Forestry seedling raising optimization method based on big data
By detecting cloudy weather in real time and processing light sensor data, the problem of unstable light data in cloudy weather is solved, the success rate and quality of seedling cultivation is improved, and the accuracy and stability of light management is achieved.
Patent Information
- Application Number
- CN202411328275.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-24
- Publication Date
- 2024-11-22
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing forestry seedling optimization technology based on big data in cloudy weather conditions causes fluctuations in the reading of the light sensor due to intermittent shading of cloud layers, affecting the stability and continuity of the light data, and thus affecting the growth and seedling success rate of seedlings.
By detecting cloudy weather in real time and identifying the intermittent shading period of cloud layers, obtaining and preprocessing the light sensor data, calculating the light variation coefficient and shading interference index, dividing the disturbed and steady-state sensors, and adjusting the affected sensors according to the light management measures of the steady-state sensors Light management of disturbing sensors.
It improves the stability and continuity of light data, ensures accurate monitoring and recording of the big data analysis system, improves the photosynthesis efficiency and overall growth and development quality of seedlings, and significantly improves the success rate and quality of seedling cultivation.
Smart Images

Figure CN119005528A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of forestry seedling cultivation optimization, and in particular to a forestry seedling cultivation optimization method based on big data. Background Art
[0002] Forestry seedling cultivation refers to the process of propagating and cultivating seeds and seedlings in a specific environment through artificial cultivation technology to produce high-quality seedlings that meet the needs of forest growth. The importance of forestry seedling cultivation lies in its ability to provide stable and high-quality seedling resources, support the recovery and development of forest ecosystems, improve the utilization rate of forest resources, and thus promote ecological environmental protection and sustainable development. Optimizing forestry seedling cultivation, especially through big data technology, can significantly improve the efficiency and success rate of seedling cultivation, reduce resource waste, reduce seedling cultivation costs, and enhance the adaptability of seedlings to different environmental conditions, ultimately realizing the scientific, intelligent and modern forestry production, and promoting the high-quality development of forestry and the improvement of the ecological environment.
[0003] The existing forestry seedling optimization technology based on big data achieves the optimization of forestry seedling cultivation through multiple steps. First, the soil, water, climate, light and other parameters in the seedling cultivation environment are monitored in real time through sensor networks and satellite remote sensing technology to collect a large amount of data; then, the collected data is stored, processed and analyzed using a big data platform, and the data is deeply mined using machine learning algorithms to identify the key factors affecting the seedling cultivation effect and the optimal seedling cultivation conditions; then, through data modeling and simulation technology, the seedling cultivation process under different conditions is simulated to predict the growth of seedlings; finally, based on the analysis results and simulation predictions, a personalized and scientific seedling cultivation plan is formulated, and the environmental parameters and operating procedures in the seedling cultivation process are adjusted in real time, thereby achieving accurate and efficient seedling management, greatly improving the growth quality and survival rate of seedlings, reducing seedling cultivation costs, and promoting the modernization and intelligence of forestry production.
[0004] The prior art has the following deficiencies: Under cloudy weather conditions, due to intermittent obstruction by clouds, light sensors will experience periodic data interference when measuring solar radiation intensity. This rapidly changing cloud layer causes sensor readings to fluctuate dramatically or fail intermittently, resulting in unstable and discontinuous light data. In this case, since light data is subject to periodic interference, the big data analysis system cannot continuously and accurately monitor and record light intensity, thus affecting the establishment and application of light optimization models. Existing technologies are unable to filter and correct these interference data in real time, resulting in the inability to accurately implement light management plans, causing seedlings to lack the necessary light during critical growth periods, affecting their photosynthesis and overall growth and development, and thus reducing the success rate and quality of seedling cultivation.
[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention
[0006] The purpose of the present invention is to provide a forestry seedling cultivation optimization method based on big data to solve the problems in the above-mentioned background technology.
[0007] In order to achieve the above object, the present invention provides the following technical solution: a forestry seedling optimization method based on big data, specifically comprising the following steps: During the seedling raising period, the weather condition is detected in real time to determine whether it is cloudy, and if cloudy is detected, the time period when the clouds are intermittently obscured; Obtain the light data of the seedling raising area collected by each light sensor during the intermittent cloud cover period, and perform preprocessing after acquisition; Extract interference information when each light sensor collects light data of the seedling area during the intermittent cloud cover period, and analyze it after extraction to evaluate whether the light data of the seedling area collected by each light sensor during the intermittent cloud cover period is disturbed by the intermittent cloud cover, and divide each light sensor into a disturbed light sensor and a steady-state light sensor according to the evaluation result; Obtaining the position information of each disturbed light sensor and each steady-state light sensor, and determining the seedling raising area monitored by each sensor; For each disturbed light sensor, the nearest steady-state light sensor is selected as a reference, and based on the light management measures of the reference sensor, the light management measures of the seedling raising area monitored by the disturbed light sensor are adjusted; Regularly monitor and record the effects of adjusted lighting management, and generate a seedling lighting management report for management personnel and technicians.
[0008] Preferably, the interference information of each light sensor when collecting the light data of the seedling area during the intermittent cloud cover period is extracted, and analyzed after extraction to evaluate whether the light data of the seedling area collected by each light sensor during the intermittent cloud cover period is disturbed due to the intermittent cloud cover, and each light sensor is divided into a disturbed light sensor and a steady-state light sensor according to the evaluation result, which specifically includes the following steps: Extract interference information from the illumination data of the seedling raising area collected by each illumination sensor during the intermittent cloud cover period, including illumination intensity data and cloud cover data in the illumination data collected by each illumination sensor at different times within a period of time; Preprocessing the light intensity data and cloud cover data extracted from the light data collected by each light sensor at different times within a period of time; The light intensity data and cloud cover data collected by each light sensor at different times within a period of time after preprocessing are analyzed respectively, and the light variation coefficient and the cloud cover interference index of each light sensor are generated respectively; Determine the threshold of illumination coefficient of variation and the threshold of shading interference index; The generated illumination variation coefficient and shading interference index of each light sensor are compared with the illumination variation coefficient threshold and the shading interference index threshold respectively, to evaluate whether the illumination data of the seedling area collected by each light sensor during the period of intermittent cloud shading is disturbed by the intermittent cloud shading, and according to the evaluation results, each light sensor is divided into a disturbed light sensor and a steady-state light sensor.
[0009] Preferably, the logic for obtaining the illumination variation coefficient of each illumination sensor is as follows: Extract the light intensity data from the preprocessed light data collected by each light sensor at different times over a period of time, including the actual light intensity collected by each light sensor at different times over a period of time and the corresponding time points, and use the function according to the time series To express, t is the time point, and the time period is defined as , It represents the actual light intensity collected by the mth light sensor at time t within a period of time. , h is a positive integer; Calculate the average value of the actual light intensity collected by each light sensor at different times over a period of time , according to the formula: ; Calculate the illumination variation coefficient of each illumination sensor. The specific calculation formula is as follows: ; In the formula, is the illumination variation coefficient of the mth illumination sensor.
[0010] Preferably, the logic for obtaining the shielding interference index of each light sensor is as follows: Extract the cloud cover data from the pre-processed illumination data collected by each illumination sensor at different times over a period of time, including the actual cloud cover intensity collected by each illumination sensor at different times over a period of time and the corresponding time points, and use the function according to the time series To express, t is the time point, and the time period is defined as , represents the actual cloud cover intensity collected by the mth illumination sensor at time t within a period of time; Calculate the shielding interference index of each light sensor. The specific calculation formula is as follows: ; In the formula, is the shielding interference index of the mth light sensor, It is the rate of change of the actual cloud cover intensity collected by the mth illumination sensor at different times over a period of time.
[0011] Preferably, the illumination variation coefficient of each illumination sensor generated is and shadowing interference index The illumination coefficient of variation threshold and the threshold value of the masking interference index Compare and evaluate whether the light data of the seedling area collected by each light sensor during the intermittent cloud cover period is disturbed by the intermittent cloud cover, and divide each light sensor into a disturbed light sensor and a steady-state light sensor according to the evaluation result, which specifically includes the following steps: The light variation coefficient of each light sensor generated Threshold of light variation coefficient Compare: If , then the sensor is preliminarily marked as a fluctuation-disturbed sensor; The occlusion interference index of each light sensor generated and masking interference index threshold Compare: If , then the sensor is preliminarily marked as a shielded disturbed sensor; According to the comparison results of the two parameters, the sensors are comprehensively analyzed: if a sensor is marked as disturbed in both comparisons, the light data of the seedling area collected by the light sensor during the intermittent cloud-blocking period is disturbed due to the intermittent cloud-blocking, and it is classified as a disturbed light sensor; if a sensor is not marked as disturbed in both comparisons, the light data of the seedling area collected by the light sensor during the intermittent cloud-blocking period is not disturbed due to the intermittent cloud-blocking, and it is classified as a steady-state light sensor; For sensors with different results in the two comparisons, further analysis is performed based on the average value of their disturbance levels to ultimately determine their classification results.
[0012] Preferably, for sensors with different results in the two comparisons, further analysis is performed based on the average value of their disturbance levels to ultimately determine their classification results. The specific analysis is as follows: For sensors with different results in the comparison of illumination variation coefficient and shielding interference index, record their illumination variation coefficient respectively. and shadowing interference index The value of Calculate the average value of the disturbance level of each light sensor according to the formula: ; In the formula, is the average value of the disturbance degree of the mth light sensor; Determine the combined average threshold of all light sensors' disturbance levels ; The average value of the disturbance level of each light sensor With the comprehensive average threshold Compare and finally determine the division result according to the comparison result. The specific division process is as follows: like , then the light data of the seedling area collected by the light sensor during the intermittent cloud-shading period is disturbed due to the intermittent cloud-shading, and it is classified as a disturbed light sensor; like , the light data of the seedling area collected by the light sensor during the intermittent cloud-blocking period is not disturbed by the intermittent cloud-blocking, and it is classified as a steady-state light sensor.
[0013] Preferably, for each disturbed light sensor, the nearest steady-state light sensor is selected as a reference, and based on the light management measures of the reference sensor, the light management measures of the seedling raising area monitored by the disturbed light sensor are adjusted, specifically comprising the following steps: Extracting the location information of each disturbed light sensor and each steady-state light sensor, and uploading it to the central data server, generating a distribution map of each disturbed light sensor and each steady-state light sensor, and determining the monitoring area of each sensor according to the distribution map; Using the position information of the sensor, calculate the distance between each disturbed light sensor and all steady-state light sensors, and select the nearest steady-state light sensor as the reference sensor; Obtaining the light management measures of the reference steady-state light sensor, and associating the light management data of the reference sensor with its geographic location information; Based on the light management measures of the reference steady-state light sensor, an adjustment plan is formulated to adjust the light management measures of the area monitored by the disturbed light sensor, and the adjusted light management data is monitored and analyzed in real time.
[0014] In the above technical solution, the technical effects and advantages provided by the present invention are: 1. The present invention detects in real time whether the weather condition is cloudy, and identifies the time period when the cloud layer is intermittently obscured when cloudy weather is detected. The system can accurately capture the changes in light data. On this basis, the light data collected by each light sensor during the intermittent cloud obscuration period is obtained and preprocessed, which can effectively filter out the disturbed data and extract stable light intensity information. The extracted interference information can accurately evaluate the degree of disturbance of each sensor by calculating the light variation coefficient and the shielding interference index, and divide the sensors into two categories: disturbed and steady-state. This method significantly improves the stability and continuity of light data, solves the problems of data fluctuation and discontinuity caused by cloud obscuration, thereby ensuring that the big data analysis system can continuously and accurately monitor and record light intensity, and provide a reliable data basis for the establishment of a light optimization model.
[0015] 2. The present invention obtains the position information of each disturbed light sensor and steady-state light sensor, determines the seedling raising area monitored by each sensor, and the system can accurately manage the disturbed area. Select the nearest steady-state light sensor as a reference, and adjust the light management measures of the area monitored by the disturbed light sensor based on its light management measures, such as increasing or decreasing artificial light sources, adjusting sun visors, etc. Through these adjustment measures, it is possible to effectively compensate for insufficient or excessive light fluctuations caused by intermittent cloud cover, and ensure that the seedling raising area obtains stable light during the critical growth period. This not only improves the photosynthetic efficiency and overall growth and development quality of seedlings, but also significantly improves the success rate and quality of seedling raising, and solves the problem of high seedling raising failure rate caused by inaccurate light management in the prior art.
[0016] 3. The present invention generates a seedling lighting management report by regularly monitoring and recording the adjusted lighting management effect, and provides it to managers and technicians. By utilizing the Internet of Things platform and the big data analysis system, it is possible to collect and process lighting data in real time, and automatically generate a detailed seedling lighting management report. These reports include details such as the comparison of lighting data before and after adjustment, the trend of light intensity changes, and the growth of seedlings. Through the automated report generation and distribution system, managers can promptly understand the actual effect of lighting management and further optimize the seedling strategy based on the content of the report. This automated monitoring and analysis method not only improves the efficiency and accuracy of data processing, but also provides a scientific basis for seedling management, continuously optimizes seedling strategies, and ensures that lighting management during the seedling process is always in the best state, thereby comprehensively improving the success rate and quality of seedling cultivation. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0018] Figure 1 It is a schematic diagram of the process of a forestry seedling optimization method based on big data of the present invention. DETAILED DESCRIPTION
[0019] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.
[0020] The present invention provides Figure 1 A forestry seedling optimization method based on big data is shown, which specifically includes the following steps: During the seedling raising period, the weather condition is detected in real time to determine whether it is cloudy, and if cloudy is detected, the time period when the clouds are intermittently obscured; Real-time detection of whether the weather conditions are cloudy can be achieved through the meteorological sensor network and satellite remote sensing technology deployed in the seedling area. The meteorological sensor network includes sensors such as temperature, humidity, wind speed and light intensity. These sensors can collect weather data in real time and send the data to the central processing system through wireless transmission. The central processing system uses big data analysis algorithms to conduct a comprehensive analysis of these real-time data. For example, it combines parameters such as light intensity changes, humidity and temperature to identify whether it is cloudy weather. At the same time, satellite remote sensing technology can provide cloud cover images, analyze the distribution and changes of clouds through image recognition algorithms, and combine with ground sensor data to further confirm whether it is cloudy weather. The software system displays these analysis results in real time on the monitoring interface and sends early warning notifications to relevant personnel.
[0021] Identifying time periods when clouds are intermittently obstructing the field can be achieved through data analysis of light sensors and machine learning algorithms. First, light sensors deployed in the nursery area monitor light intensity in real time, and sensor data is transmitted to the central processing system via a wireless network. The software system uses time series analysis methods to continuously monitor and process light data and identify fluctuation patterns in light intensity. Machine learning algorithms (such as LSTM or RNN) can be trained to detect sudden changes or fluctuations in light intensity and distinguish between normal light changes and light changes caused by intermittent cloud cover. When characteristic rapid fluctuations or intermittent failures are detected in the light data, the system marks these time periods as time periods of intermittent cloud cover and records the relevant timestamps and sensor data for subsequent interference data processing and light management adjustments.
[0022] Obtain the light data of the seedling raising area collected by each light sensor during the intermittent cloud cover period, and perform preprocessing after acquisition; Acquiring the light data of the seedling area collected by each light sensor during the intermittent cloud cover period can be achieved by establishing a wireless sensor network. Specifically, multiple light sensors are deployed in the seedling area. These sensors can monitor the light intensity data in real time and transmit the data to the central processing system through the wireless communication module. The central processing system receives the light data from each sensor through the data aggregation software, and classifies and stores the data according to the timestamp and sensor ID. When the weather monitoring system identifies a period of cloudy weather and intermittent cloud cover, the system automatically extracts the data of all relevant sensors in this period. The sensor data can be transmitted to the central database via the Internet or local network, and uniformly stored and managed by the big data processing platform. This method ensures the real-time and integrity of the light data and provides data support for subsequent analysis.
[0023] Preprocessing of light data is to ensure the accuracy and consistency of the data and provide a reliable basis for subsequent analysis and decision-making. The preprocessing steps include data cleaning, denoising, missing value filling and data standardization. Data cleaning improves the accuracy of data by removing outliers and erroneous data, while denoising reduces data fluctuations caused by sensor errors or environmental interference through smoothing algorithms (such as moving average or Kalman filtering). Missing value filling can be done through interpolation or machine learning prediction methods to ensure the continuity and integrity of the data. Data standardization facilitates subsequent comparison and analysis by converting data from different sensors to a unified scale. These preprocessing operations can be automatically performed by data processing software, using big data processing frameworks (such as Hadoop or Spark) to efficiently process large amounts of sensor data. Through preprocessing, the problem of unstable and discontinuous data caused by intermittent cloud cover can be effectively solved, the accuracy of data analysis can be improved, and the light management model can be optimized to ensure stable light in the seedling area.
[0024] Extract interference information when each light sensor collects light data of the seedling area during the intermittent cloud cover period, and analyze it after extraction to evaluate whether the light data of the seedling area collected by each light sensor during the intermittent cloud cover period is disturbed by the intermittent cloud cover, and divide each light sensor into a disturbed light sensor and a steady-state light sensor according to the evaluation result; In this embodiment, the interference information of each light sensor when collecting the light data of the seedling raising area during the intermittent cloud-shading period is extracted, and the information is analyzed after extraction to evaluate whether the light data of the seedling raising area collected by each light sensor during the intermittent cloud-shading period is disturbed due to the intermittent cloud-shading, and each light sensor is divided into a disturbed light sensor and a steady-state light sensor according to the evaluation result, which specifically includes the following steps: Extract interference information from the illumination data of the seedling raising area collected by each illumination sensor during the intermittent cloud cover period, including illumination intensity data and cloud cover data in the illumination data collected by each illumination sensor at different times within a period of time; Extracting interference information from the illumination data of the seedling area collected by each illumination sensor during the intermittent cloud cover period can be achieved by establishing a distributed sensor network and a big data processing platform. Specifically, multiple illumination sensors and cloud cover sensors are deployed in the seedling area, which can monitor the light intensity and cloud cover in real time. The sensor transmits the data to the central data server through the wireless communication module. After receiving the data, the central data server uses data processing software (such as Apache Kafka) to perform real-time data stream processing, and marks and classifies the data by timestamp and sensor ID. Through a time series database (such as InfluxDB), the system can extract the data collected by each sensor during the intermittent cloud cover period by time period, including light intensity data and cloud cover data. The big data processing platform (such as Apache Hadoop or Apache Spark) further processes and stores these data for subsequent analysis. This method ensures the real-time and integrity of the data, and realizes efficient extraction and management of data through software.
[0025] Preprocessing the light intensity data and cloud cover data extracted from the light data collected by each light sensor at different times within a period of time; The extracted light intensity data and cloud cover data are preprocessed to ensure the accuracy, consistency and reliability of the data, thereby providing a reliable basis for subsequent analysis and decision-making. The preprocessing steps include data cleaning, denoising, missing value filling and data standardization. First, data cleaning improves the accuracy of the data by removing outliers and erroneous data; this can be achieved by setting reasonable upper and lower thresholds. Secondly, denoising reduces data fluctuations caused by sensor errors or environmental interference through smoothing algorithms (such as moving average or Kalman filtering) to ensure data stability. Then, missing value filling can be completed by interpolation methods (such as linear interpolation or polynomial interpolation) or machine learning prediction methods to ensure data continuity and integrity. Finally, data standardization facilitates subsequent comparison and analysis by converting data from different sensors to a unified scale. These preprocessing operations can be automatically performed by big data processing platforms (such as Apache Spark), using its efficient parallel processing capabilities to process large amounts of sensor data. Through preprocessing, the problems of data instability and discontinuity caused by intermittent cloud cover can be effectively solved, and the accuracy of data analysis can be improved, thereby optimizing the light management model and ensuring stable light in the seedling area.
[0026] The light intensity data and cloud cover data collected by each light sensor at different times within a period of time after preprocessing are analyzed respectively, and the light variation coefficient and the cloud cover interference index of each light sensor are generated respectively; Determine the threshold of illumination coefficient of variation and the threshold of shading interference index; Determining the threshold of the coefficient of variation of light and the threshold of the shading interference index can be achieved through historical data analysis and machine learning algorithms. First, collect a large amount of historical light data and cloud cover data from the seedling area to establish a large data set containing light intensity and cloud cover under different weather conditions. Use data mining tools (such as Pandas and Scikit-learn in Python) to perform statistical analysis on historical data and calculate the distribution of the coefficient of variation of light and the shading interference index in different time periods. By analyzing these distributions, determine the preliminary threshold range of the coefficient of variation of light and the shading interference index. Then, apply machine learning algorithms (such as K-means clustering or decision trees) to train and validate historical data, and optimize these thresholds to improve classification accuracy. Through techniques such as cross-validation, evaluate the performance of different thresholds, and select the threshold with the highest classification accuracy as the final threshold of the coefficient of variation of light and the shading interference index. Ultimately, these determined thresholds can be used in real-time monitoring to assess whether light data is disturbed, helping to accurately divide disturbed light sensors from steady-state light sensors, thereby optimizing light management strategies and ensuring that seedling areas receive stable light during critical growth periods.
[0027] The generated illumination variation coefficient and shading interference index of each light sensor are compared with the illumination variation coefficient threshold and the shading interference index threshold respectively, to evaluate whether the illumination data of the seedling area collected by each light sensor during the period of intermittent cloud shading is disturbed by the intermittent cloud shading, and according to the evaluation results, each light sensor is divided into a disturbed light sensor and a steady-state light sensor.
[0028] In this embodiment, the logic for obtaining the illumination variation coefficient of each illumination sensor is as follows: Extract the light intensity data from the preprocessed light data collected by each light sensor at different times over a period of time, including the actual light intensity collected by each light sensor at different times over a period of time and the corresponding time points, and use the function according to the time series To express, t is the time point, and the time period is defined as , It represents the actual light intensity collected by the mth light sensor at time t within a period of time. , h is a positive integer; Extracting the pre-processed light intensity data collected by each light sensor at different times within a period of time, including the actual light intensity collected by each light sensor at different times within a period of time and the corresponding time points can be achieved through the distributed sensor network and big data processing platform deployed in the seedling area. Specifically, firstly, multiple light sensors are deployed in the seedling area, which can monitor the light intensity in real time and record the corresponding time points. The sensor transmits the collected data to the central data server in real time through the wireless communication module. The central data server uses data processing software (such as Apache Kafka) to process real-time data streams, marking and classifying the data by timestamp and sensor ID. By storing and managing the data through a time series database (such as InfluxDB), the system can extract the light intensity data collected by each sensor at different time points according to the specified time period. The big data processing platform (such as ApacheSpark) further preprocesses the data to ensure the accuracy and consistency of the data. In this way, the system can efficiently and accurately extract the light intensity data collected by each light sensor at different times within a period of time and its corresponding time points, providing a reliable data basis for subsequent analysis and decision-making.
[0029] Calculate the average value of the actual light intensity collected by each light sensor at different times over a period of time , according to the formula: ; Calculate the illumination variation coefficient of each illumination sensor. The specific calculation formula is as follows: ; In the formula, is the illumination variation coefficient of the mth illumination sensor.
[0030] The size of the illumination variation coefficient of the mth illumination sensor is closely related to the evaluation of whether the illumination data of the seedling area collected by each illumination sensor during the intermittent cloud cover period is disturbed by the intermittent cloud cover. Specifically, the illumination variation coefficient reflects the stability of the light intensity over time. If the illumination variation coefficient of a sensor is high, it means that the illumination data recorded by the sensor during the intermittent cloud cover period has large fluctuations, which may be disturbed by the intermittent cloud cover, resulting in instability and discontinuity of the illumination data. This will directly affect the accuracy of the illumination management system, making it impossible for the system to correctly evaluate the light intensity and optimize the illumination management measures, thereby affecting the photosynthesis and overall growth and development of seedlings during the critical growth period. By calculating and analyzing the illumination variation coefficient, the disturbed sensors can be identified, and corresponding measures can be taken to adjust the illumination management plan to ensure that the seedling area can still obtain stable light during the intermittent cloud cover period, thereby improving the success rate and quality of seedling cultivation.
[0031] In this embodiment, the logic for obtaining the shielding interference index of each light sensor is as follows: Extract the cloud cover data from the pre-processed illumination data collected by each illumination sensor at different times over a period of time, including the actual cloud cover intensity collected by each illumination sensor at different times over a period of time and the corresponding time points, and use the function according to the time series To express, t is the time point, and the time period is defined as , represents the actual cloud cover intensity collected by the mth illumination sensor at time t within a period of time; Extracting the cloud cover data collected by each light sensor at different times within a period of time after preprocessing, including the actual cloud cover intensity collected by each light sensor at different times within a period of time and the corresponding time points can be achieved through the light sensor network and data processing system deployed in the seedling area. Specifically, multiple light sensors with cloud cover detection function are deployed in the seedling area. These sensors can monitor and record the cloud cover intensity and its corresponding time points in real time. The sensor transmits the collected data to the central data server through the wireless communication module. The central data server uses data processing software (such as Apache Kafka) to process real-time data streams, marking and classifying the data by timestamp and sensor ID. Then, the data is stored and managed through a time series database (such as InfluxDB). The system can extract the cloud cover intensity data collected by each sensor at different time points according to the specified time period. The big data processing platform (such as Apache Spark) further preprocesses these data, including removing outliers, denoising and filling missing values to ensure the accuracy and consistency of the data. In this way, the system can efficiently and accurately extract the cloud obscuration intensity data collected by each light sensor at different times over a period of time and its corresponding time points, providing a reliable data basis for subsequent analysis and decision-making.
[0032] Calculate the shielding interference index of each light sensor. The specific calculation formula is as follows: ; In the formula, is the shielding interference index of the mth light sensor, It is the rate of change of the actual cloud cover intensity collected by the mth illumination sensor at different times over a period of time.
[0033] The size of the shielding interference index of the mth light sensor is directly related to the evaluation of whether the light data of the seedling area collected by each light sensor during the intermittent cloud shielding period is disturbed by the intermittent cloud shielding. Specifically, the shielding interference index reflects the degree of change of the cloud shielding intensity over time. If the shielding interference index of a sensor is high, it means that the cloud shielding intensity recorded by the sensor during the time period changes dramatically, indicating that the fluctuation of cloud shielding is frequent and dramatic, resulting in significant fluctuation and instability of light data. This interference will affect the continuity and accuracy of light data, resulting in the inability of the light management system to reliably evaluate the light intensity and optimize the light management plan, so that the seedlings may lack stable light during the critical growth period, thereby affecting their photosynthesis and overall growth and development. By calculating and analyzing the shielding interference index, sensors that are severely disturbed by intermittent cloud shielding can be identified, and light management measures can be adjusted accordingly to ensure that the seedling area can still obtain stable light under changing weather conditions, thereby improving the success rate and quality of seedling cultivation.
[0034] In this embodiment, the illumination variation coefficient of each illumination sensor is generated and shadowing interference index The illumination coefficient of variation threshold and the threshold value of the masking interference index Compare and evaluate whether the light data of the seedling area collected by each light sensor during the intermittent cloud cover period is disturbed by the intermittent cloud cover, and divide each light sensor into a disturbed light sensor and a steady-state light sensor according to the evaluation result, which specifically includes the following steps: The light variation coefficient of each light sensor generated Threshold of light variation coefficient Compare: If , then the sensor is preliminarily marked as a fluctuation-disturbed sensor; The occlusion interference index of each light sensor generated and masking interference index threshold Compare: If , then the sensor is preliminarily marked as a shielded disturbed sensor; According to the comparison results of the two parameters, the sensors are comprehensively analyzed: if a sensor is marked as disturbed in both comparisons, the light data of the seedling area collected by the light sensor during the intermittent cloud-blocking period is disturbed due to the intermittent cloud-blocking, and it is classified as a disturbed light sensor; if a sensor is not marked as disturbed in both comparisons, the light data of the seedling area collected by the light sensor during the intermittent cloud-blocking period is not disturbed due to the intermittent cloud-blocking, and it is classified as a steady-state light sensor; If a sensor is marked as disturbed in both comparisons of the light variation coefficient and the shading interference index, the light data of the seedling area collected by the light sensor during the intermittent cloud shading period is disturbed by the intermittent cloud shading. This means that the light data recorded by the sensor is significantly fluctuating and unstable, and cannot reliably reflect the actual light intensity. In this case, the light management system cannot accurately optimize the light management plan based on these unstable data, resulting in the seedlings lacking the necessary stable light during the critical growth period, affecting their photosynthesis and overall growth and development, thereby reducing the success rate and quality of seedling cultivation. By classifying these sensors as disturbed light sensors, the system can identify and process these disturbed data, and take remedial measures such as adding artificial light sources or adjusting the position of the seedling shed to ensure that the seedling area receives stable light.
[0035] If a sensor is not marked as disturbed in both comparisons of the light variation coefficient and the shading interference index, the light data of the seedling area collected by the light sensor during the intermittent cloud shading period was not disturbed by intermittent cloud shading. This means that the light data recorded by the sensor is relatively stable and can accurately reflect the actual light intensity. In this case, the light management system can optimize the light management plan based on these stable data to ensure that the seedlings receive the necessary and stable light during the critical growth period, thereby promoting their photosynthesis and overall growth and development, and improving the success rate and quality of seedling cultivation. Classifying these sensors as steady-state light sensors helps the system focus on processing disturbed sensors, optimize the overall light management strategy, and ensure a healthy growth environment in the seedling area.
[0036] For sensors with different results in the two comparisons, further analysis is performed based on the average value of their disturbance levels to ultimately determine their classification results.
[0037] In this embodiment, for sensors with different results in the two comparisons, further analysis is performed based on the average value of their disturbance levels to ultimately determine their classification results. The specific analysis is as follows: For sensors with different results in the comparison of illumination variation coefficient and shielding interference index, record their illumination variation coefficient respectively. and shadowing interference index The value of Calculate the average value of the disturbance level of each light sensor according to the formula: ; In the formula, is the average value of the disturbance degree of the mth light sensor; Determine the combined average threshold of all light sensors' disturbance levels ; Determining the comprehensive average threshold of the disturbance degree of all light sensors can be achieved through historical data analysis and machine learning algorithms. Specifically, first collect a large amount of historical light data and cloud cover data in the seedling area to establish a large data set containing light intensity and cloud cover under different weather conditions. Use data processing and analysis tools (such as Pandas and Scikit-learn in Python) to perform statistical analysis on historical data and calculate the light variation coefficient and shielding interference index of each light sensor in different time periods. Then, apply machine learning algorithms (such as K-means clustering or decision trees) to train these data to determine the average disturbance degree of each sensor AMmAM^mAMm. The performance of different average disturbance degrees is evaluated by cross-validation technology, and the value with the best classification effect is selected as the comprehensive average threshold AMyzAM^{yz}AMyz. This method can be achieved through software automation to ensure that the threshold can accurately reflect the disturbance of different light sensors under variable weather conditions, providing a reliable basis for subsequent light management.
[0038] The average value of the disturbance level of each light sensor With the comprehensive average threshold Compare and finally determine the division result according to the comparison result. The specific division process is as follows: like , then the light data of the seedling area collected by the light sensor during the intermittent cloud-shading period is disturbed due to the intermittent cloud-shading, and it is classified as a disturbed light sensor; like , the light data of the seedling area collected by the light sensor during the intermittent cloud-blocking period is not disturbed by the intermittent cloud-blocking, and it is classified as a steady-state light sensor.
[0039] The average value of the disturbance level of the mth light sensor The size of directly reflects the comprehensive degree of interference to the sensor during the intermittent cloud cover period. Greater than the comprehensive average threshold , which indicates that the sensor's illumination variation coefficient and shielding interference index are both high during this period, which means that the illumination data collected by the sensor is significantly disturbed by intermittent cloud shielding and cannot stably reflect the actual light intensity, thus affecting the optimization effect of the light management system. Therefore, this sensor needs to be classified as a disturbed light sensor so that remedial measures can be taken during the light management process, such as adding artificial light sources or adjusting the seedling environment to ensure that the seedling area receives stable light. If Less than or equal to the comprehensive average threshold , it indicates that the illumination variation coefficient and shielding interference index of the sensor are within the acceptable range, and the illumination data collected by it is relatively stable and can accurately reflect the actual light intensity. Therefore, it can be classified as a steady-state illumination sensor to ensure that the illumination management system is optimized based on reliable data, thereby improving the success rate and quality of seedling cultivation.
[0040] Obtaining the position information of each disturbed light sensor and each steady-state light sensor, and determining the seedling raising area monitored by each sensor; Obtaining the location information of each disturbed light sensor and each steady-state light sensor and determining the seedling area monitored by each sensor can be achieved by integrating the geographic location information module and data processing software. Specifically, when installing the light sensor, each sensor is equipped with a GPS module to record its geographic coordinates. After installation, the sensor transmits the location information to the central data server in real time through the wireless communication module. The central data server uses the geographic information system (GIS) software to process and store this location information and generate a distribution map of each sensor. At the same time, the data processing software (such as Apache Kafka or Apache Spark) will associate the location information of the sensor with the light data it collects, and establish a corresponding relationship between the sensor ID and the geographic location. With this information, the system can clearly identify the specific seedling area monitored by each light sensor. Regularly update and calibrate the location information to ensure that the location information of the sensor is accurate, so as to achieve accurate light management and optimization of the seedling area.
[0041] For each disturbed light sensor, the nearest steady-state light sensor is selected as a reference, and based on the light management measures of the reference sensor, the light management measures of the seedling raising area monitored by the disturbed light sensor are adjusted; In this embodiment, for each disturbed light sensor, the nearest steady-state light sensor is selected as a reference, and based on the light management measures of the reference sensor, the light management measures of the seedling raising area monitored by the disturbed light sensor are adjusted, specifically including the following steps: Extracting the location information of each disturbed light sensor and each steady-state light sensor, and uploading it to the central data server, generating a distribution map of each disturbed light sensor and each steady-state light sensor, and determining the monitoring area of each sensor according to the distribution map; Extracting the location information of each disturbed light sensor and each steady-state light sensor and uploading it to the central data server can be achieved by integrating geographic location information modules and wireless communication technologies. Specifically, each light sensor is equipped with a GPS module when installed to record its geographic coordinates. After installation, these sensors transmit the recorded location information to the central data server in real time through wireless communication modules (such as Wi-Fi, LoRa or NB-IoT). The central data server receives and stores this location information and performs preliminary processing using data processing software (such as Apache Kafka or Apache Spark) to ensure the integrity and accuracy of the data. In addition, the location information of the sensor can also be updated by manual recording and batch uploading to ensure the accuracy and consistency of the location information of all sensors in the system.
[0042] Generating distribution maps for each disturbed light sensor and each steady-state light sensor, and determining the monitoring area of each sensor based on the distribution maps can be achieved through geographic information system (GIS) software and big data analysis platforms. First, the central data server imports the stored sensor location information into GIS software, such as ArcGIS or QGIS, to generate a geographic distribution map of the sensors. The GIS software uses the geographic coordinates of the sensors to generate distribution maps of each sensor, showing their specific locations in the seedling area. Next, using a big data analysis platform (such as Apache Spark), the location information of the sensor is associated with the light data it monitors to determine the monitoring area of each sensor. The system can automatically divide the monitoring area of each sensor based on the distribution map and the coverage of the monitoring data, ensuring that each area can be accurately monitored by light data, thereby providing a reliable geographical basis for subsequent light management and optimization.
[0043] Using the location information of the sensor, calculate the distance between each disturbed light sensor and all steady-state light sensors, use a distance calculation algorithm (such as Euclidean distance) to perform distance calculation, and select the nearest steady-state light sensor as the reference sensor; Using the location information of the sensor, the distance between each disturbed light sensor and all steady-state light sensors is calculated, and the distance calculation algorithm (such as Euclidean distance) is used for distance calculation. The selection of the nearest steady-state light sensor as the reference sensor can be achieved through big data processing and geographic information system software. First, the geographic location information (longitude and latitude) of each sensor is imported into the central data server. The location information is batch processed using a big data processing platform (such as Apache Spark), and the distance calculation algorithm (such as Euclidean distance, Manhattan distance or great circle distance) is used to calculate the distance between each disturbed light sensor and all steady-state light sensors. Specifically, for each pair of sensors, a formula is applied to calculate the straight-line distance between the two points, and the results are stored in a data table. Then, through database query or big data analysis tools, the nearest steady-state light sensor to each disturbed light sensor is selected as the reference sensor. This process can be performed regularly through automated scripts to ensure that the system can dynamically update the selection of reference sensors as the sensor location or status changes, thereby providing timely and accurate basic data for adjusting light management measures.
[0044] Obtain the light management measures of the reference steady-state light sensor, including data such as light duration, light intensity, and use of artificial light sources, and associate the light management data of the reference sensor with its geographic location information; The light management measures of the reference steady-state light sensor, including data such as light time, light intensity, and artificial light source usage, can be obtained. The light management data of the reference sensor can be associated with its geographic location information through the Internet of Things platform and the big data analysis system. Specifically, the data management of all sensors is first integrated on the Internet of Things platform (such as Azure IoT, AWS IoT, or GoogleCloud IoT), and the light management data of the reference steady-state light sensor is transmitted to the central data server in real time. After the light management measures data of the sensor (such as light time, light intensity, and artificial light source usage) are uploaded through the wireless communication module, the data is processed and stored using a big data analysis system (such as Apache Hadoop or Apache Spark). In order to associate these data with the geographic location information of the sensor, data fusion technology can be used to match the sensor's ID, geographic coordinates, and its light management data, and store them in a relational database (such as MySQL, PostgreSQL) or a non-relational database (such as MongoDB). Through GIS software (such as ArcGIS or QGIS), these associated data are visualized to ensure that the light management measures of each reference sensor accurately correspond to its geographic location, providing a reliable basis for adjusting the light management measures of the disturbed light sensor. This process can be automated through software to ensure the real-time and accuracy of data.
[0045] Based on the light management measures of the reference steady-state light sensor, an adjustment plan is formulated to adjust the light management measures of the area monitored by the disturbed light sensor. Specific adjustment measures include increasing or decreasing artificial light sources, adjusting sun visors, etc., and the adjusted light management data is monitored and analyzed in real time.
[0046] Based on the light management measures of the reference steady-state light sensor, an adjustment plan is formulated to adjust the light management measures of the area monitored by the disturbed light sensor. The specific adjustment measures include increasing or decreasing artificial light sources, adjusting sunshades, etc., and real-time monitoring and analysis of the adjusted light management data can be achieved by comprehensively utilizing the Internet of Things platform, automated control system, and big data analysis platform. First, based on the light management data obtained from the reference steady-state light sensor, these data are analyzed through the Internet of Things platform (such as Azure IoT, AWS IoT, or Google Cloud IoT), and an adjustment plan is formulated to determine the specific measures such as the number of artificial light sources that need to be increased or decreased, and the angle and position of the sunshade. Then, these adjustment instructions are remotely executed using an automated control system (such as a PLC controller or an intelligent lighting control system) to optimize the light management of the seedling area monitored by the disturbed light sensor. All adjusted light data are transmitted back to the central data server in real time through the sensor, and the big data analysis platform (such as Apache Spark or Hadoop) monitors and analyzes these data in real time to evaluate the adjustment effect. The monitoring and analysis results are displayed to managers through data visualization tools (such as Tableau or Power BI) to provide real-time feedback and further optimization suggestions. This process is automated through software, ensuring that lighting management measures can be adjusted and optimized in a timely manner according to actual needs, thereby improving lighting conditions in the seedling area.
[0047] Regularly monitor and record the effects of adjusted lighting management, and generate seedling lighting management reports, which will be provided to managers and technicians to further optimize seedling strategies.
[0048] Regularly monitor and record the effect of adjusted light management, and generate seedling light management reports to provide to managers and technicians to further optimize seedling strategies. This can be achieved through IoT platforms, data collection systems, and report generation software. First, the sensor network regularly collects and records the adjusted light data through IoT platforms (such as Azure IoT, AWS IoT, or Google Cloud IoT), including light intensity, duration, use of artificial light sources, etc., and transmits the data to the central data server in real time. Big data analysis platforms (such as Apache Spark or Hadoop) process and analyze the collected data in real time to evaluate the effect of light management adjustment measures. Then, report generation software (such as Tableau, Power BI, or JasperReports) is used to convert the analysis results into visual seedling light management reports. These reports include detailed content such as comparison of light data before and after adjustment, light intensity change trend, and seedling growth. Through an automated report generation and distribution system, the generated reports are regularly sent to managers and technicians so that they can further optimize seedling strategies and light management measures based on the report content. This process is achieved through software automation to ensure the accuracy and timeliness of data collection, analysis, and report generation.
[0049] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0050] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.
[0051] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0052] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0053] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0054] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0055] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0056] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A forestry seedling optimization method based on big data, It is characterized in that The specific steps include: During the seedling raising period, the weather condition is detected in real time to determine whether it is cloudy, and if cloudy is detected, the time period when the clouds are intermittently obscured; Obtain the light data of the seedling raising area collected by each light sensor during the intermittent cloud cover period, and perform preprocessing after acquisition; Extract interference information when each light sensor collects light data of the seedling area during the intermittent cloud cover period, and analyze it after extraction to evaluate whether the light data of the seedling area collected by each light sensor during the intermittent cloud cover period is disturbed by the intermittent cloud cover, and divide each light sensor into a disturbed light sensor and a steady-state light sensor according to the evaluation result; Obtaining the position information of each disturbed light sensor and each steady-state light sensor, and determining the seedling raising area monitored by each sensor; For each disturbed light sensor, the nearest steady-state light sensor is selected as a reference, and based on the light management measures of the reference sensor, the light management measures of the seedling raising area monitored by the disturbed light sensor are adjusted; Regularly monitor and record the effects of adjusted lighting management, and generate a seedling lighting management report to provide to managers and technicians; Extract interference information when each light sensor collects light data of the seedling area during the intermittent cloud cover period, and analyze it after extraction to evaluate whether the light data of the seedling area collected by each light sensor during the intermittent cloud cover period is disturbed by the intermittent cloud cover, and divide each light sensor into a disturbed light sensor and a steady-state light sensor according to the evaluation result, specifically including the following steps: Extract interference information from the illumination data of the seedling raising area collected by each illumination sensor during the intermittent cloud cover period, including illumination intensity data and cloud cover data in the illumination data collected by each illumination sensor at different times within a period of time; Preprocessing the light intensity data and cloud cover data extracted from the light data collected by each light sensor at different times within a period of time; The light intensity data and cloud cover data collected by each light sensor at different times within a period of time after preprocessing are analyzed respectively, and the light variation coefficient and the cloud cover interference index of each light sensor are generated respectively; Determine the threshold of illumination coefficient of variation and the threshold of shading interference index; The generated illumination variation coefficient and shading interference index of each light sensor are compared with the illumination variation coefficient threshold and the shading interference index threshold respectively, to evaluate whether the illumination data of the seedling area collected by each light sensor during the period of intermittent cloud shading is disturbed by the intermittent cloud shading, and according to the evaluation results, each light sensor is divided into a disturbed light sensor and a steady-state light sensor.
2. According to the forestry seedling optimization method based on big data as described in claim 1, It is characterized in that The logic for obtaining the illumination variation coefficient of each illumination sensor is as follows: Extract the light intensity data from the preprocessed light data collected by each light sensor at different times over a period of time, including the actual light intensity collected by each light sensor at different times over a period of time and the corresponding time points, and use the function according to the time series To express, t is the time point, and the time period is defined as , It represents the actual light intensity collected by the mth light sensor at time t within a period of time. , h is a positive integer; Calculate the average value of the actual light intensity collected by each light sensor at different times over a period of time , according to the formula: ; Calculate the illumination variation coefficient of each illumination sensor. The specific calculation formula is as follows: ; In the formula, is the illumination variation coefficient of the mth illumination sensor.
3. According to the forestry seedling optimization method based on big data as described in claim 2, It is characterized in that The logic for obtaining the shielding interference index of each light sensor is as follows: Extract the cloud cover data from the pre-processed illumination data collected by each illumination sensor at different times over a period of time, including the actual cloud cover intensity collected by each illumination sensor at different times over a period of time and the corresponding time points, and use the function according to the time series To express, t is the time point, and the time period is defined as , represents the actual cloud cover intensity collected by the mth illumination sensor at time t within a period of time; Calculate the shielding interference index of each light sensor. The specific calculation formula is as follows: ; In the formula, is the shielding interference index of the mth light sensor, It is the rate of change of the actual cloud cover intensity collected by the mth illumination sensor at different times over a period of time.
4. According to the forestry seedling optimization method based on big data in claim 3, It is characterized in that The light variation coefficient of each light sensor generated and shadowing interference index The illumination coefficient of variation threshold and the threshold value of the masking interference index Compare and evaluate whether the light data of the seedling area collected by each light sensor during the intermittent cloud cover period is disturbed by the intermittent cloud cover, and divide each light sensor into a disturbed light sensor and a steady-state light sensor according to the evaluation result, which specifically includes the following steps: The light variation coefficient of each light sensor generated Threshold of light variation coefficient Compare: If , then the sensor is preliminarily marked as a fluctuation-disturbed sensor; The occlusion interference index of each light sensor generated and masking interference index threshold Compare: If , then the sensor is preliminarily marked as a shielded disturbed sensor; According to the comparison results of the two parameters, the sensors are comprehensively analyzed: if a sensor is marked as disturbed in both comparisons, the light data of the seedling area collected by the light sensor during the intermittent cloud-blocking period is disturbed due to the intermittent cloud-blocking, and it is classified as a disturbed light sensor; if a sensor is not marked as disturbed in both comparisons, the light data of the seedling area collected by the light sensor during the intermittent cloud-blocking period is not disturbed due to the intermittent cloud-blocking, and it is classified as a steady-state light sensor; For sensors with different results in the two comparisons, further analysis is performed based on the average value of their disturbance levels to ultimately determine their classification results.
5. A forestry seedling optimization method based on big data according to claim 4, It is characterized in that For sensors with different results in the two comparisons, further analysis is performed based on the average value of their disturbance degree to finally determine their classification results. The specific analysis is as follows: For sensors with different results in the comparison of illumination variation coefficient and shielding interference index, record their illumination variation coefficient respectively. and shadowing interference index The value of Calculate the average value of the disturbance level of each light sensor according to the formula: ; In the formula, is the average value of the disturbance degree of the mth light sensor; Determine the combined average threshold of all light sensors' disturbance levels ; The average value of the disturbance level of each light sensor With the comprehensive average threshold Compare and finally determine the division result according to the comparison result. The specific division process is as follows: like , then the light data of the seedling area collected by the light sensor during the intermittent cloud-shading period is disturbed due to the intermittent cloud-shading, and it is classified as a disturbed light sensor; like , the light data of the seedling area collected by the light sensor during the intermittent cloud-blocking period is not disturbed by the intermittent cloud-blocking, and it is classified as a steady-state light sensor.
6. A forestry seedling optimization method based on big data according to claim 5, It is characterized in that For each disturbed light sensor, the nearest steady-state light sensor is selected as a reference, and based on the light management measures of the reference sensor, the light management measures of the seedling area monitored by the disturbed light sensor are adjusted, specifically including the following steps: Extracting the location information of each disturbed light sensor and each steady-state light sensor, and uploading it to the central data server, generating a distribution map of each disturbed light sensor and each steady-state light sensor, and determining the monitoring area of each sensor according to the distribution map; Using the position information of the sensor, calculate the distance between each disturbed light sensor and all steady-state light sensors, and select the nearest steady-state light sensor as the reference sensor; Obtaining the light management measures of the reference steady-state light sensor, and associating the light management data of the reference sensor with its geographic location information; Based on the light management measures of the reference steady-state light sensor, an adjustment plan is formulated to adjust the light management measures of the area monitored by the disturbed light sensor, and the adjusted light management data is monitored and analyzed in real time.
Citation Information
Cited By
Intelligent Juncao transplanting method and system based on Internet of Things technology
CN119624140A
Seedling raising environment intelligent analysis and dynamic regulation and control method and system
CN121014427A
A method and system for intelligent analysis and dynamic control of seedling environment
CN121014427B
