Seaweed bearable capacity intelligent evaluation method and system based on data analysis

Abstract

The invention relates to the technical field of data processing, and discloses a method and a system for intelligently evaluating the bearable capacity of algae based on data analysis. The method comprises the following steps: acquiring environmental parameters of a seaweed culture area through a multi-layer sensor, and obtaining a standardized data set by using an abnormal value detection algorithm; dividing the breeding area into environment layering sub-areas by adopting a clustering algorithm; training the relationship between the environment and the bearing capacity by using a machine learning algorithm to obtain regionalized prediction data; calculating ecological, economic and social three-dimensional indexes, and establishing a sustainable evaluation index system; and constructing a neural network model, and outputting an intelligent evaluation value of the alga bearable capacity. According to the method, the problems of insufficient multi-dimensional data processing capability and lack of regional differentiation assessment in an existing alga bearing capacity assessment method are solved, and the accuracy and the intelligent level of alga bearing capacity assessment are improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and system for intelligently evaluating the carrying capacity of seaweed based on data analysis. Background Art

[0002] With the rapid development of the marine economy, seaweed aquaculture, a key marine industry, continues to expand. Traditional methods for assessing seaweed carrying capacity rely primarily on manual sampling and laboratory analysis. These methods regularly collect seawater and seaweed samples for physical and chemical analysis, combined with simple biological models to calculate the maximum aquaculture capacity of an area. Several data-based assessment methods have also emerged. These employ single environmental parameter monitoring and linear regression models to predict seaweed carrying capacity. Sensors collect basic environmental data such as water temperature and salinity, and statistical methods are used to model the relationship between environmental factors and seaweed growth.

[0003] However, existing data analysis methods have significant shortcomings: first, data collection lacks systematicity and real-time nature, and can only obtain environmental information in local areas, making it difficult to reflect the spatial heterogeneity and temporal dynamics of the marine environment; second, existing methods mainly use linear modeling approaches, which cannot effectively capture the complex nonlinear relationship between environmental factors and seaweed growth in marine ecosystems, and lack consideration of the differences in environmental characteristics of different sea areas; third, traditional assessment methods only focus on biological carrying capacity, ignoring the comprehensive impact of seaweed aquaculture on the ecological environment, economic benefits and social sustainability.

[0004] Based on the above analysis, we can see that the fundamental problem with existing technologies lies in the lack of intelligent processing capabilities for multidimensional environmental data and a mechanism for regionalized differential assessment. Due to the complexity of the marine environment and the multi-factor dependence of seaweed growth, simple linear models cannot accurately predict carrying capacity, and the lack of consideration of sustainability makes it difficult for assessment results to guide long-term aquaculture planning. More importantly, existing methods cannot effectively integrate indicators from multiple ecological, economic, and social dimensions, and lack intelligent nonlinear aggregation algorithms to handle the complex interactions between multidimensional indicators. This directly affects the accuracy and practicality of seaweed carrying capacity assessments. Summary of the Invention

[0005] The present application provides a method and system for intelligent assessment of seaweed carrying capacity based on data analysis, which is used to solve the problems of insufficient multi-dimensional data processing capabilities and lack of regional differentiated assessment in existing seaweed carrying capacity assessment methods, and improves the accuracy and intelligence level of seaweed carrying capacity assessment.

[0006] In a first aspect, the present application provides a method for intelligently assessing the carrying capacity of seaweed based on data analysis, the method comprising: Step S1: collect water temperature, salinity, dissolved oxygen concentration, light intensity, and nutrient concentration in the seaweed cultivation area through a multi-level sensor network, and use an outlier detection algorithm to remove abnormal data points to obtain a standardized marine environment data set; Step S2: input the standardized marine environment data set into a clustering algorithm, and divide the aquaculture area into several sub-areas according to the similarity of environmental parameters to form environmental stratified sub-areas; Step S3: collecting seaweed growth rate and biomass data for each of the environmental stratification sub-regions, using a machine learning algorithm to train the relationship between environmental parameters and seaweed carrying capacity, and obtaining regionalized carrying capacity prediction data; Step S4: Calculate the ecological environmental impact index, economic benefit index, and social sustainability index respectively, use the analytic hierarchy process to determine the weight coefficient of each dimension, and establish a multi-dimensional sustainability evaluation index system; Step S5: construct a neural network model, use the multi-dimensional sustainability assessment index system and the regionalized carrying capacity prediction data as input features, and output an intelligent assessment value of the seaweed carrying capacity.

[0007] In a second aspect, the present application provides a seaweed carrying capacity intelligent assessment system based on data analysis, the seaweed carrying capacity intelligent assessment system based on data analysis comprising: The elimination module is used to collect water temperature, salinity, dissolved oxygen concentration, light intensity and nutrient concentration in the seaweed cultivation area through a multi-level sensor network, and use the outlier detection algorithm to eliminate abnormal data points to obtain a standardized marine environment data set; An input module is used to input the standardized marine environment data set into a clustering algorithm, and divide the aquaculture area into several sub-areas according to the similarity of environmental parameters to form environmental stratified sub-areas; a training module for collecting seaweed growth rate and biomass data for each of the environmental stratification sub-regions, using a machine learning algorithm to train the relationship between environmental parameters and seaweed carrying capacity, and obtaining regionalized carrying capacity prediction data; Establish modules to calculate the ecological and environmental impact index, economic benefit index, and social sustainability index respectively, use the analytic hierarchy process to determine the weight coefficients of each dimension, and establish a multi-dimensional sustainability evaluation indicator system; The output module is used to construct a neural network model, take the multi-dimensional sustainability assessment index system and the regionalized carrying capacity prediction data as input features, and output an intelligent assessment value of the seaweed carrying capacity.

[0008] In a third aspect, a device for intelligently assessing the carrying capacity of seaweed based on data analysis is provided, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the device for intelligently assessing the carrying capacity of seaweed based on data analysis executes the above-mentioned method for intelligently assessing the carrying capacity of seaweed based on data analysis.

[0009] In a fourth aspect, a computer-readable storage medium is provided, wherein instructions are stored in the computer-readable storage medium. When the computer-readable storage medium is executed, the computer executes the above-mentioned method for intelligently assessing the carrying capacity of seaweed based on data analysis.

[0010] In the technical solution provided by this application, multi-dimensional environmental parameters such as water temperature, salinity, dissolved oxygen concentration, light intensity and nutrient concentration in the seaweed cultivation area are collected through a multi-level sensor network, and abnormal data points are eliminated by combining an outlier detection algorithm to ensure the comprehensiveness and accuracy of data collection, providing a high-quality data foundation for subsequent analysis. A clustering algorithm is used to divide the cultivation area into environmental stratification sub-areas according to the similarity of environmental parameters, which effectively solves the problem of spatial heterogeneity of the marine environment and enables areas with different environmental characteristics to be differentiated and accurately assessed. By training the relationship between environmental parameters and seaweed carrying capacity through machine learning algorithms, an intelligent prediction model is constructed, which can better capture the complex nonlinear relationship between environmental factors and seaweed growth than traditional linear modeling methods. The established multi-dimensional sustainability assessment index system covers the ecological environmental impact index, economic benefit index and social sustainability index. The hierarchical analysis method is used to determine the weight coefficients of each dimension, realizing the transition from a single biological carrying capacity to a comprehensive sustainability assessment, providing a more comprehensive decision-making basis for the scientific planning of seaweed cultivation.

[0011] The construction of the neural network model fully leverages its technical advantages in processing multi-dimensional nonlinear data. It uses a multi-dimensional sustainability assessment indicator system and regional carrying capacity prediction data as input features. Through nonlinear transformation and weight learning of multiple layers of neurons, it can automatically identify complex interaction patterns and potential correlations between indicators. Compared with traditional linear weighted aggregation methods, neural network algorithms can effectively handle pairwise interactions and high-order nonlinear relationships between indicators, avoiding information loss and evaluation bias caused by simple weighted summation. Especially in the specific application field of intelligent assessment of seaweed carrying capacity, the adaptive learning ability of neural networks enables it to automatically adjust model parameters according to the environmental characteristics and historical data of different sea areas, realize personalized carrying capacity predictions, and significantly improve the accuracy and reliability of assessment results. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 This is a schematic diagram of an embodiment of a method for intelligently evaluating the carrying capacity of seaweed based on data analysis in an embodiment of the present application; Figure 2 This is a graph showing the clustering effect evaluation results under different K values ​​in the embodiment of this application; Figure 3 This is a flowchart of a visualization scheme for a multi-dimensional indicator system for evaluating the sustainability of seaweed farming in an embodiment of the present application; Figure 4 This is a schematic diagram of an embodiment of a seaweed carrying capacity intelligent assessment system based on data analysis in an embodiment of the present application; Figure 5 It is a schematic block diagram of the structure of the seaweed carrying capacity intelligent assessment device based on data analysis in an embodiment of the present invention. DETAILED DESCRIPTION

[0014] The embodiments of the present application provide a method and system for intelligently assessing the carrying capacity of seaweed based on data analysis. The terms "first," "second," "third," "fourth," and so forth (if any) in the specification and claims of this application and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. Furthermore, the terms "including," "comprising," "having," and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, product, or apparatus.

[0015] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 In the embodiments of the present application, an embodiment of the method for intelligently evaluating the carrying capacity of seaweed based on data analysis includes: Step S1: collect water temperature, salinity, dissolved oxygen concentration, light intensity, and nutrient concentration in the seaweed cultivation area through a multi-level sensor network, and use an outlier detection algorithm to remove abnormal data points to obtain a standardized marine environment data set; Step S2: input the standardized marine environmental data set into the clustering algorithm, and divide the aquaculture area into several sub-areas according to the similarity of environmental parameters to form environmental stratified sub-areas; Step S3: Collect seaweed growth rate and biomass data for each environmental stratification sub-region, use machine learning algorithms to train the relationship between environmental parameters and seaweed carrying capacity, and obtain regionalized carrying capacity prediction data; Step S4: Calculate the ecological environmental impact index, economic benefit index, and social sustainability index respectively, use the analytic hierarchy process to determine the weight coefficient of each dimension, and establish a multi-dimensional sustainability evaluation index system; Step S5: Construct a neural network model, take the multi-dimensional sustainability assessment index system and regional carrying capacity prediction data as input features, and output the intelligent assessment value of seaweed carrying capacity.

[0016] It is understandable that the execution subject of this application can be the seaweed carrying capacity intelligent assessment system based on data analysis, or a terminal or a server, which is not limited here. The embodiment of this application is described by taking the server as the execution subject as an example.

[0017] Specifically, the water temperature, salinity, dissolved oxygen concentration, light intensity and nutrient concentration of the seaweed cultivation area are collected through a multi-level sensor network, and the outlier detection algorithm is used to eliminate abnormal data points to obtain a standardized marine environmental data set; the standardized marine environmental data set is then input into the clustering algorithm, and the cultivation area is divided into several sub-areas according to the similarity of environmental parameters to form environmental stratification sub-areas; on this basis, seaweed growth rate and biomass data are collected for each environmental stratification sub-area, and the relationship between environmental parameters and seaweed carrying capacity is trained using a machine learning algorithm to obtain regionalized carrying capacity prediction data; then the ecological environmental impact index, economic benefit index and social sustainability index are calculated respectively, and the hierarchical analysis method is used to determine the weight coefficient of each dimension to establish a multi-dimensional sustainability evaluation index system; a neural network model is constructed, and the multi-dimensional sustainability evaluation index system and regionalized carrying capacity prediction data are used as input features to output an intelligent evaluation value of seaweed carrying capacity.

[0018] In a specific embodiment, step S1 further includes: Water temperature, salinity, dissolved oxygen concentration, light intensity, and nutrient concentration are collected through a sensor array, and the collected data are sorted according to timestamps to obtain time-series environmental parameter data; The mean and standard deviation of the time-series environmental parameter data were calculated based on the 3σ criterion, and data points that deviated from the mean by more than three times the standard deviation were eliminated to obtain the environmental parameter data after cleaning; The environmental parameter data after cleaning is processed using the minimum-maximum normalization algorithm to convert the numerical range to the range of 0 to 1 to obtain normalized environmental parameter data; The integrity of the normalized environmental parameter data was checked, and the data integrity rate and precision error rate were calculated to obtain a standardized marine environmental data set.

[0019] Specifically, a sensor array collects water temperature, salinity, dissolved oxygen concentration, light intensity, and nutrient concentration. The collected data is sorted by timestamp to generate time-series environmental parameter data. Based on this, the mean and standard deviation of the time-series environmental parameter data are calculated using the 3σ criterion. Data points that deviate from the mean by more than three standard deviations are removed to obtain cleaned environmental parameter data. The cleaned environmental parameter data are processed using a minimum-maximum normalization algorithm, converting the numerical range to the range of 0 to 1 to obtain normalized environmental parameter data. After data normalization, the normalized environmental parameter data is subjected to an integrity check, and the data integrity rate and precision error rate are calculated to obtain a standardized marine environmental dataset. This process effectively ensures the accuracy and consistency of the data, providing a reliable data foundation for subsequent analysis and modeling. This step ensures that the collected environmental data is not only time-series-based but also effectively removes outliers, thereby improving the accuracy of subsequent analysis and prediction results.

[0020] For example, a sensor array can be used to collect water temperature data from a seaweed cultivation area. Suppose the water temperature data for a particular area at specific time points is: 22.5°C, 23.1°C, 22.8°C, 23.0°C, 25.5°C, 22.7°C, and 23.3°C. Because the fifth data point (25.5°C) deviates significantly from the other data points, a calculation based on the 3σ criterion indicates that its deviation exceeds three standard deviations and is therefore removed, resulting in a cleaned water temperature dataset.

[0021] When performing a completeness check on the normalized data, assume that the light intensity data was missing data at certain time points. By calculating the data completeness rate, assuming it is 85%, the missing data percentage is 15%. Furthermore, by calculating the precision error rate, we conclude that the error rate for this dataset is 3.5%. These test results will further influence the construction of the standardized dataset.

[0022] In a specific embodiment, step S2 further includes: Principal component analysis was performed on the standardized marine environment dataset to extract the principal components with a cumulative contribution rate of 85% and obtain the dimension-reduced feature vector. The reduced-dimensional feature vector is input into the K-means++ clustering algorithm, and the optimal number of clusters is determined by the silhouette coefficient method and the elbow rule to obtain the clustering parameter configuration; Based on the clustering parameter configuration, iterative clustering calculation is performed on the breeding areas, and the Euclidean distance is used as the similarity metric to obtain the regional clustering results; The regional clustering results were validated, and the coefficient of variation of environmental parameters in each sub-region and the ratio of the within-class sum of squares to the between-class sum of squares were calculated to obtain the environmental stratification sub-regions.

[0023] Specifically, principal component analysis (PCA) was performed on a standardized marine environmental dataset. The variance contribution of each principal component was calculated, and the principal component with a cumulative contribution of 85% was extracted to generate a reduced-dimensionality feature vector. This step effectively reduced the data dimensionality while retaining key environmental information and reducing computational complexity. These reduced-dimensionality feature vectors were then input into the K-means++ clustering algorithm, where the optimal number of clusters was determined using the silhouette coefficient method and the elbow rule. The silhouette coefficient method evaluated clustering quality by calculating the similarity of each data point with other points in the same cluster and with the nearest different cluster. The elbow rule determined the optimal number of clusters by plotting the relationship between the number of clusters and the within-cluster sum of squares. Once the number of clusters was determined, iterative clustering was performed on the aquaculture areas based on these clustering parameter configurations, using Euclidean distance as the similarity metric to generate clusters of multiple environmentally similar areas. Next, the validity of these regional clustering results was verified by calculating the coefficient of variation of the environmental parameters within each sub-area to determine the consistency within the sub-area. The effectiveness of the clustering was also assessed by calculating the ratio of the within-cluster sum of squares to the between-cluster sum of squares. This ensured that the environmental characteristics of each subregion were distinct, with small intra-cluster differences and large inter-cluster differences. These validations yielded environmental stratification subregions, providing clear regional delineation for subsequent seaweed growth prediction and carrying capacity assessment.

[0024] When performing principal component analysis on a standardized marine environmental dataset, assume that the original dataset contains multiple environmental parameters such as water temperature, salinity, and dissolved oxygen concentration. Calculations show that water temperature contributes 30% to the variance, salinity 25%, and dissolved oxygen concentration 20%, with other parameters contributing less. The principal component with a cumulative contribution of 85% is extracted, retaining the three principal components of water temperature, salinity, and dissolved oxygen concentration to obtain the dimensionality-reduced feature vector. This condenses the originally multi-dimensional environmental data into these three dimensions. In the application of the K-means++ clustering algorithm, assume that during the clustering process, the silhouette coefficient method is used to calculate the scores for different numbers of clusters. The results show that the silhouette coefficient is maximized when the number of clusters is 4, indicating the best clustering effect. Next, using the elbow rule, a curve is plotted showing the relationship between the number of clusters and the within-cluster sum of squares. The inflection point of the curve occurs at K = 4, so the number of clusters is selected as 4. This clustering parameter configuration provides a basis for subsequent regionalization.

[0025] For example, when calculating regional clusters, using Euclidean distance as a similarity metric, assume that in a specific region, the Euclidean distance calculated for parameters such as water temperature, salinity, and dissolved oxygen concentration is small, indicating that the environmental conditions in that region are highly similar to those in other regions. Therefore, these regions are grouped together into the same cluster, forming sub-regions with similar environmental characteristics.

[0026] In a specific embodiment, the step of inputting the reduced-dimensional feature vector into the K-means++ clustering algorithm, determining the optimal number of clusters by the silhouette coefficient method and the elbow rule, and obtaining the clustering parameter configuration may specifically include the following steps: The number of clusters K is set to range from 3 to 8, and clustering calculations with different K values ​​are performed on the reduced-dimensional feature vectors to obtain multiple clustering schemes; Based on the silhouette coefficient method, the average distance of each sample point to other points of the same category and the average distance to the nearest point of a different category in each clustering scheme are calculated to obtain the silhouette coefficient matrix; The elbow rule is used to calculate the intra-class sum of squares of each clustering scheme, and the relationship curve between K value and intra-class sum of squares is plotted. The inflection point of the curve is determined to obtain the candidate optimal K value. The silhouette coefficient matrix and the candidate optimal K value are comprehensively evaluated, and the K value with the largest silhouette coefficient and located near the inflection point is selected as the final number of clusters to obtain the clustering parameter configuration.

[0027] Specifically, the number of clusters, K, is set between 3 and 8. First, the reduced feature vectors are clustered using multiple sets of different K values ​​to generate multiple clustering schemes. Each scheme is then evaluated for different K values, ranging from 3 to 8, and the results for each clustering scheme are calculated. During this calculation, the silhouette coefficient method is used to evaluate the average distance of each sample point to other points in the same category and to the nearest point in a different category, resulting in a silhouette coefficient matrix. A larger silhouette coefficient indicates a better clustering effect. Therefore, by comparing silhouette coefficient values ​​for different K values, the clustering quality of each scheme can be effectively evaluated. The elbow rule is then used to calculate the within-class sum of squares for each clustering scheme, and a curve is plotted against the K value. By observing the changes in the curve, the inflection point corresponding to the K value is determined. The candidate optimal K value is the K value at the inflection point, i.e., the point where the within-class sum of squares decreases the most. At this point, the candidate optimal K value is essentially determined. Finally, by comprehensively evaluating the silhouette coefficient matrix and candidate optimal K values, the K value with the largest silhouette coefficient and located near the inflection point is selected as the final number of clusters to ensure clustering quality and accuracy. Through these steps, the optimal clustering parameter configuration is ultimately obtained, providing an accurate basis for subsequent environmental stratification and data analysis.

[0028] In one embodiment, the number of clusters, K, is set to a range of 3 to 8. Assume that the reduced eigenvectors represent environmental data for seaweed aquaculture areas, including water temperature, salinity, and dissolved oxygen concentration. K-means++ clustering calculations yield multiple clustering schemes. For example, when K = 3, the clustering results show that the aquaculture areas are divided into three main categories, with significant differences in water temperature and salinity, while dissolved oxygen concentration varies less across categories. When K = 5, the clustering results reveal more subdivided areas, with more uniform environmental characteristics within each area.

[0029] In another embodiment, the silhouette coefficient of each clustering scheme is calculated based on the silhouette coefficient method. Assume that when K=4, the silhouette coefficient of a sub-region is 0.85, indicating that the clustering effect of the region is good. When K=6, the silhouette coefficient drops to 0.68, indicating that the clustering effect has declined. By comparing the silhouette coefficients under different K values, it is possible to clearly determine which K value corresponds to the best clustering effect. Figure 2 ,This figure shows the clustering effect evaluation under different K values.

[0030] In a specific embodiment, step S3 further includes: Biomass monitoring equipment is deployed in each environmental stratification sub-region to collect seaweed growth rate and biomass density data. The collected data are classified and labeled according to the sub-region number to obtain regional seaweed biological data; The regional algae biological data are correlated and matched with the environmental parameter data of the corresponding sub-regions to construct a paired dataset of environmental parameter-biomass and obtain a training sample dataset; The training sample data set is divided into a training set and a test set in a ratio of 7 to 3. The random forest algorithm is used to train the model on the training set to obtain the environment-carrying capacity mapping model. Based on the environment-carrying capacity mapping model, the carrying capacity of each environmental stratified sub-region is predicted and calculated, and the maximum carrying capacity value of each sub-region is output to obtain regional carrying capacity prediction data.

[0031] Specifically, biomass monitoring equipment was deployed in each environmental stratification sub-region, collecting data on seaweed growth rate and biomass density. For example, in one sub-region, the monitoring equipment recorded environmental data such as water temperature and light intensity, and also measured a seaweed growth rate of 0.15 cm / day and a biomass density of 5 g / m². The collected data was categorized and labeled according to the sub-region number, resulting in a seaweed biomass dataset for each sub-region. These sub-regional seaweed biomass data were correlated and matched with the corresponding sub-region's environmental parameter data to construct a paired dataset between environmental parameters and biomass, thus generating a training sample dataset. This data provided the foundation for subsequent model training. The training sample dataset was divided into training and test sets in a 7:3 ratio, with 70% of the data used for model training and 30% for testing and verifying the model's accuracy. A random forest algorithm was used to train the model on the training set. During the training process, an ensemble of multiple decision trees was used to develop a mapping model between the environment and seaweed carrying capacity. This model effectively captures the influence of environmental parameters on seaweed growth and predicts carrying capacity under different environmental conditions. Based on this mapping model, carrying capacity predictions were calculated for each environmental stratification sub-region, yielding the maximum carrying capacity for each sub-region. For example, in one sub-region, the model predicted a maximum carrying capacity of 3,000 kg / ha. The carrying capacities of other sub-regions were calculated and output accordingly, resulting in regionalized carrying capacity predictions, providing a scientific basis for further aquaculture optimization.

[0032] For example, when deploying biomass monitoring equipment, assume that in a certain environmental stratification sub-area, the equipment records a water temperature of 24°C, a light intensity of 1500 lux, an algae growth rate of 0.2 cm / day, and a biomass density of 8 g / m². Based on the collected data, after classifying and labeling it, the algae biomass data for that sub-area is obtained. This data is then matched with the environmental parameters of that sub-area, such as water temperature, dissolved oxygen concentration, and salinity, to construct a paired dataset of environmental parameters and biomass. For example, the environmental parameters in a dataset are a water temperature of 25°C, a dissolved oxygen concentration of 8 mg / L, and a biomass density of 7 g / m². These data are used as input for training the model.

[0033] In another example, assume that a training sample dataset contains 1,000 sample points, 70% of which is used for training, and the remaining 30% is used as a test set. The training set includes biomass data under different environmental parameters, such as water temperature ranging from 22°C to 30°C and salinity ranging from 10 ppt to 35 ppt. The training dataset is 700 data points in size. A random forest algorithm is used to train a model on the training set. By integrating multiple decision trees, the relationship between environmental parameters and biomass density is fitted, ultimately generating a mapping model between environmental parameters and carrying capacity. Based on this model, it is assumed that for a certain sub-area, the maximum carrying capacity is predicted to be 3,500 kg / ha, reflecting the maximum algae growth that the area can support under current environmental conditions. In this way, predicted carrying capacity data for each sub-area is obtained.

[0034] In a specific embodiment, step S4 further includes: The ecological environment impact index was calculated based on the ratio of water pollutant concentration to the environmental quality standard limit, and the Shannon-Wiener index was used to assess biodiversity impact to obtain ecological environment dimension indicators; The output value per unit area is calculated by multiplying the seaweed output by the market price minus the production cost, and the return on investment is calculated based on the ratio of annual net income to total investment to obtain the economic benefit dimension indicator; The employment contribution is calculated by the ratio of the number of jobs created to the total employed population in the region, and the industry driving effect is calculated using the input-output multiplier method to obtain the social sustainability dimension indicator; The ecological environment dimension indicators, economic benefit dimension indicators and social sustainability dimension indicators are input into the hierarchical analysis method for weight distribution calculation, and a judgment matrix is ​​constructed and consistency test is performed to obtain a multi-dimensional sustainability evaluation index system. Figure 3 ,This figure shows the process of visualizing the multi-dimensional indicator system for the sustainability assessment of seaweed farming.

[0035] Specifically, the Ecological and Environmental Impact Index (EIA) is calculated based on the ratio of water pollutant concentration to the environmental quality standard limit. For example, assuming the water pollutant concentration in a seaweed aquaculture area is 30 mg / L and the environmental quality standard limit is 40 mg / L, the ratio is 0.75. Based on this ratio, the EIA for that area is 0.75, indicating that the water quality is close to the standard limit. Subsequently, the Shannon-Wiener index is used to assess biodiversity impacts. Assuming the biodiversity index for that area is 3.2, a comprehensive indicator for the EIA dimension is further calculated, ultimately yielding an assessment of the EIA for that area. In the economic benefit assessment, the per-unit-area output value is calculated by multiplying the seaweed yield by the market price, minus the production cost. For example, if the annual seaweed yield in a certain area is 5,000 kg / ha, the market price is 10 yuan / kg, and the production cost is 3,000 yuan / ha, the per-unit-area output value is 5,000 × 10 - 3,000 = 20,000 yuan / ha. Next, the return on investment is calculated based on the ratio of annual net income to total investment. Assuming the region's annual net income is 10,000 yuan and the total investment is 50,000 yuan, the return on investment is 10,000 yuan / 50,000 yuan = 0.2, which means a 20% return on investment. Combining these data yields an assessment of the region's economic benefits.

[0036] In the social sustainability assessment, the employment contribution is calculated by the ratio of jobs created to the region's total employed population. For example, if a region creates 50 jobs and has a total employed population of 1,000, the employment contribution is 50 / 1,000 = 0.05. Furthermore, the input-output multiplier method is used to calculate the industry driving effect. Assuming the industry driving effect for this region is 1.8, this is combined with the employment contribution to determine the region's social sustainability assessment value. Indicators for the ecological environment, economic benefits, and social sustainability dimensions are input into the analytic hierarchy process to calculate weights. By constructing a judgment matrix and performing a consistency test, weight coefficients for each dimension are determined, ultimately forming a multidimensional sustainability assessment indicator system to ensure the rationality and consistency of each indicator in the overall assessment. This comprehensive assessment system provides a comprehensive decision-making basis for the sustainable development of seaweed aquaculture.

[0037] In a specific embodiment, step S5 further includes: Design a three-layer feedforward neural network architecture, use the various dimensional indicators in the multi-dimensional sustainability assessment indicator system as input layer nodes, set the number of hidden layer neurons, and obtain the neural network structure configuration; The multi-dimensional sustainability assessment indicator system and regional carrying capacity prediction data are combined to construct a neural network training dataset, and the interaction feature terms between the indicators are added as supplementary input to obtain an extended feature dataset. The Adam optimization algorithm is used to train the neural network, the learning rate and batch size parameters are set, and the network weights and biases are updated through the back-propagation algorithm to obtain the trained neural network model; The sustainability indicator data of the area to be assessed is input into the trained neural network model for forward calculation, and processed through the output layer activation function to obtain the intelligent assessment value of the seaweed carrying capacity.

[0038] Specifically, a three-layer feedforward neural network architecture is designed, each dimension indicator in the multi-dimensional sustainability evaluation index system is used as the input layer node, and the number of hidden layer neurons is set to obtain the neural network structure configuration. Assume that the input layer is: , where each Represents evaluation indicators of different dimensions, and is the number of dimensions of the input features. Set the number of hidden layer neurons to , the output layer is the intelligent evaluation value of the seaweed carrying capacity.

[0039] The multi-dimensional sustainability assessment index system and regional carrying capacity prediction data are combined to construct a neural network training dataset, and the interactive feature items between the indicators are added as supplementary input to obtain an extended feature dataset. ,in is the interaction feature term between indicators. The input dimension of the neural network is Increase to .

[0040] During the training process, the Adam optimization algorithm is used to train the neural network, and the optimization goal is to minimize the loss. , the loss function is often expressed by mean square error (MSE), that is: ,in is the number of training samples, is the actual value of the training sample, is the value predicted by the model. The Adam optimization algorithm adjusts the weights of the network and bias To minimize the loss function. At each iteration, the back propagation algorithm is used to update the weights and biases. The formula is: ,in is the current weight, is the updated weight, is the learning rate, and are the first-order moment estimate and the second-order moment estimate, respectively. A minimum value to prevent division by zero errors.

[0041] After the training is completed, the sustainability indicator data of the area to be evaluated is input into the trained neural network model for forward calculation. The forward propagation process can be expressed as: , , , , , ,in, is the weighted input of each layer, is the expanded input dataset, It is the weight matrix of the neural network, corresponding to the weights from the input layer to the first hidden layer, from the first hidden layer to the second hidden layer, and from the second hidden layer to the output layer. is the bias term, corresponding to the bias of each layer, is the activation value of each layer, Is the activation function, through the output layer activation function , and obtain the intelligent evaluation value of seaweed carrying capacity , which represents the output of the sustainability index of the area to be assessed in the neural network model.

[0042] Taking the assessment of seaweed carrying capacity as an example, a three-layer feedforward neural network architecture was designed. The input layer included various dimensional indicators from a multidimensional sustainability assessment indicator system, such as water temperature, light intensity, and nutrient concentration, assumed to be input features. The number of hidden layer neurons was set to 128, and the optimal neural network configuration was obtained through experimental tuning. The training dataset was obtained by combining the sustainability assessment indicator system with regionalized carrying capacity prediction data, adding interaction features between the indicators to create an extended feature dataset, thereby increasing the input dimensionality of the neural network. The neural network was trained using the Adam optimization algorithm, optimizing the model by minimizing the mean squared error (MSE) loss function. During training, the network weights and biases were continuously updated using a backpropagation algorithm until the loss function converged. After training, the sustainability indicator data for the region to be assessed was fed into the trained neural network model for forward computation. The model was processed through the activation function in the output layer, ultimately yielding an intelligent assessment value for the seaweed carrying capacity, which served as the predicted seaweed carrying capacity for the region under assessment.

[0043] The above describes the seaweed carrying capacity intelligent evaluation method based on data analysis in the embodiment of the present application. The following describes the seaweed carrying capacity intelligent evaluation system based on data analysis in the embodiment of the present application. Figure 4 In one embodiment of the present application, an intelligent evaluation system for seaweed carrying capacity based on data analysis includes: The elimination module is used to collect water temperature, salinity, dissolved oxygen concentration, light intensity and nutrient concentration in the seaweed cultivation area through a multi-level sensor network, and use the outlier detection algorithm to eliminate abnormal data points to obtain a standardized marine environment data set; An input module is used to input the standardized marine environment data set into a clustering algorithm, and divide the aquaculture area into several sub-areas according to the similarity of environmental parameters to form environmental stratified sub-areas; a training module for collecting seaweed growth rate and biomass data for each of the environmental stratification sub-regions, using a machine learning algorithm to train the relationship between environmental parameters and seaweed carrying capacity, and obtaining regionalized carrying capacity prediction data; Establish modules to calculate the ecological and environmental impact index, economic benefit index, and social sustainability index respectively, use the analytic hierarchy process to determine the weight coefficients of each dimension, and establish a multi-dimensional sustainability evaluation indicator system; The output module is used to construct a neural network model, take the multi-dimensional sustainability assessment index system and the regionalized carrying capacity prediction data as input features, and output an intelligent assessment value of the seaweed carrying capacity.

[0044] above Figure 4 The seaweed carrying capacity intelligent assessment system based on data analysis in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The seaweed carrying capacity intelligent assessment device based on data analysis in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0045] Reference Figure 5 In an embodiment of the present invention, there is also provided a device for intelligently evaluating the carrying capacity of seaweed based on data analysis. The device for intelligently evaluating the carrying capacity of seaweed based on data analysis may be a server, and its internal structure may be as follows: Figure 5 As shown. The seaweed carrying capacity intelligent assessment device based on data analysis includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the computer-designed processor is used to provide computing and control capabilities. The memory of the seaweed carrying capacity intelligent assessment device based on data analysis includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the seaweed carrying capacity intelligent assessment device based on data analysis is used to store the corresponding data in this embodiment. The network interface of the seaweed carrying capacity intelligent assessment device based on data analysis is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0046] Those skilled in the art will understand that Figure 5The structure shown in the figure is merely a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the intelligent assessment device for seaweed carrying capacity based on data analysis to which the solution of the present invention is applied.

[0047] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions. When the instructions are executed on a computer, the computer executes the steps of the method for intelligently assessing the carrying capacity of seaweed based on data analysis.

[0048] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0049] If the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a data-analysis-based intelligent seaweed carrying capacity assessment device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0050] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An intelligent evaluation method for seaweed carrying capacity based on data analysis, characterized in that: The method comprises: Step S1: collect water temperature, salinity, dissolved oxygen concentration, light intensity, and nutrient concentration in the seaweed cultivation area through a multi-level sensor network, and use an outlier detection algorithm to remove abnormal data points to obtain a standardized marine environment data set; Step S2: input the standardized marine environment data set into a clustering algorithm, and divide the aquaculture area into several sub-areas according to the similarity of environmental parameters to form environmental stratified sub-areas; Step S3: collecting seaweed growth rate and biomass data for each of the environmental stratification sub-regions, using a machine learning algorithm to train the relationship between environmental parameters and seaweed carrying capacity, and obtaining regionalized carrying capacity prediction data; Step S4: Calculate the ecological environmental impact index, economic benefit index, and social sustainability index respectively, use the analytic hierarchy process to determine the weight coefficient of each dimension, and establish a multi-dimensional sustainability evaluation index system; Step S5: construct a neural network model, use the multi-dimensional sustainability assessment index system and the regionalized carrying capacity prediction data as input features, and output an intelligent assessment value of the seaweed carrying capacity.

2. The method for intelligently assessing the carrying capacity of seaweed based on data analysis according to claim 1, characterized in that: The step S1 further comprises: Water temperature, salinity, dissolved oxygen concentration, light intensity, and nutrient concentration are collected through a sensor array, and the collected data are sorted according to timestamps to obtain time-series environmental parameter data; Calculate the mean and standard deviation of the time-series environmental parameter data based on the 3σ criterion, remove data points that deviate from the mean by more than three times the standard deviation, and obtain the environmental parameter data after cleaning; The post-cleaning environmental parameter data is processed using a minimum-maximum normalization algorithm to convert the numerical range to an interval of 0 to 1 to obtain normalized environmental parameter data; The normalized environmental parameter data is subjected to an integrity check, and the data integrity rate and precision error rate are calculated to obtain a standardized marine environmental data set.

3. The method for intelligently assessing the carrying capacity of seaweed based on data analysis according to claim 1, characterized in that: The step S2 further comprises: Performing principal component analysis on the standardized marine environment dataset, extracting principal components with a cumulative contribution rate of 85%, and obtaining a dimension-reduced feature vector; Input the reduced-dimensional feature vector into the K-means++ clustering algorithm, determine the optimal number of clusters by the silhouette coefficient method and the elbow rule, and obtain the clustering parameter configuration; Performing iterative clustering calculation on the breeding areas based on the clustering parameter configuration, using Euclidean distance as a similarity metric to obtain regional clustering results; The regional clustering results were validated, and the coefficient of variation of the environmental parameters in each sub-region and the ratio of the intra-class sum of squares to the inter-class sum of squares were calculated to obtain the environmental stratification sub-regions.

4. The method for intelligently assessing seaweed carrying capacity based on data analysis according to claim 3, characterized in that: The reduced dimension feature vector is input into the K-means++ clustering algorithm, and the optimal number of clusters is determined by the silhouette coefficient method and the elbow rule to obtain the clustering parameter configuration, including: The number of clusters K is set to a value range of 3 to 8, and clustering calculations with different K values ​​are performed on the reduced-dimensional feature vectors to obtain multiple clustering schemes; Calculate the average distance of each sample point from other points of the same category and the average distance from the nearest point of a different category in each clustering scheme based on the silhouette coefficient method to obtain a silhouette coefficient matrix; The elbow rule is used to calculate the intra-class sum of squares of each clustering scheme, and a relationship curve between the K value and the intra-class sum of squares is plotted to determine the inflection point of the curve to obtain the candidate optimal K value; The silhouette coefficient matrix and the candidate optimal K value are comprehensively evaluated, and the K value with the largest silhouette coefficient and located near the inflection point is selected as the final number of clusters to obtain the clustering parameter configuration.

5. The method for intelligently assessing seaweed carrying capacity based on data analysis according to claim 1, characterized in that: The step S3 further comprises: Deploying biomass monitoring equipment for each of the environmental stratification sub-regions to collect seaweed growth rate and biomass density data, classifying and labeling the collected data according to the sub-region number to obtain regional seaweed biological data; Correlating and matching the regional seaweed biological data with the environmental parameter data of the corresponding sub-regions, constructing an environmental parameter-biomass paired data set to obtain a training sample data set; The training sample data set is divided into a training set and a test set in a ratio of 7 to 3, and a random forest algorithm is used to train the model on the training set to obtain an environment-carrying capacity mapping model; Based on the environment-carrying capacity mapping model, a carrying capacity prediction calculation is performed on each environmental layered sub-region, and the maximum carrying capacity value of each sub-region is output to obtain regionalized carrying capacity prediction data.

6. The method for intelligently assessing seaweed carrying capacity based on data analysis according to claim 1, characterized in that: The step S4 further comprises: The ecological environment impact index was calculated based on the ratio of water pollutant concentration to the environmental quality standard limit, and the Shannon-Wiener index was used to assess biodiversity impact to obtain ecological environment dimension indicators; The output value per unit area is calculated by multiplying the seaweed output by the market price minus the production cost, and the return on investment is calculated based on the ratio of annual net income to total investment to obtain the economic benefit dimension indicator; The employment contribution is calculated by the ratio of the number of jobs created to the total employed population in the region, and the industry driving effect is calculated using the input-output multiplier method to obtain the social sustainability dimension indicator; The ecological environment dimension indicators, the economic benefit dimension indicators and the social sustainability dimension indicators are input into the hierarchical analysis method for weight distribution calculation, a judgment matrix is ​​constructed and a consistency test is performed to obtain a multi-dimensional sustainability evaluation indicator system.

7. The method for intelligently assessing seaweed carrying capacity based on data analysis according to claim 1, characterized in that: The step S5 further comprises: Designing a three-layer feedforward neural network architecture, using each dimensional indicator in the multi-dimensional sustainability assessment indicator system as an input layer node, setting the number of hidden layer neurons, and obtaining a neural network structure configuration; Combining the multi-dimensional sustainability assessment indicator system and the regionalized carrying capacity prediction data to construct a neural network training data set, adding interactive feature items between the indicators as supplementary inputs to obtain an extended feature data set; The Adam optimization algorithm is used to train the neural network, the learning rate and batch size parameters are set, and the network weights and biases are updated through the back propagation algorithm to obtain a trained neural network model; The sustainability indicator data of the area to be assessed is input into the trained neural network model for forward calculation, and processed by the output layer activation function to obtain an intelligent assessment value of the seaweed carrying capacity.

8. An intelligent assessment system for seaweed carrying capacity based on data analysis, characterized in that: For implementing the method for intelligently evaluating the carrying capacity of seaweed based on data analysis according to any one of claims 1 to 7, the intelligent evaluation system for the carrying capacity of seaweed based on data analysis comprises: The elimination module is used to collect water temperature, salinity, dissolved oxygen concentration, light intensity and nutrient concentration in the seaweed cultivation area through a multi-level sensor network, and use the outlier detection algorithm to eliminate abnormal data points to obtain a standardized marine environment data set; An input module is used to input the standardized marine environment data set into a clustering algorithm, and divide the aquaculture area into several sub-areas according to the similarity of environmental parameters to form environmental stratified sub-areas; a training module for collecting seaweed growth rate and biomass data for each of the environmental stratification sub-regions, using a machine learning algorithm to train the relationship between environmental parameters and seaweed carrying capacity, and obtaining regionalized carrying capacity prediction data; Establish modules to calculate the ecological and environmental impact index, economic benefit index, and social sustainability index respectively, use the analytic hierarchy process to determine the weight coefficients of each dimension, and establish a multi-dimensional sustainability evaluation indicator system; The output module is used to construct a neural network model, take the multi-dimensional sustainability assessment index system and the regionalized carrying capacity prediction data as input features, and output an intelligent assessment value of the seaweed carrying capacity.

9. An intelligent evaluation device for seaweed carrying capacity based on data analysis, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the method for intelligently evaluating the carrying capacity of seaweed based on data analysis according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the processor is enabled to perform the method for intelligently assessing the carrying capacity of seaweed based on data analysis according to any one of claims 1 to 7.

Images