Autonomous heat preservation and moisture preservation special-shaped plant lawn laying method based on high polymer fibers

Abstract

The invention discloses an automatic heat and moisture preservation special-shaped plant lawn laying method based on high polymer fibers, and relates to the technical field of lawn laying, and the method comprises the following steps: after laying of a special-shaped plant lawn is completed, an irrigation system continuously supplies water to the lawn at an initial flow rate, and it is ensured that the water requirement for early growth of the lawn is met; a humidity sensor is installed in a special-shaped plant lawn, the moisture content of the surface of the lawn is monitored in real time, and humidity data obtained by the humidity sensor are summarized to form an analysis set. Through real-time monitoring of the humidity sensor and intelligent prediction of the machine learning model, the lawn water retention risk is accurately judged, the irrigation flow is dynamically adjusted, excessive water accumulation is avoided, and diseases are prevented. Meanwhile, the alarm system timely notifies management personnel to take measures, so that healthy growth of the lawn is guaranteed, the water management accuracy is improved, and the stability of the lawn ecological system is enhanced.

Description

Technical Field

[0001] The invention relates to the technical field of lawn laying, and in particular to a method for laying a self-heat-insulating and moisture-retaining special-shaped plant lawn based on high-polymer fibers. Background Art

[0002] The self-insulating and moisturizing special-shaped plant lawn laying technology based on high-polymer fiber is an innovative lawn laying method that combines the heat preservation and moisture retention properties of high-performance polymer fiber materials to provide plants with a more stable growth environment. This lawn uses specially designed special-shaped structures and materials to ensure that the lawn can adapt to different terrains and climatic conditions, effectively keep the soil moist and slow down water evaporation. High-polymer fiber materials can not only retain heat under low temperature conditions and improve the cold resistance of the lawn, but also maintain the moisture of the soil during droughts, reducing irrigation frequency and water waste. In addition, this technology also has strong environmental adaptability and can be widely used in various natural environments, reducing the maintenance cost required for traditional lawn laying and improving the sustainability and aesthetics of the lawn.

[0003] The prior art has the following deficiencies:

[0004] In the process of laying special-shaped plant lawns, the existing technology usually uses an irrigation system to continuously supply water in a quantitative manner to keep the lawn moist and ensure that the plants get enough water to support normal growth. The purpose of continuous water supply is to provide a stable and appropriate amount of water to prevent the lawn from drying out. However, if the high-polymer fiber material is laid too thick or unevenly on the lawn surface, it will cause excessive accumulation of water in certain areas, especially in areas with poor drainage. At this time, the moisturizing function of the high-polymer fiber may cause water retention on the lawn surface, especially in the case of long-term water supply. When this happens, the existing technology is usually unable to perceive it intelligently. Excessive water accumulation may cause hypoxia in the roots of plants, thereby causing serious diseases such as root rot. This not only inhibits lawn growth, but may even cause large-scale plant death, ultimately affecting the health and stability of the entire ecosystem.

[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 method for laying an autonomous heat-insulating and moisture-retaining special-shaped plant lawn based on high-polymer fiber, which effectively solves the problem of water retention that may be caused by high-polymer fiber materials during the laying of special-shaped plant lawns through an intelligent moisture monitoring and adjustment method. By installing a humidity sensor in the lawn and monitoring the moisture data in real time, combined with the intelligent prediction of the machine learning model, the risk of moisture retention in the lawn area can be accurately judged, and the irrigation flow rate can be dynamically adjusted when an abnormality is found to avoid excessive moisture accumulation and prevent the occurrence of diseases such as root rot. In addition, the alarm system can promptly notify the management personnel to take measures to ensure the healthy growth of the lawn. This method not only improves the accuracy of lawn moisture management, but also reduces plant damage caused by excessive moisture, and enhances the stability and sustainability of the lawn ecosystem 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 method for laying a self-heat-insulating and moisture-retaining special-shaped plant lawn based on high-polymer fiber, comprising the following steps:

[0008] After the shaped plant lawn is laid, the irrigation system will continue to supply water to the lawn at the initial flow rate to ensure that the moisture demand of the lawn in its initial growth is met;

[0009] Install humidity sensors in the lawn of special-shaped plants to monitor the moisture content of the lawn surface in real time, and summarize the humidity data obtained by the humidity sensors to form an analysis set;

[0010] Extract key data reflecting water retention from the analysis set, perform feature engineering on the extracted data under the monitoring window, and preliminarily quantify the water retention of the heteromorphic plant lawn through the processed indicators;

[0011] The data processed by feature engineering is input into a pre-trained machine learning model. The machine learning model makes intelligent predictions based on the input feature data to determine whether there is a risk of excessive water retention in the current irregular plant lawn area.

[0012] When the machine learning model detects that there is a risk of excessive water retention in the lawn, the initial flow of the irrigation system is dynamically regulated based on the model's prediction results. Specifically, the water supply flow is reduced to ensure that the lawn does not accumulate excessive water and avoid damage to the plants caused by water retention.

[0013] When the water supply flow of the irrigation system is adjusted to the set threshold, an alarm will be issued to notify relevant personnel that there is an abnormal moisture problem in the lawn.

[0014] Preferably, the initial flow rate refers to the first stage water flow rate set when the irrigation system starts to supply water after the special-shaped plant lawn is laid. The initial flow rate is used to provide sufficient moisture for the lawn to help the plant roots quickly adapt to the environment and start growth.

[0015] Preferably, the initial flow rate is set between 20% and 40% of the maximum flow rate of the irrigation system to ensure balanced water management of the lawn.

[0016] Preferably, key data reflecting water retention are extracted from the analysis set, wherein the extracted data include the water evaporation rate of the lawn surface and the diffusion rate of humidity between the lawn surface and the soil. Under the monitoring window, the water evaporation rate of the lawn surface and the diffusion rate of humidity between the lawn surface and the soil are subjected to feature engineering processing to generate water evaporation reference values ​​and humidity diffusion reference values, respectively. The water retention of the heteromorphic plant lawn is preliminarily quantified by the water evaporation reference values ​​and the humidity diffusion reference values.

[0017] Preferably, the water evaporation reference value and humidity diffusion reference value processed by feature engineering are input into a pre-trained machine learning model. The machine learning model performs intelligent prediction based on the input feature data and generates a retention assessment coefficient. The retention assessment coefficient is used to determine whether there is a risk of excessive water retention in the current area of ​​the irregular plant lawn.

[0018] Preferably, the retention assessment coefficient generated when the water retention risk of the current irregular plant lawn area is intelligently predicted by the machine learning model is compared and analyzed with a preset retention assessment coefficient reference threshold to determine whether there is a risk of excessive water retention in the current irregular plant lawn area. The specific determination steps are as follows:

[0019] If the retention assessment coefficient is greater than the retention assessment coefficient reference threshold, it is determined that there is a risk of excessive water retention in the current irregular plant lawn area;

[0020] If the retention assessment coefficient is less than or equal to the retention assessment coefficient reference threshold, it is determined that there is no risk of excessive water retention in the current irregular plant lawn area.

[0021] Preferably, in the monitoring window, the specific steps of performing feature engineering processing on the water evaporation rate of the lawn surface to generate a water evaporation reference value are as follows:

[0022] Considering the diffusion and evaporation of water from the lawn surface, the evaporation rate of water on the lawn surface is calculated. The evaporation rate of water is described by the following calculus equation. The specific expression is:

[0023]

[0024] , where: E(x, y) represents the evaporation rate of water on the lawn surface, k is the water diffusion coefficient, which represents the diffusion rate of water from the soil to the surface, is the Laplace operator of the moisture position on the lawn surface, representing the spatial variation of moisture, α is the evaporation constant related to climate conditions, W(x, y) is the moisture content of the lawn surface at position (x, y), and W max is the maximum water retention capacity of the area;

[0025] By integrating the evaporation rate E(x, y) with the moisture content, a water evaporation reference value is generated to quantify the water retention. The water evaporation reference value is calculated by spatially integrating the product of the evaporation rate and the moisture content to represent the overall performance of water evaporation in the lawn area. The calculation expression is:

[0026]

[0027] , where: S ei (x, y) represents the water evaporation reference value, which reflects the evaporation intensity and retention of water in the monitoring area. A is the monitoring area of ​​the lawn. W(x, y) represents the standardized value of water content, which represents the ratio of lawn surface water to the maximum water retention capacity.

[0028] Preferably, in the monitoring window, the specific steps of performing feature engineering processing on the diffusion rate of humidity between the lawn surface and the soil to generate a humidity diffusion reference value are as follows:

[0029] First, the water diffusion model is used to calculate the rate at which water on the lawn surface diffuses into the soil. Assume that the surface humidity of the lawn is H surface and soil moisture is H soil , the humidity diffusion rate is calculated by the following formula:

[0030]

[0031] , where ΔH diff It represents the moisture diffusion rate, that is, the moisture diffusion change caused by the moisture difference between the lawn surface moisture and the soil moisture, R soil It is the soil’s penetration resistance, which represents the soil’s resistance to water penetration;

[0032] According to the calculated humidity diffusion rate, a humidity diffusion reference value is further generated. The generation logic of the humidity diffusion reference value is based on the relationship between the humidity diffusion rate and the soil penetration resistance. It is used to quantify the humidity diffusion condition between the lawn surface and the soil. The calculation formula of the humidity diffusion reference value is as follows:

[0033]

[0034] , where: H dti Indicates the humidity diffusion reference value, C soil It represents the soil characteristic constant, represents the permeability of the soil, and controls the degree of saturation during the diffusion process.

[0035] Preferably, when the machine learning model detects that there is a risk of excessive water retention in the lawn, the initial flow of the irrigation system is dynamically regulated according to the prediction results of the model. The specific steps are as follows:

[0036] The retention assessment coefficient is compared with the preset retention assessment coefficient reference threshold, and the relative risk of water retention is obtained by calculating the difference between the two. The calculation expression is:

[0037]

[0038] , where: ΔRisk is the relative increment of water retention risk, indicating the extent to which the current retention risk exceeds the reference value, Retention eval is the retention evaluation coefficient generated by the machine learning model, Threshold is the preset reference threshold of the retention assessment coefficient, indicating the critical risk value of water retention;

[0039] Based on the calculated risk increment, the initial water supply flow of the irrigation system is adjusted by the dynamic flow control factor. The expression of dynamic adjustment is:

[0040] ΔQ new =Q initial ·(1-τ x )

[0041] , where: Q initial is the initial flow rate of the irrigation system, that is, the initial water supply flow rate, ΔQ new is the adjusted water supply flow, τ x The dynamic flow adjustment factor is dynamically calculated based on the degree of deviation of the retention assessment coefficient. The goal is to prevent water from being retained on the lawn surface and affecting the health of plant roots by appropriately reducing the water supply flow. The calculation formula of the dynamic flow control factor is:

[0042]

[0043] , where: S sensitive is the sensitivity coefficient used to adjust the intensity of the impact of water retention risk on irrigation flow regulation.

[0044] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0045] The present invention effectively solves the problem of water retention that may be caused by high-polymer fiber materials during the laying process of special-shaped plant lawns through an intelligent moisture monitoring and regulation method. By installing a humidity sensor in the lawn and monitoring the moisture data in real time, combined with the intelligent prediction of the machine learning model, it is possible to accurately judge the risk of water retention in the lawn area, and dynamically adjust the irrigation flow when an abnormality is found, to avoid excessive water accumulation and prevent the occurrence of diseases such as root rot. In addition, the alarm system can promptly notify managers to take measures to ensure the healthy growth of the lawn. This method not only improves the accuracy of lawn moisture management, but also reduces plant damage caused by excessive moisture, and enhances the stability and sustainability of the lawn ecosystem. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] 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.

[0047] Figure 1 The present invention is a method flow chart of a method for laying a self-heat-insulating and moisture-retaining special-shaped plant lawn based on high-polymer fiber. DETAILED DESCRIPTION

[0048] 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.

[0049] The present invention provides Figure 1 The method for laying a high-polymer fiber-based autonomous heat-insulating and moisture-retaining special-shaped plant lawn includes the following steps:

[0050] After the shaped plant lawn is laid, the irrigation system will continue to supply water to the lawn at the initial flow rate to ensure that the moisture demand of the lawn in its initial growth is met;

[0051] The purpose of this step is to provide an initial moist environment for the lawn, ensuring that the plants can get enough water to support their growth when they are first laid. Proper water supply helps the plants quickly adapt to the new environment and avoids early growth stagnation due to lack of water.

[0052] Definition of initial flow:

[0053] Initial flow refers to the first stage water flow set when the irrigation system starts to supply water after the shaped plant lawn is laid. This flow is used to provide enough water for the lawn to help the plant roots quickly adapt to the environment and start growing. The initial flow is usually mild and will not cause excessive water accumulation, but ensure that the lawn is adequately supported by water in the initial stage to avoid drought or premature drying. It is the first step in lawn irrigation management. Setting a reasonable initial flow can provide a reference for subsequent water regulation.

[0054] How to set the initial flow rate:

[0055] The setting of the initial flow rate needs to take into account multiple factors, including the type of lawn plants, soil drainage, climatic conditions, and the moisture requirements of the lawn. Generally speaking, the initial flow rate should match the soil's water infiltration capacity and the plant's water absorption capacity to prevent excessive or insufficient water accumulation. When setting it specifically, the flow rate of the irrigation system can be adjusted by testing the moisture content of the soil, the lawn's moisture requirements, and local climatic conditions. Normally, the initial flow rate will be set between 20%-40% of the maximum flow rate of the irrigation system to ensure balanced moisture management of the lawn.

[0056] The initial flow rate is set to 20%-40% of the maximum flow rate of the irrigation system to ensure that the lawn can obtain sufficient water in the early stage of laying, while avoiding excessive water accumulation or water retention. The basis for this setting is mainly based on the soil's water absorption and drainage capacity and the water demand of the plant. In the early stage of lawn laying, the soil is not yet completely stable. Excessive water flow may cause the water to not be absorbed in time, causing water accumulation and increasing the risk of root hypoxia. A smaller flow rate can ensure that water penetrates evenly into the deep soil layer, helping the plant roots to take root and grow smoothly. Existing technologies usually set the initial flow rate based on soil moisture, plant needs and climatic conditions. This ratio range (20%-40%) is considered to be an effective and safe starting point for water supply in actual operations, which helps to achieve healthy growth and reasonable irrigation of the lawn.

[0057] Install humidity sensors in the lawn of special-shaped plants to monitor the moisture content of the lawn surface in real time, and summarize the humidity data obtained by the humidity sensors to form an analysis set;

[0058] The layout of humidity sensors should be designed according to the specific conditions of the lawn to ensure that the entire lawn area is covered, especially those areas where moisture may be trapped. Humidity sensors can collect soil moisture data at regular intervals and transmit this data to the central control system. By collecting moisture data in real time, humidity sensors provide accurate basic information for subsequent data analysis. This step ensures real-time monitoring of lawn moisture conditions.

[0059] Extract key data reflecting water retention from the analysis set, perform feature engineering on the extracted data under the monitoring window, and preliminarily quantify the water retention of the heteromorphic plant lawn through the processed indicators;

[0060] Key data reflecting water retention are extracted from the analysis set, including the water evaporation rate of the lawn surface and the diffusion rate of humidity between the lawn surface and the soil. Under the monitoring window, the water evaporation rate of the lawn surface and the diffusion rate of humidity between the lawn surface and the soil are feature engineered to generate water evaporation reference values ​​and humidity diffusion reference values, respectively. The water retention of the heteromorphic plant lawn is preliminarily quantified by the water evaporation reference values ​​and the humidity diffusion reference values.

[0061] After the laying of the special-shaped plant lawn, the low evaporation rate of the lawn surface usually indicates that the lawn is at risk of water retention. The evaporation rate is an important indicator of the surface water dynamics of the lawn. Under normal circumstances, the surface water of the lawn will gradually decrease during the day through evaporation and plant transpiration. If the evaporation rate of the lawn surface is low, it may mean that the water has not effectively penetrated or evaporated, but is retained in the surface of the lawn or in the soil. This water retention may be caused by poor soil drainage, excessive moisture retention of high-polymer fiber materials, etc. Excessive water accumulation will lead to root hypoxia, which in turn causes diseases such as root rot. Therefore, a low evaporation rate can be used as a potential indicator of water retention, suggesting that the water management of the lawn needs to be further monitored.

[0062] Under the monitoring window, the specific steps for feature engineering the water evaporation rate of the lawn surface to generate the water evaporation reference value are as follows:

[0063] To calculate the evaporation rate of water from the lawn surface, we first need to consider the volatilization and loss of water from the lawn surface. The evaporation rate is not only affected by the surface humidity, but also by environmental factors such as temperature and wind speed. By considering the diffusion and evaporation of water from the lawn surface, the evaporation rate can be described by the following calculus equation:

[0064]

[0065] , where: E(x, y) represents the evaporation rate of water on the lawn surface, k is the water diffusion coefficient, which represents the diffusion rate of water from the soil to the surface, is the Laplace operator of the moisture position on the lawn surface, representing the spatial variation of moisture (i.e., the rate of moisture loss), α is the evaporation constant related to climate conditions (such as temperature and wind speed), W(x, y) is the moisture content of the lawn surface at position (x, y), and W max is the maximum water retention capacity of the area;

[0066] This step describes the spatial diffusion of water by using the Laplace operator, combining the evaporation constant α and the maximum water content W max , effectively reflects the spatial differences in water loss on the lawn surface, thus providing a basis for subsequent water retention assessment. The calculated water evaporation rate can accurately reflect the water changes in the lawn area and identify possible water accumulation areas.

[0067] The evaporation constant α can be obtained through a series of experiments and theoretical derivations. Generally, the evaporation constant is closely related to environmental factors such as temperature, wind speed, air humidity, and the physical properties of the lawn surface (such as surface roughness, soil type, etc.). By experimentally measuring the evaporation rate of water on the lawn surface under a specific environment, and based on known meteorological conditions (such as temperature and wind speed), the value of α can be derived using a classic evaporation model (such as the Penman-Monteith formula). Specifically, the evaporation constant is usually calibrated according to the climatic conditions, seasonal changes, and characteristics of lawn planting in different regions to ensure its accuracy in practical applications. In the experiment, the evaporation rate of the lawn can be measured by controlling variables such as temperature, humidity, and wind speed, and the α value associated with these variables can be determined using regression analysis methods.

[0068] By integrating the evaporation rate E(x, y) with the moisture content, a water evaporation reference value is generated to quantify the water retention. The water evaporation reference value is calculated by spatially integrating the product of the evaporation rate and the moisture content to represent the overall performance of water evaporation in the lawn area. The calculation expression is:

[0069]

[0070] , where: S ei (x, y) represents the water evaporation reference value, which reflects the evaporation intensity and retention of water in the monitoring area, A is the monitoring area of ​​the lawn, W(x, y) represents the standardized value of water content, which represents the ratio of the surface water of the lawn to the maximum water retention capacity;

[0071] The purpose of this step is to integrate the relationship between the evaporation rate and the moisture content, comprehensively consider the evaporation status of the lawn in the spatial range, and generate an overall evaporation reference value. The evaporation reference value can intuitively reflect the severity of water retention in the lawn area. If the evaporation reference value is low, it indicates that the water evaporation in the area is not smooth and there is a risk of retention.

[0072] It can be seen from the water evaporation reference value that under the monitoring window, the smaller the performance value of the water evaporation reference value generated by feature engineering of the water evaporation rate on the lawn surface, the lower the water evaporation rate on the lawn surface, which usually indicates that the accumulation of water on the lawn surface is high, thereby increasing the risk of water retention. When the evaporation rate of water on the lawn surface is low, the water fails to evaporate from the soil or surface in time, which may indicate that the drainage of the lawn is poor, or that the water has been excessively retained in the surface layer, hindering normal water loss. On the contrary, if the value of the water evaporation reference value is large, it indicates that the water evaporation rate on the lawn surface is high, the water can evaporate in time, and the retention phenomenon is less, so the risk of water retention is small. Therefore, the change of the water evaporation reference value can effectively reflect whether there is a potential risk of water retention in the lawn.

[0073] After the laying of the special-shaped plant lawn, if the diffusion rate of moisture between the lawn surface and the soil is slow, this usually indicates that the lawn is at risk of water retention. When moisture cannot quickly penetrate into the deep soil layer, or when moisture stagnates on the surface for a long time, moisture tends to accumulate on the surface, leading to the occurrence of water retention. This situation may be caused by poor soil drainage, imperfect drainage structure in the lower layer of the lawn, or excessive moisture-retaining materials (such as high-polymer fibers). When moisture stays on the lawn surface or upper soil for a long time, it is easy to cause root hypoxia, thereby increasing the risk of plant growth disorders, root rot and other diseases. Therefore, a slow moisture diffusion rate is an important indicator of water retention and can be used as a key factor in judging lawn health and drainage capacity.

[0074] Under the monitoring window, the specific steps for feature engineering the diffusion rate of humidity between the lawn surface and the soil to generate a humidity diffusion reference value are as follows:

[0075] The humidity diffusion rate refers to the mutual diffusion rate between the moisture on the lawn surface and the moisture in the soil. First, the moisture diffusion model is used to calculate the diffusion rate of moisture on the lawn surface to the soil. Assume that the surface humidity of the lawn is H surface and soil moisture is H soil , the humidity diffusion rate is calculated by the following formula:

[0076]

[0077] , where ΔH diff It represents the moisture diffusion rate, that is, the moisture diffusion change caused by the moisture difference between the lawn surface moisture and the soil moisture, R soil It is the soil’s penetration resistance, which represents the soil’s resistance to water penetration;

[0078] The purpose of this step is to evaluate the diffusion rate of water in the lawn by calculating the humidity difference and soil penetration resistance, and to help preliminarily determine whether the water can penetrate effectively and avoid retention.

[0079] According to the calculated humidity diffusion rate, a humidity diffusion reference value is further generated. The generation logic of the humidity diffusion reference value is based on the relationship between the humidity diffusion rate and the soil penetration resistance. It is used to quantify the humidity diffusion condition between the lawn surface and the soil. The calculation formula of the humidity diffusion reference value is as follows:

[0080]

[0081] , where: H dti Indicates the humidity diffusion reference value, C soil Represents the soil property constant, represents the permeability of the soil, controls the saturation level during the diffusion process, and uses an exponential function It can effectively reflect the nonlinear effect of humidity difference on diffusion rate and suppress the diffusion rate in the case of water retention, so that the humidity diffusion reference value can more sensitively reflect the retention risk;

[0082] The generation of a humidity diffusion reference value can quantify the efficiency of water diffusion. A low humidity diffusion reference value usually means that the water on the lawn surface cannot be effectively diffused to the soil, and there is a significant retention problem; while a high humidity diffusion reference value indicates that the water is well diffused and there is less retention. Through the humidity diffusion reference value, the system can detect potential water retention areas in real time.

[0083] It can be seen from the moisture evaporation reference value that under the monitoring window, the smaller the performance value of the humidity diffusion reference value generated by feature engineering of the diffusion rate of humidity between the lawn surface and the soil, the smaller the humidity difference between the lawn surface moisture and the soil moisture, and the slower the diffusion rate of moisture in the lawn, which usually indicates that the moisture fails to effectively penetrate into the soil layer, which may cause moisture retention on the lawn surface, thereby increasing the risk of moisture retention. On the contrary, if the performance value of the humidity diffusion reference value is large, it indicates that the diffusion rate of moisture between the lawn surface and the soil is fast, and the moisture can quickly penetrate from the surface to the soil, avoiding excessive water accumulation and retention problems. Therefore, the humidity diffusion reference value can be used as an effective indicator for moisture retention risk assessment. The smaller the value, the greater the retention risk, and vice versa, it means that the moisture penetration is good and the retention risk is small.

[0084] The data processed by feature engineering is input into a pre-trained machine learning model. The machine learning model makes intelligent predictions based on the input feature data to determine whether there is a risk of excessive water retention in the current irregular plant lawn area.

[0085] The water evaporation reference value and humidity diffusion reference value processed by feature engineering are input into a pre-trained machine learning model. The machine learning model performs intelligent prediction based on the input feature data and generates a retention assessment coefficient. The retention assessment coefficient is used to determine whether there is a risk of excessive water retention in the current irregular plant lawn area.

[0086] A pre-trained machine learning model is an algorithmic model that has been trained, optimized, and validated with a large amount of data before use. In the context of lawn water retention, this model has been trained with a series of specific data sets to identify patterns and features of lawn water retention. The training process is a process of learning the relationship between input data and target results through an algorithm. During this process, the machine learning model continuously adjusts its internal parameters to improve prediction accuracy and reliability. In this scenario, the training process uses a data set containing humidity data, water evaporation reference values, humidity diffusion reference values, and known retention conditions to learn the laws of lawn water behavior, diffusion characteristics, and retention risk. Through this training process, the model can automatically extract meaningful patterns from the input feature data, thereby predicting the risk of lawn water retention.

[0087] In order to enable the model to effectively predict the risk of moisture retention in lawns, it is necessary to use appropriate machine learning algorithms. Common algorithms include decision trees, support vector machines, random forests, neural networks, etc. Different algorithms have different ways of processing data, but they all rely on the correlation between input feature data (such as humidity evaporation index, humidity diffusion reference value, etc.) and target variables (i.e., whether there is a risk of moisture retention). For example, the support vector machine algorithm classifies data by finding the best boundary, while the random forest makes predictions based on the voting results of multiple decision trees. The trained model uses specific feature weights (obtained through continuous optimization during the training process) in each node to accurately predict whether there is a risk of excessive moisture retention in the lawn area based on given humidity data (including indicators such as evaporation and diffusion). When training these models, they are first trained with labeled data sets (including actually observed moisture retention data and non-retention data). The model is adjusted through continuous feedback, and finally forms a system that can make accurate predictions based on new input data. During the process of laying and maintaining lawns, the system obtains humidity data of the lawn area through real-time monitoring and inputs these data into the trained machine learning model. Based on the learned rules, the model outputs a retention assessment coefficient, which measures the risk of water retention in the lawn area. A high retention assessment coefficient indicates that there may be excessive water retention in the area, while a low retention assessment coefficient indicates that the moisture status of the lawn is within the normal range and there is no risk of excessive retention.

[0088] In order to train the machine learning model, a large amount of historical data needs to be collected first. These data include the humidity changes of the lawn, the evaporation of water in different areas, the reference value of humidity diffusion, and the final retention. These data can be obtained through humidity sensors installed on the lawn and other environmental monitoring equipment. The collected data contains multiple variables, such as lawn surface humidity, soil humidity, precipitation, temperature, wind speed, etc., which work together to manage the moisture of the lawn. After feature engineering processing, key parameters such as humidity evaporation index and humidity diffusion reference value are extracted as input features of the model. These features not only describe the diffusion rate of water in the lawn and the law of humidity changes, but also reflect information such as the drainage capacity of the soil and the use of moisturizing materials. In the model training stage, the algorithm will learn based on the relationship between these features and the actual retention risk, so as to identify which factors can most affect the moisture retention of the lawn, and then build a prediction model.

[0089] When the machine learning model is fully trained, it can be used to monitor the moisture status of the lawn in real time. By inputting the real-time collected humidity data into the trained model, the system can quickly make a judgment and assess whether there is a risk of excessive water retention in the current lawn area. For example, assuming that the system detects that the humidity diffusion rate in a certain area is low (that is, the water fails to effectively penetrate the soil) and the water evaporation reference value is also low (that is, the water evaporates slowly), the model can judge that there is a risk of water retention in the area based on the learned pattern. The model generates a retention assessment coefficient based on the feature input. Usually, this retention assessment coefficient is a continuous value used to quantify the severity of retention. When the retention assessment coefficient is high, it means that the risk of water retention in the area is high, which may cause root hypoxia, plant diseases and other problems. When the retention assessment coefficient is low, it indicates that water penetration and evaporation are normal and there is no obvious water retention problem.

[0090] The machine learning model is not specifically limited here, and can achieve the water evaporation reference value S ei (x, y) and humidity diffusion reference value H dti Perform comprehensive analysis to generate retention evaluation coefficient eval In order to realize the technical solution of the present invention, the present invention provides a specific implementation method; the retention evaluation coefficient Retention eval The resulting calculation formula is:

[0091]

[0092] , where p x 、p y They are respectively the water evaporation reference values ​​S ei (x, y) and humidity diffusion reference value Hdti The weight factor, and p x 、p y Both are greater than 0.

[0093] It can be seen from the retention assessment coefficient that, under the monitoring window, the smaller the performance value of the moisture evaporation reference value generated by feature engineering the moisture evaporation rate of the lawn surface, the smaller the performance value of the humidity diffusion reference value generated by feature engineering the diffusion rate of humidity between the lawn surface and the soil. That is, under the monitoring window, the larger the performance value of the retention assessment coefficient generated when the moisture retention risk of the current irregular plant lawn area is intelligently predicted by the pre-trained machine learning model, the greater the risk of moisture retention in the lawn, and vice versa.

[0094] The retention assessment coefficient generated by the intelligent prediction of the water retention risk of the current irregular plant lawn area through the machine learning model is compared and analyzed with the preset retention assessment coefficient reference threshold to determine whether there is a risk of excessive water retention in the current irregular plant lawn area. The specific judgment steps are as follows:

[0095] If the retention assessment coefficient is greater than the retention assessment coefficient reference threshold, it is determined that there is a risk of excessive water retention in the current irregular plant lawn area;

[0096] If the retention assessment coefficient is less than or equal to the retention assessment coefficient reference threshold, it is determined that there is no risk of excessive water retention in the current irregular plant lawn area.

[0097] When the machine learning model detects that there is a risk of excessive water retention in the lawn, the initial flow of the irrigation system is dynamically regulated based on the model's prediction results. Specifically, the water supply flow is reduced to ensure that the lawn does not accumulate excessive water and avoid damage to the plants caused by water retention.

[0098] When the machine learning model detects that there is a risk of excessive water retention in the lawn, the initial flow of the irrigation system is dynamically adjusted based on the model's prediction results. The specific steps are as follows:

[0099] The retention assessment coefficient is compared with the preset retention assessment coefficient reference threshold, and the relative risk of water retention is obtained by calculating the difference between the two. The calculation expression is:

[0100]

[0101] , where: ΔRisk is the relative increment of water retention risk, indicating the extent to which the current retention risk exceeds the reference value, Retention eval is the retention evaluation coefficient generated by the machine learning model, Thresholdis the preset reference threshold of the retention assessment coefficient, indicating the critical risk value of water retention;

[0102] The purpose of this step is to determine the water retention risk of the lawn area by calculating the difference between the retention assessment coefficient and the reference threshold, providing a basis for subsequent dynamic regulation.

[0103] Based on the calculated risk increment, the initial water supply flow of the irrigation system is adjusted by the dynamic flow control factor. The expression of dynamic adjustment is:

[0104] ΔQ new =Q initial ·(1-τ x )

[0105] , where: Q initial is the initial flow rate of the irrigation system, that is, the initial water supply flow rate, ΔQ new is the adjusted water supply flow, τ x The dynamic flow adjustment factor is dynamically calculated based on the degree of deviation of the retention assessment coefficient. The goal is to prevent water from being retained on the lawn surface and affecting the health of plant roots by appropriately reducing the water supply flow. The calculation formula of the dynamic flow control factor is:

[0106]

[0107] , where: S sensitive is the sensitivity coefficient, which is used to adjust the impact of water retention risk on irrigation flow regulation. The value of the sensitivity coefficient can be adjusted according to specific needs. If the sensitivity coefficient S sensitive A larger value means that the response to water retention is more sensitive and the flow rate will be adjusted significantly. sensitive If it is smaller, the reaction will be milder and the flow adjustment will be smaller;

[0108] The formula reduces the flow factor to reflect the risk of water retention, thereby avoiding excessive water accumulation in the lawn area. Specifically, the dynamic flow adjustment factor τ x The risk of excessive retention can be effectively converted into a dynamic adjustment value for water supply flow. When the risk of retention is high, the flow is adjusted to reduce irrigation and maintain the balance of lawn moisture.

[0109] When the machine learning model detects that there is a risk of excessive water retention in the lawn, it can effectively prevent excessive water accumulation on the lawn surface by dynamically adjusting the initial flow of the irrigation system, specifically by reducing the water supply flow. Excessive water accumulation can cause plant root hypoxia, thereby increasing the risk of diseases such as root rot. By reducing the water supply flow and reducing water retention, the appropriate humidity level of the lawn soil and surface can be maintained, promoting uniform water penetration and evaporation, ensuring the healthy growth of the lawn, and avoiding the adverse effects of excessive water, thereby improving the accuracy of lawn management and ecological stability.

[0110] When the water supply flow of the irrigation system is adjusted to the set threshold, an alarm will be issued to inform relevant personnel that the lawn has abnormal moisture problems;

[0111] When the water supply flow of the irrigation system is adjusted to the set threshold, the purpose of issuing an alarm is to promptly notify relevant personnel of abnormal moisture problems in the lawn, ensuring that managers can respond quickly and take necessary measures. Through real-time monitoring and alarm mechanisms, the health of the lawn can be prevented from being affected when moisture is retained or the water supply is insufficient. Alarm prompts provide timely warnings for decision-making, helping managers identify potential problems as early as possible and intervene, such as adjusting irrigation strategies, increasing drainage capacity, or improving soil management, thereby ensuring that the growth environment of the lawn is always in an ideal state, reducing the risk of disease, and ensuring the long-term health and stability of the lawn.

[0112] This alarm can be sent through mobile phone applications, emails or other communication tools to ensure that managers receive information in time and take necessary measures for manual intervention. The purpose of the alarm is to ensure the timeliness of manual intervention. While automatically adjusting the irrigation flow, the alarm system provides managers with an additional safety guarantee to avoid extreme situations or potential failures that the system cannot handle being ignored, thereby ensuring the long-term health of the lawn.

[0113] The present invention effectively solves the problem of water retention that may be caused by high-polymer fiber materials during the laying process of special-shaped plant lawns through an intelligent water monitoring and regulation method. By installing humidity sensors in the lawn and monitoring water data in real time, combined with the intelligent prediction of the machine learning model, it is possible to accurately judge the water retention risk of the lawn area, and dynamically adjust the irrigation flow when an abnormality is found, to avoid excessive water accumulation and prevent the occurrence of diseases such as root rot. In addition, the alarm system can promptly notify managers to take measures to ensure the healthy growth of the lawn. This method not only improves the accuracy of lawn water management, but also reduces plant damage caused by excessive water, and enhances the stability and sustainability of the lawn ecosystem.

[0114] 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.

[0115] 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.

[0116] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for laying an autonomous heat-insulating and moisture-retaining special-shaped plant lawn based on high-polymer fiber, characterized in that: The following steps are involved: After the shaped plant lawn is laid, the irrigation system will continue to supply water to the lawn at the initial flow rate to ensure that the moisture demand of the lawn in its initial growth is met; Install humidity sensors in the lawn of special-shaped plants to monitor the moisture content of the lawn surface in real time, and summarize the humidity data obtained by the humidity sensors to form an analysis set; Extract key data reflecting water retention from the analysis set, perform feature engineering on the extracted data under the monitoring window, and preliminarily quantify the water retention of the heteromorphic plant lawn through the processed indicators; The data processed by feature engineering is input into a pre-trained machine learning model. The machine learning model makes intelligent predictions based on the input feature data to determine whether there is a risk of excessive water retention in the current irregular plant lawn area. When the machine learning model detects that there is a risk of excessive water retention in the lawn, the initial flow of the irrigation system is dynamically regulated based on the model's prediction results. Specifically, the water supply flow is reduced to ensure that the lawn does not accumulate excessive water and avoid damage to the plants caused by water retention. When the water supply flow of the irrigation system is adjusted to the set threshold, an alarm will be issued to notify relevant personnel that there is an abnormal moisture problem in the lawn.

2. The method for laying a high-polymer fiber-based autonomous heat-insulating and moisture-retaining special-shaped plant lawn according to claim 1, characterized in that: The initial flow rate refers to the first stage water flow rate set when the irrigation system starts to supply water after the special-shaped plant lawn is laid. The initial flow rate is used to provide sufficient moisture for the lawn to help the plant roots quickly adapt to the environment and start growing.

3. The method for laying a high-polymer fiber-based autonomous heat-insulating and moisture-retaining special-shaped plant lawn according to claim 1, characterized in that: The initial flow rate is set between 20% and 40% of the maximum flow rate of the irrigation system to ensure balanced moisture management of the lawn.

4. The method for laying a high-polymer fiber-based autonomous heat-insulating and moisture-retaining special-shaped plant lawn according to claim 1, characterized in that: Key data reflecting water retention are extracted from the analysis set, including the water evaporation rate of the lawn surface and the diffusion rate of humidity between the lawn surface and the soil. Under the monitoring window, the water evaporation rate of the lawn surface and the diffusion rate of humidity between the lawn surface and the soil are feature engineered to generate water evaporation reference values ​​and humidity diffusion reference values, respectively. The water retention of the heteromorphic plant lawn is preliminarily quantified by the water evaporation reference values ​​and the humidity diffusion reference values.

5. The method for laying a high-polymer fiber-based autonomous heat-insulating and moisture-retaining special-shaped plant lawn according to claim 4, characterized in that: The water evaporation reference value and humidity diffusion reference value processed by feature engineering are input into a pre-trained machine learning model. The machine learning model performs intelligent prediction based on the input feature data and generates a retention assessment coefficient. The retention assessment coefficient is used to determine whether there is a risk of excessive water retention in the current irregular plant lawn area.

6. The method for laying a high-polymer fiber-based autonomous heat-insulating and moisture-retaining special-shaped plant lawn according to claim 5, characterized in that: The retention assessment coefficient generated by the intelligent prediction of the water retention risk of the current irregular plant lawn area through the machine learning model is compared and analyzed with the preset retention assessment coefficient reference threshold to determine whether there is a risk of excessive water retention in the current irregular plant lawn area. The specific judgment steps are as follows: If the retention assessment coefficient is greater than the retention assessment coefficient reference threshold, it is determined that there is a risk of excessive water retention in the current irregular plant lawn area; If the retention assessment coefficient is less than or equal to the retention assessment coefficient reference threshold, it is determined that there is no risk of excessive water retention in the current irregular plant lawn area.

7. The method for laying a high-polymer fiber-based autonomous heat-insulating and moisture-retaining special-shaped plant lawn according to claim 4, characterized in that: Under the monitoring window, the specific steps for feature engineering the water evaporation rate of the lawn surface to generate the water evaporation reference value are as follows: Considering the diffusion and evaporation of water from the lawn surface, the evaporation rate of water on the lawn surface is calculated. The evaporation rate of water is described by the following calculus equation. The specific expression is: ， Where: E(x, y) represents the evaporation rate of water on the lawn surface, k is the water diffusion coefficient, which represents the diffusion rate of water from the soil to the surface, is the Laplace operator of the moisture position on the lawn surface, representing the spatial variation of moisture, α is the evaporation constant related to climate conditions, W(x, y) is the moisture content of the lawn surface at position (x, y), and W max is the maximum water retention capacity of the area; By integrating the evaporation rate E(x, y) with the moisture content, a water evaporation reference value is generated to quantify the water retention. The water evaporation reference value is calculated by spatially integrating the product of the evaporation rate and the moisture content to represent the overall performance of water evaporation in the lawn area. The calculation expression is: ， Where: S ei (x, y) represents the water evaporation reference value, which reflects the evaporation intensity and retention of water in the monitoring area. A is the monitoring area of ​​the lawn. W(x, y) represents the standardized value of water content, which represents the ratio of lawn surface water to the maximum water retention capacity.

8. The method for laying a thermal insulation and moisture-retaining special-shaped plant lawn based on high-polymer fiber according to claim 4, characterized in that: Under the monitoring window, the specific steps for feature engineering the diffusion rate of humidity between the lawn surface and the soil to generate a humidity diffusion reference value are as follows: First, the water diffusion model is used to calculate the rate at which water on the lawn surface diffuses into the soil. Assume that the surface humidity of the lawn is H surface and soil moisture is H soil , the humidity diffusion rate is calculated by the following formula: ， Where ΔH diff It represents the moisture diffusion rate, that is, the moisture diffusion change caused by the moisture difference between the lawn surface moisture and the soil moisture, R soil It is the soil’s penetration resistance, which represents the soil’s resistance to water penetration; According to the calculated humidity diffusion rate, a humidity diffusion reference value is further generated. The generation logic of the humidity diffusion reference value is based on the relationship between the humidity diffusion rate and the soil penetration resistance. It is used to quantify the humidity diffusion condition between the lawn surface and the soil. The calculation formula of the humidity diffusion reference value is as follows: ， Where: H dti Indicates the humidity diffusion reference value, C soil It represents the soil characteristic constant, represents the permeability of the soil, and controls the degree of saturation during the diffusion process.

9. The method for laying a high-polymer fiber-based autonomous heat-insulating and moisture-retaining special-shaped plant lawn according to claim 6, characterized in that: When the machine learning model detects that there is a risk of excessive water retention in the lawn, the initial flow of the irrigation system is dynamically adjusted based on the model's prediction results. The specific steps are as follows: The retention assessment coefficient is compared with the preset retention assessment coefficient reference threshold, and the relative risk of water retention is obtained by calculating the difference between the two. The calculation expression is: ， Among them: ΔRisk is the relative increment of water retention risk, indicating the degree to which the current retention risk exceeds the reference value, Retention eval is the retention evaluation coefficient generated by the machine learning model, Threshold is the preset reference threshold of the retention assessment coefficient, indicating the critical risk value of water retention; Based on the calculated risk increment, the initial water supply flow of the irrigation system is adjusted by the dynamic flow control factor. The expression of dynamic adjustment is: ΔQ new =Q initial ·(1-τ x ), Where: Q initial is the initial flow rate of the irrigation system, that is, the initial water supply flow rate, ΔQ new is the adjusted water supply flow, τ x The dynamic flow adjustment factor is dynamically calculated based on the degree of deviation of the retention assessment coefficient. The goal is to prevent water from being retained on the lawn surface and affecting the health of plant roots by appropriately reducing the water supply flow. The calculation formula of the dynamic flow control factor is: ， Where: S sensitive is the sensitivity coefficient used to adjust the intensity of the impact of water retention risk on irrigation flow regulation.

Images