Algae growth value-added prediction system and device

Abstract

The present invention relates to the technical field of algae growth value-added prediction. Disclosed are an algae growth value-added prediction system and device. The present invention comprises a sensor system, a data acquisition module, a processing unit, a prediction module, an analysis module, a communication module, and a repository. The sensor system is used for monitoring various parameters of an algae growth environment in real time and transmitting acquired data to the data acquisition module. The present invention achieves accurate monitoring and prediction of algae growth environment parameters by means of real-time monitoring and data processing. The system can not only optimize algae growth conditions and value-added production efficiency, but can also implement accurate prediction model adjustment by comparing prediction data with actual data by means of an analysis module, thereby improving the scientificity of decision-making and the efficiency of production management. Furthermore, data is transferred to a user interface by means of a communication module, thereby implementing real-time monitoring and feedback of environmental parameters and system state by an operator, and effectively supporting decision-making and adjustment.

Description

Algae growth and value-added prediction system and device TECHNICAL FIELD

[0001] The present application belongs to the field of algae growth and value-added prediction, and particularly relates to an algae growth and value-added prediction system and device. BACKGROUND

[0002] Algae are important biological resources and are widely used in food, feed, chemical industry, energy and other fields. Through the prediction system, the growth environment and management strategy of algae can be optimized, the growth rate and biological yield can be improved, and the production efficiency and economic benefits can be improved. Through the prediction system, the growth trend of algae and market demand can be predicted in advance, which provides an important basis for market strategy formulation for producers. By timely adjusting production plans and resource allocation, market demand can be better met and market competitiveness can be improved.

[0003] The existing system may be inefficient in processing multi-modal data fusion and large-scale data, or there may be problems of incomplete data integration, which cannot fully reflect the comprehensive situation of complex algae growth environment. Specifically, when integrating multiple parameters such as light intensity, temperature, pH value, dissolved oxygen and nutrients, the system may face challenges such as slow data processing speed, poor information interaction or insufficient data integrity. These problems limit the system's accurate grasp of environmental dynamics and precise prediction ability, affecting decision-making and production efficiency optimization.

[0004] Therefore, the present application is proposed.

[0005] SUMMARY

[0006] The technical problem to be solved by the present application is to overcome the shortcomings of the prior art and provide an algae growth and value-added prediction system and device that solves the problems raised in the background.

[0007] To solve the above technical problems, the basic idea of the first application embodiment of the present application is:

[0008] An algae growth and value-added prediction system, comprising: a sensor system, a data acquisition module, a processing unit, a prediction module, an analysis module, a communication module, and a repository.

[0009] The sensor system is used to monitor the parameters of the algae growth environment in real time and transmit the collected data to the data acquisition module.

[0010] The data acquisition module is used to receive and preprocess the data transmitted by the sensor, and then perform multi-modal fusion on the sensor data.

[0011] The processing unit is configured to perform local model training on the edge computing devices distributed in different geographical locations and to aggregate the parameters sent by the edge computing devices to generate a global model.

[0012] The prediction module uses the constructed global model to predict the trend of algal growth and the value-added efficiency.

[0013] The analysis module is configured to compare the prediction data with the actual data of the prediction time and to set the prediction module according to the comparison result.

[0014] The communication module is configured to transmit the prediction module and the analysis module to the user interface.

[0015] The repository is configured to receive the data results of the hybrid prediction module and the analysis module of the data acquisition module.

[0016] Optionally, the sensor includes a multi-parameter sensor for monitoring light intensity, temperature, pH value and nutrient concentration parameters in the algal growth environment.

[0017] Optionally, after the sensor system receives the sensor data in the data acquisition module, the sensor data is preprocessed and the specific steps of multi-modal fusion after preprocessing are as follows:

[0018] Step A1, receiving transmitted light intensity, temperature, pH value, dissolved oxygen and nutrient concentration parameters from multiple sensors and performing denoising, outlier processing and data normalization operations on the received sensor data to obtain preprocessed data;

[0019] Step A2, extracting basic statistical features, frequency domain features, time domain features and sample entropy from the preprocessed data and using a data fusion method to fuse the features extracted from different sensors to comprehensively reflect the complexity and diversity of the algal growth environment;

[0020] Step A3, integrating the fused multi-modal data into a complete data set and storing it in the repository;

[0021] Step A4, real-time monitoring of the fused data, displaying the monitoring results through a user interface or a system feedback mechanism, and providing real-time feedback according to the monitoring results.

[0022] Optionally, the step of Step A2 in the feature fusion is as follows:

[0023] Step A2.1, calculating the mean, standard deviation, maximum value and minimum value from the preprocessed data, extracting frequency domain features through Fourier transform or power spectral density analysis, extracting time domain features based on time series data, and finally applying sample entropy analysis to measure the complexity and randomness of the data as a measure of data dynamic change and complexity.

[0024] Step A2.2, different weights are assigned according to the importance or credibility of the features, and the features extracted from different sensors are fused.

[0025] Optionally, the processing unit locally trains the model on the edge computing devices distributed in different geographical locations, and the specific steps are as follows:

[0026] Step B1, collect environmental data at the edge computing devices in different geographical locations, and build and train a deep learning model at the edge computing devices, and generate model parameters after the training of the model is completed;

[0027] Step B2, receive the model parameters sent by the edge computing devices and aggregate the model parameters generated by the edge computing devices to generate the parameters of the global model;

[0028] Step B3, use the parameters of the global model to build a global model, and redeploy the updated global model to the edge device.

[0029] Optionally, the step B2 in generating the parameters of the global model is:

[0030] Step B2.1, weighted average the model parameters according to the credibility or performance weight of the edge device;

[0031] Step B2.2, according to the selected aggregation method, the decoded model parameters are combined or weighted averaged, and the specific formula includes: Wherein, θ global is the parameter of the global model, θ i is the model parameter generated by the i-th edge device, ω i is the device weight, which is usually related to the data contribution or performance of the device;

[0032] Step B2.3, according to the aggregated result, generate the parameter θ global of the global model.

[0033] Step B2.3, apply the generated global model parameters to tasks that need to be predicted or inferred.

[0034] Optionally, the constructed global model is used to predict the trend of algal growth and the value-added efficiency, and the specific steps are as follows:

[0035] Step C1, collect real-time environmental data through the data acquisition module and input the collected data into the constructed global model for prediction;

[0036] Step C2, using the global model to predict the trend of algae growth, output the expected state of algae growth in the future period of time, and evaluate the value-added efficiency under the current algae growth condition based on the prediction result of the global model;

[0037] Step C3, real-time monitoring the prediction result of the global model, and making operation adjustment and decision-making according to the monitoring result to optimize the algae growth environment and value-added production efficiency, wherein the adjustment mode includes but is not limited to adjusting light, temperature, water quality and nutrient supply.

[0038] Optionally, the following steps are used to predict the trend of algae growth and value-added efficiency using the constructed global model:

[0039] Step D1, collecting actual algae growth data and corresponding time information, the growth data including growth rate, biomass growth, environmental parameter change and obtaining the predicted growth trend and biomass growth expectation in the same time period output by the prediction module;

[0040] Step D2, comparing and analyzing the actual data and the predicted data, comparing the consistency and difference of the two in growth trend, growth rate and key environmental factors, and obtaining the comparison and analysis result;

[0041] Step D3, setting the error range, deviation trend and periodic change between the predicted data and the actual data;

[0042] Step D4, evaluating the accuracy and deviation of the prediction module according to the comparison and analysis result, and finally adjusting the parameters and settings of the prediction model according to the evaluation result.

[0043] Optionally, the user interface transmitted by the communication module adopts virtual reality technology to provide an intuitive algae growth environment and data visualization interface for the operator, which can display the environmental parameters, prediction results and system running state in real time.

[0044] The second invention of the embodiment provides an equipment comprising the algae growth and value-added prediction system of the first invention.

[0045] After adopting the above technical solution, the present application has the following advantages compared with the prior art, of course, any product implementing the present application does not necessarily need to achieve all the advantages described below:

[0046] Through real-time monitoring and data processing, the precise monitoring and prediction of algal growth environment parameters are realized. This system not only optimizes algal growth conditions and value-added production efficiency, but also compares predicted data with actual data through the analysis module to realize precise prediction model adjustment, thereby improving the scientificity of decision-making and the efficiency of production management. At the same time, through the communication module, data is transmitted to the user interface to realize real-time monitoring and feedback of the operating personnel on the environmental parameters and system state, effectively supporting decision-making and adjustment.

[0047] The specific embodiments of the present application will be further described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0048] The following description of the drawings is merely some embodiments, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings. In the drawings:

[0049] Figure 1 is a flowchart of an algal growth and value-added prediction system.

[0050] It should be noted that these drawings and written descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0051] The present application will now be further described in detail with reference to the accompanying drawings.

[0052] In this embodiment, an algal growth and value-added prediction system is provided, as shown in Figure 1, which includes a sensor system for real-time monitoring of various parameters of the algal growth environment, and the collected data is transmitted to a data acquisition module;

[0053] It should be noted that the sensor system can continuously monitor key parameters in the algal growth environment, such as light intensity, temperature, pH value, dissolved oxygen and nutrient concentration. Real-time monitoring helps to discover and respond to environmental changes in a timely manner, improving the stability of algal growth and production efficiency.

[0054] The data acquisition module is used to receive and preprocess the data transmitted by the sensor, and after preprocessing, the sensor data is fused in multiple modes.

[0055] It should be noted that: through multi-modal data fusion, multiple data types (such as light, temperature, pH, dissolved oxygen, etc.) from different sensors can be integrated to provide more comprehensive and integrated environmental state information, which helps to fully understand the algal growth environment. Through comprehensive analysis of multi-modal data, more accurate and comprehensive environmental state assessment and prediction can be provided, which helps to make more scientific and optimized decisions and improve the fine level of algal growth management.

[0056] The processing unit is used for local model training of edge computing devices distributed in different geographical locations and aggregation of parameters sent by the edge computing devices to generate a global model.

[0057] It should be noted that: by using edge computing devices distributed in different geographical locations for local model training, the computing load can be effectively dispersed to avoid the bottleneck of centralized computing resources and improve the utilization efficiency of computing resources. Local model training on edge computing devices can reduce the delay of data transmission to the central server and improve the real-time performance of model training and application, which is particularly important in application scenarios that require fast response.

[0058] The prediction module uses the constructed global model to predict the trend and value-added efficiency of algal growth. The prediction module uses the constructed global model to predict the trend and value-added efficiency of algal growth. The global model combines the local model parameters of multiple edge computing devices, which can more accurately reflect the algal growth under different geographical locations and environmental conditions, thereby improving the prediction accuracy. Through the real-time prediction results of the prediction module, the growth conditions of algae such as light, temperature, and nutrient concentration can be adjusted and optimized in time to ensure that algae grow in the best environment and improve production efficiency and quality.

[0059] The analysis module is used to compare the prediction data and actual data, and set the prediction module according to the comparison result.

[0060] It should be noted that: by comparing the prediction data and the actual data, the analysis module can find the deviation and shortcomings of the prediction model, thereby providing feedback for adjusting and optimizing the prediction module to improve the accuracy and precision of the model. By comparing the prediction data and the actual data in real time, the analysis module can provide immediate feedback to support the prediction module to make rapid adjustments and optimizations to ensure that the system can quickly respond to environmental changes and needs.

[0061] The communication module is used to transmit the prediction module and the analysis module to the user interface

[0062] The repository is used to receive the data results of the hybrid prediction module and its analysis module of the data acquisition module.

[0063] The sensor of the embodiment includes a multi-parameter sensor for monitoring parameters such as light intensity, temperature, pH value, and nutrient concentration in the algal growth environment.

[0064] In the embodiment, after the sensor system receives the sensor data in the data acquisition module, the sensor data is preprocessed and the specific steps of multi-modal fusion of the sensor data after preprocessing are as follows:

[0065] Step A1, receiving transmitted light intensity, temperature, pH value, dissolved oxygen, and nutrient concentration parameters from multiple sensors and performing denoising, outlier processing, and data normalization operations on the received sensor data to obtain preprocessed data;

[0066] Step A2, extracting basic statistical features, frequency domain features, time domain features, and sample entropy from the preprocessed data and using a data fusion method to fuse the features extracted from different sensors to comprehensively reflect the complexity and diversity of the algal growth environment;

[0067] Step A3, integrating the fused multi-modal data into a complete data set and storing it in a repository;

[0068] Step A4, real-time monitoring of the fused data, displaying the monitoring results through a user interface or system feedback mechanism, and providing real-time feedback based on the monitoring results.

[0069] It should be noted that multi-modal data fusion improves the robustness and anti-interference ability of the system, ensuring that even if some sensors fail or are abnormal, the system can still provide reliable environmental monitoring and feedback. Real-time monitoring of the fused data and displaying the results through a user interface or system feedback mechanism can timely discover and respond to environmental changes, support rapid adjustment and optimization of algal growth conditions, and improve production efficiency and quality. Storing the fused multi-modal data in the repository facilitates historical data analysis, trend prediction, and model training, supporting long-term environmental monitoring and management.

[0070] In the embodiment, the steps in Step A2 when performing feature fusion are as follows:

[0071] Step A2.1, calculate the mean, standard deviation, maximum value, minimum value from the pre-processed data, and extract the frequency domain features by Fourier transform or power spectral density analysis, extract the time domain features based on the time series data, and finally apply sample entropy to analyze the complexity and randomness of the data as a measure of the dynamic changes and complexity of the data. It should be noted that by calculating the mean, standard deviation, maximum value, minimum value, and extracting the frequency domain and time domain features, the characteristics of the environmental data can be fully represented from multiple dimensions, providing rich information for analysis and prediction. Applying sample entropy to analyze the complexity and randomness of the data can effectively capture the dynamic changes and complexity of the data, helping to identify potential environmental change trends and abnormal situations.

[0072] Step A2.2, according to the importance or credibility of the features, different weights are assigned to the features extracted from different sensors. By real-time analysis and fusion of different feature data, the model parameters can be dynamically adjusted and optimized to maintain the efficiency and adaptability of the system.

[0073] In this embodiment, the processing unit performs local model training on edge computing devices distributed in different geographic locations, and the specific steps are as follows:

[0074] Step B1, collect environmental data at the edge computing device in the geographic location, and construct and train a deep learning model at the edge computing device. After completing the training of the model, the edge computing device generates model parameters. By constructing and training a deep learning model on the edge computing device, the local data and computing resources can be fully utilized to improve the performance and accuracy of the model, especially when dealing with environmental data with geographic location correlation.

[0075] Step B2, receive the model parameters sent by the edge computing device and aggregate the model parameters generated by the edge computing device through parameter aggregation to summarize and integrate the parameters of the global model; by parameter aggregation, the model parameters generated by each edge device are summarized and integrated, which can integrate the training results in different geographic locations and environments, construct a more comprehensive and powerful global model, and optimize the overall model performance.

[0076] Step B3, use the parameters of the global model to construct the global model, and redeploy the updated global model to the edge device. Using the updated global model to redeploy to the edge device can realize continuous learning and model improvement, continuously improve the prediction ability and adaptability of the model, and maintain the efficiency and frontiers of the system.

[0077] The step B2 of the embodiment is as follows when generating the parameters of the global model:

[0078] Step B2.1, weighted average of the model parameters according to the credibility or performance weight of the edge device;

[0079] It should be noted that the weighted average of the model parameters according to the credibility or performance weight of the edge device can optimize the parameters of the global model. Such weighted average can effectively screen and integrate high-quality model parameters, thereby improving the prediction accuracy and stability of the global model.

[0080] Step B2.2, according to the selected aggregation method, the decoded model parameters are merged or weighted averaged, and the specific formula includes: θ = ∑ i = 1 n ω i θ i global is the parameter of the global model, θ i is the model parameter generated by the i-th edge device, ω i is the device weight, which is usually related to the data contribution or performance of the device;

[0081] It should be noted that using the selected aggregation method to merge or weighted average the decoded model parameters can effectively integrate multi-source data from different geographical locations or environmental conditions, thereby improving the comprehensive utilization efficiency of data

[0082] Step B2.3, according to the aggregated result, the parameters θ global of the global model are generated.

[0083] It should be noted that generating the parameters of the global model according to the aggregated result can comprehensively consider the contribution of each edge device, optimize the performance of the global model, and make it better adapt to complex and variable actual environment.

[0084] Step B2.3, the generated global model parameters are applied to the tasks that need to be predicted or inferred.

[0085] The embodiment uses the constructed global model to predict the trend and value-added efficiency of algal growth, and the specific steps are as follows:

[0086] Step C1, real-time environmental data is collected by the data collection module and the collected data is input into the constructed global model for prediction;

[0087] Step C2, using the global model to predict the trend of algae growth, output the expected state of algae growth in the future period of time, and based on the prediction result of the global model, evaluate the value-added efficiency under the current algae growth condition; through real-time collection of environmental data by the data collection module and prediction by the global model, timely prediction of algae growth trend and evaluation of value-added efficiency can be provided, providing scientific basis and real-time support for decision making. Based on the prediction result of the global model, the value-added efficiency under the current algae growth condition can be accurately evaluated, helping to optimize production management and resource allocation.

[0088] Step C3, real-time monitoring of the prediction result of the global model, and according to the monitoring result, adjusting the operation and making decisions to optimize the algae growth environment and value-added production efficiency, wherein the adjustment methods include but are not limited to adjusting the light, temperature, water quality and nutrient supply. Real-time monitoring of the prediction result of the global model can quickly find out the environmental changes and abnormal growth state, and timely operation adjustment and decision making. According to the monitoring result, operation adjustment and decision making, such as adjusting the light, temperature, water quality and nutrient supply, improve the adaptability and response speed to environmental changes.

[0089] In this embodiment, the constructed global model is used to predict the trend of algae growth and value-added efficiency in the following steps:

[0090] Step D1, collect actual algae growth data and corresponding time information, growth data including growth rate, biomass increase, environmental parameter change and obtain the predicted growth trend and biomass increase expectation in the same time period output by the prediction module.

[0091] It should be noted that by collecting actual algae growth data and corresponding time information, and comparing the prediction data output by the prediction module (steps D1 and D2), the accuracy of the prediction model in predicting the growth trend, growth rate and key environmental factors can be comprehensively evaluated.

[0092] Step D2, compare and analyze the actual data and the prediction data, compare the consistency and difference of the two in the growth trend, growth rate and key environmental factors, and obtain the comparison and analysis result;

[0093] Step D3, set the error range, deviation trend and periodic change between the prediction data and the actual data;

[0094] Step D4, according to the comparison and analysis result, evaluate the accuracy and deviation of the prediction module, and finally, according to the evaluation result, adjust the parameters and settings of the prediction model.

[0095] It should be noted that according to the comparative analysis result, the error range, deviation trend and periodic change between the predicted data and the actual data can be identified, which helps to adjust and optimize the parameters and settings of the prediction model, thereby improving the accuracy and reliability of the prediction. By evaluating the accuracy and bias of the prediction model, a scientific basis can be provided for decision making, reducing the risk of making wrong decisions based on inaccurate predictions, and improving the efficiency of management and operation.

[0096] In this embodiment, the user interface transmitted by the communication module uses virtual reality technology to provide an intuitive algae growth environment and data visualization interface for the operator, which can display the environmental parameters, prediction results and system running status in real time. With the user interface using virtual reality technology, the operator can intuitively observe and interact with the algae growth environment and data visualization interface. This intuitiveness makes the complex environmental parameters and prediction results easier to understand and analyze, helping the operator to quickly make decisions and adjustments.

[0097] Embodiment 2

[0098] Embodiment 2 of the present application provides a device comprising the algae growth value-added prediction system of embodiment 1

[0099] The present application is not limited to the above embodiments, and anyone should know that any structural changes made under the inspiration of the present application fall within the protection scope of the present application. The technical, shape and structure parts not described in detail in the present application are known technologies.

Claims

1. A system for predicting the growth and proliferation of algae, characterized in that, It includes a sensor system, a data acquisition module, a processing unit, a prediction module, an analysis module, a communication module, and a storage library; The sensor system is used to monitor various parameters of the algae growth environment in real time and transmit the collected data to the data acquisition module. The data acquisition module is used to receive data transmitted from the sensor and preprocess the data, and then perform multimodal fusion on the sensor data after preprocessing. The processing unit is used to train local models on edge computing devices distributed in different geographical locations and to aggregate the parameters sent by the edge computing devices to generate a global model. The prediction module uses a constructed global model to predict the growth trend and proliferation efficiency of algae. The analysis module is used to compare the predicted data with the actual data at the predicted time, and to set the prediction module according to the comparison results; A communication module is used to transmit the prediction and analysis modules to the user interface. The storage library is used to receive data results from the hybrid prediction module and its analysis module of the data acquisition module.

2. The algal growth and proliferation prediction system according to claim 1, characterized in that: The sensor includes a multi-parameter sensor for monitoring light intensity, temperature, pH value, and nutrient concentration parameters in the algae growth environment.

3. The algal growth and proliferation prediction system according to claim 2, characterized in that: The specific steps of the sensor system after receiving sensor data by the data acquisition module, preprocessing the sensor data, and then performing multimodal fusion on the preprocessed sensor data are as follows: Step A1: Receive multiple parameters transmitted from various sensors, including light intensity, temperature, pH value, dissolved oxygen, and nutrient concentration, and perform noise reduction and outlier handling on the received sensor data. The data is processed and normalized to obtain preprocessed data. Step A2: Extract basic statistical features, frequency domain features, time domain features, and sample entropy from the preprocessed data, and use data fusion methods to fuse the features extracted from different sensors to comprehensively reflect the complex diversity of algal growth environment; Step A3: Combine the fused multimodal datasets into a complete dataset and store it in the repository; Step A4: Monitor the merged data in real time, display the monitoring results through the user interface or system feedback mechanism, and provide real-time feedback based on the monitoring results.

4. The algal growth and proliferation prediction system according to claim 3, characterized in that: The steps in step A2 for feature fusion are as follows: Step A2.1: Calculate the mean, standard deviation, maximum value, and minimum value from the preprocessed data, and extract frequency domain features through methods such as Fourier transform or power spectral density analysis. Extract time domain features based on time series data, and finally apply sample entropy analysis to analyze the complexity and randomness of the data as a measure of data dynamic changes and complexity. Step A2.2: Assign different weights based on the importance or reliability of the features, and fuse various features extracted from different sensors.

5. The algal growth and proliferation prediction system according to claim 1, characterized in that: The processing unit performs local model training on edge computing devices distributed in different geographical locations. The specific steps are as follows: Step B1: Obtain environmental data collected by the edge computing device at the geographic location, build and train a deep learning model at the edge computing device, and generate model parameters after the model training is completed. Step B2: Receive the model parameters sent by the edge computing device and aggregate and integrate the model parameters generated by the edge computing device to generate the parameters of the global model. Step B3: Build a global model using the parameters of the global model, and redeploy the updated global model to the edge device.

6. The algal growth and proliferation prediction system according to claim 5, characterized in that: Step B2 involves the following steps when generating the parameters for the global model: Step B2.1: Calculate a weighted average of the model parameters based on the credibility or performance weight of the edge devices; Step B2.2: Based on the selected aggregation method, merge or weighted average the decoded model parameters. Specific formulas include: Where, θ global These are the parameters of the global model, θ i w are the model parameters generated by the i-th edge device. i This refers to device weight, which is usually related to the device's data contribution or performance. Step B2.3: Based on the aggregated results, generate the parameters θ of the global model. global ; Step B2.3: Apply the generated global model parameters to the task that requires prediction or inference.

7. The algal growth and proliferation prediction system according to claim 1, characterized in that: The constructed global model is used to predict the growth trend and proliferation efficiency of algae. The specific steps are as follows: Step C1: Collect real-time environmental data through the data acquisition module and input the collected data into the constructed global model for prediction; Step C2: Use a global model to predict the growth trend of algae, output the expected state of algae growth in the future, and evaluate the proliferation efficiency under the current algae growth conditions based on the prediction results of the global model. Step C3: Monitor the prediction results of the global model in real time, and make operational adjustments and decisions based on the monitoring results to optimize the algae growth environment and increase production efficiency. The adjustment methods include, but are not limited to, adjusting the supply of light, temperature, water quality and nutrients.

8. The algal growth and proliferation prediction system according to claim 1, characterized in that: The following steps are used to predict algal growth trends and proliferation efficiency using the constructed global model: Step D1: Collect actual algal growth data and corresponding time information. Growth data includes growth rate, biomass growth, changes in environmental parameters, and obtain the predicted growth trend and expected biomass growth within the same time period output by the prediction module. Step D2: Compare and analyze the actual data and the predicted data, and compare the consistency and differences between the two in terms of growth trend, growth rate and key environmental factors to obtain the comparative analysis results. Step D3: Set the error range, offset trend, and periodic changes between the predicted data and the actual data; Step D4: Based on the comparative analysis results, evaluate the accuracy and bias of the prediction module. Finally, based on the evaluation results, adjust the parameters and settings of the prediction model.

9. The algal growth and proliferation prediction system according to claim 1, characterized in that: The user interface transmitted by the communication module adopts virtual reality technology, providing operators with an intuitive algae growth environment and data visualization interface, which can display environmental parameters, prediction results and system operating status in real time.

10. A device, characterized in that, Includes the algal growth and proliferation prediction system according to any one of claims 1 to 9.

Images