Intelligent remote irrigation control device in forest cultivation

Abstract

The invention discloses an intelligent remote irrigation control device in forest cultivation, and relates to the technical field of forest irrigation, and the device comprises a remote sensing platform which is connected to obtain image data of a forest area; soil characteristic analysis is carried out, and soil irrigation requirements are excavated; performing mandatory evaluation on the control nodes, and setting a mandatory coefficient of each control node; extracting a forced constraint node according to the forced coefficient of the control node; obtaining an irrigation execution target by taking the maximum forced coefficient cumulant of the irrigation time sequence as an evaluation condition; and carrying out irrigation strategy analysis to obtain irrigation control information. The technical problems that in the prior art, due to the fact that the set irrigation time and frequency are depended, the moisture condition of soil, the change of climate conditions and the growth requirements of forest plants cannot be accurately reflected, irrigation control is not accurate, response lags behind, and water resources are wasted are solved. The technical effects of improving the accuracy and real-time performance of irrigation control, improving the irrigation efficiency and saving water resources are achieved.

Description

Technical Field

[0001] The present application relates to the technical field related to forest irrigation, and in particular to an intelligent remote irrigation control device in forest cultivation. Background Art

[0002] As an important means of ecological environmental protection and forest resource management, forest irrigation technology has been widely used around the world. Traditional forest irrigation control methods mainly rely on artificial experience and timing control, with the purpose of ensuring the healthy growth of forest vegetation, especially the cultivation of seedlings, and ensuring sufficient water supply. However, traditional methods have many limitations. For example, traditional irrigation control methods mostly rely on artificially set irrigation time and frequency, lacking the ability to dynamically adjust irrigation according to actual soil conditions, meteorological changes and plant needs. Experience-based irrigation methods often cannot accurately reflect the soil moisture conditions, changes in climate conditions and the growth needs of forest plants, resulting in waste of water resources or insufficient irrigation. In some cases, too high an irrigation frequency will lead to excess water, causing soil compaction or root rot; insufficient irrigation may lead to slow growth or death of plants; irrigation is based on a fixed periodic schedule, and there is no mechanism for real-time monitoring of environmental changes. During droughts, it is impossible to respond quickly to changes in soil drought, resulting in insufficient water. In rainy weather, if the irrigation volume is not reduced in time, it may cause waste of water resources and other ecological problems.

[0003] Therefore, the current relevant technologies rely on set irrigation time and frequency, which cannot accurately reflect the moisture conditions of the soil, changes in climate conditions, and the growth needs of forest plants, which in turn leads to inaccurate irrigation control, delayed response, and technical problems such as waste of water resources. Summary of the invention

[0004] The present application solves the technical problems in the prior art that the irrigation time and frequency are dependent on set irrigation time and frequency, which cannot accurately reflect the soil moisture conditions, changes in climatic conditions and the growth needs of forest plants, thereby leading to inaccurate irrigation control, delayed response and waste of water resources, by providing an intelligent remote irrigation control device for forest cultivation. The application achieves the technical effect of improving the accuracy and real-time performance of irrigation control, enhancing irrigation efficiency and saving water resources.

[0005] The present application provides an intelligent remote irrigation control device for forest cultivation, the device comprising: a remote sensing platform connection module, used to connect to a remote sensing platform and obtain image data of a forest area; a soil feature analysis module, used to perform soil feature analysis based on the image data, explore soil irrigation requirements, and construct a seedling cultivation requirement sequence in combination with seedling growth characteristics and meteorological data; a mandatory coefficient setting module, used to perform mandatory evaluation of control nodes according to the seedling cultivation requirement sequence, and set mandatory coefficients of each control node based on mandatory evaluation results, wherein the mandatory coefficients are used to reflect the urgency of irrigation requirements for seedling cultivation; a mandatory constraint node extraction module, used to extract mandatory constraint nodes according to the mandatory coefficients of the control nodes, wherein the mandatory constraint nodes are control nodes whose mandatory coefficients reach an irrigation threshold; an irrigation execution target acquisition module, used to perform irrigation time series search with the mandatory constraint nodes and a single maximum irrigation amount as constraint conditions, and obtain irrigation execution targets with the maximum cumulative amount of mandatory coefficients of the irrigation time series as an evaluation condition, wherein the irrigation execution targets include irrigation target areas and irrigation water volumes; an irrigation strategy analysis module, used to perform irrigation strategy analysis with the irrigation target areas and irrigation water volumes, and obtain irrigation control information.

[0006] In a possible implementation, the soil feature analysis module further performs the following processing: the image data includes a hyperspectral image and a thermal infrared image, and the hyperspectral image and the thermal infrared image are spatially registered; soil feature analysis is performed on the hyperspectral image and the thermal infrared image respectively to obtain spectral soil analysis results and thermal infrared soil analysis results; based on the spatial registration relationship, the spectral soil analysis results and the thermal infrared soil analysis results are fused to obtain fused soil features; irrigation demand analysis is performed based on the fused soil features to obtain the soil irrigation demand.

[0007] In a possible implementation, the soil feature analysis module also performs the following processing: performing hierarchical segmentation according to the spectral soil analysis results and the thermal infrared soil analysis results, establishing associated feature pairs according to the equivalence relationship of the segmentation levels, and the associated feature pairs are spectral features and thermal infrared features of the same segmentation level; hierarchically dividing the associated feature pairs according to the sorting relationship of the segmentation levels to construct a multi-feature hierarchy, each feature hierarchy corresponds to a segmentation level, and has built-in spectral features and thermal infrared features of the corresponding segmentation level; based on the multi-feature hierarchy, performing first-order feature interaction in the same feature hierarchy to obtain first-order feature interaction results; performing second-order interaction in adjacent feature hierarchies to obtain second-order feature interaction results; merging the first-order feature interaction results with the second-order feature interaction results to obtain the fused soil feature.

[0008] In a possible implementation, the soil feature analysis module further performs the following processing: identifying the contribution of the spectral feature and the thermal infrared feature to the soil moisture feature of the current segmentation level, and obtaining the key spectral feature and the key thermal infrared feature; The key spectral features and key thermal infrared features are used to analyze soil moisture features to obtain spectral humidity features and thermal infrared humidity features; the spectral humidity features and thermal infrared humidity features are averaged and fused to obtain the first-order interaction results of the features.

[0009] In a possible implementation, the soil feature analysis module also performs the following processing: obtaining the change gradient relationship between the key spectral features, key thermal infrared features and neighborhood features in the same feature level, and fitting the associated feature relationship; fusing the change coefficients of the associated feature relationship of the spectral features and the associated feature relationship of the thermal infrared features to obtain the feature change relationship; obtaining the feature change relationship of adjacent feature levels, performing inter-level aggregation, and obtaining the feature second-order interaction result.

[0010] In a possible implementation, the soil characteristic analysis module also performs the following processing: evaluating the current soil moisture content based on the fused soil characteristics; using the evaporation model constructed using historical forest soil monitoring data to estimate water loss based on the monitored soil characteristics of the current period, and obtaining the water loss rate; using the forest soil water content threshold, performing a time-series compensation analysis on the current soil moisture content according to the water loss rate, and obtaining the soil irrigation demand, wherein the soil irrigation demand represents the time-series demand for soil water replenishment when the forest soil water content threshold is reached.

[0011] In a possible implementation, the soil characteristic analysis module also performs the following processing: sorting the soil irrigation demand characteristics according to the time series relationship to construct a soil demand characteristic time series diagram; obtaining the seedling soil moisture threshold according to the seedling growth characteristics, and correcting the soil demand characteristic time series diagram using the deviation between the seedling soil moisture threshold and the forest soil water content threshold; analyzing the irrigation demand of the growth time period according to the seedling growth characteristics to construct a growth irrigation constraint characteristic time series diagram; extracting humidity influence values ​​according to the meteorological data, the humidity influence values ​​including positive influence and negative influence, sorting the humidity influence values ​​according to time information to construct a meteorological influence characteristic time series diagram; aligning the soil demand characteristic time series diagram, the growth irrigation constraint characteristic time series diagram, and the meteorological influence characteristic time series diagram according to the time series relationship, superimposing features according to the time series alignment relationship to construct a seedling irrigation demand time series diagram, the seedling irrigation demand time series diagram having a seedling soil moisture threshold mark; obtaining the seedling demand sequence based on the seedling irrigation demand time series diagram.

[0012] In a possible implementation, the irrigation execution target acquisition module also performs the following processing: setting the irrigation penalty coefficient for cultivating the seedlings; taking the product of the standard deviation of the forced coefficient and the irrigation penalty coefficient as a correction factor; and adding the correction factor and its irrigation penalty coefficient to the evaluation conditions.

[0013] In a possible implementation, the irrigation execution target obtaining module further performs the following processing: the expression of the evaluation condition is: ,in, , To evaluate the results, is the mandatory coefficient of the i-th seedling in the selected area, is the irrigation requirement of the i-th seedling in the region, i is the number of seedlings in the selected irrigation area, j is the number of seedlings in the unselected area, is the correction factor for the jth seedling not selected, is the irrigation penalty coefficient for not selecting the jth seedling, is the mandatory coefficient for the jth seedling that is not selected.

[0014] Through the intelligent remote irrigation control device for forest cultivation proposed in this application, it is planned to connect the remote sensing platform to obtain image data of the forest area; conduct soil feature analysis to explore soil irrigation needs; conduct mandatory evaluation of control nodes and set mandatory coefficients of each control node; extract mandatory constraint nodes according to the mandatory coefficients of control nodes; take the maximum cumulative amount of mandatory coefficients of irrigation time series as the evaluation condition to obtain irrigation execution targets; perform irrigation strategy analysis to obtain irrigation control information. It solves the technical problems existing in the prior art that the irrigation time and frequency are dependent on the settings, and the soil moisture conditions, changes in climate conditions, and the growth needs of forest plants cannot be accurately reflected, which leads to inaccurate irrigation control, delayed response, and waste of water resources. It achieves the technical effect of improving the accuracy and real-time performance of irrigation control, improving irrigation efficiency, and saving water resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the device according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0016] Figure 1 A schematic diagram of the structure of an intelligent remote irrigation control device for forest cultivation provided in an embodiment of the present application; Figure 2 A schematic diagram of the execution flow of the soil characteristic analysis module in the intelligent remote irrigation control device for forest cultivation provided in an embodiment of the present application.

[0017] Explanation of the reference numerals: remote sensing platform connection module 10, soil characteristic analysis module 20, forced coefficient setting module 30, forced constraint node extraction module 40, irrigation execution target acquisition module 50, irrigation strategy analysis module 60. DETAILED DESCRIPTION

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0019] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0020] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, device, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0021] The present application embodiment provides an intelligent remote irrigation control device for forest cultivation, such as Figure 1 As shown, the device comprises: The remote sensing platform connection module 10 is used to connect to the remote sensing platform to obtain image data of the forest area.

[0022] Preferably, image data of forest areas are obtained in real time through remote sensing platforms, which usually come from satellite remote sensing, UAV remote sensing, ground sensors and other equipment, and can provide detailed information about forest areas, such as soil moisture, vegetation cover, climate change, vegetation health, etc. Specifically, a remote sensing platform refers to a platform that uses satellites, UAVs or other high-altitude / ground equipment to collect images, and usually collects spectral data of different bands through sensors to generate image data, which can cover a wide area and is particularly suitable for monitoring large-scale forest areas; image data of forest areas, that is, image information obtained from remote sensing platforms, may include satellite images, such as ground images taken by satellites such as Landsat and MODIS; UAV images, high-definition images taken by UAVs equipped with high-resolution cameras; thermal infrared imaging, which uses thermal imaging technology to obtain the temperature distribution of forest areas for analysis of water evaporation, soil moisture, etc.; multispectral / hyperspectral images, which analyze images of different spectral bands (visible light, infrared light, etc.) to provide information on the health of soil and vegetation.

[0023] The soil characteristic analysis module 20 is used to perform soil characteristic analysis based on the image data, explore soil irrigation requirements, and construct a seedling cultivation requirement sequence in combination with seedling cultivation growth characteristics and meteorological data.

[0024] Preferably, by analyzing the image data provided by the remote sensing platform, features related to soil, seedling growth and meteorology are extracted, thereby intelligently evaluating irrigation needs and constructing a seedling demand sequence in combination with seedling growth characteristics and meteorological data. Specifically, soil feature analysis refers to the analysis of image data obtained through the remote sensing platform (such as satellite images, images taken by drones, etc.), which may include evaluating information such as soil moisture, soil type, and soil temperature in the forest area to generate soil feature analysis results. For example, through multispectral images, remote sensing technology can identify changes in soil moisture, evaluate whether the soil is dry or needs irrigation, and then analyze the current soil moisture status based on the soil feature analysis results to determine whether the moisture level required for seedling growth is met, thereby generating soil irrigation needs. Specifically, by analyzing the soil moisture information in the remote sensing data and combining it with historical meteorological data (such as precipitation, temperature, etc.), it can be inferred when the soil needs irrigation to achieve the effect of precise irrigation. The soil moisture demand needs to be combined with the growth needs of the plant. For example, seedlings in forest cultivation will have different needs for moisture during their growth process.

[0025] Preferably, a seedling demand sequence is constructed in combination with the growth characteristics of the cultivated seedlings and meteorological data. Specifically, each plant has different water requirements at different growth stages. For example, the seedlings have a higher demand for water in the early growth stage, but it may decrease in the mature stage. The growth status of the seedlings is monitored by remote sensing technology, sensors, etc., and the growth data of the seedlings (such as leaf area index, tree height, root development, etc.) are obtained in real time. Then, real-time meteorological data (such as temperature, humidity, precipitation, wind speed, etc.) are obtained to predict future climate changes and adjust the irrigation plan. For example, if it is expected that the precipitation will be insufficient in the future, the irrigation demand will increase; otherwise, the irrigation amount may be reduced. Then, the meteorological data, the current soil irrigation demand and the growth characteristics of the cultivated seedlings are combined to dynamically adjust the irrigation strategy and establish an irrigation demand sequence, that is, the seedling demand sequence, which represents the irrigation amount and irrigation priority required at different time points in the future (such as a week, a month, etc.). Through this sequence, the irrigation time, irrigation amount and priority can be planned in advance to ensure timely water supply during the growth of the seedlings and ensure the timeliness and scientificity of the irrigation.

[0026] The mandatory coefficient setting module 30 is used to perform mandatory evaluation of the control nodes according to the seedling cultivation demand sequence, and set the mandatory coefficient of each control node based on the mandatory evaluation result, wherein the mandatory coefficient is used to reflect the urgency of the irrigation required for the seedling cultivation.

[0027] Preferably, the urgency of the irrigation control node is evaluated according to the irrigation demand sequence of the cultivated seedlings, and the irrigation priority of each irrigation node is dynamically adjusted by setting a mandatory coefficient. Specifically, by analyzing the demand sequence of the cultivated seedlings, it is determined in which periods the seedlings have a higher demand for water and in which periods the demand is lower. The control node usually refers to a point that can control the water flow or irrigation amount, such as the switch of the irrigation pipe, the sprinkler controller, the valve, etc., which are distributed in different positions of the irrigation area and control the irrigation process of different areas. The mandatory evaluation of the control node refers to judging the irrigation urgency of each control node according to the demand sequence of the cultivated seedlings. For example, if the soil in a certain area is too dry, or the seedlings in the area are in urgent need of water within a certain period of time, then the control node in the area will be evaluated as a high mandatory node, which means that priority irrigation is required; then The mandatory coefficient of the control node is set according to the mandatory assessment results to quantify the urgency of each control node, that is, the degree to which the node should be executed first in the irrigation system. For example, a node with a higher mandatory coefficient means that the soil drought in the area is more serious, or the irrigation demand of the seedlings is more urgent and requires immediate irrigation; a node with a lower mandatory coefficient indicates that the moisture condition in the area is better and no water replenishment is needed temporarily. The basis for setting the mandatory coefficient usually includes soil moisture (if the soil moisture is too low, the mandatory coefficient will be higher), seedling growth stage and meteorological conditions (under climatic conditions such as drought and high temperature, the urgency of irrigation will increase). The mandatory coefficient is used to reflect the urgency of irrigation for seedling cultivation. That is, the level of the mandatory coefficient determines the operation priority of each irrigation node, which can help the irrigation system make reasonable scheduling according to the needs of different regions.

[0028] The mandatory constraint node extraction module 40 is used to extract mandatory constraint nodes according to the mandatory coefficient of the control node, wherein the mandatory constraint node is a control node whose mandatory coefficient reaches an irrigation threshold.

[0029] Preferably, based on the forcing coefficient of each irrigation control node, it is determined which control nodes have urgent irrigation needs, so that irrigation operations are given priority, wherein the irrigation threshold is a critical value preset based on historical data and actual needs, which is used to determine which control nodes have urgent irrigation needs and must be irrigated immediately. For example, it can be set that when the forcing coefficient reaches or exceeds a certain value (such as 0.8 or 1.0), it means that the irrigation demand of the control node is already very urgent and action needs to be taken as soon as possible. Specifically, when the forcing coefficient of the control node reaches the irrigation threshold, that is, the irrigation demand of these nodes has reached or exceeded the set threshold, indicating that the irrigation demand of these areas is already very urgent and irrigation needs to be given priority. The control nodes that need to be irrigated immediately among all control nodes are screened as forced constraint nodes for priority irrigation scheduling, so as to accurately and effectively respond to the water needs of different areas, avoid waste of water resources and ensure the rapid recovery of seedlings and soil moisture.

[0030] The irrigation execution target acquisition module 50 is used to search the irrigation sequence with the mandatory constraint node and the single maximum irrigation amount as constraint conditions, and obtain the irrigation execution target with the maximum cumulative amount of the mandatory coefficient of the irrigation sequence as the evaluation condition. The irrigation execution target includes the irrigation target area and its irrigation water amount.

[0031] Preferably, the best irrigation time and amount are determined according to the urgent needs of the irrigation control nodes (mandatory constraint nodes) and the limitation of the single maximum irrigation amount. Finally, the optimal irrigation plan is selected by evaluating the effects of different irrigation timings, and the final irrigation execution target, that is, the irrigation target area and its required water volume, is determined. Specifically, the mandatory constraint node represents the area with the most urgent irrigation demand, the single maximum irrigation volume refers to the maximum water limit that the irrigation system can apply at each irrigation, and the irrigation timing search refers to simulating and exploring different irrigation timings with mandatory constraint nodes and the single maximum irrigation volume as constraints, that is, by evaluating each timing plan, the most suitable irrigation timing is found, including the best irrigation time and water distribution method, and then the mandatory coefficient cumulative amount of each timing plan is calculated, that is, the mandatory coefficient cumulative amount of each irrigation is calculated. The sum of the forced coefficients of all control nodes within the time period. Among multiple irrigation timing schemes, the irrigation scheme with the largest cumulative forced coefficient is taken as the optimal irrigation scheme, indicating that the scheme can most effectively meet the irrigation needs of all forced constraint nodes, ensuring that water is replenished in time to the places where it is most needed, and then obtaining the irrigation execution target, where the irrigation execution target includes the irrigation target area and its irrigation water volume. The irrigation target area refers to the specific geographical area that needs to be irrigated, which is usually the area with the most urgent irrigation demand determined by the selection of forced constraint nodes; the irrigation water volume refers to the amount of water that needs to be replenished in each target area during each irrigation period. For example, the amount of water replenished in the forced constraint node area is determined based on factors such as soil moisture conditions, climatic conditions, and plant growth requirements, and does not exceed the maximum irrigation volume, thereby ensuring efficient and reasonable allocation of water resources.

[0032] The irrigation strategy analysis module 60 is used to analyze the irrigation strategy according to the irrigation target area and the irrigation water volume to obtain irrigation control information.

[0033] Preferably, after determining the target area for irrigation and the amount of water required for irrigation, the irrigation strategy is analyzed and specific irrigation control information is generated to guide irrigation operations, ensure that the irrigation system can accurately and effectively perform irrigation tasks, and maximize the efficiency of water resource use. Specifically, the irrigation strategy analysis is to formulate a reasonable irrigation strategy based on the target area and irrigation water volume, which usually includes comprehensive consideration of weather forecasts (such as precipitation, temperature, wind speed, etc.), soil type, seedling requirements, etc., to determine the irrigation time window for each target area, to ensure that irrigation can be carried out at the most appropriate time, and to avoid water evaporation loss; to determine the irrigation intensity based on the permeability and water absorption capacity of the soil, that is, to reasonably allocate the amount of water for each irrigation, to ensure that the water can be Effective absorption; select the most suitable irrigation method (such as drip irrigation, sprinkler irrigation, infiltration irrigation, etc.); determine the irrigation cycle frequency according to the changes in soil moisture and the needs of seedlings in different time periods; and then generate specific irrigation control information, including starting irrigation equipment (such as water pumps, sprinklers, drip irrigation systems, etc.) according to the requirements of irrigation target areas, irrigation periods and irrigation intensity, and determine which irrigation equipment should be started and when according to irrigation strategies. For example, some areas may need to turn on multiple irrigation equipment for simultaneous irrigation; and water flow control information for each irrigation node (flow rate, irrigation duration, etc.). The irrigation system performs specific irrigation operations based on the irrigation control information and ensures the accuracy, timeliness and rational use of resources of the irrigation process.

[0034] The intelligent remote irrigation control device for forest cultivation according to the embodiment of the present invention is used to solve the technical problem that the existing technology relies on the set irrigation time and frequency, cannot accurately reflect the soil moisture condition, the change of climate conditions and the growth requirements of forest plants, and thus leads to inaccurate irrigation control, delayed response and waste of water resources, thereby achieving the technical effect of improving the accuracy and real-time performance of irrigation control, improving irrigation efficiency and saving water resources. The intelligent remote irrigation control device for forest cultivation includes: a remote sensing platform connection module 10, a soil characteristic analysis module 20, a forced coefficient setting module 30, a forced constraint node extraction module 40, an irrigation execution target acquisition module 50, and an irrigation strategy analysis module 60.

[0035] The specific configuration of the soil characteristic analysis module 20 will be described in detail below. Figure 2As shown, the soil feature analysis module 20 may further include: the image data includes a hyperspectral image and a thermal infrared image, and the hyperspectral image and the thermal infrared image are spatially registered; soil feature analysis is performed on the hyperspectral image and the thermal infrared image respectively to obtain spectral soil analysis results and thermal infrared soil analysis results; based on the spatial registration relationship, the spectral soil analysis results and the thermal infrared soil analysis results are fused to obtain fused soil features; irrigation demand analysis is performed according to the fused soil features to obtain the soil irrigation demand.

[0036] Preferably, hyperspectral images collect information in different spectral bands through hyperspectral imaging technology, and provide more detailed reflectance information of soil, vegetation and other objects than ordinary color images, so as to identify the chemical composition, moisture, mineral distribution and other characteristics of the soil. Thermal infrared images detect thermal radiation emitted by the surface through thermal infrared imaging technology to obtain detailed information on surface temperature and heat changes, and help analyze soil temperature, evaporation rate and soil moisture, etc. The hyperspectral image and the thermal infrared image are then spatially registered, that is, the two different types of image data are aligned so that they correspond to the same position in space, to ensure that data from different image sources can be combined and analyzed in the same geographic coordinate system, thereby maintaining the geometric consistency between the two images.

[0037] Preferably, soil feature analysis of hyperspectral images refers to identifying different material components in the soil (such as organic matter, minerals, etc.), as well as soil moisture, pH value and other properties through spectral analysis technology (such as analysis of spectral reflectance curves), wherein the reflectance of different bands can reflect the moisture, salinity, mineral composition and other conditions of the soil, thereby judging the irrigation needs of the soil; soil feature analysis of thermal infrared images refers to obtaining the moisture condition and evaporation condition of the soil by measuring the temperature distribution of the soil with thermal infrared images, and the temperature change of the soil can indirectly reflect the wetness of the soil, because when the soil is rich in moisture, the evaporation rate is low and the temperature is relatively low; conversely, when the soil is short of water, the evaporation rate increases, the soil temperature rises, the temperature of dry soil changes quickly, and the temperature of moist soil changes slowly, which appears as a higher temperature on the thermal infrared image.

[0038] Preferably, the spectral analysis results provided by the hyperspectral image and the thermal analysis results provided by the thermal infrared image are fused according to the spatial registration relationship, that is, the advantages of the two images are combined by using data fusion methods such as weighted average and principal component analysis (PCA), so as to provide more comprehensive and accurate soil characteristic data. For example, the spectral image provides the chemical and moisture information of the soil, while the thermal infrared image provides the temperature and evaporation information of the soil. The fused soil characteristics include multi-dimensional characteristics such as the spectral information, temperature information, moisture status, evaporation rate, etc. of the soil, which can more comprehensively and accurately analyze the moisture status and irrigation needs of the soil; then, the irrigation demand analysis is performed based on the fused soil characteristics, that is, analyzing whether the soil is in a drought state (needing to supplement water). For example, if the soil temperature is too high and the humidity is low, it is recommended to increase the irrigation amount; if the soil moisture is moderate, the irrigation amount can be reduced to avoid waste of water resources, thereby accurately predicting the irrigation needs of the soil and ensuring the accuracy and efficiency of irrigation.

[0039] The specific configuration of the soil feature analysis module 20 will be described in detail below. The soil feature analysis module 20 may further include: performing hierarchical segmentation according to the spectral soil analysis results and the thermal infrared soil analysis results, establishing associated feature pairs according to the equivalence relationship of the segmentation levels, and the associated feature pairs are spectral features and thermal infrared features of the same segmentation level; hierarchically dividing the associated feature pairs according to the sorting relationship of the segmentation levels, constructing a multi-feature hierarchy, each feature hierarchy corresponds to a segmentation level, and has built-in spectral features and thermal infrared features of the corresponding segmentation level; based on the multi-feature hierarchy, performing first-order feature interaction in the same feature hierarchy to obtain first-order feature interaction results; performing second-order interaction in adjacent feature hierarchies to obtain second-order feature interaction results; merging the first-order feature interaction results with the second-order feature interaction results to obtain the fused soil feature.

[0040] Preferably, the analysis results of the hyperspectral and thermal infrared images are graded, and through the interaction of features at different levels, a comprehensive soil feature is generated by combining multi-dimensional information, thereby improving the accuracy of irrigation decisions. Specifically, the spectral analysis results and the thermal infrared analysis results are graded, usually according to certain characteristics of the soil (such as moisture, temperature, mineral content, etc.). For example, soil moisture may be divided into different levels such as dry, moderate, and moist, and soil temperature may also be divided into different levels. According to the equivalence relationship of the segmentation levels, an associated feature pair is established, that is, in the spectral features and thermal infrared features, each The spectral features and thermal infrared features in each segmentation level correspond one to one, and the soil features of each level are defined by the spectral data and thermal infrared data to ensure the consistency of the two types of data; then the associated feature pairs are divided into levels according to the level segmentation, and each feature level corresponds to a segmentation level. Each level contains the spectral features and thermal infrared features of this level. For example, level 1 may correspond to the spectral features and thermal infrared features of "dry" soil, and level 2 corresponds to the features of "moderate" soil, and so on. A multi-feature hierarchy is established to organize and store soil features of different segmentation levels, and the feature information of each level can be classified and processed.

[0041] Preferably, according to the established multi-feature hierarchy, a first-order interaction of features is performed in the same feature hierarchy, that is, spectral data and thermal infrared data are combined by mathematical methods (such as weighted summation, correlation analysis, etc.) to perform a first-order interaction analysis to extract the comprehensive information of spectral and thermal infrared features in the hierarchy as a first-order interaction result (feature combination at the hierarchy), which reflects the comprehensive characteristics of the soil at the segmentation level; then a second-order interaction is performed in adjacent feature hierarchies, that is, the first-order interaction results in the two hierarchies are combined to perform a higher-level feature interaction, such as using a cross analysis or weighted summation method to fuse information at different hierarchies to produce a more comprehensive soil feature as a second-order interaction result to capture the relationship between different segmentation levels; the first-order interaction result and the second-order interaction result are then merged to obtain the final fused soil feature, which contains the comprehensive information of spectral and thermal infrared data, can reflect the information of multiple dimensions such as soil moisture, temperature, humidity, etc., and provide accurate input for subsequent irrigation demand analysis.

[0042] The specific configuration of the soil feature analysis module 20 will be described in detail below. The soil feature analysis module 20 may further include: identifying the contribution of the spectral feature and the thermal infrared feature to the soil moisture feature of the current segmentation level, and obtaining the key spectral feature and the key thermal infrared feature; using the key spectral feature and the key thermal infrared feature to perform soil moisture feature analysis, and obtaining the spectral moisture feature and the thermal infrared moisture feature; averaging the spectral moisture feature and the thermal infrared moisture feature to obtain the first-order interaction result of the feature.

[0043] Preferably, by identifying key features in spectral and thermal infrared data, combining these features to analyze soil moisture, and finally obtaining a comprehensive moisture analysis result through feature fusion, which is then used for irrigation decision-making. Specifically, the contribution of spectral features to soil moisture features is identified. Hyperspectral images contain information on multiple spectral bands. The reflectivity of different bands corresponds to different soil and vegetation characteristics. The reflectivity of some spectral bands is more sensitive to humidity, while other bands may be less sensitive to humidity changes. By analyzing the data of these bands, key spectral features that are highly correlated with soil moisture are identified; thermal infrared images can provide information on soil surface temperature. Soil moisture usually affects the temperature distribution of soil. By analyzing the changes in soil temperature and thermal radiation in thermal infrared images, key thermal infrared features that are closely related to soil moisture can be identified. For example, moist soil usually has a lower temperature because the evaporation of water can absorb a certain amount of heat, while dry soil has a higher temperature.

[0044] Preferably, soil moisture feature analysis is performed based on key spectral features, that is, the change of soil moisture is analyzed by extracting key features from spectral data. For example, certain spectral bands (such as near-infrared bands) are very sensitive to water reflection and can reflect the high and low soil moisture, thereby obtaining spectral moisture features, that is, the manifestation of soil moisture in spectral features; soil moisture feature analysis is performed based on key thermal infrared features, that is, the influence of soil moisture on temperature is analyzed by extracting key features from thermal infrared images. For example, higher humidity usually means lower soil temperature, thereby obtaining thermal infrared moisture features, that is, the manifestation of soil moisture in thermal infrared data; the spectral moisture features and thermal infrared moisture features are averaged and fused to obtain more accurate soil moisture features, which, as the first-order interaction result of features, represent the joint analysis and comprehensive reflection of soil moisture by spectral features and thermal infrared features at the same level, thereby enhancing the reliability and accuracy of soil moisture estimation, thereby optimizing irrigation management and saving water resources.

[0045] The specific configuration of the soil feature analysis module 20 will be described in detail below. The soil feature analysis module 20 may further include: obtaining the change gradient relationship between the key spectral features, the key thermal infrared features and the neighborhood features in the same feature level, fitting the associated feature relationship; fusing the change coefficients of the associated feature relationship of the spectral features and the associated feature relationship of the thermal infrared features to obtain the feature change relationship; obtaining the feature change relationship of adjacent feature levels, performing inter-level aggregation, and obtaining the feature second-order interaction result.

[0046] Preferably, by analyzing the changing relationship between spectral features and thermal infrared features, using gradient information to fit the correlation between features, and integrating the feature relationships at different levels, a more comprehensive description of soil features is obtained, thereby optimizing irrigation decisions. Specifically, in the same feature level, each spectral feature and thermal infrared feature is not only associated with other features, but may also have a changing relationship with its neighboring features. By analyzing the changing gradients of these neighborhood features (i.e., the rate of change of the feature value with space or time), the local changing laws of soil features can be captured. For example, the change of soil moisture at different locations may be affected by the soil conditions in the neighborhood. Then, by calculating the gradient changes of spectral features and thermal infrared features, the trend and amplitude of the changes of these features in the local range are identified to determine the importance of certain features to soil moisture or other soil properties. For example, the spectral features of certain bands may show strong gradient changes in areas where the soil moisture changes greatly, indicating that the features of these bands have a strong correlation with soil moisture. Then, the changing gradient relationship between spectral features, thermal infrared features and neighborhood features is fitted to establish a correlation feature relationship. For example, the features of certain spectral bands may have a linear relationship with soil moisture, while other bands may show a nonlinear relationship.

[0047] Preferably, the correlation feature relationship of the spectral features and the correlation feature relationship of the thermal infrared features are fused by the variation coefficient, that is, the variation coefficient (sensitivity or weight of feature change) is introduced to fuse the correlation feature relationship of the spectral features and the thermal infrared features, so as to balance the role of the two in the feature changes such as soil moisture. For example, the spectral feature change of a certain band has a greater impact on soil moisture, while the thermal infrared feature changes less, then the variation coefficient of the spectral feature may be given a higher weight, and vice versa, the thermal infrared feature is given a higher weight, thereby obtaining a comprehensive feature change relationship, reflecting the relative importance and role of the two data sources in soil feature analysis; and then adopting weighted averaging, summation and other methods, according to the variation coefficient and correlation of each level, the feature change relationship of adjacent feature levels is fused to capture the feature interactions and associations between different levels, so as to obtain a more comprehensive soil feature description, that is, to obtain the feature second-order interaction results, and more accurately mine soil features and describe soil status.

[0048] The specific configuration of the soil characteristic analysis module 20 will be described in detail below. The soil characteristic analysis module 20 may further include: evaluating the current soil moisture content according to the fused soil characteristics; using the evapotranspiration model constructed by the historical forest soil monitoring data to estimate the water loss based on the monitored soil characteristics of the current period to obtain the water loss rate; using the forest soil water content threshold, performing a time series compensation analysis on the current soil moisture content according to the water loss rate to obtain the soil irrigation demand, which represents the soil water replenishment time series demand when the forest soil water content threshold is reached.

[0049] Preferably, the soil moisture content is estimated based on the fused soil characteristics, and the water loss rate is evaluated in combination with the evapotranspiration model, and finally the irrigation replenishment amount and time required to meet the soil moisture demand are calculated, wherein the evapotranspiration model is established based on historical data and climate conditions, and is used to estimate the loss of water in the soil. The evapotranspiration model usually considers the influence of meteorological factors (such as temperature, humidity, wind speed, solar radiation, etc.) on water loss, and analyzes the evaporation of soil moisture under different climatic conditions and the law of plant transpiration (i.e. "evapotranspiration") through historical forest soil monitoring data; specifically, by analyzing the fused soil characteristics and combining the soil moisture model (such as the relationship between moisture and spectral characteristics), the current soil moisture content is estimated, which reflects the current wetness of the soil, usually expressed as a percentage (the proportion of moisture in the soil to the soil), and then the evapotranspiration model is used to estimate the water loss of the soil characteristics monitored during the current monitoring period, so as to obtain the water loss rate, which reflects the amount of water lost per unit time under the current climate conditions, and is usually affected by meteorological conditions (such as temperature, precipitation, wind speed, etc.) and soil properties (such as soil type, structure, humidity, etc.).

[0050] Preferably, the current soil moisture content is analyzed for time series compensation according to the water loss rate based on the forest soil moisture content threshold, that is, based on the current soil humidity level and the future water loss rate, the amount of water that needs to be supplemented in certain future periods in order to maintain the soil moisture above the threshold is calculated. The time series compensation analysis can be adjusted according to the water loss rate, climate change and soil characteristics in different time periods. The soil moisture content threshold refers to the minimum soil moisture level required for forest plant growth. For example, when the soil moisture content is lower than a certain threshold, the growth of plants will be affected, which may lead to excessive water stress and affect their normal development. Ultimately, the required soil irrigation demand is obtained, which characterizes the amount of water required to be supplemented and the timing of irrigation in order to make the soil moisture reach the set forest soil moisture content threshold, that is, the time period for irrigation and the amount of water for each irrigation. This is used as the soil water replenishment timing demand, which provides a scientific basis for precise forest irrigation management.

[0051] The specific configuration of the soil characteristic analysis module 20 will be described in detail below. The soil characteristic analysis module 20 may further include: sorting the soil irrigation demand demand characteristics according to the time series relationship, and constructing a soil demand characteristic time series diagram; obtaining the soil moisture threshold of the cultivated seedling according to the growth characteristics of the cultivated seedling, and using the deviation between the soil moisture threshold of the cultivated seedling and the water content threshold of the forest soil to correct the soil demand characteristic time series diagram; analyzing the irrigation demand of the growth time period according to the growth characteristics of the cultivated seedling, and constructing a growth irrigation constraint characteristic time series diagram; extracting the humidity impact value according to the meteorological data, the humidity impact value includes positive impact and negative impact, sorting the humidity impact value according to the time information, and constructing a meteorological impact characteristic time series diagram; aligning the soil demand characteristic time series diagram, the growth irrigation constraint characteristic time series diagram, and the meteorological impact characteristic time series diagram according to the time series relationship, superimposing the features according to the time series alignment relationship, and constructing a cultivated seedling irrigation demand time series diagram, wherein the cultivated seedling irrigation demand time series diagram has a cultivated seedling soil moisture threshold mark; based on the cultivated seedling irrigation demand time series diagram, obtaining the cultivated seedling demand sequence.

[0052] Preferably, the soil irrigation demand in each irrigation period is sorted in chronological order, that is, the demands in different time periods are sorted according to factors such as the urgency of the irrigation demand, soil moisture and meteorological changes, and a soil demand characteristic time series diagram is compiled to show the soil demand for different areas at different time points, as well as the changes in soil moisture and irrigation demand in each time period. Each seedling has its specific soil moisture demand during the growth process. The soil moisture threshold for the cultivated seedlings is obtained according to the growth characteristics of the cultivated seedlings, and then the soil demand characteristic time series diagram is corrected through the deviation between the soil moisture threshold for the cultivated seedlings and the forest soil water content threshold, so that the irrigation plan is more in line with the growth characteristics of the seedlings. Then, according to the growth time cycle of the seedlings, the irrigation demand at different growth stages is analyzed, and a growth irrigation constraint characteristic time series diagram is constructed to describe the water demand and irrigation timing of the seedlings at different growth stages.

[0053] Preferably, the humidity impact value is obtained by analyzing the meteorological data, and the positive and negative impacts are classified. The positive impact usually refers to beneficial water replenishment such as precipitation, while the negative impact refers to the increased evaporation of soil moisture due to increased temperature or increased wind speed. The humidity impact values ​​are sorted according to the time information to form a meteorological impact characteristic time series diagram to show the specific impact of meteorological conditions on soil moisture and irrigation demand in different time periods; then the soil demand characteristic time series diagram, the growth irrigation constraint characteristic time series diagram, and the meteorological impact characteristic time series diagram are aligned in time, that is, aligned in time order to ensure that all demand characteristics, meteorological impacts and growth stage information can correspond to each other on the time axis, and the characteristics of each time series diagram are aligned. The above data are superimposed to form a time series diagram of the irrigation demand for seedlings, which integrates factors such as soil moisture demand, meteorological influence, and seedling growth characteristics to make more accurate irrigation decisions. Among them, the time series diagram of the irrigation demand for seedlings will mark the soil moisture threshold of the seedlings to clarify which periods need to increase irrigation and which periods can reduce irrigation. Finally, based on the time series diagram of the irrigation demand for seedlings, a detailed seedling demand sequence is extracted, which not only reflects the irrigation demand of seedlings in different time periods, but also takes into account soil moisture threshold, meteorological changes, seedling growth stage and other factors, providing an accurate irrigation scheduling plan for the irrigation system to ensure that seedlings can get the required water supply at different growth stages to achieve the best growth effect.

[0054] The specific configuration of the irrigation execution target acquisition module 50 will be described in detail below. The irrigation execution target acquisition module 50 may further include: setting the irrigation penalty coefficient of the cultivated seedlings; taking the product of the standard deviation of the mandatory coefficient and the irrigation penalty coefficient as a correction factor; and adding the correction factor and its irrigation penalty coefficient to the evaluation condition.

[0055] Preferably, the accuracy and rationality of irrigation decisions are adjusted by introducing irrigation penalty coefficients and correction factors, thereby ensuring that the execution of irrigation plans is more in line with demand and avoiding improper irrigation. Specifically, the irrigation penalty coefficient is used to represent the penalty or cost of irrigation behavior. For example, for different cultivated seedlings, when irrigating, not only whether it is an irrigation demand node is considered, but also the growth characteristics of the cultivated seedlings (high price, high irrigation requirements, high growth environment requirements, etc.) are considered. The irrigation penalty coefficient is set based on these characteristics, specifically including defining a penalty function for each cultivated seedling, which is used to calculate the penalty value based on factors such as the irrigation demand, growth characteristics, and economic value of the cultivated seedlings. For the selected cultivated seedlings, if the irrigation operation meets the needs of the cultivated seedlings, the penalty value can be lower; if it does not meet the needs, the penalty value can be higher; for the unselected cultivated seedlings, their penalty values ​​are calculated based on their irrigation needs and the potential impact of the current irrigation strategy, and the penalties for the selected and unselected cultivated seedlings are comprehensively considered, such as The penalty value of the selected seedlings is combined with the penalty value of the unselected seedlings to form a comprehensive penalty value; then the standard deviation of the forced coefficient (the degree of dispersion of the forced coefficient values ​​of all control nodes) is multiplied by the determined irrigation penalty coefficient to obtain the correction factor, which is used to fine-tune the irrigation decision. If the irrigation demand in a certain area fluctuates greatly (that is, the standard deviation is large) and the irrigation penalty coefficient is high, the correction factor will be larger, thereby increasing the irrigation priority for the area and avoiding excessive or insufficient irrigation; finally, the correction factor and the irrigation penalty coefficient are added to the evaluation conditions, where the evaluation conditions are used to measure the pros and cons of different irrigation schemes, usually including soil moisture, irrigation demand, meteorological factors, etc. By adding the correction factor and the irrigation penalty coefficient to the evaluation conditions, it is possible to more accurately balance the irrigation demand and potential negative impact of each region when making irrigation decisions, thereby effectively balancing the needs of precision irrigation and water conservation, and improving the overall irrigation efficiency, ensuring the efficient use of water resources and the healthy growth of seedlings.

[0056] The specific configuration of the irrigation execution target acquisition module 50 will be described in detail below. The irrigation execution target acquisition module 50 may further include: the expression of the evaluation condition is: ,in, , To evaluate the results, is the mandatory coefficient of the i-th seedling in the selected area, is the irrigation requirement of the i-th seedling in the region, i is the number of seedlings in the selected irrigation area, j is the number of seedlings in the unselected area, is the correction factor for the jth seedling not selected, is the irrigation penalty coefficient for not selecting the jth seedling, is the mandatory coefficient for the jth seedling that is not selected.

[0057] Although the present application makes various references to certain modules in the device according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0058] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. Intelligent remote irrigation control device in forest cultivation, characterized in that: The device comprises: A remote sensing platform connection module is used to connect to the remote sensing platform to obtain image data of the forest area; A soil characteristic analysis module is used to analyze soil characteristics according to the image data, explore soil irrigation requirements, and construct a seedling cultivation requirement sequence in combination with seedling cultivation growth characteristics and meteorological data; A mandatory coefficient setting module, used to perform mandatory evaluation of control nodes according to the seedling cultivation demand sequence, and set the mandatory coefficient of each control node based on the mandatory evaluation result, wherein the mandatory coefficient is used to reflect the urgency of the seedling cultivation needing irrigation; A mandatory constraint node extraction module, used for extracting mandatory constraint nodes according to the mandatory coefficient of the control node, wherein the mandatory constraint node is a control node whose mandatory coefficient reaches an irrigation threshold; An irrigation execution target acquisition module is used to use the mandatory constraint node and the single maximum irrigation amount as constraint conditions to search the irrigation time series, and use the maximum cumulative amount of mandatory coefficients of the irrigation time series as an evaluation condition to obtain the irrigation execution target, wherein the irrigation execution target includes the irrigation target area and the irrigation water amount; The irrigation strategy analysis module is used to analyze the irrigation strategy according to the irrigation target area and the irrigation water volume to obtain irrigation control information.

2. The intelligent remote irrigation control device for forest cultivation as claimed in claim 1, characterized in that: The soil characteristic analysis module performs the following steps: The image data includes a hyperspectral image and a thermal infrared image, and the hyperspectral image and the thermal infrared image are spatially registered; Perform soil characteristic analysis on the hyperspectral image and the thermal infrared image respectively to obtain spectral soil analysis results and thermal infrared soil analysis results; Based on the spatial registration relationship, the spectral soil analysis results and the thermal infrared soil analysis results are fused to obtain fused soil features; An irrigation demand analysis is performed based on the fused soil characteristics to obtain the soil irrigation demand.

3. The intelligent remote irrigation control device for forest cultivation as claimed in claim 2, characterized in that: The soil characteristic analysis module performs the following steps: Performing level segmentation according to the spectral soil analysis results and the thermal infrared soil analysis results, and establishing associated feature pairs according to the equivalence relationship of the segmentation levels, wherein the associated feature pairs are spectral features and thermal infrared features of the same segmentation level; According to the sorting relationship of the segmentation levels, the associated feature pairs are hierarchically divided to construct a multi-feature hierarchy, each feature hierarchy corresponds to a segmentation level, and the spectral features and thermal infrared features corresponding to the segmentation level are built-in; Based on the multiple feature levels, performing first-order feature interaction in the same feature level to obtain a first-order feature interaction result; Perform second-order interactions in adjacent feature levels to obtain feature second-order interaction results; The first-order interaction result of the feature is combined with the second-order interaction result of the feature to obtain the fused soil feature.

4. The intelligent remote irrigation control device for forest cultivation as claimed in claim 3, characterized in that: The soil characteristic analysis module performs the following steps: Identify the contribution of the spectral features and thermal infrared features to the soil moisture features of the current segmentation level, and obtain key spectral features and key thermal infrared features; Utilizing the key spectral features and the key thermal infrared features to analyze soil moisture features, and obtaining spectral moisture features and thermal infrared moisture features; The spectral humidity feature and the thermal infrared humidity feature are averaged and fused to obtain the first-order interaction result of the feature.

5. The intelligent remote irrigation control device for forest cultivation as claimed in claim 4, characterized in that: The soil characteristic analysis module performs the following steps: Obtaining the change gradient relationship between the key spectral features, the key thermal infrared features and the neighborhood features in the same feature level, and fitting the associated feature relationship; The correlation characteristic relationship of the spectral feature and the correlation characteristic relationship of the thermal infrared feature are fused by the variation coefficient to obtain the characteristic variation relationship; The feature change relationship between adjacent feature levels is obtained, and inter-level aggregation is performed to obtain the second-order interaction result of the features.

6. The intelligent remote irrigation control device for forest cultivation as claimed in claim 2, characterized in that: The soil characteristic analysis module performs the following steps: evaluating current soil moisture content based on the fused soil characteristics; Using the evapotranspiration model constructed using historical forest soil monitoring data, water loss was estimated based on the monitored soil characteristics of the current period to obtain the water loss rate; Based on the forest soil water content threshold, the current soil water content is subjected to time series compensation analysis according to the water loss rate to obtain the soil irrigation demand, which represents the soil water replenishment time series demand when the forest soil water content threshold is reached.

7. The intelligent remote irrigation control device for forest cultivation as claimed in claim 6, characterized in that: The soil characteristic analysis module performs the following steps: Sort the soil irrigation demand characteristics according to the time series relationship, and construct a soil demand characteristic time series diagram; According to the growth characteristics of the cultivated seedlings, a soil moisture threshold of the cultivated seedlings is obtained, and the deviation between the soil moisture threshold of the cultivated seedlings and the water content threshold of the forest soil is used to correct the soil demand characteristic time series diagram; Performing irrigation demand analysis during the growth period according to the growth characteristics of the cultivated seedlings, and constructing a time series diagram of growth irrigation constraint characteristics; Extract humidity impact values ​​according to the meteorological data, wherein the humidity impact values ​​include positive impact and negative impact, sort the humidity impact values ​​according to time information, and construct a meteorological impact feature time series diagram; According to the time series relationship, the soil demand characteristic time series diagram, the growth irrigation constraint characteristic time series diagram, and the meteorological influence characteristic time series diagram are time-series aligned, and the characteristics are superimposed according to the time series alignment relationship to construct a seedling cultivation irrigation demand time series diagram, wherein the seedling cultivation irrigation demand time series diagram has a seedling cultivation soil moisture threshold mark; Based on the seedling cultivation irrigation demand timing diagram, the seedling cultivation demand sequence is obtained.

8. The intelligent remote irrigation control device for forest cultivation as claimed in claim 1, characterized in that: The irrigation execution target acquisition module performs the following steps: Setting the irrigation penalty coefficient for the seedling cultivation; The product of the standard deviation of the mandatory coefficient and the irrigation penalty coefficient is used as a correction factor; The correction factor and the irrigation penalty coefficient thereof are added to the evaluation conditions.

9. The intelligent remote irrigation control device for forest cultivation as claimed in claim 8, characterized in that: The expression of the evaluation condition is: ,in, , To evaluate the results, is the mandatory coefficient of the i-th seedling in the selected area, is the irrigation requirement of the i-th seedling in the region, i is the number of seedlings in the selected irrigation area, j is the number of seedlings in the unselected area, is the correction factor for the jth seedling that was not selected, is the irrigation penalty coefficient for not selecting the jth seedling, is the mandatory coefficient for the jth seedling that is not selected.

Images