Municipal garden soil humidity intelligent regulation and control method

Abstract

The invention provides a municipal garden soil humidity intelligent regulation and control method which comprises the following steps: acquiring environmental characteristics of a target area, and constructing a plant collaborative water demand model according to the acquired environmental characteristics of the target area; continuously monitoring environmental characteristics of the target area, and inputting the environmental characteristics into the plant collaborative water demand model to obtain water demand data of the target area; the method comprises the following steps: collecting water demand data of a target area, constructing a plant irrigation water model according to the collected water demand data of plants in the target area so as to output the water consumption of the plants in the target area in a growth stage, and collecting multi-dimensional water demand data such as plant transpiration rate, stomatal conductance and in-vivo moisture content so as to obtain the water consumption of the plants in the target area. The model is built by combining the environmental parameters and the growth stage information, the specific water consumption of the plant in the current growth stage can be accurately output, the irrigation accuracy is greatly improved, and the negative influence on plant growth caused by insufficient or excessive irrigation is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of municipal gardens, and in particular to an intelligent control method for soil moisture in municipal gardens. Background Art

[0002] Soil moisture control is crucial in the construction and management of municipal gardens, especially in areas with unique geographical environments, such as islands. The unique climatic and geographical conditions of islands present numerous challenges for regulating soil moisture in gardens. For one thing, the sources of salt are complex and diverse. Strong sea breezes frequently carry large quantities of salt particles, depositing them on garden soils. Over time, this can significantly increase soil salinity. If garden irrigation water involves desalinated water or groundwater affected by seawater infiltration, residual salt in the water will continue to accumulate in the soil. Furthermore, some island vegetation has inherent salt-secreting properties, releasing salt into the surrounding soil during its growth and metabolism, further complicating the dynamic changes in soil salinity.

[0003] On the other hand, existing intelligent control systems have significant flaws. Their soil moisture and irrigation strategies often set parameters and algorithms based on the water requirements of plants under normal soil conditions. Faced with the rapid and complex changes in island soil salinity, they lack real-time monitoring and effective feedback mechanisms for salinity changes. The system is unable to quickly detect soil salinity fluctuations and adjust irrigation strategies in a timely manner. When salinity rises, plant roots are hampered from absorbing water due to changes in osmotic pressure, while the system continues to irrigate according to the original pattern. This not only fails to alleviate plant water shortages, but the excess water also dissolves more salt, exacerbating root toxicity. When salinity decreases, the system is unable to adjust irrigation levels in a timely manner, potentially affecting plant growth due to insufficient water supply.

[0004] Furthermore, plant water requirement models have serious deficiencies. Different plants exhibit significant variations in their physiological responses and water requirements under salt stress. Island plants, having long adapted to their specialized habitats, have even more unique water requirements. However, the plant water requirement models built into existing regulatory systems are overly rigid and fail to fully account for the dynamic water requirements of island plants in complex salinity environments. This makes it difficult to accurately determine the actual water needs of various plant species, and it is impossible to provide precise irrigation plans for garden plants that are tailored to their growth stage and salinity.

[0005] At the same time, there is a lack of a model for the coordinated water requirements of native and introduced island plants. Native island plants are adapted to the local environment, while introduced plants are ornamental. They differ significantly in their growth habits, water requirements, and adaptability to environmental factors such as salinity. However, most current plant water requirement models are constructed for a single plant type or general plants. There is a lack of models that can comprehensively consider the coordinated growth needs of native and introduced island plants. This makes it impossible to develop differentiated irrigation plans based on the characteristics of different plants in municipal garden planning and irrigation management, which is not conducive to the harmonious coexistence of multiple plants and the sustainable development of garden landscapes.

[0006] Therefore, an intelligent control method for soil moisture in municipal gardens is proposed. Summary of the Invention

[0007] In view of this, the embodiments of the present invention hope to provide a method for intelligently controlling soil moisture in a municipal garden to solve or alleviate the technical problems existing in the prior art and at least provide a beneficial option.

[0008] To solve the above technical problems, a technical solution adopted in this application is to provide a method for intelligently controlling soil moisture in a municipal garden, comprising the following steps:

[0009] Acquire environmental characteristics of the target area, and construct a plant cooperative water demand model based on the acquired environmental characteristics of the target area;

[0010] Continuously monitor the environmental characteristics of the target area and input them into the plant collaborative water demand model to obtain water demand data of the target area;

[0011] Collect water demand data of the target area, and build a plant irrigation water consumption model based on the collected water demand data of the plants in the target area to output the water consumption of the plants in the target area during their growth stage;

[0012] The soil moisture in the target area is regulated based on the output results.

[0013] As a further preferred embodiment of the present technical solution: the environmental characteristics of the target area include instantaneous increment of sea breeze salt particle deposition, change in plant rhizosphere osmotic pressure, groundwater salt infiltration rate, reference evapotranspiration, soil temperature and rainfall.

[0014] As a further preferred embodiment of the present technical solution, the water requirement data of the plants in the target area are used to show the transpiration rate, stomatal conductance of leaves, water absorption rate of roots of different plants at different growth stages, and physiological response data to salt stress.

[0015] As a further preferred embodiment of the present technical solution, the step of obtaining the environmental characteristics of the target area and constructing a plant collaborative water demand model according to the obtained environmental characteristics of the target area includes:

[0016] The environmental characteristics of the target area are obtained based on a distributed sensor network. Vibrating salt sensors are laid at preset intervals on the surface to obtain the instantaneous increment of salt particle deposition caused by the sea breeze. Micro-osmometers are buried at preset depths in the plant rhizosphere to obtain changes in plant rhizosphere osmotic pressure. Distributed optical fibers are laid at regular intervals along the groundwater flow direction to obtain the groundwater salt infiltration rate. Reference evapotranspiration is obtained through a meteorological station. Soil temperature is obtained using a soil temperature sensor. Rainfall is obtained using a rainfall sensor.

[0017] Preprocess the acquired environmental feature data, including data cleaning, filtering, normalization and other operations to remove noise and outliers;

[0018] Plants in the target area are divided into salt-tolerant plants and sensitive plants according to their salt tolerance;

[0019] For salt-tolerant plants, a correlation model between irrigation amount and environmental factors is established based on environmental characteristic data, and the irrigation amount is adjusted according to the root salt secretion rate;

[0020] For sensitive plants, a correlation model between irrigation volume and environmental factors is established, and a soil conductivity threshold is set. When the threshold is exceeded, a low-salt water source is switched.

[0021] The models of salt-tolerant plants and sensitive plants were integrated to construct a coordinated plant water demand model.

[0022] As a further preferred embodiment of the present technical solution, the continuously monitoring environmental characteristics of the target area and inputting the characteristics into the plant collaborative water demand model to obtain water demand data of the target area includes:

[0023] Continuously monitoring the environmental characteristics of the target area in real time based on the distributed sensor network;

[0024] The real-time monitored environmental characteristic data are format converted and pre-processed according to the input requirements of the plant collaborative water demand model;

[0025] Input the processed real-time environmental characteristic data into the established plant cooperative water demand model;

[0026] The plant collaborative water demand model calculates and outputs the water demand data of different plants in the target area under the current environment based on the input real-time data. The water demand data includes the expected irrigation amount and irrigation time interval of different plants.

[0027] As a further preferred embodiment of the present technical solution, the water demand data of the target area is collected, and a plant irrigation water model is constructed based on the collected water demand data of the plants in the target area to output the water consumption of the plants in the target area during their growth stages, including:

[0028] By installing transpiration rate sensors and stomatal conductance meters on garden plants and regularly collecting plant tissue samples to test physiological indicators, we collect water demand data for different plants at different growth stages. This data is combined with historical observation records to produce a comprehensive water demand dataset.

[0029] A plant irrigation water use model was constructed using a machine learning algorithm, with plant characteristics as independent variables and the actual water requirements of plants as the dependent variable.

[0030] Based on the collected water demand data, the constructed plant irrigation water use model is trained and optimized, and the model parameters are adjusted to improve the model's prediction accuracy;

[0031] The current growth stage information of the plants in the target area and the corresponding environmental parameters are input into the trained plant irrigation water use model, and the plant irrigation water use model outputs the specific water consumption of the plant in the current growth stage.

[0032] As a further preferred embodiment of the present technical solution: the plant characteristics include plant species, growth stage, ambient temperature, relative humidity, light intensity, and soil salt concentration.

[0033] As a further preferred embodiment of the present technical solution, the regulating the soil moisture in the target area according to the output result includes:

[0034] receiving the water consumption of the target area during the plant growth stage output by the plant irrigation water use model;

[0035] Formulate an irrigation plan based on the water consumption information in combination with the environmental characteristics of the target area, wherein the irrigation plan includes the irrigation area, irrigation time, and irrigation interval;

[0036] Start irrigation according to the irrigation plan;

[0037] During irrigation, soil moisture and plant growth conditions were continuously monitored;

[0038] The actual soil moisture monitored in real time is compared with the expected soil moisture. If there is a deviation, the irrigation plan is adjusted. The adjustment of the irrigation plan includes increasing or decreasing the irrigation amount and adjusting the irrigation time to achieve soil moisture control in the target area.

[0039] To solve the above technical problems, another technical solution adopted in this application is: a computer device, which includes a processor and a memory coupled to the processor, wherein program instructions are stored in the memory, and when the program instructions are executed by the processor, the processor executes the steps of a method for intelligent control of soil moisture in a municipal garden as described above.

[0040] In order to solve the above technical problems, another technical solution adopted in this application is: a storage medium storing program instructions that can implement a municipal garden soil moisture intelligent control method as described above.

[0041] The embodiment of the present invention adopts the above technical solution, which has the following advantages:

[0042] Precision irrigation decision-making: By collecting multi-dimensional water requirement data such as plant transpiration rate, stomatal conductance, and body water content, and combining it with environmental parameters and growth stage information to build a model, we can accurately output the specific water requirements of plants in their current growth stage. This allows irrigation decisions to break away from the traditional empirical and extensive model, greatly improving irrigation accuracy and avoiding the negative impact of insufficient or excessive irrigation on plant growth.

[0043] Improved water resource efficiency: Accurate water usage forecasting allows for rational allocation of water resources, avoiding unnecessary water consumption. Compared to traditional irrigation methods, this effectively reduces water waste and improves water utilization efficiency. In today's increasingly scarce water resources landscape, this is of great significance for sustainable garden development, helping to achieve efficient water utilization while ensuring the effectiveness of garden landscapes.

[0044] Adapting to Complex Environments and Plant Diversity: Taking into account the varying water requirements of different plants at different growth stages, as well as complex and changing environmental factors (such as temperature, humidity, and light intensity), the model constructed in this solution is highly adaptable. Whether drought-tolerant or water-loving, and whether in hot and dry seasons or wet and rainy periods, it can provide appropriate irrigation recommendations for various plants, meeting the needs of garden plant diversity and promoting the stability and balance of garden ecosystems.

[0045] Model Self-Optimization and Long-Term Validity: The model is trained and optimized using mean squared error as a loss function, and the optimal parameters are selected through cross-validation, allowing the model to continuously learn and improve. As more water demand data is collected, the model's prediction accuracy will continue to improve, ensuring long-term validity. This means that garden irrigation management can be continuously optimized over time, better adapting to environmental changes and the dynamic changes in plant growth requirements.

[0046] Reduced maintenance costs and labor intensity: Precise irrigation plans reduce problems such as poor plant growth and pest infestation caused by improper irrigation, lowering subsequent garden maintenance costs. Automated model predictions also reduce the need for manual judgment and adjustment of irrigation volumes, reducing labor intensity and improving garden management efficiency, allowing garden managers to focus more on other important garden maintenance tasks.

[0047] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 is a flow chart of the method of the present invention;

[0050] Figure 2 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0052] It should be clear that the following embodiments of the present disclosure are described through specific concrete examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other in the absence of conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

[0053] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on this disclosure, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this device and / or practice this method.

[0054] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present disclosure. The illustrations only show components related to the present disclosure and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0055] Additionally, in the following description, specific details are provided to provide a thorough understanding of the examples. However, one skilled in the art will appreciate that the aspects described can be practiced without these specific details.

[0056] Figure 1 This is a flow chart of a method for intelligently controlling soil moisture in a municipal garden according to an embodiment of the present invention. It should be noted that if there are substantially the same results, the method of this application is not limited to Figure 1 The process sequence shown is limited. Figure 1 As shown: A method for intelligently controlling soil moisture in a municipal garden comprises the following steps: obtaining environmental characteristics of a target area, and constructing a plant collaborative water demand model based on the obtained environmental characteristics of the target area; continuously monitoring the environmental characteristics of the target area and inputting them into the plant collaborative water demand model to obtain water demand data of the target area; collecting water demand data of the target area, and constructing a plant irrigation water use model based on the collected water demand data of plants in the target area to output water consumption during the growth stage of plants in the target area; and regulating the soil moisture in the target area based on the output results.

[0057] Specifically, the environmental characteristics of the target area include instantaneous increment of sea breeze salt deposition, changes in plant rhizosphere osmotic pressure, groundwater salt infiltration rate, reference evapotranspiration, soil temperature and rainfall.

[0058] More specifically, the environmental characteristics of the target area are obtained, and a plant cooperative water demand model is constructed based on the obtained environmental characteristics of the target area, including:

[0059] The environmental characteristics of the target area are acquired using a distributed sensor network. This distributed sensor network includes deploying vibrating salt sensors at preset intervals (e.g., 2m x 2m) on the surface of the target area to monitor sea breeze salt deposition in real time, thereby obtaining the instantaneous increment of sea breeze salt deposition. Micro-osmometers are buried at a preset depth (e.g., 10-30cm) below the plant rhizosphere to monitor real-time changes in plant rhizosphere osmotic pressure. Distributed optical fibers are laid at preset intervals (e.g., 5m-8m) along the groundwater flow path to monitor groundwater salt infiltration rates. Reference evapotranspiration is obtained from a meteorological station. Soil temperature sensors are used to monitor soil temperature in real time. Rainfall sensors are used to obtain rainfall data. Based on these environmental characteristic data, a collaborative plant water demand model is constructed. The vibrating salt sensors have an accuracy of ±0.03%, the micro-osmometers have a response time of less than 5s, and the distributed optical fiber salt measurement has an accuracy of ±0.05%.

[0060] Preprocessing the acquired environmental feature data includes basic data cleaning, filtering, normalization and other operations to remove noise and outliers;

[0061] Plants in the target area are divided into salt-tolerant plants and sensitive plants according to their salt tolerance;

[0062] For salt-tolerant plants, a correlation model between irrigation amount and environmental factors was established based on environmental characteristic data. The irrigation amount was adjusted according to the root salt secretion rate. The irrigation amount for salt-tolerant plants was calculated using the following formula:

[0063] Q n =k n ·ET0·(α+β)S;

[0064] Among them, Q n is the irrigation amount for salt-tolerant plants, k n is the salt tolerance coefficient, ET0 is the reference evapotranspiration, S is the salt concentration, α is the basic irrigation coefficient (for example, 1), and β is the adjusted irrigation coefficient.

[0065] For sensitive plants, a correlation model between irrigation amount and environmental factors is established. A soil conductivity threshold k1 is set. When the threshold is exceeded, the low-salt water source is switched (S>k1). The irrigation amount for salt-tolerant plants is calculated using the following formula:

[0066] Q i =k i ·ET0·(α-γ)S;

[0067] Among them, Q i is the irrigation amount for sensitive plants, k i is the sensitivity coefficient, and γ is the adjustment irrigation coefficient.

[0068] Adjust irrigation rates based on root salt secretion rates, including:

[0069] The models of salt-tolerant plants and sensitive plants were integrated to construct a coordinated plant water demand model.

[0070] Specifically, the environmental characteristics of the target area are continuously monitored and input into the plant collaborative water demand model to obtain water demand data for the target area, including:

[0071] Continuously monitoring the environmental characteristics of the target area in real time based on the distributed sensor network;

[0072] Real-time monitored environmental characteristic data is formatted and preprocessed according to the input requirements of the plant collaborative water demand model. This step may include: Once the real-time environmental characteristic data is acquired, it is immediately processed for each sensor. The analog voltage signal output by the vibrating salt sensor is converted to a digital value by the ADC module. The amount of salt particle deposition caused by the sea breeze is then accurately calculated according to established conversion rules. The digital signal output by the micro-osmometer is directly read, and abnormal data exceeding the plant physiological threshold is subsequently filtered out. Distributed optical fiber demodulates the phase difference of the optical signal and uses OTDR technology to estimate the groundwater salinity concentration. A continuous salt transport curve is generated by interpolation at 5-meter intervals.

[0073] Then, using an NTP server, a unified UTC timestamp was assigned to all sensor data. After calibration, the time error between sensor data at different levels was maintained within one second. To effectively filter out noise, a five-point sliding average filter was used to capture minute-level trends in high-frequency noise, such as sea breeze gusts. For slowly varying data such as soil temperature and evapotranspiration, a median filter was used to eliminate spikes caused by transient sensor failures.

[0074] Because different sensor data have varying dimensions, data such as sea breeze salt deposition, rhizosphere osmotic pressure, and groundwater salt transport rate are converted to dimensionless values ranging from 0 to 1 through minimum-maximum normalization. Reference data such as evapotranspiration, soil temperature, and rainfall are retained in their original units to adapt to the model input requirements. If a single sensor's data is missing for more than 10 minutes, linear interpolation is used to fill the gap. If three consecutive periods are missing, the data is marked invalid and a fault alarm is triggered. This series of processing allows data to be accurately and timely input into the plant collaborative water demand model in an adapted format, laying a solid foundation for the precise calculation of plant water demand data.

[0075] Input the processed real-time environmental characteristic data into the established plant cooperative water demand model;

[0076] The plant collaborative water demand model calculates and outputs the water demand data of different plants in the target area under the current environment based on the input real-time data. The water demand data includes the expected irrigation amount and irrigation time interval of different plants.

[0077] Specifically, water demand data of the target area is collected, and a plant irrigation water use model is constructed based on the collected water demand data of the plants in the target area to output the water consumption of the plants in the target area during their growth stages, including:

[0078] By installing transpiration rate sensors and stomatal conductance meters on garden plants and regularly collecting plant tissue samples to test physiological indicators, we collect water demand data for different plants at different growth stages. This data is combined with historical observation records to produce a comprehensive water demand dataset.

[0079] A plant irrigation water use model was constructed using a machine learning algorithm, with plant characteristics as independent variables and the actual water requirements of plants as the dependent variable.

[0080] Based on the collected water demand data, the constructed plant irrigation water use model is trained and optimized, and the model parameters are adjusted to improve the model's prediction accuracy;

[0081] The current growth stage information of the plants in the target area and the corresponding environmental parameters are input into the trained plant irrigation water use model, and the plant irrigation water use model outputs the specific water consumption of the plant in the current growth stage.

[0082] The step of collecting water demand data of the target area and constructing a plant irrigation water model based on the collected water demand data of the plants in the target area to output water consumption during the growth stage of the plants in the target area includes:

[0083] By installing transpiration rate sensors and stomatal conductance meters on garden plants and regularly collecting plant tissue samples to test physiological indicators, we collect water demand data for different plants at different growth stages. This data is combined with historical observation records to produce a comprehensive water demand dataset.

[0084] A plant irrigation water use model was constructed using a machine learning algorithm, with plant characteristics as independent variables and the actual water requirements of plants as the dependent variable.

[0085] Based on the collected water demand data, the constructed plant irrigation water use model is trained and optimized, and the model parameters are adjusted to improve the model's prediction accuracy;

[0086] The current growth stage information of the plants in the target area and the corresponding environmental parameters are input into the trained plant irrigation water use model, and the plant irrigation water use model outputs the specific water consumption of the plant in the current growth stage.

[0087] More specifically, the steps above involve: using a transpiration rate sensor mounted on a garden plant to measure the transpiration rate (T), which reflects the rate at which plants lose water through their leaf surfaces; using a stomatal conductance meter to measure leaf stomatal conductance (G), which reflects the ability of leaf stomata to conduct water vapor and carbon dioxide, and is closely linked to plant transpiration. Simultaneously, plant tissue samples are regularly collected to measure physiological indicators, such as the water content (C) within the plant.

[0088] Combined with historical observation records, these records cover the growth status and water requirements of plants in different periods and under different environmental conditions. By integrating multi-source data, a comprehensive water demand dataset D is output, which can be expressed as:

[0089]

[0090] Among them, i represents the i-th sample, Ti represents the transpiration rate of the i-th sample, G i is the stomatal conductance of the ith sample, C i is the water content of the plant in the i-th sample, E i are environmental parameters (such as temperature, humidity, light intensity, etc.), P i is the plant growth stage parameter (such as seedling stage, growth stage, flowering stage, etc.), Y i is the actual water requirement of the plant corresponding to the i-th sample.

[0091] Using machine learning algorithms to build plant irrigation water use models:

[0092] For example, the random forest regression algorithm can be used to construct a plant irrigation water model M with plant characteristics as the independent variable X and the actual water requirement of the plant as the dependent variable Y. The plant characteristics X can be expressed as:

[0093] X = [T, G, C, E, P];

[0094] The random forest regression model consists of multiple decision trees, each of which is constructed based on different sample subsets and feature subsets during training. For the input plant feature X, the output of model M is the predicted value of the actual water requirement Y of the plant. It can be expressed as:

[0095]

[0096] The training process includes training and optimizing the constructed plant irrigation water model M based on the collected water demand dataset D. The mean square error (MSE) is used as the loss function to measure the difference between the model's predicted value and the actual value. The mean square error calculation formula is:

[0097]

[0098] Among them, Y i is the actual water requirement of the plant corresponding to the i-th sample, is the predicted water requirement for the i-th sample. By adjusting model parameters (such as the number and depth of decision trees), the mean squared error (MSE) is minimized to improve the prediction accuracy of this plant irrigation water model. Cross-validation is used to select the optimal model parameters to ensure the model has good generalization ability on different datasets. The cross-validation method: divide the dataset D into k mutually exclusive subsets. Each time, one of the subsets is selected as the test set, and the remaining k-1 subsets are used as the training set. Repeat this k times, calculate the mean squared error for each result, and take the average. By comparing the average MSE under different parameter combinations, the optimal parameters are determined.

[0099] Output the specific water consumption of plants in the current growth stage: the current growth stage information of plants in the target area Pcur And the corresponding environmental parameters E cur Input the trained plant irrigation water model M and combine it with the real-time measured plant transpiration rate T cur , stomatal conductance G cur and water content in plants C cur , forming the input vector X cur :

[0100] X cur =[P cur , E cur , T cur , G cur , C cur ];

[0101] Plant irrigation water model M is based on the input vector X cur Output the specific water consumption of the plant at the current growth stage

[0102]

[0103] Through the above steps, the collected water demand data is used to build and optimize the plant irrigation water use model, which can accurately predict the specific water consumption of plants in the target area during the current growth stage and provide a basis for reasonable irrigation.

[0104] The plant characteristics include plant species, growth stage, ambient temperature, relative humidity, light intensity, and soil salt concentration.

[0105] The regulating the soil moisture in the target area according to the output result includes:

[0106] receiving the water consumption of the target area during the plant growth stage output by the plant irrigation water use model;

[0107] Formulate an irrigation plan based on the water consumption information in combination with the environmental characteristics of the target area, wherein the irrigation plan includes the irrigation area, irrigation time, and irrigation interval;

[0108] Start irrigation according to the irrigation plan;

[0109] During irrigation, soil moisture and plant growth conditions were continuously monitored;

[0110] The actual soil moisture monitored in real time is compared with the expected soil moisture. If there is a deviation, the irrigation plan is adjusted. The adjustment of the irrigation plan includes increasing or decreasing the irrigation amount and adjusting the irrigation time to achieve soil moisture control in the target area.

[0111] The specific irrigation plan includes: combining the environmental characteristics of the target area, such as terrain undulation h(x, y) (x, y are plane coordinates), soil type (which can be represented by the soil texture parameter a, such as sandy soil has a smaller a value and clay soil has a larger a value), light distribution I(x, y), etc., and formulating an irrigation plan based on water consumption information.

[0112] Irrigation area division: Based on plant distribution and water demand characteristics, clustering algorithms (such as K-means clustering) are used to divide the target area into multiple irrigation sub-areas R j (j=1, 2, ..., N). For example, plants with similar water requirements and adjacent spatial locations are divided into the same area. In the division process, the terrain factors are taken into consideration. For areas with low terrain and prone to water accumulation, the irrigation amount is appropriately reduced and the irrigation amount is adjusted using the formula:

[0113] Where θ is the coefficient related to soil drainage performance, h low It is the degree of lowness of the area relative to the average terrain.

[0114] Irrigation time determination: Considering the physiological characteristics of plants and environmental factors, irrigation is generally carried out in the early morning or evening to reduce water evaporation loss. At the same time, according to the water urgency of the plant (which can be determined by calculating the plant water deficit index WDI:

[0115]

[0116] Among them ET c is the crop potential evapotranspiration, ET a is the actual evapotranspiration), and irrigation is given priority for plants with higher WDI.

[0117] Irrigation interval calculation: Irrigation interval t in It can be determined based on the soil moisture decay law and plant water demand rate. Assume that the soil moisture decay function is S(t) = S0·e -μt , where S0 is the initial soil moisture content after irrigation, μ is the soil moisture decay coefficient, t is the time variable, and the plant water demand rate r is

[0118]

[0119] Among them, t day The length of a day when the soil moisture content drops to the minimum moisture content S required for plant growth min When the next irrigation is carried out, the equation Solve for the irrigation interval:

[0120]

[0121] Start irrigation according to the irrigation plan:

[0122] According to the established irrigation plan, the corresponding irrigation equipment, such as sprinkler systems and drip irrigation systems, is activated. For sprinkler systems, the flow rate and spray range of the sprinkler nozzles are adjusted according to the area of ​​irrigated area and the required irrigation volume to ensure that each irrigation area receives the required amount of water evenly. For drip irrigation systems, the flow rate and arrangement density of the drippers are controlled to achieve precise water supply. During the irrigation period, soil moisture sensors are used to continuously monitor soil moisture.

[0123] Deviation judgment and plan adjustment

[0124] Compare the actual soil moisture S monitored in real time real (t) and expected soil moisture S ex (t). The expected soil moisture can be determined according to the plant growth stage and soil type. For example, for herbaceous plants in the growth stage, the suitable soil moisture range is S low ≤S ex (t)≤S high If the actual soil moisture exceeds this range, that is, |S real (t)-S ex (t)|>ΔS (ΔS is the allowable humidity deviation threshold), then adjust the irrigation plan:

[0125] Increase or decrease irrigation volume: If S real (t) low}, increase the irrigation amount. Let the increased irrigation amount be ΔQ, which can be determined based on the degree of deviation and soil water holding characteristics, such as:

[0126]

[0127] , where k2 is the coefficient related to the soil water absorption capacity. real (t)>S high , then reduce the irrigation amount, the reduced irrigation amount is:

[0128]

[0129] , k3 is the correlation coefficient.

[0130] Adjust irrigation time: If soil moisture rises too quickly or too slowly, adjust the next irrigation time. For example, if soil moisture rises too quickly, advance the next irrigation time. Let the advance time be Δt, which can be calculated by the formula

[0131]

[0132] Calculate, where k4 is the adjustment coefficient and r is the plant water demand rate. By continuously adjusting the irrigation plan, the actual soil moisture is brought closer to the expected soil moisture, achieving precise control of soil moisture in the target area.

[0133] ​The method of the present invention has the following benefits by adopting the above steps:

[0134] Precision irrigation decision-making: By collecting multi-dimensional water requirement data such as plant transpiration rate, stomatal conductance, and body water content, and combining it with environmental parameters and growth stage information to build a model, we can accurately output the specific water requirements of plants in their current growth stage. This allows irrigation decisions to move away from traditional empirical and extensive models, greatly improving irrigation accuracy and avoiding the negative impact of insufficient or excessive irrigation on plant growth. For example, during droughts, plants can be replenished with timely and appropriate amounts of water to ensure normal growth while avoiding water waste.

[0135] Improved water resource efficiency: Accurate water usage forecasting allows for rational allocation of water resources, avoiding unnecessary water consumption. Compared to traditional irrigation methods, this effectively reduces water waste and improves water utilization efficiency. In today's increasingly scarce water resources landscape, this is of great significance for sustainable garden development, helping to achieve efficient water utilization while ensuring the effectiveness of garden landscapes.

[0136] Adapting to Complex Environments and Plant Diversity: Taking into account the varying water requirements of different plants at different growth stages, as well as complex and changing environmental factors (such as temperature, humidity, and light intensity), the model constructed in this solution is highly adaptable. Whether drought-tolerant or water-loving, and whether in hot and dry seasons or wet and rainy periods, it can provide appropriate irrigation recommendations for various plants, meeting the needs of garden plant diversity and promoting the stability and balance of garden ecosystems.

[0137] Model Self-Optimization and Long-Term Validity: The model is trained and optimized using mean squared error as a loss function, and the optimal parameters are selected through cross-validation, allowing the model to continuously learn and improve. As more water demand data is collected, the model's prediction accuracy will continue to improve, ensuring long-term validity. This means that garden irrigation management can be continuously optimized over time, better adapting to environmental changes and the dynamic changes in plant growth requirements.

[0138] Reduced maintenance costs and labor intensity: Precise irrigation plans reduce problems such as poor plant growth and pest infestation caused by improper irrigation, lowering subsequent garden maintenance costs. Automated model predictions also reduce the need for manual judgment and adjustment of irrigation volumes, reducing labor intensity and improving garden management efficiency, allowing garden managers to focus more on other important garden maintenance tasks.

[0139] Application Example 1

[0140] The present invention also provides an embodiment of a practical application of the method of the present invention:

[0141] A park green space with an area of 5000m 2 .

[0142] Water consumption: During the peak summer growing season, the trained plant irrigation water use model provides predicted water consumption for different plant species in the park's green space. Among them, there are 80 large trees (Sophora japonica), each requiring approximately 30 liters of water per day, for a total daily demand of 2,400 liters. There are 1,500 small shrubs (Boxwood), each requiring approximately 2 liters of water per day, for a total daily demand of 3,000 liters. Ground cover plants (Ophiopogon japonicus) cover an area of approximately 2,000 square meters, requiring approximately 1 liter of water per square meter per day, for a total daily demand of 2,000 liters. The total predicted daily water consumption for the entire park's green space is 7,400 liters.

[0143] Irrigation Plan Development: Irrigation Zone Division: The park's green space was divided into four irrigation sub-areas. Area A, primarily planted with locust trees, covers an area of 1,200 square meters; Area B, planted with boxwood, covers an area of 1,800 square meters; Area C, planted with ophiopogon japonicus, covers an area of 2,000 square meters; and Area D, a small, low-lying depression with a small amount of mixed planting, covers an area of approximately 200 square meters. Because Area D is prone to waterlogging, its irrigation volume was reduced by 15% of the total water requirement. This means that the original allocation of approximately 296 liters (7,400 × 200 ÷ 5,000) was reduced to 251.6 liters.

[0144] Irrigation timing: Calculate the water deficit index for different plants. The potential evapotranspiration of Sophora japonica is 10 mm, the actual evapotranspiration is 6 mm, and the water deficit index is 0.4; the potential evapotranspiration of Boxwood is 8 mm, the actual evapotranspiration is 5 mm, and the water deficit index is 0.375; the potential evapotranspiration of Ophiopogon japonicus is 6 mm, the actual evapotranspiration is 4 mm, and the water deficit index is 0.33. Sophora japonica has the highest water deficit index and the most urgent water needs, so prioritize irrigation between 5 and 7 a.m. for Sophora japonica. Next, irrigate Boxwood between 7 and 9 a.m., and Ophiopogon japonicus between 9 and 11 a.m.

[0145] Calculation of irrigation interval: Based on past experience, the initial soil moisture content can be maintained at a relatively suitable state for about 7 days after irrigation, so the irrigation interval is determined to be 7 days.

[0146] Start irrigation according to the irrigation plan: Use a sprinkler irrigation system: In the Sophora japonica planting area in Area A, the sprinkler flow rate is adjusted to 1200 liters per hour, and the irrigation time is 2 hours to meet the daily water demand of 2400 liters. In the boxwood planting area in Area B, the sprinkler flow rate is 1500 liters per hour, and the irrigation time is 2 hours to meet the daily water demand of 3000 liters. In the Ophiopogon japonicus ground cover area in Area C, the sprinkler flow rate is 1000 liters per hour, and the irrigation time is 2 hours to meet the daily water demand of 2000 liters. In Area D, the sprinkler flow rate is adjusted to 125.8 liters per hour, and the irrigation time is 2 hours to meet the adjusted daily water demand of 251.6 liters.

[0147] Monitoring during irrigation: During irrigation, soil moisture sensors installed at different depths in different areas monitor soil moisture in real time. In Area A, soil moisture data is recorded every two hours. Simultaneously, cameras capture plant images to observe any abnormalities such as yellowing or curling of locust leaves. A handheld chlorophyll meter regularly monitors chlorophyll content in plant leaves to assess photosynthetic efficiency and health.

[0148] Deviation Judgment and Plan Adjustment: The soil moisture in the locust tree planting area in Area A was expected to be maintained at 60%-70%. During a certain period, soil moisture in Area A was monitored to have dropped to 55%, below the lower limit. Since Area A covers an area of 1,200 square meters, it was decided to increase the irrigation volume by 2 liters per square meter for the next irrigation, i.e., an increase of 2,400 liters. It was discovered that soil moisture in Area B was rising too rapidly, so the original 7-day irrigation interval was shortened to 5 days to prevent excessive soil moisture from affecting plant root respiration. By continuously adjusting the irrigation plan based on actual monitoring results, the soil moisture in each area of the park's green space is maintained within a range suitable for plant growth.

[0149] Application Example 2

[0150] The present invention also provides an embodiment of a practical application of the method of the present invention:

[0151] A coastal garden with an area of about 8000m 2 .

[0152] Water Consumption: In autumn, the plant irrigation water use model calculates the following water requirements for the garden plants: 50 salt-tolerant palm trees require approximately 40 liters of water per tree per day, for a total daily requirement of 2,000 liters; 800 salt-tolerant shrubs, such as the seashore hibiscus, require approximately 3 liters of water per tree per day, for a total daily requirement of 2,400 liters; and salt-tolerant ground cover plants, such as the saltwort, cover an area of 3,000 square meters, requiring approximately 1.5 liters of water per square meter per day, for a total daily requirement of 4,500 liters. The total daily water consumption for the garden plants is projected to be 8,900 liters.

[0153] Irrigation Plan Development: Irrigation Zone Division: The garden was divided into five irrigation sub-zones. Zone E, covering 2,000 square meters, is dedicated to palm trees; Zone F, 2,500 square meters, is dedicated to coastal hibiscus shrubs; Zone G, 3,000 square meters, is dedicated to the ground cover of Suaeda salsa; Zone H, 300 square meters, is a mixed planting area near the sea with a higher salinity; and Zone I, 200 square meters, is dedicated to the relatively low-salinity landscape flower area in the center of the garden. Soil salinity sensors measured the soil salinity in Zone H at 0.4%, far exceeding the ideal range of 0.1%-0.2% for garden plants. Therefore, the irrigation rate for Zone H was increased by 30% to promote salt leaching. The original allocation was approximately 334 liters (8,900 × 300 ÷ 8,000), but the adjusted amount was 434.2 liters. The soil salinity in area I is 0.08%, which is relatively low. The irrigation volume is reduced by 20% based on the original allocation. The original allocation is about 223 liters (8900×200÷8000), but after adjustment it is 178.4 liters.

[0154] Determining irrigation timing: The electrical conductivity of the rhizosphere soil of different plants was measured. The conductivity of the rhizosphere soil of palm trees was 2.5 mS / cm, that of Hibiscus sylvestris was 2.2 mS / cm, and that of Suaeda salsa was 2.8 mS / cm. The higher the conductivity, the greater the impact of soil salinity on the plant and the greater the urgency of its water needs. Therefore, prioritize irrigation between 4 and 6 a.m. for Suaeda salsa, followed by irrigation between 6 and 8 a.m. for palm trees and 8 and 10 a.m. for Hibiscus sylvestris. In Area H, due to the high salinity, an additional short irrigation session between 5 and 6 p.m. will be conducted in the evening to promote salt removal.

[0155] Irrigation interval calculation: Long-term monitoring of soil moisture and salinity reveals that salt-tolerant plants consume water more rapidly when soil salinity is high. Given the current season and salinity conditions, the irrigation interval for salt-tolerant plants has been adjusted to 5 days. For low-salt landscape flowers in Zone I, which are sensitive to salt and are less affected by soil salinity changes, the irrigation interval remains at 7 days.

[0156] Start irrigation according to the irrigation plan: use a system that combines drip irrigation and micro-sprinkler irrigation. In the palm tree area of area E, the drip irrigation pipe flow rate is adjusted to 1,000 liters per hour, and the irrigation time is 2 hours. In the coastal hibiscus shrub area of area F, the micro-sprinkler nozzle flow rate is 1,200 liters per hour, and the irrigation time is 2 hours. In the salt marsh salsa ground cover area of area G, the drip irrigation pipe flow rate is 900 liters per hour, and the irrigation time is 5 hours. In area H, the drip irrigation pipe flow rate is adjusted to 217.1 liters per hour, and irrigation is carried out for 2 hours in the early morning and another 0.5 hour in the evening. In area I, the micro-sprinkler nozzle flow rate is 89.2 liters per hour, and the irrigation time is 2 hours.

[0157] Monitoring during irrigation: During irrigation, soil salinity and moisture sensors were buried at different depths in different areas, recording data every three hours. In Area E, soil salinity and moisture levels at a depth of 5-20 cm around the root systems of palm trees were monitored. A drone equipped with a multispectral camera regularly photographed the garden, analyzing the color and spectral characteristics of plant leaves to determine whether the plants were experiencing salt stress. A portable plant physiological analyzer was also used to measure the proline content in plant leaves. Elevated proline levels often indicate salt stress.

[0158] Deviation judgment and program adjustment: It is expected that the soil moisture in the palm tree area of region E will remain at 55%-65%, and the soil salt content will be stable at 0.2%-0.3%. During a certain period of time, it was monitored that the soil salt content in region E rose to 0.35% and the soil moisture dropped to 50%. During the next irrigation, the irrigation volume was increased by 20% and the irrigation time was extended by 0.5 hours to enhance the salt leaching effect. It was found that the soil moisture in region F rose too quickly and the soil salt content was less than 0.15%. The irrigation interval was extended from 5 days to 6 days to avoid soil nutrient loss due to excessive irrigation. By continuously adjusting the irrigation plan based on the actual monitored soil salinity and moisture conditions, it is ensured that the soil environment in each area of the municipal garden is suitable for plant growth and the accuracy of irrigation water use is improved.

[0159] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similarities between the various embodiments can be referred to in conjunction with each other. For system-related embodiments, since they are generally similar to method-related embodiments, their description is relatively simple. For relevant details, refer to the description of the method-related embodiments.

[0160] An electronic device according to an embodiment of the present disclosure includes a memory and a processor. The memory is used to store non-transitory computer-readable instructions. Specifically, the memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may, for example, include a read-only memory (ROM), a hard disk, a flash memory, etc.

[0161] The processor can be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and can control other components in the electronic device to perform desired functions. In one embodiment of the present disclosure, the processor is used to execute the computer-readable instructions stored in the memory, causing the electronic device to execute all or part of the steps of the municipal garden soil moisture intelligent control method described in each embodiment of the present disclosure.

[0162] Those skilled in the art should understand that in order to solve the technical problem of how to obtain a good user experience, this embodiment may also include well-known structures such as a communication bus and an interface, and these well-known structures should also be included in the scope of protection of this disclosure.

[0163] like Figure 2 The present invention provides a schematic structural diagram of an electronic device according to an embodiment of the present invention, which is suitable for implementing the electronic device according to an embodiment of the present invention. Figure 2 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0164] like Figure 2 As shown, the electronic device may include a processor (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage device into a random access memory (RAM). In the RAM, various programs and data required for the operation of the electronic device are also stored. The processor, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0165] Typically, the following devices can be connected to the I / O interface: input devices such as sensors or visual information acquisition devices; output devices such as display screens; storage devices such as tapes and hard disks; and communication devices. The communication device allows the electronic device to communicate with other devices (such as edge computing devices) wirelessly or by wire to exchange data. Figure 2 The electronic device is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0166] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by the processor, all or part of the steps of a municipal garden soil moisture intelligent control method of an embodiment of the present disclosure are executed.

[0167] For detailed description of this embodiment, please refer to the corresponding description in the aforementioned embodiments, which will not be repeated here.

[0168] According to an embodiment of the present disclosure, a computer-readable storage medium stores non-transitory computer-readable instructions. When the non-transitory computer-readable instructions are executed by a processor, all or part of the steps of the method for intelligently controlling soil moisture in a municipal garden described in each embodiment of the present disclosure are executed.

[0169] The above-mentioned computer-readable storage media include, but are not limited to, optical storage media (e.g., CD-ROMs and DVDs), magneto-optical storage media (e.g., MOs), magnetic storage media (e.g., magnetic tapes or mobile hard disks), media with built-in rewritable non-volatile memory (e.g., memory cards), and media with built-in ROM (e.g., ROM cartridges).

[0170] For detailed description of this embodiment, please refer to the corresponding description in the aforementioned embodiments, which will not be repeated here.

[0171] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this disclosure are merely illustrative and not restrictive, and should not be construed as necessarily possessed by each embodiment of the present disclosure. Furthermore, the specific details disclosed above are provided for illustrative purposes and to facilitate understanding, rather than as limitations. These details do not limit the present disclosure to necessarily being implemented using these specific details.

[0172] In the present disclosure, relational terms such as first and second, etc. are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. The block diagrams of the devices, devices, equipment, and systems involved in the present disclosure are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "including," "comprising," "having," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0173] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0174] It should also be noted that in the system and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0175] Various changes, substitutions, and modifications may be made to the technology described herein without departing from the teachings defined by the appended claims. Moreover, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of things, means, methods, and actions described above. Currently existing or later developed processes, machines, manufactures, compositions of things, means, methods, or actions that perform substantially the same function or achieve substantially the same results as the corresponding aspects described herein may be utilized. Accordingly, the appended claims include within their scope such processes, machines, manufactures, compositions of things, means, methods, or actions.

[0176] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0177] The above description has been provided for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for intelligently controlling soil moisture in municipal gardens, characterized in that: The following steps are involved: Acquire environmental characteristics of the target area, and construct a plant cooperative water demand model based on the acquired environmental characteristics of the target area; Continuously monitor the environmental characteristics of the target area and input them into the plant collaborative water demand model to obtain water demand data of the target area; Collect water demand data of the target area, and build a plant irrigation water consumption model based on the collected water demand data of the plants in the target area to output the water consumption of the plants in the target area during their growth stage; The soil moisture in the target area is regulated based on the output results.

2. The method for intelligently controlling soil moisture in a municipal garden according to claim 1, characterized in that: The environmental characteristics of the target area include instantaneous increment of sea breeze salt particle deposition, changes in plant rhizosphere osmotic pressure, groundwater salt infiltration rate, reference evapotranspiration, soil temperature and rainfall.

3. The method for intelligently controlling soil moisture in a municipal garden according to claim 1, characterized in that: The water requirement data of the plants in the target area are used to show the transpiration rate, stomatal conductance of leaves, water absorption rate of roots of different plants at different growth stages, as well as physiological response data to salt stress.

4. The method for intelligently controlling soil moisture in a municipal garden according to claim 1, characterized in that: The step of obtaining the environmental characteristics of the target area and constructing a plant cooperative water demand model according to the obtained environmental characteristics of the target area includes: Acquire the environmental characteristics of the target area based on a distributed sensor network; Preprocess the acquired environmental feature data to remove noise and outliers; Plants in the target area are divided into salt-tolerant plants and sensitive plants according to their salt tolerance; For salt-tolerant plants, a correlation model between irrigation volume and environmental factors is established based on environmental characteristic data, and irrigation volume is adjusted according to the root salt secretion rate. For sensitive plants, a correlation model between irrigation volume and environmental factors is established, and a soil conductivity threshold is set. When the threshold is exceeded, a low-salt water source is switched. The models of salt-tolerant plants and sensitive plants were integrated to construct a coordinated plant water demand model.

5. The method for intelligently controlling soil moisture in a municipal garden according to claim 4, characterized in that: The continuous monitoring of the environmental characteristics of the target area and inputting them into the plant collaborative water demand model to obtain water demand data of the target area include: Continuously monitoring the environmental characteristics of the target area in real time based on the distributed sensor network; The real-time monitored environmental characteristic data are format converted and pre-processed according to the input requirements of the plant collaborative water demand model; Input the processed real-time environmental characteristic data into the established plant cooperative water demand model; The plant collaborative water demand model calculates and outputs the water demand data of different plants in the target area under the current environment based on the input real-time data. The water demand data includes the expected irrigation amount and irrigation time interval of different plants.

6. The method for intelligently controlling soil moisture in a municipal garden according to claim 1, characterized in that: The collecting of water demand data of the target area and constructing a plant irrigation water model based on the collected water demand data of the plants in the target area to output the water consumption of the plants in the target area during their growth stages include: By installing transpiration rate sensors and stomatal conductance meters on garden plants and regularly collecting plant tissue samples to test physiological indicators, we collect water demand data for different plants at different growth stages. This data is combined with historical observation records to produce a comprehensive water demand dataset. A plant irrigation water use model was constructed using a machine learning algorithm, with plant characteristics as independent variables and the actual water requirements of plants as the dependent variable. Based on the collected water demand data, the constructed plant irrigation water use model is trained and optimized, and the model parameters are adjusted to improve the model's prediction accuracy; The current growth stage information of the plants in the target area and the corresponding environmental parameters are input into the trained plant irrigation water use model, and the plant irrigation water use model outputs the specific water consumption of the plant in the current growth stage.

7. The method for intelligently controlling soil moisture in a municipal garden according to claim 6, characterized in that: The plant characteristics include plant species, growth stage, ambient temperature, relative humidity, light intensity, and soil salt concentration.

8. The method for intelligently controlling soil moisture in a municipal garden according to claim 1, characterized in that: The regulating the soil moisture in the target area according to the output result includes: receiving the water consumption of the target area during the plant growth stage output by the plant irrigation water use model; Formulate an irrigation plan based on the water consumption information in combination with the environmental characteristics of the target area, wherein the irrigation plan includes the irrigation area, irrigation time, and irrigation interval; Start irrigation according to the irrigation plan; During irrigation, soil moisture and plant growth conditions were continuously monitored; The actual soil moisture monitored in real time is compared with the expected soil moisture. If there is a deviation, the irrigation plan is adjusted. The adjustment of the irrigation plan includes increasing or decreasing the irrigation amount and adjusting the irrigation time to achieve soil moisture control in the target area.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the municipal garden soil moisture intelligent control method described in any one of claims 1-10.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, which are used to enable a computer to execute the municipal garden soil moisture intelligent control method described in any one of claims 1-10.

Images