Sustainable organic rose disease and insect pest integrated prevention and control method

Abstract

The invention relates to the technical field of planting insect pest prevention and control, solves the defect that an insect pest prevention and control method in the prior art cannot meet the special requirements of organic rose planting, and particularly discloses a sustainable organic rose insect pest integrated prevention and control method. Comprehensively collecting environment, plant and pest signal data related to pest occurrence in the organic rose planting area; data processing and analysis: integrating and analyzing the collected data, judging the risk level of plant diseases and insect pests, and matching an adaptive prevention and control strategy; prevention and control: based on a data processing result, implementing prevention and control means which comprise ecology and biology and conform to an organic standard to carry out targeted control; performing real-time data evaluation, acquiring dynamic data after prevention and control implementation, and evaluating a prevention and control effect; and performing feedback optimization adjustment. The method is used for automatic adaptive prevention and control of insect pests in the planting process of organic roses, and has the characteristics of self-regulation of prevention and control means and high prevention and control accuracy.

Description

Technical Field

[0001] This invention relates to the field of pest control technology in planting, and in particular to a sustainable integrated pest control method for organic roses. Background Technology

[0002] Organic rose cultivation strictly prohibits the use of synthetic chemical pesticides, fertilizers, and growth regulators. This presents unique technical challenges in pest and disease control, fundamentally different from the requirements of conventional rose cultivation. While conventional rose cultivation can achieve rapid and broad-spectrum pest and disease control through chemical pesticides, organic rose cultivation requires ensuring the organic nature of the product. This results in a very narrow range of control methods, and the effectiveness of control measures is easily affected by environmental factors, leading to poor stability.

[0003] Specifically, the core challenges in pest and disease control in organic rose cultivation are mainly reflected in the following aspects: First, pest and disease monitoring is lagging behind. In organic cultivation environments, the initial signals of pests and diseases are weak, and there is a lack of efficient monitoring tools such as chemical attractants, making it easy to miss the best control opportunity and cause the spread of the disease. Second, the ecosystem is fragile. Under the single-crop rose cultivation model, the number of beneficial biological communities in the planting area is insufficient, the natural pest control capacity is weak, and pests and diseases are prone to outbreaks. Third, the coordination of control measures is poor. Existing organic control measures are mostly applied individually and have not formed a comprehensive control system, making it difficult to meet the pest and disease control needs of roses at different growth stages. Fourth, emergency control is limited. When pests and diseases break out, there is a lack of emergency response measures that are both efficient and organically compliant, which can easily lead to a significant drop in yield or even failure to meet quality standards.

[0004] Currently, existing pest and disease control technologies are mostly applicable to conventional crop or flower cultivation, failing to fully consider the specific limitations of organic rose cultivation. This results in problems such as incompatibility between control methods and organic standards, and a mismatch between control logic and the growth characteristics of roses. For example, some existing biological control technologies are not adapted to common organic rose pests and diseases such as rose black spot, powdery mildew, aphids, and spider mites, leading to inconsistent control effects. Furthermore, some ecological control methods introduce companion plants that may compete with roses for nutrients, negatively impacting rose growth. Therefore, there is an urgent need for an integrated pest and disease control method specifically designed for organic rose cultivation, balancing sustainability and precision, to solve these technical challenges. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing pest and disease control methods that cannot adapt to the special needs of organic rose cultivation, and to provide a sustainable integrated pest and disease control method for organic roses.

[0006] The technical solution adopted in this invention is:

[0007] A sustainable integrated pest management method for organic roses includes the following steps:

[0008] S100, multi-dimensional data collection, comprehensively collects environmental, plant and pest signal data related to the occurrence of diseases and pests in the organic rose planting area;

[0009] S200: Data processing and analysis, integrating and analyzing the collected data, determining the risk level of pests and diseases and matching appropriate prevention and control strategies;

[0010] S300, prevention and control, based on data processing results, implements targeted control measures that include ecological and biological aspects and meet organic standards;

[0011] S400, real-time data assessment, collects dynamic data after the implementation of prevention and control measures, and assesses the effectiveness of prevention and control;

[0012] S500, feedback optimization and adjustment, dynamically corrects prevention and control parameters and strategies based on real-time assessment results, forming a data-driven closed-loop prevention and control system.

[0013] Furthermore, step S100 includes the following sub-steps:

[0014] S101. Sampling point layout: The monitoring units are divided according to the different growth stages of organic roses. Environmental sensors, plant status collection points and pest trapping collection points are set up in each unit.

[0015] S102. Multi-dimensional data acquisition: Real-time environmental data is collected through sensors, and plant physiological status data and pest and disease sample data at trapping points are collected periodically.

[0016] S103. Preliminary data verification and removal of abnormal data.

[0017] Furthermore, in step S102, the environmental data includes soil temperature and humidity, air temperature and humidity, light intensity and ventilation rate, and the plant physiological status data includes leaf chlorophyll content and plant height growth. The data acquisition process adopts a physical acquisition and sensing monitoring method without chemical intervention.

[0018] Furthermore, step S200 includes the following sub-steps:

[0019] S201. Data integration and modeling: The verified multi-dimensional data is structured and integrated, and then input into the preset pest and disease risk assessment model.

[0020] S202. Risk level determination: The model analysis outputs the probability of pest and disease occurrence, potential scope of harm, and risk level.

[0021] S203. Matching of control strategies: Based on the risk level and data characteristics, match the corresponding control measures and implementation parameters from the preset organic control strategy library.

[0022] Furthermore, in step S201, the preset pest and disease risk assessment model is trained and generated based on historical pest and disease data of organic rose cultivation and corresponding environmental and plant data. The model output results are associated with the prevention and control priorities under different risk levels.

[0023] Furthermore, step S300 includes the following sub-steps:

[0024] S301, Ecological regulation, for low to medium risk levels, optimizes the growth environment by adjusting ventilation in the planting area and supplementing organic substrate;

[0025] S302. Biological control: For medium- and high-risk levels, release natural enemy insects or spray plant- or microbial control agents.

[0026] S303. Control process recording: Real-time recording of the implementation details of control measures and synchronously collected environmental and plant data.

[0027] Furthermore, step S400 includes the following sub-steps:

[0028] S401. Evaluation indicators are determined by selecting changes in the population size of pests and diseases, the area of ​​plant damage, and the physiological recovery status of plants as core evaluation indicators.

[0029] S402. Real-time data acquisition: Collect assessment indicator data and corresponding environmental data within the prevention and control area at a preset frequency.

[0030] S403. Preliminary assessment of effectiveness: Compare the collected data with the baseline data before prevention and control to preliminarily determine whether the prevention and control effect meets the standard.

[0031] Furthermore, step S500 includes the following sub-steps:

[0032] S501. Analysis of assessment results: Combining the data recorded during the prevention and control process with real-time assessment data, analyze the reasons why the prevention and control effect did not meet the standards.

[0033] S502. Adjustment of strategy parameters: For situations where standards are not met, adjust the type of prevention and control measures, implementation timing, or related parameters.

[0034] S503. Model optimization and update: Supplement the historical database with the data from the entire prevention and control process, and optimize the pest and disease risk assessment model.

[0035] Furthermore, in step S102, the environmental data is collected every 2-4 hours, the plant physiological status data is collected every 3-5 days, and the pest and disease sample data is collected once a day, with the collection time selected in the early morning when there is no dew.

[0036] Furthermore, in step S302, when spraying plant-derived control agents, the spraying amount is controlled at 100-150 ml per square meter, the spraying interval is 5-7 days, the continuous spraying does not exceed 2 times, and the interval between the last spraying and rose harvest is not less than 15 days.

[0037] The beneficial effects of this invention are:

[0038] This invention addresses the technical problem of insufficient adaptability in pest and disease control for organic roses through data acquisition, regulation, and systematic prevention and control. The process involves multi-dimensional data collection, gathering environmental plant and pest / disease signal data within the planting area. This overcomes the shortcomings of weak early-stage pest and disease signals and insufficient monitoring tools in organic farming environments. Data processing, analysis, and integration of the collected information determine the risk level of pests and diseases and match appropriate control strategies, changing the current situation of blindly applying control methods. Based on this, targeted regulation is implemented using ecological and biological control methods that meet organic standards. Simultaneously, real-time data evaluation of control effectiveness and dynamic feedback optimization of control parameters and strategies form a complete closed-loop control system. This process solves the problem of monitoring lag during control, enhances the number of beneficial biological communities in the planting area through ecological control methods, improves natural pest control capabilities, mitigates the fragility of the planting ecosystem, and enhances the synergy of control methods through closed-loop regulation, while also making emergency response more targeted. Compared with existing technologies, this solution achieves targeted adaptation to organic rose planting scenarios, the control logic is more compatible with the growth characteristics of roses, the stability of control effect is significantly improved, effectively reducing the risk of pest and disease outbreaks, reducing the occurrence of yield decline and substandard quality, and taking into account the sustainability and precision of control, filling the gap in integrated control technology for organic roses. Attached Figure Description

[0039] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0040] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0041] Example 1

[0042] A sustainable integrated pest management method for organic roses, such as Figure 1 As shown, it includes the following steps:

[0043] S100, multi-dimensional data collection, comprehensively collects environmental, plant and pest signal data related to the occurrence of diseases and pests in the organic rose planting area;

[0044] S200: Data processing and analysis, integrating and analyzing the collected data, determining the risk level of pests and diseases and matching appropriate prevention and control strategies;

[0045] S300, prevention and control, based on data processing results, implements targeted control measures that include ecological and biological aspects and meet organic standards;

[0046] S400, real-time data assessment, collects dynamic data after the implementation of prevention and control measures, and assesses the effectiveness of prevention and control;

[0047] S500, feedback optimization and adjustment, dynamically corrects prevention and control parameters and strategies based on real-time assessment results, forming a data-driven closed-loop prevention and control system.

[0048] This embodiment addresses the technical problem of insufficient adaptability in pest and disease control for organic roses through data acquisition, regulation, and systematic prevention and control. The solution involves multi-dimensional data collection, gathering environmental plant and pest / disease signal data within the planting area. This overcomes the shortcomings of weak early-stage pest and disease signals and insufficient monitoring tools in organic farming environments. Data processing, analysis, and integration of the collected information determine the risk level of pests and diseases and match appropriate control strategies, changing the current situation of blindly applying control methods. Based on this, targeted regulation is implemented using ecological and biological control methods that meet organic standards. Simultaneously, real-time data evaluation of control effectiveness and dynamic feedback optimization of control parameters and strategies form a complete closed-loop control system. This process solves the problem of monitoring lag during control, enhances the number of beneficial biological communities in the planting area through ecological control methods, improves natural pest control capabilities, mitigates the fragility of the planting ecosystem, and enhances the synergy of control methods through closed-loop regulation, while also making emergency response more targeted. Compared with existing technologies, this solution achieves targeted adaptation to organic rose planting scenarios, the control logic is more compatible with the growth characteristics of roses, the stability of control effect is significantly improved, effectively reducing the risk of pest and disease outbreaks, reducing the occurrence of yield decline and substandard quality, and taking into account the sustainability and precision of control, filling the gap in integrated control technology for organic roses.

[0049] Example 2

[0050] This embodiment is based on the foregoing embodiments, such as Figure 1 As shown, step S100 includes the following sub-steps:

[0051] S101. Sampling point layout: The monitoring units are divided according to the different growth stages of organic roses. Environmental sensors, plant status collection points and pest trapping collection points are set up in each unit.

[0052] S102. Multi-dimensional data acquisition: Real-time environmental data is collected through sensors, and plant physiological status data and pest and disease sample data at trapping points are collected periodically.

[0053] S103. Preliminary data verification and removal of abnormal data.

[0054] This embodiment first establishes the data collection points. Independent monitoring units are divided according to different growth stages of roses, such as seedling stage, flowering stage, and harvesting stage, ensuring targeted monitoring in each unit. Environmental sensors, plant status collection points, and pest and disease trapping collection points are strategically placed within each unit. The spacing between collection points is determined based on the area of ​​the monitoring unit and the planting density of the roses, ensuring comprehensive data coverage. Next, a multi-dimensional data collection phase begins. Environmental sensors capture relevant environmental data in real time, and staff regularly collect plant-related data at the plant status collection points. Simultaneously, pest and disease samples are collected at the pest and disease trapping collection points. The entire collection process requires no chemical intervention, avoiding any impact on organic properties. Finally, preliminary data verification is performed, using a combination of data validity threshold judgment and data consistency checks to eliminate abnormal data that exceeds reasonable limits or is contradictory, ensuring the reliability of subsequent data analysis. This solution achieves precise coverage by deploying collection points in stages, ensures comprehensive information through multi-source data collection, and guarantees data quality through preliminary verification. The solution effectively solves the problem of lagging pest and disease monitoring in organic rose cultivation, provides a high-quality data foundation for subsequent data processing and analysis, improves the targeting and comprehensiveness of monitoring, and avoids risk misjudgment caused by insufficient monitoring scope or data anomalies.

[0055] Example 3

[0056] This embodiment is based on the foregoing embodiments, such as Figure 1 As shown, in step S102, the environmental data includes soil temperature and humidity, air temperature and humidity, light intensity and ventilation rate, and the plant physiological status data includes leaf chlorophyll content and plant height growth. The data acquisition process adopts a physical acquisition and sensing monitoring method without chemical intervention.

[0057] Environmental data acquisition utilizes a combination of specialized sensors. Soil temperature and humidity data are collected using a soil temperature and humidity sensor, specifically the SHT30 model. This sensor is inserted 5-10 cm below the soil surface using a probe and detects soil temperature and humidity based on capacitive sensing principles. Air temperature and humidity data are collected using a DHT22 air temperature and humidity sensor. Light intensity data is collected using a BH1750 light sensor, and ventilation rate data is collected using an FS4003 wind speed sensor. All sensors are installed at the locations specified in Example 2 to achieve real-time data acquisition. Leaf chlorophyll content data for plant physiological status is collected using a SPAD-502Plus chlorophyll meter. This instrument uses two different wavelengths of light to illuminate the leaves and calculates the relative chlorophyll content by detecting the intensity of transmitted light. Plant height growth is physically measured using a measuring tape. All data acquisition employs chemical-free physical acquisition and sensing methods to avoid the impact of chemical substances on the organic rose growing environment and plants. This embodiment leverages the precise sensing of specialized sensors and the directness of physical measurements to achieve interference-free acquisition of key data. This solution improves the accuracy and standardization of data collection, while strictly adhering to organic farming standards, avoiding the damage to organic properties caused by chemical intervention, and providing more accurate and reliable data for subsequent risk level assessment. Compared with existing methods, it is more suitable for the needs of organic rose cultivation.

[0058] Example 4

[0059] This embodiment is based on the foregoing embodiments, such as Figure 1 As shown, step S200 includes the following sub-steps:

[0060] S201. Data integration and modeling: The verified multi-dimensional data is structured and integrated, and then input into the preset pest and disease risk assessment model.

[0061] S202. Risk level determination: The model analysis outputs the probability of pest and disease occurrence, potential scope of harm, and risk level.

[0062] S203. Matching of control strategies: Based on the risk level and data characteristics, match the corresponding control measures and implementation parameters from the preset organic control strategy library.

[0063] This embodiment first performs data integration and modeling. The multi-dimensional data, which has undergone preliminary verification in Embodiment 3, is imported into the system. Through data structuring processing, unstructured sample data and structured sensor data are integrated to form a standardized dataset, which is then input into a preset pest and disease risk assessment model. This model is an ensemble model based on machine learning, mainly composed of a data preprocessing module, a feature extraction module, a risk calculation module, and a result output module. The input data includes soil temperature and humidity, air temperature and humidity, light intensity, ventilation rate, leaf chlorophyll content, plant height growth, and pest and disease sample data. The calculation and assessment process is as follows: the preprocessing module normalizes the input data; the feature extraction module uses a random forest algorithm to select the feature parameters most correlated with the occurrence of pests and diseases; the risk calculation module calculates the probability of pest and disease occurrence and the potential range of harm based on the selected feature parameters, and then classifies the risk into three levels: low, medium, and high according to preset probability thresholds and range thresholds. For matching control strategies, the system retrieves the corresponding control measures and implementation parameters from the preset organic control strategy library based on the output risk level and data characteristics. The strategy library pre-stores ecological and biological control measures and related implementation standards suitable for different risk levels.

[0064] This embodiment utilizes the model's data analysis and strategy matching capabilities to determine risks and adapt control strategies, solving the problem of blindly applying existing control methods, improving the pertinence and adaptability of control strategies, and providing a basis for subsequent control. Compared with existing analysis methods, it is more in line with the characteristics and patterns of organic rose pests and diseases.

[0065] Example 5

[0066] This embodiment is based on the foregoing embodiments, such as Figure 1 As shown, in step S201, the preset pest and disease risk assessment model is trained and generated based on historical pest and disease data of organic rose cultivation and corresponding environmental and plant data. The model output results are associated with the prevention and control priorities under different risk levels.

[0067] In this embodiment, the model training phase pre-collects historical pest and disease data for organic rose cultivation, and simultaneously matches corresponding environmental data and plant physiological state data to construct a historical database. This database is divided into a training set and a test set in a 7:3 ratio. The training set is used to train the integrated model, and the test set is used to continuously adjust model parameters and optimize model accuracy, ultimately forming a dedicated model adapted for organic rose cultivation. During model operation, the input data is the standardized dataset integrated in Example 4. The calculation and evaluation process, based on Example 4, adds a control priority correlation logic. Specifically, based on the superposition analysis of risk level and potential hazard range, the priority of control work is determined. High-risk areas with a wide hazard range are set as the highest priority and require priority control measures; medium-risk areas are set as medium priority and control measures are implemented according to the conventional time sequence; low-risk areas are set as low priority and only require enhanced monitoring. The model output data includes the probability of pest and disease occurrence, potential hazard range, risk level, and control priority.

[0068] This embodiment is based on training and optimization using historical data, enabling the model to more accurately capture the patterns of pests and diseases in organic roses. By prioritizing and associating factors, it achieves a reasonable allocation of control resources, thereby improving the targeting and accuracy of the risk assessment model. This avoids the problem of insufficient adaptation of existing models to organic rose planting scenarios. At the same time, by setting control priorities, it improves the efficiency of control work, ensures that high-risk areas are dealt with in a timely manner, and further reduces the risk of pest and disease spread.

[0069] Example 6

[0070] This embodiment is based on the foregoing embodiments, such as Figure 1 As shown, step S300 includes the following sub-steps:

[0071] S301, Ecological regulation, for low to medium risk levels, optimizes the growth environment by adjusting ventilation in the planting area and supplementing organic substrate;

[0072] S302. Biological control: For medium- and high-risk levels, release natural enemy insects or spray plant- or microbial control agents.

[0073] S303. Control process recording: Real-time recording of the implementation details of control measures and synchronously collected environmental and plant data.

[0074] This embodiment initiates corresponding prevention and control measures based on the risk level output in Embodiment 4. For low to medium risk levels, ecological regulation is implemented by activating intelligent ventilation equipment in the planting area to adjust the ventilation rate and adjusting the equipment's operating power in real time based on environmental data feedback. Simultaneously, organic substrate is supplemented to the planting area manually or with small fertilization machinery to optimize the soil ecological environment. For medium to high risk levels, biological control is implemented. If the pests are identified as aphids, spider mites, etc., the corresponding natural enemy insects are released evenly in a preset quantity using a natural enemy release device. If the pests are identified as rose black spot, powdery mildew, etc., plant-derived or microbial-derived control agents are sprayed using an electric sprayer. During the implementation of prevention and control measures, details such as the type, time, dosage, and coverage of the control measures are recorded in real time through a data recording terminal. At the same time, environmental data and plant status data of the implementation area are collected simultaneously to ensure the traceability of the control process.

[0075] This embodiment implements differentiated prevention and control measures based on risk levels, and achieves complete data retention through process recording, providing a basis for subsequent effectiveness evaluation. This solution addresses the problem of poor coordination among existing prevention and control measures, enabling adaptation of measures to different risk levels. Compared to existing single prevention and control measures, it offers more stable prevention and control effects and stronger adaptability.

[0076] Example 7

[0077] This embodiment is based on the foregoing embodiments, such as Figure 1 As shown, step S400 includes the following sub-steps:

[0078] S401. Evaluation indicators are determined by selecting changes in the population size of pests and diseases, the area of ​​plant damage, and the physiological recovery status of plants as core evaluation indicators.

[0079] S402. Real-time data acquisition: Collect assessment indicator data and corresponding environmental data within the prevention and control area at a preset frequency.

[0080] S403. Preliminary assessment of effectiveness: Compare the collected data with the baseline data before prevention and control to preliminarily determine whether the prevention and control effect meets the standard.

[0081] This embodiment first identifies core evaluation indicators, selecting changes in pest and disease populations, affected plant area, and plant physiological recovery status as key evaluation dimensions. Changes in pest and disease populations reflect the inhibitory effect of control measures, affected plant area reflects the protective effect of control measures, and plant physiological recovery status reflects the plant's growth recovery after control measures. Real-time data collection is then conducted. Population data is obtained by counting pest and disease trapping points at a preset frequency. A high-definition camera combined with image recognition technology is used to obtain data on the affected plant area. The sensors and measuring tools described in Example 3 are used to collect physiological recovery data such as leaf chlorophyll content and plant height growth, while corresponding environmental data is collected simultaneously. Finally, a preliminary effect assessment is performed. The collected real-time data and baseline data before control are imported into a data processing terminal. Data comparison software calculates the changes in each indicator. If the pest and disease population decreases, the affected plant area shrinks, and plant physiological indicators return to normal, the control effect is considered satisfactory; otherwise, it is considered unsatisfactory.

[0082] This embodiment achieves an objective and quantitative assessment of the control effect by selecting core indicators and comparing data before and after. This embodiment fills the gap in existing organic rose control methods that lack systematic effect evaluation, enabling real-time monitoring and scientific determination of control effects. It provides a basis for subsequent feedback, optimization, and adjustments, avoiding the problem of delayed or ineffective implementation of measures due to the inability to promptly grasp the control effect.

[0083] Example 8

[0084] This embodiment is based on the foregoing embodiments, such as Figure 1 As shown, step S500 includes the following sub-steps:

[0085] S501. Analysis of assessment results: Combining the data recorded during the prevention and control process with real-time assessment data, analyze the reasons why the prevention and control effect did not meet the standards.

[0086] S502. Adjustment of strategy parameters: For situations where standards are not met, adjust the type of prevention and control measures, implementation timing, or related parameters.

[0087] S503. Model optimization and update: Supplement the historical database with the data from the entire prevention and control process, and optimize the pest and disease risk assessment model.

[0088] This embodiment first analyzes the evaluation results, importing the preliminary judgment results from Embodiment 7 and the control process record data from Embodiment 6 into a data analysis terminal. Combined with synchronously collected environmental data, a causal analysis algorithm is used to investigate the reasons for the failure to meet control standards. If the failure is due to mismatched control methods, the control methods are changed; if the failure is due to inappropriate timing, the implementation sequence is adjusted; if the implementation parameters are unreasonable, parameters such as dosage and frequency are optimized. Subsequently, strategy parameters are adjusted, generating adjustment plans based on the analysis results. Adjustments are executed manually or through intelligent control equipment, such as changing the species of natural enemy insects, adjusting the sprayer's spray volume or interval, etc. Finally, the model is optimized and updated. The collected data, implementation data, evaluation data, and adjustment data from the entire control process are added to the historical database. The newly added data is used to retrain the pest and disease risk assessment model, optimizing the model's feature weights and threshold parameters to improve the model's prediction accuracy.

[0089] This solution identifies the root cause of problems through correlation analysis between evaluation results and process data. It achieves dynamic optimization of the control system through parameter adjustments and model updates, forming a data-driven closed loop. This implementation addresses the lack of dynamic optimization capabilities in existing control methods, enabling the control system to continuously adapt to the pest and disease control needs of organic roses at different growth stages. This improves the sustainability and stability of control measures. Compared to existing fixed control models, it effectively addresses the challenges posed by environmental changes and pest and disease variations, and its long-term application can continuously improve control effectiveness.

[0090] Example 9

[0091] This embodiment sets differentiated collection frequencies based on the changing characteristics of different data. Environmental data, which changes rapidly due to external influences, is collected every 2-4 hours, automatically via timed triggering functions of sensors and data acquisition terminals, with real-time transmission to the data processing center. Plant physiological state data changes relatively slowly, with a collection frequency of every 3-5 days, collected by staff at fixed times using physical measurement and sensing tools. Pest and disease sample data, requiring timely capture of population dynamics, is collected daily. All data are collected in the early morning before dew, avoiding the impact of dew on sensor accuracy. During this time, pest and disease activity is relatively stable, resulting in more representative sample data, and the plant's physiological state is also relatively stable, leading to more accurate measurements. This scheme sets reasonable collection frequencies based on the changing patterns of different data and selects the optimal collection time based on environmental conditions to ensure the timeliness and accuracy of the data. This embodiment avoids data lag due to too low a collection frequency or resource waste due to too high a collection frequency by setting time requirements for data collection. At the same time, by optimizing the collection timing, the accuracy of data collection is improved, providing more reliable data support for subsequent risk assessment and effect determination. Compared with the method without standardized collection time sequence, the data quality is significantly improved.

[0092] The specific scheme can be set up as follows:

[0093] Option 1: Environmental data collection frequency of 2 hours / time, plant physiological status data collection frequency of 3 days / time, and pest and disease sample data collection frequency of 1 day / time; the effect tends to be high-precision monitoring. High-frequency collection can capture subtle changes in the environment and plants to the greatest extent and detect early signs of pests and diseases in a timely manner. It is suitable for the peak season of pests and diseases or the critical growth stage of roses. It can reduce the probability of missed detection, but it will increase the energy consumption of equipment and manpower.

[0094] Option 2: Environmental data collection frequency is 3 hours / time, plant physiological status data collection frequency is 4 days / time, and pest and disease sample data collection frequency is 1 day / time; the effect tends to balance accuracy and efficiency, and reasonably controls collection costs while ensuring the timeliness of data meets the needs of risk assessment, making it suitable for routine monitoring of organic roses during their normal growth stages.

[0095] Option 3: Environmental data collection frequency of 4 hours / time, plant physiological status data collection frequency of 5 days / time, and pest and disease sample data collection frequency of 1 day / time; the effect is inclined towards low-cost and energy-saving monitoring. By reducing the collection frequency, resource consumption is reduced. It is suitable for periods of low incidence of pests and diseases or stable growth stages of roses, which can meet basic monitoring needs while controlling planting costs.

[0096] Example 10

[0097] This embodiment is based on the aforementioned embodiment. In step S302, when it is determined that a plant-derived control agent needs to be sprayed, the total amount to be sprayed is first calculated based on the planting area. The amount to be sprayed in a single area is determined according to the standard of 100-150 ml per square meter. An electric sprayer is selected as the spraying equipment. This equipment pressurizes the control agent through a pump and then atomizes it through the nozzle to ensure that the agent evenly covers both sides of the plant leaves. The spraying interval is set to 5-7 days. This interval is determined based on the effective period of the plant-derived control agent, which can ensure the continuity of the control effect and avoid excessive accumulation of the agent. At the same time, the number of consecutive sprays is strictly controlled to not exceed 2, and the interval between the last spray and the rose harvest is not less than 15 days. The spraying time is recorded by a timer to ensure that it meets the harvesting standards of organic roses. By controlling the spraying amount, interval, and number of sprays, organic planting is followed while ensuring the control effect and avoiding the impact of agent residue on the quality of roses. This embodiment solves the problem of non-standard pesticide application in biological control, ensuring both control effectiveness and organic properties. It avoids substandard quality or control failure caused by unreasonable spraying parameters. Compared with the existing method without standardized spraying parameters, it is more in line with the requirements of organic rose cultivation.

[0098] The specific scheme can be set up as follows:

[0099] Option 1: Spraying dosage 100 ml / m², spraying interval 5 days, one consecutive spray, and a 15-day interval between the last spray and harvest; the effect is geared towards light control and high compliance. The low spraying dosage combined with short-interval single spraying can quickly suppress mild pests and diseases while controlling the amount of pesticide used. The short harvest interval can ensure timely harvesting of roses. It is suitable for scenarios where pests and diseases occur mildly and the harvest period is approaching, minimizing the risk of pesticide residue.

[0100] Option 2: Spraying dosage 125 ml / m², spraying interval 6 days, spray twice consecutively, with an 18-day interval between the last spray and harvest; the effect tends to be balanced between control and quality assurance. The moderate spraying dosage and interval can take into account the continuity of control effect and the risk of pesticide accumulation. Two sprays can effectively deal with moderate pests and diseases. The appropriate harvesting interval balances the control needs and rose quality, and is suitable for the control of moderate pests and diseases during the regular flowering period of organic roses.

[0101] Option 3: Spraying dosage 150 ml / m², spraying interval 7 days, spray twice consecutively, with a 20-day interval between the last spray and harvest; the effect tends to enhance control and safety redundancy. The high spraying dosage can improve the suppression of pests and diseases, the long spraying interval reduces the superposition of pesticides, the two sprays can cover the high incidence period of pests and diseases, and the extended harvest interval further reduces the risk of residues. It is suitable for scenarios with moderate to severe pest and disease occurrence and a long time before harvest.

[0102] The embodiments described above are merely illustrative of specific implementations of the present invention, and while the descriptions are detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention.

Claims

1. A sustainable integrated pest management method for organic roses, characterized in that, Includes the following steps: S100, multi-dimensional data collection, comprehensively collects environmental, plant and pest signal data related to the occurrence of diseases and pests in the organic rose planting area; S200: Data processing and analysis, integrating and analyzing the collected data, determining the risk level of pests and diseases and matching appropriate prevention and control strategies; S300, prevention and control, based on data processing results, implements targeted control measures that include ecological and biological aspects and meet organic standards; S400, real-time data assessment, collects dynamic data after the implementation of prevention and control measures, and assesses the effectiveness of prevention and control; S500, feedback optimization and adjustment, dynamically corrects prevention and control parameters and strategies based on real-time assessment results, forming a data-driven closed-loop prevention and control system.

2. The integrated pest and disease control method for sustainable organic roses according to claim 1, characterized in that, Step S100 includes the following sub-steps: S101. Sampling point layout: The monitoring units are divided according to the different growth stages of organic roses. Environmental sensors, plant status collection points and pest trapping collection points are set up in each unit. S102. Multi-dimensional data acquisition: Real-time environmental data is collected through sensors, and plant physiological status data and pest and disease sample data at trapping points are collected periodically. S103. Preliminary data verification and removal of abnormal data.

3. The integrated pest and disease control method for sustainable organic roses according to claim 2, characterized in that, In step S102, the environmental data includes soil temperature and humidity, air temperature and humidity, light intensity and ventilation rate, and the plant physiological status data includes leaf chlorophyll content and plant height growth. The data acquisition process adopts a physical acquisition and sensing monitoring method without chemical intervention.

4. The integrated pest and disease control method for sustainable organic roses according to claim 1, characterized in that, Step S200 includes the following sub-steps: S201. Data integration and modeling: The verified multi-dimensional data is structured and integrated, and then input into the preset pest and disease risk assessment model. S202. Risk level determination: The model analysis outputs the probability of pest and disease occurrence, potential scope of harm, and risk level. S203. Matching of control strategies: Based on the risk level and data characteristics, match the corresponding control measures and implementation parameters from the preset organic control strategy library.

5. The integrated pest and disease control method for sustainable organic roses according to claim 4, characterized in that, In step S201, the preset pest and disease risk assessment model is trained and generated based on historical pest and disease data of organic rose cultivation and corresponding environmental and plant data. The model output results are associated with the prevention and control priorities under different risk levels.

6. The integrated pest and disease control method for sustainable organic roses according to claim 1, characterized in that, Step S300 includes the following sub-steps: S301, Ecological regulation, for low to medium risk levels, optimizes the growth environment by adjusting ventilation in the planting area and supplementing organic substrate; S302. Biological control: For medium- and high-risk levels, release natural enemy insects or spray plant- or microbial control agents. S303. Control process recording: Real-time recording of the implementation details of control measures and synchronously collected environmental and plant data.

7. The integrated pest and disease control method for sustainable organic roses according to claim 1, characterized in that, Step S400 includes the following sub-steps: S401. Evaluation indicators are determined by selecting changes in the population size of pests and diseases, the area of ​​plant damage, and the physiological recovery status of plants as core evaluation indicators. S402. Real-time data acquisition: Collect assessment indicator data and corresponding environmental data within the prevention and control area at a preset frequency. S403. Preliminary assessment of effectiveness: Compare the collected data with the baseline data before prevention and control to preliminarily determine whether the prevention and control effect meets the standard.

8. The integrated pest and disease control method for sustainable organic roses according to claim 1, characterized in that, Step S500 includes the following sub-steps: S501. Analysis of assessment results: Combining the data recorded during the prevention and control process with real-time assessment data, analyze the reasons why the prevention and control effect did not meet the standards. S502. Adjustment of strategy parameters: For situations where standards are not met, adjust the type of prevention and control measures, implementation timing, or related parameters. S503. Model optimization and update: Supplement the historical database with the data from the entire prevention and control process, and optimize the pest and disease risk assessment model.

9. The integrated pest and disease control method for sustainable organic roses according to claim 2, characterized in that, In step S102, environmental data is collected every 2-4 hours, plant physiological status data is collected every 3-5 days, and pest and disease sample data is collected once a day. The collection time is selected in the early morning when there is no dew.

10. A method for integrated pest and disease control of sustainable organic roses according to claim 6, characterized in that, In step S302, when spraying plant-derived control agents, the spraying amount is controlled at 100-150 ml per square meter, the spraying interval is 5-7 days, the continuous spraying does not exceed 2 times, and the interval between the last spraying and rose harvest is not less than 15 days.

Images