a scientific basis for regional water resources security, ecological environment protection and sustainable economic development. Attached Figure Description

[0023] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the following description is only one embodiment of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 A flowchart for identifying key indicators in a dual diagnostic method for small watershed drive-obstacles.

[0025] Figure 2 This is a diagram of the key driving factors for the target watershed in this invention.

[0026] Figure 3 This is a key obstacle factor diagram of the target watershed in this invention.

[0027] Figure 4 This is a flowchart of a key indicator identification system for dual diagnosis of small watershed drive and obstacle. Detailed Implementation

[0028] This invention proposes a method and system for identifying key indicators for dual diagnosis of drive and obstacle in small watersheds. To facilitate understanding of this invention by those skilled in the art, the specific embodiments of this invention are described below with reference to the accompanying drawings.

[0029] A method for identifying key indicators for dual diagnosis of drive and obstacle in small watersheds, such as Figure 1As shown, firstly, a target small watershed is selected, and the water-sediment-ecological-economic system indicators of the small watershed are analyzed to construct a basic dataset for the small watershed. This dataset includes multi-source heterogeneous data on water and sediment resources, ecological environment, and socio-economic factors. Secondly, grey relational analysis is used to obtain key driving factors; then, a barrier degree model is used to obtain key barrier factors. Finally, the driving and barrier factors are integrated to determine the key influencing factors of the target small watershed, and the diagnostic results are visualized and output.

[0030] Specifically, in this embodiment, the target small watershed is a typical small watershed in the Sanmenxia Reservoir area, which administratively includes three cities: Hubin District, Shanzhou District, and Lingbao City. This embodiment will be described using Shanzhou District as an example.

[0031] 1. Data Acquisition (1) Components of the water-sediment-ecology-economic system in a small watershed From a systems theory perspective, the target small watershed can be regarded as an open and complex mega-system, including water and sediment resource subsystems, ecological environment subsystems, and socio-economic subsystems.

[0032] Taking into account data availability and correlations among indicators, the following indicators were selected to construct a water-sediment-ecology-economy system indicator system. The water-sediment resources subsystem indicators include seven indicators: annual runoff, sediment concentration, water supply, proportion of residential water consumption, water consumption per 10,000 yuan of GDP, water production modulus, and per capita water consumption. The ecological environment subsystem indicators include six indicators: comprehensive utilization rate of solid waste, wastewater discharge per 10,000 yuan of GDP, energy consumption per unit of GDP, wastewater treatment capacity, waste gas treatment capacity, and forest area. The socio-economic subsystem indicators include eight indicators: GDP, local fiscal revenue, population size, proportion of tertiary industry in GDP, planting area, and grain output.

[0033] (2) Data sources for water-sediment-ecology-economic system indicators in small watersheds The data for the water and sediment resources subsystem of small watersheds mainly come from the "Sanmenxia City Water Resources Bulletin" (2013-2022); the data for the ecological environment subsystem and socio-economic subsystem come from the "Sanmenxia City Statistical Yearbook", "Sanmenxia City National Economic and Social Development Bulletin", and "Sanmenxia City Ecological Environment Quality Bulletin"; for some missing data, interpolation was used to fill in the missing data.

[0034] 2. Use grey relational analysis to identify key driving factors. The grey relational model, through dimensionless processing of sequence data and calculation of correlation degree, can effectively reveal the dynamic correlation between variables in nonlinear and non-stationary systems. This method has no special requirements for data distribution, overcoming the limitations of methods such as correlation analysis that have high data requirements, and has unique advantages in the analysis of complex systems.

[0035] The calculation method for grey relational analysis is as follows: Standardize the indicators for each sequence: (1) Obtain the standardized matrix: (2) Calculate the correlation coefficient: (3) Calculate the correlation: (4) In the formula, These are the standardized values. These are the original values ​​of each sequence indicator. This represents the mean of the original values ​​of each sequence indicator. As a reference sequence, For comparison sequences, m is the number of indicators and n is the length of the time series. The resolution coefficient is set to 0.5. ; . The correlation coefficient, This represents the grey relational degree.

[0036] Table 1 presents the results of key driving factors obtained using grey relational analysis. The table shows that the top 50% of the indicators include 10 indicators: grain output, waste gas treatment capacity, the proportion of the tertiary industry in GDP, forest area, planting area, the proportion of the secondary industry in GDP, local fiscal revenue, population size, per capita water consumption, and GDP. These indicators were identified as the key driving factors for the target small watershed.

[0037] Table 1. Results of Grey Relational Analysis

[0038] 3. Use obstacle degree models to obtain key obstacle factors. The obstacle degree model is formed on the basis of the comprehensive evaluation model, and it can determine the degree of obstruction of the evaluation object by the influencing factors.

[0039] The obstacle degree model calculation method is as follows: The indicators of each sequence were standardized using the same method as in grey relational analysis. Indicator Deviation: (5) The degree of obstacle to the system by the j-th indicator: (6) (7) System obstacle degree at each subsystem layer: (8) In the formula, yyij As an indicator j The standardization results YY ij As an indicator j The degree of deviation SP j As an indicator j Obstacles U t For subsystem t The degree of system obstacle.

[0040] Table 2 presents the results of obtaining key obstacle factors using the obstacle degree model. The table shows that the top 50% of the indicators include 10 indicators such as wastewater treatment facility capacity, water production modulus, water supply, GDP, annual runoff, comprehensive utilization rate of solid waste, the proportion of the tertiary industry in GDP, energy consumption per unit of GDP, waste gas treatment facility capacity, and local fiscal revenue. These indicators were identified as key obstacle factors for the target small watershed.

[0041] Table 2 Obstacles model calculation results

[0042] 4. Construction of a dual-diagnostic model The top 50% of indicators obtained from grey relational analysis were taken as key driving factors, and the top 50% of indicators obtained from the obstacle degree model were taken as key obstacle factors. Table 3 shows the union of these two factors, which together constitutes 16 factors, forming the set of key influencing factors for the water-sediment-ecology-economic system of the target small watershed. Among them, indicators with positive attributes indicate that an increase in the indicator is beneficial to system development, focusing on revealing the driving mechanism for improving the coordinated development of the system; indicators with negative attributes indicate that an increase in the indicator is detrimental to system development, focusing on the bottleneck problems restricting the coordinated development of the system.

[0043] In practical applications, a relatively large number of key influencing factors can affect the focus of decision-making. It is necessary to further screen out the absolutely key influencing factors to ensure that the selected indicators have a significant impact while excluding the influence of weak factors, so as to avoid wasting resources on non-critical issues and to ensure that the selected indicators can reflect the actual differences in needs. The threshold method is used to process the above results a second time, that is, to select indicators with a gray relational degree value greater than 0.90 and a barrier degree value greater than 10% as the final key influencing factors, as shown in Table 4.

[0044] Table 3 Key Influencing Factors of the Target Small Watershed

[0045] Table 4 Ultimate Key Influencing Factors of the Target Small Watershed

[0046] 5. Results Visualization and Evaluation like Figure 2 As shown, the key driving factors for the target small watershed include grain output, waste gas treatment capacity, the proportion of the tertiary industry in GDP, forest area, planting area, the proportion of the secondary industry in GDP, local fiscal revenue, population size, per capita water consumption, and GDP.

[0047] like Figure 3 As shown, the key obstacles to the target small watershed include wastewater treatment capacity, water production modulus, water supply, GDP, annual runoff, comprehensive utilization rate of solid waste, the proportion of the tertiary industry in GDP, energy consumption per unit of GDP, waste gas treatment capacity, and local fiscal revenue.

[0048] Ultimately, the key influencing factors are water supply, water production modulus, wastewater treatment capacity, waste gas treatment capacity, and grain yield.

[0049] like Figure 4 As shown, this embodiment also provides a key indicator identification system for dual diagnosis of drive and obstacle in small watersheds that can implement the above method, including: The data acquisition module is used to acquire and update multi-source heterogeneous data from small watersheds.

[0050] The data processing module is used to clean, imputate, and standardize the data.

[0051] The model calculation module is used to construct a driver-obstacle dual diagnostic model and calculate the correlation and obstacle degree of each indicator.

[0052] The indicator identification module is used to identify key driving factors and obstacle factors based on the model output.

[0053] The visualization analysis module is used to graphically display and compare diagnostic results.

[0054] The decision support module is used to output targeted governance suggestions or development path solutions.

[0055] Each module can be implemented using computer programs and their storage media.

[0056] The decision support module is connected to the artificial intelligence model service platform via a programming interface.

[0057] The embodiments of the present invention described above do not constitute a limitation on the scope of protection of the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A method for identifying key indicators of catchment-driven-barrier dual diagnosis, characterized in that, Comprise the following steps: S1, data acquisition: select the target small watershed, analyze the small watershed water and sediment-ecological-economic system index, build small watershed basic data set, the data set includes water and sediment resources, ecological environment and social economy multi-source heterogeneous data; S2, key driving factor acquisition: using grey correlation analysis to obtain key driving factor; S3, key obstacle factor acquisition: using obstacle degree model to obtain key obstacle factor; S4, double diagnosis model construction: integrate driving factor and obstacle factor, determine the key influence factor of target small watershed; S5, result visualization and evaluation: the diagnosis result is visualized and displayed, and the intuitive evaluation of the development short board and advantage of different small watersheds is realized.

2. The method according to claim 1, wherein the method is characterized by: The target small watershed is a typical small watershed in Sanmenxia Reservoir area, including Hubin District, Shanzhou District and Lingbao City of Sanmenxia City.

3. The method according to claim 1, wherein the method is characterized by: The small watershed water and sediment-ecological-economic system refers to the water and sediment resource subsystem, ecological environment subsystem and social economy subsystem of small watershed.

4. The method according to claim 1, wherein the method is characterized by: The grey correlation analysis calculation method is, Standardization of each sequence index: ; The normalized matrix is obtained: ; Computing the correlation coefficient: ; Computing the correlation: ; In the formula, is the standardized value, is the original value of each sequence index, is the mean of the original value of each sequence index. is the reference sequence, is the comparison sequence, m is the number of indexes, and n is the length of the time sequence. is the resolution coefficient, which is 0.5; ; . is the correlation coefficient, is the grey correlation degree.

5. The method according to claim 1, wherein the method is characterized by: The obstacle degree model calculation method is, Standardize each sequence index, the method is the same as grey correlation analysis, Index deviation: ; j the degree of impairment of the system by the first metric​ ； ； System impairment of each subsystem: ; In the formula, yy ij As an indicator j The standardization results YY ij As an indicator j The degree of deviation SP j As an indicator j Obstacles U t For subsystem t The degree of system obstacle.

6. The method according to claim 1, wherein the method is characterized by: The integration of driving factor and obstacle factor refers to taking the top 50% indexes based on the results of grey correlation analysis as key driving factor, taking the top 50% indexes based on the results of obstacle degree model as key obstacle factor, and merging the two factors, that is, as the key influence factor set of the system.

7. The method according to claim 6, wherein the method is characterized by: The indexes in the key influence factor set are screened by threshold method to obtain the final key influence factor, and the threshold method evaluation standard is that the grey correlation degree value is greater than 0.90 and the obstacle degree value is greater than 10%.

8. A small watershed drive-barrier dual diagnosis key indicator identification system for performing claim 1 7. The small watershed drive-barrier dual diagnosis key indicator identification method according to any one of claims 1 to 6, wherein Comprise: Data acquisition module, used for acquiring and updating multi-source heterogeneous data of small watershed; Data processing module, used for cleaning, interpolation and standardization of data; Model calculation module, used for constructing driving-obstacle double diagnosis model and calculating the correlation degree and obstacle degree of each index; Index identification module, used for identifying key driving factor and obstacle factor according to model output; Visual analysis module, used for graphical display and comparison of diagnosis results; Decision support module, used for outputting targeted management suggestions or development path scheme; The modules can be realized by computer program and its storage medium.

9. The small watershed driving-obstacle dual-diagnosis key indicator identification system according to claim 8, characterized in that: The decision support module is connected with artificial intelligence model service platform through programming interface.

Images