A method, system and device for intelligent identification of factors influencing fish communities

Abstract

This invention relates to an intelligent identification method, system, and apparatus for fish community influencing factors. The method includes constructing an overall sequence from fish community and environmental sequences; calculating the Euclidean distances between pairs of points in each sequence to obtain first, second, and third Euclidean distance sequences; building a comprehensive factor model based on each Euclidean distance sequence; building a species-specific single-factor model based on the second Euclidean distance sequence and the Euclidean distance sequences between pairs of points for each species; building an environmental single-factor model based on the third Euclidean distance sequence and the Euclidean distance sequences between pairs of points for each environmental indicator; substituting the species and environmental single-factor models into the comprehensive factor model to obtain a single-factor comprehensive model; and intelligently identifying fish community influencing factors based on the density distribution characteristics of the model coefficients. This invention comprehensively considers the interaction between the aquatic environment and fish communities, and can intelligently identify the guiding species and environmental factors that lead to differences in fish community structure.

Description

Technical Field

[0001] This invention relates to the field of biological community influencing factor identification, specifically to an intelligent identification method, system, and device for fish community influencing factors. Background Technology

[0002] The ecological environment within a lake comprises environmental factors, biological factors, and the interactions between them. The influence of environmental and biological factors is reciprocal; the health of the aquatic ecological environment directly affects the diversity and stability of aquatic animal communities, and the structural state of these communities can also largely reflect the health of the aquatic ecological environment. For aquatic ecosystems, ecosystem stability includes both the stability of the aquatic ecological environment (physicochemical environment) and the stability of the aquatic biological community (biological environment). Current research on aquatic ecosystem stability primarily considers the impact of aquatic biological communities, potentially neglecting or weakening the influence of aquatic environmental factors and the interactions between the aquatic environment and aquatic organisms. This bias may lead to an incomplete understanding of ecosystem stability and resilience. Fish, as a crucial component of the aquatic ecological environment, directly reflect the health of the aquatic environment through changes in their species diversity and community structure. Timely and accurate identification of key species influencing fish community structure and important indicators causing environmental differences is crucial. By observing the distribution and changes of these species and indicators, scientists and environmental managers can promptly identify signs of pollution, habitat destruction, or other environmental pressures. Therefore, it is necessary to propose an intelligent identification scheme for factors influencing fish communities. Summary of the Invention

[0003] This invention provides a method, system, and apparatus for intelligent identification of factors influencing fish communities, in order to solve at least one of the above-mentioned technical problems.

[0004] The technical solution of this invention to solve the above-mentioned technical problems is as follows: A method for intelligent identification of factors affecting fish communities, comprising:

[0005] S1. Collect fish community data and environmental data from multiple locations to obtain corresponding fish community sequences and environmental sequences, and merge the fish community sequences and environmental sequences to construct an overall sequence.

[0006] S2, calculate the Euclidean distance between each pair of points in the overall sequence, the fish community sequence, and the environmental sequence respectively, and obtain the first Euclidean distance sequence, the second Euclidean distance sequence, and the third Euclidean distance sequence accordingly;

[0007] S3, construct a comprehensive factor model based on the first Euclidean distance sequence, the second Euclidean distance sequence, and the third Euclidean distance sequence;

[0008] S4, calculate the Euclidean distance sequence between each species in the fish community sequence and each pair of points, and build a single-factor model of species based on the second Euclidean distance sequence and the Euclidean distance sequence between each species in the fish community sequence.

[0009] S5, calculate the Euclidean distance sequence between each environmental indicator in the environmental sequence and each pair of environmental indicators in the environmental sequence, and build a single-factor environmental model based on the third Euclidean distance sequence and the Euclidean distance sequence between each environmental indicator in the environmental sequence.

[0010] S6, Substitute the species single-factor model and the environment single-factor model into the comprehensive factor model to obtain the single-factor comprehensive model;

[0011] S7. Based on the density distribution characteristics of the model coefficients in the single-factor comprehensive model, the fish community influencing factors are intelligently identified.

[0012] Based on the above technical solution, the present invention can be further improved as follows.

[0013] Furthermore, in S1, the fish community sequence is represented as follows:

[0014]

[0015] The environmental sequence is represented as follows:

[0016]

[0017] The overall sequence is represented as follows:

[0018]

[0019] Where F represents the fish community sequence, n represents the total number of species in the fish community, m represents the total number of locations, j represents the ordinal number of the species, i represents the ordinal number of the location, and f ji Let represent the measurement value of the j-th species at the i-th location; E represents the environmental sequence, l represents the total number of environmental indicators, k represents the ordinal number of the environmental indicator, and e represents the environmental sequence. ki Let represent the measured value of the k-th environmental indicator at the i-th location; T represents the overall sequence.

[0020] Furthermore, in S3, the comprehensive factor model is expressed as:

[0021] T r ~α×F r +β×E r +ε;

[0022] Among them, T r Let F represent the first Euclidean distance sequence.r Denotes the second Euclidean distance sequence, E r Let represent the third Euclidean distance sequence, α and β represent the fitting coefficients using least squares, and ε represent the fitting constants using least squares.

[0023] Furthermore, in S4, the species single-factor model is expressed as:

[0024]

[0025] Among them, F r Let Q represent the second Euclidean distance sequence, n represent the total number of species in the fish community, j represent the ordinal number of the species, and Q represent the second Euclidean distance sequence. j Let a represent the Euclidean distance sequence between each pair of points for the j-th species in the fish community sequence. j ε represents the fitting coefficients obtained using least squares fitting. f This represents the fitting constant used for least squares fitting.

[0026] Furthermore, in S5, the single-factor environmental model is expressed as:

[0027]

[0028] Among them, E r Let represent the third Euclidean distance sequence, l represent the total number of environmental indicators, k represent the ordinal number of the environmental indicator, and EQ. k Let b represent the Euclidean distance sequence between each pair of points for the k-th environmental indicator in the environmental sequence. k ε represents the fitting coefficients obtained using least squares fitting. e This represents the fitting constant used for least squares fitting.

[0029] Furthermore, in S6, the single-factor comprehensive model is expressed as:

[0030]

[0031] Where, ω 1j =α×a j ω 1j ω represents the model coefficient in the single-factor integrated model, and ω represents the species impact coefficient of the j-th species on ecological environment differences. 2k =β×b k ω 2k ε′ represents the model coefficient in the single-factor comprehensive model, which indicates the environmental impact coefficient of the k-th environmental indicator on the differences in the ecological environment; ε′ represents the constant in the single-factor comprehensive model.

[0032] Furthermore, S7 specifically includes:

[0033] After taking the absolute value of the influence coefficient of each species, a density map is drawn based on the density distribution characteristics to obtain a species density map; the species influence coefficient corresponding to the highest density is extracted from the species density map as the species evaluation threshold; the species corresponding to the species influence coefficient greater than the species evaluation threshold are regarded as the main species.

[0034] After taking the absolute value of each environmental impact coefficient, a density map is drawn based on the density distribution characteristics to obtain an environmental density map; the environmental impact coefficient corresponding to the maximum density is extracted from the environmental density map as the environmental assessment threshold; the environmental indicators corresponding to the environmental impact coefficients that are greater than the environmental assessment threshold are taken as the main environmental indicators.

[0035] The main species and the main environmental indicators are the fish community influencing factors.

[0036] Furthermore, after obtaining the fish community sequence and the environmental sequence in S1, the method further includes: standardizing the fish community sequence and the environmental sequence.

[0037] Based on the above-mentioned intelligent identification method for fish community influencing factors, the present invention also provides an intelligent identification system for fish community influencing factors.

[0038] A smart identification system for factors influencing fish communities, comprising:

[0039] The overall sequence construction module is used to collect fish community data and environmental data from multiple locations, obtain corresponding fish community sequences and environmental sequences, and merge the fish community sequences and environmental sequences to construct the overall sequence.

[0040] The Euclidean distance sequence calculation module is used to calculate the Euclidean distance between pairs of points in the overall sequence, the fish community sequence, and the environmental sequence, respectively, to obtain the first Euclidean distance sequence, the second Euclidean distance sequence, and the third Euclidean distance sequence.

[0041] A comprehensive factor model building module is used to build a comprehensive factor model based on the first Euclidean distance sequence, the second Euclidean distance sequence, and the third Euclidean distance sequence;

[0042] A single-factor species model building module is used to calculate the Euclidean distance sequence between each species in the fish community sequence and between each pair of points, and to build a single-factor species model based on the second Euclidean distance sequence and the Euclidean distance sequence between each species in the fish community sequence.

[0043] An environmental single-factor model building module is used to calculate the Euclidean distance sequence between each environmental indicator in the environmental sequence and each environmental indicator in the environmental sequence and build an environmental single-factor model based on the third Euclidean distance sequence and the Euclidean distance sequence between each environmental indicator in the environmental sequence.

[0044] A single-factor integrated model building module is used to substitute the species single-factor model and the environment single-factor model into the integrated factor model to obtain a single-factor integrated model;

[0045] The influencing factor identification module is used to intelligently identify fish community influencing factors based on the density distribution characteristics of the model coefficients in the single-factor comprehensive model.

[0046] Based on the above-mentioned intelligent identification method for fish community influencing factors, the present invention also provides an intelligent identification device for fish community influencing factors.

[0047] A smart identification device for fish community influencing factors includes a processor, a memory, and a computer program stored in the memory. When the computer program is executed by the processor, it implements the smart identification method for fish community influencing factors as described above.

[0048] The beneficial effects of this invention are as follows: This invention provides an intelligent identification method, system, and device for fish community influencing factors. Based on fish community and environmental indicator data, it quantifies the comprehensive impact of biological and environmental factors by digitizing an ecological model that includes holistic factors encompassing both biological and environmental elements. This effectively avoids biases in the understanding of ecosystem stability and resilience caused by neglecting or weakening aquatic environmental factors and the interaction between the aquatic environment and aquatic organisms. Then, it constructs species-specific single-factor models and environmental single-factor models for local locations, quantifying ecological differences from top to bottom. Finally, it uses a single-factor comprehensive model to intelligently diagnose important species and environmental indicators affecting fish community structure and aquatic environmental differences based on the density distribution characteristics of model coefficients. By more comprehensively considering the interaction between the aquatic environment and fish communities, this invention can intelligently identify the guiding species and environmental factors leading to differences in fish community structure, effectively improving scientists' and environmental managers' understanding of the integrity of ecosystem stability and resilience, and providing guidance for the protection and management of aquatic ecosystems. Attached Figure Description

[0049] Figure 1 This is a flowchart of a method for intelligent identification of factors influencing fish communities according to the present invention;

[0050] Figure 2 This is a density distribution map showing the impact of species and environmental indicators on ecological environment differences in the example.

[0051] Figure 3 This is a structural block diagram of an intelligent identification system for fish community influencing factors according to the present invention. Detailed Implementation

[0052] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0053] like Figure 1 As shown, a method for intelligent identification of factors influencing fish communities includes:

[0054] S1. Collect fish community data and environmental data from multiple locations to obtain corresponding fish community sequences and environmental sequences, and merge the fish community sequences and environmental sequences to construct an overall sequence.

[0055] S2, calculate the Euclidean distance between each pair of points in the overall sequence, the fish community sequence, and the environmental sequence respectively, and obtain the first Euclidean distance sequence, the second Euclidean distance sequence, and the third Euclidean distance sequence.

[0056] S3. Construct a comprehensive factor model based on the first Euclidean distance sequence, the second Euclidean distance sequence, and the third Euclidean distance sequence.

[0057] S4. Calculate the Euclidean distance sequence between each species in the fish community sequence at each pair of points, and build a single-factor model of species based on the second Euclidean distance sequence and the Euclidean distance sequence between each species in the fish community sequence at each pair of points.

[0058] S5, calculate the Euclidean distance sequence between each pair of environmental indicators in the environmental sequence, and build a single-factor environmental model based on the third Euclidean distance sequence and the Euclidean distance sequence between each pair of environmental indicators in the environmental sequence.

[0059] S6. Substitute the species single-factor model and the environment single-factor model into the comprehensive factor model to obtain the single-factor comprehensive model.

[0060] S7. Based on the density distribution characteristics of the model coefficients in the single-factor comprehensive model, the fish community influencing factors are intelligently identified.

[0061] The following is a detailed explanation of each step.

[0062] S1 is the constructed population sequence:

[0063] The aquatic environment encompasses both physical and biological environments. To better highlight the actual conditions of the aquatic environment, both fish community data (measurements of each species within the fish community at a given location) and environmental data (measurements of various environmental indicators at a given location) are used to represent the characteristics of that location. For the aquatic environmental characteristics of the same location, two approaches are used from top to bottom to represent the differences in the ecological environment: a holistic approach and a holistic approach. The holistic approach uses fish community data to represent the biological environment of a local location and environmental indicator data to represent the physical environment of that location. The holistic approach treats both fish community data and environmental indicator data as a whole to represent the overall environmental characteristics of the aquatic ecosystem, thus constructing an overall sequence.

[0064] Fish community data is used to represent the biological environment of local sites. The measured values ​​(abundance data or biomass data) of each species in the fish community at each site constitute the fish community sequence; the fish community sequence is represented as follows:

[0065]

[0066] Where F represents the fish community sequence, n represents the total number of species in the fish community, m represents the total number of locations, j represents the ordinal number of the species, i represents the ordinal number of the location, and f ji This represents the measurement value of the j-th species at the i-th location.

[0067] Environmental index data are used to represent the physical environment of local locations. The measured values ​​of various environmental indicators at each location constitute an environmental sequence; the environmental sequence is represented as follows:

[0068]

[0069] Where E represents the environmental sequence, l represents the total number of environmental indicators, k represents the ordinal number of the environmental indicator, and e ki This represents the measured value of the k-th environmental indicator at the i-th location.

[0070] Fish community data and environmental indicator data are used as a whole to represent the overall environmental characteristics of the aquatic ecosystem, thereby constructing an overall sequence; the overall sequence is expressed as:

[0071]

[0072] Where T represents the overall sequence; [] ′ This indicates transpose.

[0073] To eliminate the influence of data units on the calculation results, the fish community sequence and environmental sequence need to be standardized before analysis, as shown in the following formula:

[0074]

[0075] Where x represents a sequence, Let σ represent the mean of sequence x, σ represent the standard deviation of sequence x, and Z represent the standardized sequence x.

[0076] Therefore, after obtaining the fish community sequence and the environmental sequence, the method further includes: standardizing the fish community sequence and the environmental sequence.

[0077] S2 to S6 are for establishing an ecological environment difference model:

[0078] The ecological environment of different locations is formed by the combined effects of biotic and abiotic factors, resulting in the unique characteristics of each location. To better showcase the ecological characteristics of each location and quantify the differences in ecological environments between locations, this invention selects spatial Euclidean distance to quantify these differences.

[0079] The differences in the ecological environment between the two sites are mainly caused by differences in biological and environmental factors. The differences in biological factors arise from variations in fish community structure, while the differences in environmental factors arise from variations in environmental indicators. Therefore, the differences in the ecological environment between the two sites can be divided into two levels: the first level is a comprehensive factor model representing the overall ecological environment, which considers biological and environmental factors as a whole to represent the characteristics of each site; the second level is a single-factor model representing the local ecological environment, which includes the distribution differences among species within biological factors and the performance differences among various environmental indicators within environmental factors.

[0080] By constructing a comprehensive factor model, we can obtain the combined impact of biological and environmental factors on overall differences. Through the analysis of single-factor models, we can assess the individual impact of each species on differences in biological factors between sites and the individual impact of each environmental indicator on differences in environmental factors, quantifying the impact of single-factor indicators on differences in fish community structure or aquatic environment. Based on the density distribution of the influence coefficients of single-factor indicators, we can intelligently and accurately identify the main species causing differences in biological factors and the main environmental indicators causing differences in environmental factors, and calculate the impact of the main species and the main environmental indicators on the overall ecological environment differences from the bottom up.

[0081] S2 is used to calculate the Euclidean distance between each sequence (environmental sequence, fish community sequence, and overall sequence).

[0082] First, calculate the Euclidean distance for each sequence. The sequence length is r = C. 2 m (m is the total number of points):

[0083] The Euclidean distances between every pair of points in the overall sequence yield the first Euclidean distance sequence: Tr ;

[0084] The Euclidean distances between pairwise points in a fish community sequence yield the second Euclidean distance sequence: F r ;

[0085] The Euclidean distances between pairwise points in the environmental sequence yield a third Euclidean distance sequence: E r ;

[0086] Specifically, in calculating the second Euclidean distance sequence F r In this process, each column of the fish community sequence F is used as a feature value for each location, and the Euclidean distance between each pair of locations is calculated based on the feature values; that is, each location is represented by a vector containing n species, and then the Euclidean distance between each vector is calculated. In calculating the third Euclidean distance sequence E... r In this process, each column of the environmental sequence E is used as a feature value for each point, and the Euclidean distance between each pair of points is calculated based on the feature values; that is, a point is represented by a vector containing l environmental indicators, and then the Euclidean distance between each vector is calculated. This is done when calculating the first Euclidean distance sequence T. r In this case, each column of the overall sequence T is used as the feature value of each point, and the Euclidean distance between each pair of points is calculated based on the feature value; that is, a point is represented by a vector containing n species and l environmental indicators, and then the Euclidean distance between each vector is calculated.

[0087] S3 is for building a comprehensive factor model:

[0088] T is calculated using the Pierce correlation coefficient. r and F r T r and E r F r and E r The correlation coefficient is considered, and the applicability of this method is better when the correlation coefficient is significant. The comprehensive factor model is constructed as follows:

[0089] T r ~α×F r +β×E r +ε;

[0090] Among them, T r Let F represent the first Euclidean distance sequence. r Denotes the second Euclidean distance sequence, E r ε represents the third Euclidean distance sequence; α and β represent the fitting coefficients using least squares, that is, α represents the comprehensive influence of biological factors on ecological and environmental differences, and β represents the comprehensive influence of environmental factors on ecological and environmental differences; ε represents the fitting constant using least squares.

[0091] S4 is for building a single-factor model - a species-based single-factor model:

[0092] For a fish community sequence F, the distribution of each species varies across locations, and these differences lead to variations in biological factors at each location. The difference between two locations for a single species is represented by the absolute value of the difference between the measurements of that species at the two locations. Let's assume the j-th species has measurements f at location i and location (i+1) respectively. ji and f ji+1 Then the difference between these two locations for this species is:

[0093] Q j,i-i+1 =|f ji -f ji+1 |;

[0094] From this, we can obtain the Euclidean distance sequence Q between each pair of points for the j-th species. j Its length is r. Therefore, the Euclidean distance sequence between each pair of points of each species can be expressed as:

[0095] [Q1,Q2,…,Q j ,…,Q n ];

[0096] The resulting single-factor model for the species is represented as follows:

[0097]

[0098] Among them, F r Let Q represent the second Euclidean distance sequence, n represent the total number of species in the fish community, j represent the ordinal number of the species, and Q represent the second Euclidean distance sequence. j Let a represent the Euclidean distance sequence between each pair of points for the j-th species in the fish community sequence. j ε represents the fitting coefficients obtained using least squares fitting. f This represents the fitting constant used for least squares fitting. j To characterize the individual impact of the j-th species on differences in biological factors, a stepwise regression method is used, and the optimal variables to be included in the model are selected based on the AIC criterion; the obtained a j That is, the individual influence of the j-th species on the differences in biological factors between sites, and the species variables included in the model are the species factors that lead to the differences in biological factors between sites.

[0099] S5 is for building a single-factor model - an environmental single-factor model:

[0100] For an environmental sequence E, the distribution of each environment varies across different locations. These differences lead to variations in environmental factors at each location. The difference between two locations for a single environment is represented by the absolute value of the difference between the measured values ​​of that environmental indicator at the two locations. Assume the k-th environmental indicator has measured values ​​e at the i-th and (i+1)-th locations. ki and e ki+1 Therefore, the difference in this environmental indicator between these two locations is:

[0101] EQ k,i-i+1 =|e ki -e ki+1 |;

[0102] Therefore, we can obtain the Euclidean distance sequence (EQ) between each pair of points for the k-th environmental indicator. k Its length is r.

[0103] Therefore, the Euclidean distance sequence between each pair of points for each environmental indicator can be expressed as:

[0104] [EQ1,EQ2,…,EQ k ,…,EQ n ];

[0105] Environmental Single Factor Model

[0106] The resulting single-factor environmental model is represented as follows:

[0107]

[0108] Among them, E r Let represent the third Euclidean distance sequence, l represent the total number of environmental indicators, k represent the ordinal number of the environmental indicator, and EQ. k Let b represent the Euclidean distance sequence between each pair of points for the k-th environmental indicator in the environmental sequence. k ε represents the fitting coefficients obtained using least squares fitting. e This represents the fitting constant used for least squares fitting. k To characterize the individual impact of the k-th environmental indicator on differences in environmental factors, a stepwise regression method is used in the solution process. Based on the AIC criterion, the optimal variables to be included in the model are selected; the obtained b... k That is, the individual impact of the k-th environmental indicator on the differences in environmental factors between locations, and the environmental variables included in the model are the environmental factors that cause the differences in environmental factors between locations.

[0109] S6 is for building a single-factor comprehensive model:

[0110] The main factors contributing to the ecological differences between the two sites include biological and environmental factors. Biological factors are influenced by the species distribution at each site, while environmental factors are affected by the performance of environmental indicators at each site. Therefore, by combining a comprehensive factor model, a species-specific single-factor model, and an environmental single-factor model, we can obtain the comprehensive impact of a single factor (species indicator or environmental indicator) on the overall ecological differences, resulting in a single-factor comprehensive model. The process is as follows:

[0111] Comprehensive Factor Model:

[0112] T r ~α×F r +β×E r +ε;

[0113] Species single-factor model:

[0114]

[0115] Environmental single-factor model:

[0116]

[0117] The species single-factor model F r Environmental Single Factor Model E r Substitute them together into the comprehensive factor model T r The single-factor comprehensive model is obtained as follows:

[0118]

[0119] After simplification, we get:

[0120]

[0121] Where, ω 1j =α×a j ω 1j ω represents the model coefficient in the single-factor integrated model, and ω represents the species impact coefficient of the j-th species on ecological environment differences. 2k =β×b k ω 2k ε′ represents the model coefficient in the single-factor comprehensive model, which indicates the environmental impact coefficient of the k-th environmental indicator on the differences in the ecological environment; ε′ represents the constant in the single-factor comprehensive model.

[0122] S7 is an important factor in intelligent recognition:

[0123] Based on a single-factor comprehensive model, the influence coefficient sequence ω of species on ecological environment differences was extracted. 1j The sequence of influence coefficients ω of environmental indicators on differences in the ecological environment 2kAfter taking the absolute values ​​of these two sequences, a density map is drawn based on the density distribution characteristics. This intelligently and accurately identifies the driving factors affecting fish community structure, including major species and key environmental indicators; the numerical value ω corresponding to the maximum density is extracted. 10 and ω 20 As an evaluation threshold, the influence coefficient of species on ecological environment differences is greater than ω. 10 The species that are considered the main species are those whose environmental indicators have a greater impact coefficient on ecological environment differences than ω. 20 The environmental indicators are the main environmental indicators.

[0124] Therefore, S7 specifically refers to:

[0125] After taking the absolute value of the influence coefficient of each species, a density map is drawn based on the density distribution characteristics to obtain a species density map; the species influence coefficient corresponding to the highest density is extracted from the species density map as the species evaluation threshold; the species corresponding to the species influence coefficient greater than the species evaluation threshold are regarded as the main species.

[0126] After taking the absolute value of each environmental impact coefficient, a density map is drawn based on the density distribution characteristics to obtain an environmental density map; the environmental impact coefficient corresponding to the maximum density is extracted from the environmental density map as the environmental assessment threshold; the environmental indicators corresponding to the environmental impact coefficients that are greater than the environmental assessment threshold are taken as the main environmental indicators.

[0127] The main species and the main environmental indicators are the fish community influencing factors.

[0128] In summary, the method of the present invention has the following advantages:

[0129] (1) The method of the present invention is based on fish community and environmental index data. It divides the ecological environment differences of sampling points into overall differences (comprehensive factor model) and local differences (species single factor model and environment single factor model) from top to bottom, which can more completely reflect the interaction between aquatic organisms and aquatic environment in the aquatic ecosystem.

[0130] (2) Species single-factor model and environment single-factor model quantify the impact of single-factor indicators on differences in fish community structure and aquatic environment, laying the foundation for intelligent identification of the main species and main environmental indicators of differences in fish community structure and aquatic environment.

[0131] (3) The single-factor comprehensive model quantifies the impact of each indicator on the overall ecological environment difference from the bottom up. It relies on the density distribution characteristics of the model coefficients to realize the intelligent identification of the factors affecting the fish community structure, effectively avoiding the difference in evaluation conclusions due to insufficient experience or inadequate understanding, and improving the universality of the model.

[0132] The method of the present invention will be illustrated below with specific examples:

[0133] Environmental and biological factors interact and influence each other in aquatic ecosystems. This example uses water physicochemical indicators as environmental factors and all fish samples collected as biological factors. Together, they constitute the environmental and biological factors influencing fish community distribution characteristics. Data used are abundance and environmental data of fish communities in the same water body at the same time period. Calculations yielded:

[0134] (1) The comprehensive factor model is as follows:

[0135] T r =0.64×F r +0.73×E r +0.37

[0136] Therefore, according to the comprehensive factor model, the environmental factor has the greatest impact on ecological environment differences, with an influence coefficient of 0.73; followed by the fish community, a biological factor, with an influence coefficient of 0.64. This coefficient more intuitively and accurately reflects the magnitude of the impact of aquatic organisms and the aquatic environment on the overall ecological environment.

[0137] (2) Single-factor model

[0138] Species single-factor model:

[0139] F r = -1.94 minnows + 0.80 Japanese prawns + 0.54 crucian carp + 0.43 +0.48 Anchovy

[0140] +0.57 Similar to a soft-shelled turtle -1.48 Intermediate soft-shelled turtle +1.18 Large-finned soft-shelled turtle +0.16 Red-finned bream

[0141] +0.80 Short-jawed Coilia

[0142] Environmental single-factor model:

[0143] E r =0.13PO4+0.24Chl.a+0.25COD+0.28DO+0.28TN+0.32NH4

[0144] +0.33SD+0.36NO3+0.37NO2+0.37WT+0.39TP

[0145] +0.40COND

[0146] The relative impact of each indicator on local differences can be determined using species-only and environment-only models, quantifying the differences in local ecological environments from top to bottom. The fish species with the greatest impact, in descending order, are: minnows, *Hemiberlesia lataniae*, *Hemiberlesia lataniae*, *Scuttonia japonica*, *Anchovy simianus*, *Carassius acutus*, and *Anchovy shad*. The environmental indicators, from largest to smallest, are: COND (conductivity), TP (total phosphorus), WT (water temperature), NO2 (nitrogen dioxide), NO3 (nitrate nitrogen), SD (transparency), NH4 (nitrite nitrogen), TN (total nitrogen), DO (dissolved oxygen), COD (permanganate index), Chl.a (chlorophyll a), and PO4 (orthophosphate). Therefore, researchers can clearly understand the relative impact of each indicator on ecological differences, which is beneficial for improving the overall understanding of the stability and resilience of the ecosystem formed by fish communities and their surrounding environment.

[0147] (3) Single-factor comprehensive model

[0148] F r E r Substitute T r The single-factor comprehensive model was obtained, and the model coefficients are shown in Table 1 below.

[0149] Table 1: Model Coefficients Table

[0150]

[0151] Density distribution map of the impact of species and environmental indicators on ecological environment differences, constructed from model coefficients, is shown below. Figure 2 As shown.

[0152] Based on the single-factor comprehensive model and density distribution map, the influence of various species on the fish community varies significantly among biological factors. The species with the largest positive influence are *Anchovy bream*, *Shrimp japonicus*, and *Gastrodon scutellarioides*, while those with the largest negative influence are *Gnaphalium affine* and *Gnaphalium affine*. Among environmental factors, the influence of each factor is relatively similar, with NO2, NO3, WT, TP, and COND having the largest impacts. Therefore, the main species significantly affected by differences in the ecological environment are *Anchovy bream*, *Shrimp japonicus*, *Gastrodon scutellarioides*, *Gnaphalium affine*, and *Gnaphalium affine*, and the main environmental indicators are NO2, NO3, WT, TP, and COND.

[0153] Therefore, in practical work, scientists and environmental managers need to focus on and study the diversity, quantity, distribution, and niche characteristics of species such as the short-jawed anchovy, Japanese prawn, large-finned bream, topmouth gudgeon, and smallmouth bass, so as to timely and accurately grasp the main biological data on changes in community structure. For water environment indicators such as NO2, NO3, WT, TP, and COND, it is necessary to pay attention to their changes, so as to timely identify signs of pollution, habitat destruction, or other environmental pressures, which has good guiding significance for effectively assessing and monitoring the health status of the aquatic ecological environment.

[0154] Based on the above-mentioned intelligent identification method for fish community influencing factors, the present invention also provides an intelligent identification system for fish community influencing factors.

[0155] like Figure 3 As shown, an intelligent identification system for factors influencing fish communities includes:

[0156] The overall sequence construction module is used to collect fish community data and environmental data from multiple locations, obtain corresponding fish community sequences and environmental sequences, and merge the fish community sequences and environmental sequences to construct the overall sequence.

[0157] The Euclidean distance sequence calculation module is used to calculate the Euclidean distance between pairs of points in the overall sequence, the fish community sequence, and the environmental sequence, respectively, to obtain the first Euclidean distance sequence, the second Euclidean distance sequence, and the third Euclidean distance sequence.

[0158] A comprehensive factor model building module is used to build a comprehensive factor model based on the first Euclidean distance sequence, the second Euclidean distance sequence, and the third Euclidean distance sequence;

[0159] A single-factor species model building module is used to calculate the Euclidean distance sequence between each species in the fish community sequence and between each pair of points, and to build a single-factor species model based on the second Euclidean distance sequence and the Euclidean distance sequence between each species in the fish community sequence.

[0160] An environmental single-factor model building module is used to calculate the Euclidean distance sequence between each environmental indicator in the environmental sequence and each environmental indicator in the environmental sequence and build an environmental single-factor model based on the third Euclidean distance sequence and the Euclidean distance sequence between each environmental indicator in the environmental sequence.

[0161] A single-factor integrated model building module is used to substitute the species single-factor model and the environment single-factor model into the integrated factor model to obtain a single-factor integrated model;

[0162] The influencing factor identification module is used to intelligently identify fish community influencing factors based on the density distribution characteristics of the model coefficients in the single-factor comprehensive model.

[0163] Based on the above-mentioned intelligent identification method for fish community influencing factors, the present invention also provides an intelligent identification device for fish community influencing factors.

[0164] A smart identification device for fish community influencing factors includes a processor, a memory, and a computer program stored in the memory. When the computer program is executed by the processor, it implements the smart identification method for fish community influencing factors as described above.

[0165] This invention discloses an intelligent identification method, system, and device for fish community influencing factors. Based on fish community and environmental indicator data, it quantifies the combined impact of biological and environmental factors by digitizing an ecological model that includes holistic factors encompassing both biological and environmental elements. This effectively avoids biases in the understanding of ecosystem stability and resilience caused by neglecting or weakening aquatic environmental factors and the interaction between the aquatic environment and aquatic organisms. Then, it constructs species-specific single-factor models and environmental single-factor models for local locations, quantifying ecological differences from top to bottom. Finally, it employs a single-factor comprehensive model to intelligently diagnose key species and environmental indicators affecting fish community structure and aquatic environmental differences based on the density distribution characteristics of model coefficients. By more comprehensively considering the interaction between the aquatic environment and fish communities, this invention can intelligently identify the guiding species and environmental factors leading to differences in fish community structure, effectively improving scientists' and environmental managers' understanding of the integrity of ecosystem stability and resilience. This has significant guiding significance for the protection and management of aquatic ecosystems.

[0166] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent identification of factors influencing fish communities, characterized in that, include: S1. Collect fish community data and environmental data from multiple locations to obtain corresponding fish community sequences and environmental sequences, and merge the fish community sequences and environmental sequences to construct an overall sequence. S2, calculate the Euclidean distance between each pair of points in the overall sequence, the fish community sequence, and the environmental sequence respectively, and obtain the first Euclidean distance sequence, the second Euclidean distance sequence, and the third Euclidean distance sequence accordingly; S3, construct a comprehensive factor model based on the first Euclidean distance sequence, the second Euclidean distance sequence, and the third Euclidean distance sequence; S4, calculate the Euclidean distance sequence between each species in the fish community sequence and each pair of points, and build a single-factor model of species based on the second Euclidean distance sequence and the Euclidean distance sequence between each species in the fish community sequence. S5, calculate the Euclidean distance sequence between each pair of environmental indicators in the environmental sequence, and build a single-factor environmental model based on the third Euclidean distance sequence and the Euclidean distance sequence between each pair of environmental indicators in the environmental sequence. S6, Substitute the species single-factor model and the environment single-factor model into the comprehensive factor model to obtain the single-factor comprehensive model; S7. Based on the density distribution characteristics of the model coefficients in the single-factor comprehensive model, the fish community influencing factors are intelligently identified. The single-factor comprehensive model is expressed as follows: Among them, T r Let Q represent the first Euclidean distance sequence; n represents the total number of species in the fish community, j represents the ordinal number of the species, and Q represents the first Euclidean distance sequence. j Let represent the Euclidean distance sequence between each pair of points for the j-th species in the fish community sequence; l represents the total number of environmental indicators, k represents the ordinal number of the environmental indicator, and EQ k ω represents the Euclidean distance sequence between each pair of points for the k-th environmental indicator in the environmental sequence; 1j ω represents the model coefficient in the single-factor integrated model, and ω represents the species impact coefficient of the j-th species on ecological environment differences. 2k ε' represents the model coefficient in the single-factor comprehensive model, indicating the environmental impact coefficient of the k-th environmental indicator on ecological environment differences; ε′ represents the constant in the single-factor comprehensive model. Specifically, S7 is: After taking the absolute value of the influence coefficient of each species, a density map is drawn based on the density distribution characteristics to obtain a species density map; the species influence coefficient corresponding to the highest density is extracted from the species density map as the species evaluation threshold; the species corresponding to the species influence coefficient greater than the species evaluation threshold are regarded as the main species. After taking the absolute value of each environmental impact coefficient, a density map is drawn based on the density distribution characteristics to obtain an environmental density map; the environmental impact coefficient corresponding to the maximum density is extracted from the environmental density map as the environmental assessment threshold; the environmental indicators corresponding to the environmental impact coefficients that are greater than the environmental assessment threshold are taken as the main environmental indicators. The main species and the main environmental indicators are the fish community influencing factors.

2. The intelligent identification method for fish community influencing factors according to claim 1, characterized in that, In S1, the fish community sequence is represented as follows: The environmental sequence is represented as follows: The overall sequence is represented as follows: Where F represents the fish community sequence, n represents the total number of species in the fish community, m represents the total number of locations, j represents the ordinal number of the species, i represents the ordinal number of the location, and f ji Let represent the measurement value of the j-th species at the i-th location; E represents the environmental sequence, l represents the total number of environmental indicators, k represents the ordinal number of the environmental indicator, and e represents the environmental sequence. ki Let represent the measured value of the k-th environmental indicator at the i-th location; T represents the overall sequence.

3. The intelligent identification method for fish community influencing factors according to claim 1, characterized in that, In S3, the comprehensive factor model is expressed as: T r ~α×F r +β×E r +e; Among them, T r Let F represent the first Euclidean distance sequence. r Denotes the second Euclidean distance sequence, E r Let represent the third Euclidean distance sequence, α and β represent the fitting coefficients using least squares, and ε represent the fitting constants using least squares.

4. The intelligent identification method for fish community influencing factors according to claim 3, characterized in that, In S4, the species single-factor model is represented as follows: Among them, F r Let Q represent the second Euclidean distance sequence, n represent the total number of species in the fish community, j represent the ordinal number of the species, and Q represent the second Euclidean distance sequence. j Let a represent the Euclidean distance sequence between each pair of points for the j-th species in the fish community sequence. j ε represents the fitting coefficients obtained using least squares fitting. f This represents the fitting constant used for least squares fitting.

5. The intelligent identification method for fish community influencing factors according to claim 4, characterized in that, In S5, the single-factor environmental model is represented as follows: Among them, E r Let represent the third Euclidean distance sequence, l represent the total number of environmental indicators, k represent the ordinal number of the environmental indicator, and EQ. k Let b represent the Euclidean distance sequence between each pair of points for the k-th environmental indicator in the environmental sequence. k ε represents the fitting coefficients obtained using least squares fitting. e This represents the fitting constant used for least squares fitting.

6. The intelligent identification method for fish community influencing factors according to claim 1, characterized in that, After obtaining the fish community sequence and the environmental sequence in S1, the method further includes: standardizing the fish community sequence and the environmental sequence.

7. An intelligent identification system for factors influencing fish communities, characterized in that, The intelligent identification method for fish community influencing factors as described in any one of claims 1 to 6 includes: The overall sequence construction module is used to collect fish community data and environmental data from multiple locations, obtain corresponding fish community sequences and environmental sequences, and merge the fish community sequences and environmental sequences to construct the overall sequence. The Euclidean distance sequence calculation module is used to calculate the Euclidean distance between pairs of points in the overall sequence, the fish community sequence, and the environmental sequence, respectively, to obtain the first Euclidean distance sequence, the second Euclidean distance sequence, and the third Euclidean distance sequence. A comprehensive factor model building module is used to build a comprehensive factor model based on the first Euclidean distance sequence, the second Euclidean distance sequence, and the third Euclidean distance sequence; A single-factor species model building module is used to calculate the Euclidean distance sequence between each species in the fish community sequence and between each pair of points, and to build a single-factor species model based on the second Euclidean distance sequence and the Euclidean distance sequence between each species in the fish community sequence. An environmental single-factor model building module is used to calculate the Euclidean distance sequence between each environmental indicator in the environmental sequence and each environmental indicator in the environmental sequence and build an environmental single-factor model based on the third Euclidean distance sequence and the Euclidean distance sequence between each environmental indicator in the environmental sequence. A single-factor integrated model building module is used to substitute the species single-factor model and the environment single-factor model into the integrated factor model to obtain a single-factor integrated model; The influencing factor identification module is used to intelligently identify fish community influencing factors based on the density distribution characteristics of the model coefficients in the single-factor comprehensive model.

8. An intelligent identification device for factors influencing fish communities, characterized in that, The system includes a processor, a memory, and a computer program stored in the memory, wherein the computer program, when executed by the processor, implements the intelligent identification method for fish community influencing factors as described in any one of claims 1 to 6.

Images