An ecologically intelligent partitioning method integrating niche theory and machine learning

Abstract

The present invention belongs to the field of resource and environmental technology, and discloses an ecological intelligent zoning method that integrates niche theory and machine learning. The method includes: measuring environmental factors and phytoplankton community data, calculating the niche width and overlap of sampling points, identifying key environmental factors, and ecological environment zoning. The present invention can effectively integrate data such as water chemical elements, phytoplankton communities, niche overlap and width, and apply machine learning algorithms for analysis, thereby identifying factors that significantly affect the ecosystem, and scientifically and rationally zoning the study area based on these key influencing factors. This method can not only accurately reflect regional ecological characteristics, but also provide important data support for ecological protection, species distribution prediction, and water resource management. At the same time, in practical applications, the present invention can provide an effective basis for ecological environment monitoring, ecological restoration, and regional environmental planning, and has high application value and broad promotion prospects.

Description

Technical Field

[0001] The present invention belongs to the field of resource and environmental technology, and in particular relates to an ecological intelligent zoning method integrating ecological niche theory and machine learning. Background Art

[0002] Currently, most ecological zoning methods rely on traditional habitat assessment techniques, but these methods often struggle to adapt to complex and changing environmental conditions. Traditional methods often rely on empirical and artificially selected environmental factors, failing to fully and objectively reflect the dynamic changes in the ecological environment. Currently, ecological zoning methods primarily rely on traditional environmental factor measurements and habitat assessments, but existing methods have numerous limitations, particularly in complex and changing ecological environments, making it difficult to fully reflect the relationship between the environment and biological communities. Traditional ecological zoning methods typically rely on empirically selected environmental factors and often overlook the interactions between various environmental factors within an ecosystem, lacking a systematic, quantitative means of analyzing the ecological environment. Furthermore, traditional methods often oversimplify the representation of regional ecological characteristics and fail to effectively reveal the key factors influencing the ecosystem, resulting in a lack of scientific and accurate ecological zoning results.

[0003] In recent years, niche theory has been applied to ecological research as a crucial tool for studying the relationships between species and environmental factors. However, its application still faces numerous challenges. Traditional niche analysis methods rely on artificially selected environmental factors and simple mathematical models, making them incapable of comprehensively analyzing large-scale, multidimensional ecological environments. Furthermore, existing research often overlooks the impact of niche overlap and breadth on ecosystem function, failing to fully explore the application of these factors in ecological zoning.

[0004] In summary, the existing ecological zoning methods have obvious shortcomings, and there is an urgent need to develop new technologies and methods to solve these problems in order to achieve more scientific and accurate ecological zoning. Summary of the Invention

[0005] In response to the above bottlenecks in the existing technology, the present invention proposes an ecological intelligent zoning method that integrates niche theory and machine learning, breaking through the data dependence limitations of traditional methods. By effectively integrating environmental factors and phytoplankton community data and using machine learning algorithms for analysis, it realizes the automatic identification and spatial heterogeneity analysis of key factors of ecosystems in complex environments, providing a scientific basis for ecological protection and resource management in data-scarce areas, thereby scientifically identifying environmental factors that have a significant impact on ecosystems and rationally zoning the ecological environment based on these factors.

[0006] The object of the present invention is achieved like this:

[0007] The present invention provides an ecological intelligent zoning method integrating ecological niche theory and machine learning, comprising the following steps:

[0008] Step 1: Measurement of environmental factors and phytoplankton community data:

[0009] S1.1: Determine the study area and sampling points, collect water chemical element samples at each sampling point, and send them to the laboratory for measurement;

[0010] S1.2: Collect phytoplankton samples from each sampling point in the study area and send them to the laboratory for measurement;

[0011] S1.3: Based on laboratory measurements of phytoplankton samples, calculate the phytoplankton biomass, species richness, or species diversity index at each sampling point;

[0012] S1.4: Calculate the dominance of each species and select species with a dominance greater than 0.02 as representative species.

[0013] Step 2: Calculation of niche width and overlap of sampling points:

[0014] S2.1: For all sampling points in the study area, different concentration ranges are divided based on all water chemical element indicators;

[0015] S2.2: Calculate the niche width of representative species under different water chemical element concentration gradients using the Levins formula;

[0016] S2.3: Calculate the niche overlap of representative species under different water chemical element concentration gradients using the Pianka overlap model;

[0017] S2.4: Calculate the niche width of each indicator at each sampling point based on the biomass proportion and niche width of the representative species at each sampling point;

[0018] S2.5: Calculate the niche overlap of each indicator at each sampling point based on the biomass proportion and niche overlap of representative species at each sampling point.

[0019] Step 3: Identify key environmental factors:

[0020] S3.1: Calculate the importance of each indicator using the random forest algorithm, using the water chemical element indicators and species richness or species diversity index calculated at each sampling point in step 1, and the niche breadth and niche overlap calculated at each sampling point in step 2;

[0021] S3.2: Based on the importance of each indicator, screen out key environmental factors.

[0022] Step 4, ecological environment zoning:

[0023] S4.1: Use the key environmental factors and species richness or species diversity index identified in step 3 as feature vectors, calculate the silhouette coefficients for different cluster numbers, and select the cluster number with the highest silhouette coefficient as the cluster number with the best clustering effect;

[0024] S4.2: Perform clustering using the unsupervised learning K-means algorithm or hierarchical clustering method to complete the ecological and environmental zoning of the study area.

[0025] Furthermore, in step 1 S1.1, the number of sampling points set is greater than 15, and the water chemical element indicators measured in each water chemical element sample include: total nitrogen, total phosphorus, total carbon, total silicon, water temperature, pH, dissolved oxygen, dissolved organic carbon, dissolved total nitrogen, dissolved total phosphorus and dissolved silicon; the indicators measured in the phytoplankton sample include: the number of phytoplankton species, cell density and biomass.

[0026] Furthermore, in step 2 S2.1, the concentration ranges of the water chemical element indicators are divided based on percentiles.

[0027] Furthermore, in step 3 S3.1, the specific steps of the random forest algorithm calculation include:

[0028] The water chemical index, niche width and niche overlap of each sampling point were input as feature vector data, and species richness or species diversity index was input as target variable. The random forest algorithm was used to calculate the importance of each index through the increase of mean square error.

[0029] Furthermore, in step 3, 3.2, if the input target variable is an even number, the environmental indicators ranked first n / 2 in importance are used as key environmental factors; if the input target variable is an odd number, the environmental indicators ranked first (n+1) / 2 in importance are used as key environmental factors.

[0030] The advantages and beneficial effects of the present invention are:

[0031] 1. Compared with traditional methods, this method combines ecological niche theory with machine learning algorithms to scientifically zon the study area. Based on the analysis of phytoplankton niche characteristics and environmental factors, it can identify key ecological factors within the region and provide reasonable standards for regional ecological zoning based on these factors. This standard can improve the accuracy of traditional ecological zoning methods, enabling them to better reflect ecosystem characteristics in a changing ecological environment;

[0032] 2. This invention enables comprehensive and systematic analysis of complex ecosystems, helping to quickly identify key areas for ecological protection and providing scientific guidance for ecological environment monitoring, restoration, and regional planning. The application of this method can more objectively and accurately reflect regional ecological characteristics, providing important data support for ecological protection, species distribution prediction, and water resource management. This method not only helps improve the efficiency of ecological protection work, but also provides important data support for water resource management and species distribution prediction, and has broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The present invention will be further described below with reference to the accompanying drawings and examples.

[0034] Figure 1 This is a flow chart of an ecological intelligent zoning method integrating ecological niche theory and machine learning according to an embodiment of the present invention;

[0035] Figure 2 Showing example areas and sampling points selected by an embodiment of the present invention;

[0036] Figure 3 is the weighted value of the niche width and niche overlap of the sampling point calculated in the embodiment of the present invention;

[0037] Figure 4 is the importance of key factors calculated in the embodiment of the present invention, and key environmental factors (water temperature, niche breadth, niche overlap, pH, DTN, TN, TP) are selected;

[0038] Figure 5 is the silhouette coefficient of different clustering trees calculated by the embodiment of the present invention. When the number of clusters is 3, the clustering effect is the best;

[0039] Figure 6 It is the ecological environment zoning result of the example area described in the present invention and the geographical distribution of different zones. DETAILED DESCRIPTION

[0040] Example 1:

[0041] like Figure 1 As shown, this embodiment provides an ecological intelligent zoning method that integrates ecological niche theory and machine learning, including the following steps:

[0042] Step 1: Measurement of environmental factors and phytoplankton community data:

[0043] S1.1: Determine the study area and sampling points, collect water chemical element samples at each sampling point, and send them to the laboratory for measurement. The number of sampling points should be greater than 15. The water chemical element indicators measured in each water chemical element sample include: total nitrogen, total phosphorus, total carbon, total silicon, water temperature, pH, dissolved oxygen, dissolved organic carbon, dissolved total nitrogen, dissolved total phosphorus, and dissolved silicon. Phytoplankton samples should include: phytoplankton species count, cell density, and biomass.

[0044] S1.2: Collect phytoplankton samples from each sampling point in the study area and send them to the laboratory for measurement;

[0045] S1.3: Based on laboratory measurements of phytoplankton samples, calculate the phytoplankton biomass, species richness, or species diversity index at each sampling point;

[0046] S1.4: Calculate the dominance of each species and select species with a dominance greater than 0.02 as representative species.

[0047] Step 2: Calculation of niche width and overlap of sampling points:

[0048] S2.1: For all sampling points in the study area, all water chemical indicators are divided into different concentration intervals; the concentration intervals of water chemical indicators are divided based on percentiles;

[0049] S2.2: Calculate the niche width of representative species under different water chemical element concentration gradients using the Levins formula;

[0050] S2.3: Calculate the niche overlap of representative species under different water chemical element concentration gradients using the Pianka overlap model;

[0051] S2.4: Calculate the niche width of each indicator at each sampling point based on the biomass proportion and niche width of the representative species at each sampling point;

[0052] S2.5: Calculate the niche overlap of each indicator at each sampling point based on the biomass proportion and niche overlap of representative species at each sampling point.

[0053] Step 3: Identify key environmental factors:

[0054] S3.1: Calculate the importance of each indicator using the random forest algorithm, using the water chemical element indicators and species richness or species diversity index calculated at each sampling point in step 1, and the niche width and niche overlap calculated at each sampling point in step 2.

[0055] The specific steps of the random forest algorithm calculation include:

[0056] The water chemical index, niche width and niche overlap of each sampling point were input as feature vector data, and species richness or species diversity index was input as target variable. The random forest algorithm was used to calculate the importance of each index through the increase of mean square error.

[0057] S3.2: Based on the importance of each indicator, key environmental factors are screened out; specifically, if the input target variable is an even number, the environmental indicators ranked in the top n / 2 (including n / 2) in importance are taken as key environmental factors; if the input target variable is an odd number, the environmental indicators ranked in the top (n+1) / 2 (including (n+1) / 2) in importance are taken as key environmental factors.

[0058] Step 4, ecological environment zoning:

[0059] S4.1: Use the key environmental factors and species richness or species diversity index identified in step 3 as feature vectors, calculate the silhouette coefficients for different cluster numbers, and select the cluster number with the highest silhouette coefficient as the cluster number with the best clustering effect;

[0060] S4.2: Perform clustering using the unsupervised learning K-means algorithm or hierarchical clustering method to complete the ecological and environmental zoning of the study area.

[0061] Application examples:

[0062] The upper Yangtze River Basin is located at 90°13′~111°30′E, 24°37′~35°54′N, from the eastern part of the Qinghai-Tibet Plateau to Yichang, Hubei Province, with an area of 1.006×10 6 km 2 The upper reaches of the Yangtze River cover approximately 55.9% of the total area of the Yangtze River Basin, are approximately 4,500 km long, or 71.4% of the total length of the basin, and have a total drop of over 5,100 meters, representing 95% of the total drop of the Yangtze River. The upper reaches of the Yangtze River Basin possess significant ecological diversity and uniqueness, complex hydrological and geographical characteristics, and significant ecological and environmental protection needs. The upper reaches of the Yangtze River are used as an example to illustrate this invention, which is quite representative.

[0063] Step 1: Measure environmental factors and phytoplankton community data in the upper reaches of the Yangtze River:

[0064] (1) The basin survey was mainly carried out in the upper reaches of the main stream, and sampling points were set up under the key power station dams. Considering that tributaries are also important sources of nutrients, some larger tributaries in the upper reaches of the Yangtze River were also surveyed, such as Dingqu, Yalong River, Hengjiang River, Minjiang River and Chishui River, and sampling points were also set up at their confluences with the main stream ( Figure 2 ).

[0065] (2) Water samples were collected on-site at each selected sampling point and sent to the laboratory for measurement and analysis. The measurement indicators included dissolved oxygen (DO), pH, water temperature (WT), total carbon (TC), dissolved organic carbon (DOC), total nitrogen (TN), dissolved total nitrogen (DTN), total phosphorus (TP), dissolved total phosphorus (DTP), total silicon (TSi), dissolved silicon (DSi), and the number of phytoplankton species, cell density, and biomass.

[0066] (3) The dominance of each species was calculated using the Mcnaughton dominance index (Y), as shown in Table 1. Species with a dominance greater than 0.02 were selected as representative species. A total of 10 dominant species with a dominance greater than 0.02 were selected, as shown in Table 2.

[0067] Table 1 Calculated dominance of phytoplankton in the example area

[0068]

[0069]

[0070] Table 2 Representative species screened

[0071]

[0072] Step 2: Calculation of niche width and overlap of sampling points

[0073] (1) For all sampling points in the study area, all water chemical element indicators were divided into five concentration intervals based on percentiles;

[0074] (2) The niche widths of 10 representative species under different concentration gradients of water chemical elements were calculated using the Levins formula based on the concentration gradients of 11 water chemical indicators, as shown in Table 3.

[0075] Table 3 Niche breadth results of representative species in 11 water chemical indicators

[0076]

[0077] (3) The Pianka overlap model was used to calculate the niche overlap of 10 representative species with other species under different concentration gradients of water chemical elements based on the concentration gradients of different indicators, as shown in Table 4.

[0078] Table 4 Niche overlap results of representative species in 11 water chemical indicators

[0079]

[0080] (4) Based on the biomass proportion of each phytoplankton at each sampling point, the proportion of each representative phytoplankton species in the total representative species was multiplied by the proportion of the species at each sampling point and then added together. Finally, the weighted niche width and niche overlap of the 26 sampling points were calculated ( Figure 3 ).

[0081] Step 3: Identify key environmental factors in the upper Yangtze River

[0082] (1) Eleven water chemical indices (dissolved oxygen (DO), pH, water temperature (WT), total carbon (TC), dissolved organic carbon (DOC), total nitrogen (TN), dissolved total nitrogen (DTN), total phosphorus (TP), dissolved total phosphorus (DTP), total silica (TSi), and dissolved silica (DSi)) from 26 sampling points, as well as niche breadth and niche overlap, were used as feature vectors, and species richness was used as the target vector to be input into the random forest model.

[0083] (2) The number of input target variables is 13, which is an odd number. The top seven environmental indicators ranked by importance are used as key environmental factors, namely water temperature (47.09), niche breadth (39.33), niche overlap (21.47), pH (17.90), dissolved total nitrogen (9.33), total nitrogen (8.05), and total phosphorus (6.41) ( Figure 4 ).

[0084] Step 4: Ecological and environmental zoning of the upper reaches of the Yangtze River

[0085] (1) The clustering results of different cluster numbers are calculated by unsupervised machine learning hierarchical clustering. When the number of clusters is 3, the clustering effect is the best ( Figure 5 ).

[0086] (2) Based on the setting of cluster number 3, the 26 sampling points in the upper reaches of the Yangtze River were clustered by unsupervised machine learning hierarchical clustering. The results showed that the 26 sampling points were divided into three clusters, containing 5, 6 and 15 sampling points respectively. The points of cluster 1 were all distributed in the upper reaches of the Jinsha River, most of the points of cluster 2 were located in the middle and lower reaches of the Jinsha River, and the points of cluster 3 were mainly concentrated in other main and tributary areas of the upper reaches of the Yangtze River connected to the lower reaches of the Jinsha River ( Figure 6Cluster 1, Cluster 2, and Cluster 3 are geographically located in the upper, middle, and lower reaches of the sample area, respectively. The characteristics of the upstream area include high pH, low water temperature (WT), medium-high concentrations of total nitrogen (TN), dissolved total nitrogen (DTN), and total phosphorus (TP), low levels of niche breadth (Breadth), niche overlap (Overlap), and species richness (Richness). The characteristics of the midstream area include medium pH and water temperature (WT), low concentrations of total nitrogen (TN), dissolved total nitrogen (DTN), and total phosphorus (TP), medium-high levels of niche breadth (Breadth) and overlap (Overlap), and low species richness (Richness). The downstream area exhibits low pH, high water temperature (WT), high concentrations of total nitrogen (TN) and dissolved total nitrogen (DTN), medium-high concentrations of total phosphorus (TP), high levels of niche breadth (Breadth) and niche overlap (Overlap), and medium levels of species richness (Richness). These conclusions provide a theoretical basis for the protection of phytoplankton communities and the management of water ecosystems in the upper reaches of the Yangtze River, and are of great reference value, especially in formulating targeted protection and restoration measures.

[0087] Finally, it should be noted that the above is only used to illustrate the technical solution of the present invention and is not limiting. Although the present invention is described in detail with reference to the preferred arrangement scheme, ordinary technicians in this field should understand that the technical solution of the present invention (such as the application of various formulas, the sequence of steps, etc.) can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. An ecological intelligent zoning method that integrates ecological niche theory and machine learning, characterized by: The method comprises the following steps: Step 1: Measurement of environmental factors and phytoplankton community data: S1.1: Determine the study area and sampling points, collect water chemical element samples at each sampling point, and send them to the laboratory for measurement; S1.2: Collect phytoplankton samples from each sampling point in the study area and send them to the laboratory for measurement; S1.3: Based on laboratory measurements of phytoplankton samples, calculate the phytoplankton biomass, species richness, or species diversity index at each sampling point; S1.4: Calculate the dominance of each species and select species with a dominance greater than 0.02 as representative species; Step 2: Calculation of niche width and overlap of sampling points: S2.1: For all sampling points in the study area, different concentration ranges are divided based on all water chemical element indicators; S2.2: Calculate the niche width of representative species under different water chemical element concentration gradients using the Levins formula; S2.3: Calculate the niche overlap of representative species under different water chemical element concentration gradients using the Pianka overlap model; S2.4: Calculate the niche width of each indicator at each sampling point based on the biomass proportion and niche width of the representative species at each sampling point; S2.5: Calculate the niche overlap of each indicator at each sampling site based on the biomass proportion and niche overlap of representative species at each sampling site; Step 3: Identify key environmental factors: S3.1: Calculate the importance of each indicator using the random forest algorithm, using the water chemical index and species richness or diversity index calculated at each sampling point in step 1, and the niche breadth and niche overlap calculated at each sampling point in step 2; S3.2: Screen out key environmental factors based on the importance of each indicator; Step 4, ecological environment zoning: S4.1: Use the key environmental factors and species richness or species diversity index identified in step 3 as feature vectors, calculate the silhouette coefficients for different cluster numbers, and select the cluster number with the highest silhouette coefficient as the cluster number with the best clustering effect; S4.2: Perform clustering using the unsupervised learning K-means algorithm or hierarchical clustering method to complete the ecological and environmental zoning of the study area.

2. The method according to claim 1, characterized in that In step 1, S1.1, the number of sampling points set is greater than 15. The water chemical element indicators measured in each water chemical element sample include: total nitrogen, total phosphorus, total carbon, total silicon, water temperature, pH, dissolved oxygen, dissolved organic carbon, dissolved total nitrogen, dissolved total phosphorus and dissolved silicon; the indicators measured in phytoplankton samples include: number of phytoplankton species, cell density and biomass.

3. The method according to claim 1, characterized in that In step 2, S2.1, the concentration ranges of water chemical element indicators are divided based on percentiles.

4. The method according to claim 1, wherein In step 3 S3.1, the specific steps of the random forest algorithm calculation include: The water chemical index, niche width and niche overlap of each sampling point were input as feature vector data, and species richness or species diversity index was input as target variable. The random forest algorithm was used to calculate the importance of each index through the increase of mean square error.

5. The method according to claim 1, wherein In step 3, 3.2, if the input target variable is an even number, the environmental indicators ranked first n / 2 in importance are used as key environmental factors; if the input target variable is an odd number, the environmental indicators ranked first (n+1) / 2 in importance are used as key environmental factors.

Images