Intelligent monitoring, regulating and controlling method and system for growth condition of sugarcane and electronic equipment

Abstract

The invention discloses an intelligent monitoring, regulating and controlling method and system for the growth condition of sugarcane and electronic equipment, and relates to the technical field of sugarcane planting.The method comprises the steps that data of a plurality of indexes associated with each sampled sugarcane are obtained, time alignment and space registration are carried out, and according to a time sequence data set of each sampled sugarcane, a plurality of indexes are obtained; the growth condition of each piece of sampled sugarcane is obtained in an artificial intelligence mode; according to the growth condition of each sampled sugarcane, an irrigation scheme is determined in an artificial intelligence mode, a large amount of time sequence data sets can be rapidly and efficiently processed and analyzed through the AI intelligent technology, the growth state of each sampled sugarcane can be accurately recognized, the irrigation scheme is adjusted in time according to actual changes, and the irrigation efficiency is improved. The dynamic management mode can better adapt to various changes in the growth process of the sugarcane, and the yield and quality of the sugarcane are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of sugarcane planting, and in particular to an intelligent monitoring and control method, system and electronic equipment for the growth condition of sugarcane. Background Art

[0002] During sugarcane planting, it is necessary to monitor the growth of sugarcane in order to adjust the planting management plan. Currently, the main monitoring methods are as follows:

[0003] 1) Traditional manual monitoring methods require a lot of manpower and time, are inefficient, and are easily affected by human factors, resulting in insufficient data accuracy and reliability. For example, when manually inspecting the growth of sugarcane, errors in judgment may occur due to differences in observer experience.

[0004] 2) Field sensors can monitor soil moisture, temperature and other parameters in real time, but their monitoring range is limited and usually only covers local areas, which cannot fully reflect the growth status of the entire sugarcane field.

[0005] 3) While remote sensing technology can capture sugarcane growth information over a wide area, its data resolution and accuracy are limited. For example, some low-resolution satellite remote sensing images may not accurately distinguish sugarcane from other crops or vegetation, thus affecting the accuracy of monitoring results. High-resolution satellite remote sensing images often come with high costs and large data transmission volumes.

[0006] In summary, existing monitoring methods are often independent of each other and lack effective data integration and analysis methods. This makes it difficult to integrate data from different sources to obtain more comprehensive and accurate information on sugarcane growth. This can lead to unscientific and unjustified assessments of sugarcane growth conditions. Summary of the Invention

[0007] The technical problem to be solved by the present invention is to address the deficiencies of the existing technology and specifically provide a method, system and electronic device for intelligently monitoring and controlling the growth status of sugarcane, as follows:

[0008] 1) In a first aspect, the present invention provides a method for intelligently monitoring and controlling the growth of sugarcane. The specific technical solution is as follows:

[0009] Acquire data of multiple indicators associated with each sampled sugarcane, perform temporal alignment and spatial registration, and obtain a time series dataset of each sampled sugarcane, wherein each sampled sugarcane is sampled from the target sugarcane planting area;

[0010] Based on the time series data set of each sampled sugarcane, and using artificial intelligence, the growth status of each sampled sugarcane is obtained;

[0011] According to the growth status of each sampled sugarcane and using artificial intelligence, the irrigation plan is determined to regulate the growth status of sugarcane in the target sugarcane planting area through the irrigation plan.

[0012] The beneficial effects of the intelligent monitoring and control method for sugarcane growth provided by the present invention are as follows:

[0013] Time series datasets can integrate monitoring information from different time periods and spatial locations, providing more comprehensive and continuous data on sugarcane growth dynamics (i.e., time series datasets). This helps to more accurately understand sugarcane growth conditions. Furthermore, AI technology enables rapid and efficient processing and analysis of large time series datasets, accurately identifying the growth status of each sampled sugarcane and promptly adjusting irrigation plans based on actual changes. This dynamic management approach can better adapt to various changes in the sugarcane growth process, ensuring that sugarcane receives appropriate water supply at different growth stages, thereby improving sugarcane yield and quality. Furthermore, target sugarcane planting areas are often large, making comprehensive monitoring of the growth status of every single cane unrealistic and costly. Selecting a representative sample of sugarcane for monitoring can significantly reduce the workload and the required manpower, material resources, and time.

[0014] Based on the above solution, the intelligent monitoring and control method for sugarcane growth of the present invention can be further improved as follows.

[0015] Furthermore, the implementation process of temporal alignment and spatial registration includes:

[0016] The timestamp alignment method is used to time align the data of multiple indicators associated with each sampled sugarcane, and the spatial coordinate registration method is used to spatially register the data of multiple indicators associated with each sampled sugarcane.

[0017] Furthermore, it also includes:

[0018] According to the growth status of each sampled sugarcane, the growth status of the sugarcane in the target sugarcane planting area is predicted to obtain the sugarcane growth status prediction result.

[0019] Furthermore, it also includes:

[0020] According to the growth status of each sampled sugarcane and using artificial intelligence, a fertilization plan is determined to regulate the growth status of sugarcane in the target sugarcane planting area through the fertilization plan.

[0021] Furthermore, the data of multiple indicators include: sugarcane stem diameter, sugarcane plant height, leaf area, sugar content, effective accumulated temperature, plant height increment, soil nitrogen content, transpiration rate, soil EC value, stem flow rate and soil water deficit.

[0022] 2) In a second aspect, the present invention further provides an intelligent monitoring and control system for sugarcane growth. The specific technical solution is as follows:

[0023] It includes data alignment module, sugarcane growth status acquisition module and solution determination module;

[0024] The data alignment and registration module is used to obtain data on multiple indicators associated with each sampled sugarcane, and perform time alignment and spatial registration to obtain a time series dataset for each sampled sugarcane, where each sampled sugarcane is sampled from the target sugarcane planting area;

[0025] The sugarcane growth status acquisition module is used to obtain the growth status of each sampled sugarcane based on the time series data set of each sampled sugarcane and using artificial intelligence;

[0026] The scheme determination module is used to determine the irrigation scheme based on the growth status of each sampled sugarcane and use artificial intelligence to regulate the growth status of sugarcane in the target sugarcane planting area through the irrigation scheme.

[0027] Based on the above solution, the intelligent monitoring and control system for sugarcane growth of the present invention can be further improved as follows.

[0028] Furthermore, the data alignment module is specifically used to:

[0029] The timestamp alignment method is used to time align the data of multiple indicators associated with each sampled sugarcane, and the spatial coordinate registration method is used to spatially register the data of multiple indicators associated with each sampled sugarcane.

[0030] Furthermore, a growth status prediction module is included, which is used to:

[0031] According to the growth status of each sampled sugarcane, the growth status of the sugarcane in the target sugarcane planting area is predicted to obtain the sugarcane growth status prediction result.

[0032] Furthermore, the plan determination module is also used to: determine the fertilization plan based on the growth status of each sampled sugarcane and use artificial intelligence to regulate the growth status of sugarcane in the target sugarcane planting area through the fertilization plan.

[0033] Furthermore, the data of multiple indicators include: sugarcane stem diameter, sugarcane plant height, leaf area, sugar content, effective accumulated temperature, plant height increment, soil nitrogen content, transpiration rate, soil EC value, stem flow rate and soil water deficit.

[0034] 3) In a third aspect, the present invention further provides an electronic device, comprising a processor coupled to a memory, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor to enable the electronic device to implement any of the aforementioned methods for intelligently monitoring and controlling sugarcane growth.

[0035] 4) In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned methods for intelligently monitoring and controlling the growth status of sugarcane.

[0036] It should be noted that the beneficial effects achieved by the technical solutions of the second to fourth aspects of the present invention and the corresponding possible implementation methods can be found in the above-mentioned technical effects of the first aspect and its corresponding possible implementation methods, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments of the present invention:

[0038] Figure 1 This is a flow chart of a method for intelligently monitoring and controlling the growth status of sugarcane according to an embodiment of the present invention;

[0039] Figure 2 This is a schematic structural diagram of an intelligent monitoring and control system for sugarcane growth conditions according to an embodiment of the present invention;

[0040] Figure 3 The figure is a schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The principles and features of the present invention are described below. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0042] The following describes in detail the technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems using specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The following embodiments of the present invention are described in conjunction with the accompanying drawings.

[0043] like Figure 1 As shown, an intelligent monitoring and control method for sugarcane growth conditions according to an embodiment of the present invention includes the following steps:

[0044] S1. Acquire data on multiple indicators associated with each sampled sugarcane, and perform temporal alignment and spatial registration to obtain a time series dataset for each sampled sugarcane, wherein each sampled sugarcane is sampled from a target sugarcane growing area;

[0045] The specific implementation process of determining the sampled sugarcane is as follows:

[0046] Using a multispectral camera mounted on an unmanned aerial vehicle (UAV), each sub-area of ​​the target sugarcane planting area is periodically scanned (the target sugarcane planting area is divided into multiple sub-areas in advance according to actual conditions), and the morphology of the initial sampled sugarcane in each sub-area (the initial sampled sugarcane in any sub-area can be any sugarcane in the sub-area) is extracted. The morphology of the sugarcane includes leaf area index, chlorophyll content and plant height.

[0047] LoRa sensors are deployed to monitor soil temperature, humidity, pH, nitrogen, phosphorus, and potassium content in each sub-area in real time, and mark abnormal areas, including drought areas and waterlogged areas.

[0048] The macro-environmental data such as temperature, humidity, wind speed, and light intensity of each sub-area are collected synchronously.

[0049] Federated learning is used to perform cross-modal alignment of images collected by multispectral cameras, data collected by LoRa sensors, and data collected by weather stations to generate a spatiotemporal feature matrix for each initial sample of sugarcane. The elements in the spatiotemporal feature matrix include the leaf area index, chlorophyll content, plant height, soil temperature and humidity, pH value, nitrogen, phosphorus, and potassium content, temperature, humidity, wind speed, and light intensity of the initial sampled sugarcane. The arrangement of the elements can be set according to actual conditions.

[0050] Cluster analysis is performed on all spatiotemporal feature matrices to obtain multiple groups. At least one initial sampling sugarcane is selected from each group as the sampling sugarcane, so that the determined sampling sugarcane is more representative and can more comprehensively cover the sugarcane growth conditions in the target sugarcane planting area.

[0051] Optionally, in the above technical solution, features are generated to characterize virtual disaster scenarios (such as persistent droughts and insect pest outbreaks), and the features and the target spatiotemporal feature matrix corresponding to any group are brought into the sugarcane survival probability prediction model to obtain the sugarcane survival probability of the group, until the sugarcane survival probability of each group is obtained. According to the sugarcane survival probability of each group, the number of sampled sugarcanes drawn from each group is determined. Generally speaking, the higher the sugarcane survival probability of any group, the fewer the number of sampled sugarcanes in the group, and the lower the sugarcane survival probability of any group, the more sampled sugarcanes in the group. In this way, more data on sampled sugarcanes that are easily affected by disasters can be obtained, so that more accurate irrigation and fertilization plans can be given.

[0052] Wherein, N = (1-P) × 100, where N is the number of sampled sugarcanes and P is the probability of sugarcane survival (the probability of sugarcane survival can be rounded to two digits). The functional relationship between the number of sampled sugarcanes and the probability of sugarcane survival can also be set according to actual conditions.

[0053] The target spatiotemporal feature matrix corresponding to any group is: the spatiotemporal feature matrix of any sugarcane in any group, or the spatiotemporal feature matrix obtained by averaging the spatiotemporal feature matrices of all sugarcanes in the group.

[0054] Characteristics that characterize persistent drought include meteorological data, soil moisture, and vegetation indices. Meteorological data such as precipitation, evaporation, temperature, and humidity are collected, and their long-term trends, seasonal variations, and extreme values ​​are calculated and represented in a matrix to obtain meteorological data characteristics. Soil moisture sensors monitor soil moisture changes at different depths, extracting characteristics such as the minimum, average, and rate of decline, and representing them in a matrix to obtain soil moisture characteristics. Vegetation index data, such as the Normalized Difference Vegetation Index (NDVI) and the Enhanced Vegetation Index (EVI), are obtained using satellite remote sensing. Characteristics such as the decline amplitude, rate of decline, and duration of the vegetation index are calculated to characterize the impact of drought on vegetation growth, and are represented in a matrix to obtain vegetation index characteristics.

[0055] Among them, characteristics characterizing insect pest outbreaks include pest monitoring data characteristics, vegetation damage characteristics, and meteorological-environmental factors. Through field surveys and trap monitoring, data on pest species, quantity, and distribution range are obtained. Characteristics such as the growth rate of pest population, distribution concentration, and frequency of occurrence are extracted and expressed in a matrix to obtain pest monitoring data characteristics. Satellite remote sensing or drone imagery is used to analyze the extent and scope of vegetation damage. Characteristics such as the growth rate of the damaged area and the severity of the damage are extracted and expressed in a matrix to obtain vegetation damage characteristics. The impact of meteorological factors such as temperature, humidity, and rainfall on the reproduction and spread of insect pests is considered. The changes in these meteorological factors before and after the insect pest outbreak are extracted and expressed in a matrix to obtain meteorological-environmental factor characteristics.

[0056] Multiple features used to characterize virtual disaster scenarios (such as persistent drought and insect pest outbreaks), historical target spatiotemporal feature matrices, and historical sugarcane survival probabilities are collected in advance, and a convolutional neural network is trained to obtain a sugarcane survival probability prediction model.

[0057] The implementation process of time alignment and spatial registration includes:

[0058] The timestamp alignment method is used to time align the data of multiple indicators associated with each sampled sugarcane, and the spatial coordinate registration method is used to spatially register the data of multiple indicators associated with each sampled sugarcane.

[0059] Among them, the data of multiple indicators include: sugarcane stem diameter, sugarcane plant height, leaf area, sugar content, effective accumulated temperature, plant height increment, soil nitrogen content, transpiration rate, soil EC value (soil electrical conductivity value), stem flow rate and soil water deficit. The soil water deficit can be measured by weighing and drying method, or by using a soil moisture rapid tester.

[0060] S2. Based on the time series data set of each sampled sugarcane, and using artificial intelligence, the growth status of each sampled sugarcane is obtained. Specifically:

[0061] A sliding time window method is used to segment each time series data set to obtain multidimensional sub-data within each time window; a principal component analysis method is used to reduce the dimensionality of the multidimensional sub-data within each time window, and multiple indicators as principal components are determined to obtain multiple dimensionality-reduced data, which include data of each principal component; sugarcane growth characteristics are extracted from each dimensionality-reduced data corresponding to any sampled sugarcane, and the sugarcane growth characteristics include multiple features; the weight of each feature of the sugarcane growth characteristics of the sampled sugarcane is obtained until the weight of each feature in the sugarcane growth characteristics of each sampled sugarcane is obtained; based on each sugarcane growth feature and the weight of each feature in each sugarcane growth feature, and using a trained sugarcane growth status recognition model, the sugarcane growth status of each sampled sugarcane is obtained, wherein the trained sugarcane growth status recognition model is obtained by training a convolutional neural network.

[0062] After the weight of each feature of any sugarcane growth feature is calculated, the weight of each feature of other sugarcane growth features is set to be the same, and repeated calculation is not required.

[0063] Among them, the sugarcane growth characteristics are extracted from each dimension-reduced data corresponding to any sampled sugarcane. The specific implementation process is as follows:

[0064] When the principal component analysis method is used to reduce the dimensionality of the multidimensional sub-data in each time window, a load matrix will be generated. The load matrix represents the linear relationship between the indicators that are not used as principal components and the indicators that are used as principal components. Through the load matrix, any reduced dimensionality data corresponding to any sampled sugarcane is reversely mapped to obtain the absolute value of the load corresponding to any data value in the reduced dimensionality data. The data value with an absolute value of the load greater than the preset absolute value threshold is selected, and the selected multiple data values ​​are processed to obtain the sugarcane growth characteristics. The sugarcane growth characteristics can be specifically: a combination of multiple characteristics, specifically stem thickness index, canopy compactness, sugar accumulation rate, nitrogen A combination of light utilization efficiency, stem flow rate and water stress response coefficient, among which stem diameter index = stem diameter / plant height × 100, stem diameter index can reflect lodging resistance, and a high value indicates a strong stem, canopy compactness = the ratio of leaf area index to the square of plant height, canopy compactness can measure light energy utilization efficiency, sugar accumulation rate = sugar content change / effective accumulated temperature, sugar accumulation rate can indicate photosynthetic product conversion efficiency, nitrogen utilization efficiency = plant height increase / soil nitrogen content, nitrogen utilization efficiency can evaluate nutrient absorption capacity, water stress response coefficient = transpiration rate decrease rate / soil water deficit, water stress response coefficient can quantify drought resistance.

[0065] The beneficial effect of this sugarcane growth feature extraction process is that data values ​​with large absolute load values ​​have a greater impact on sugarcane growth and better represent the key characteristics of sugarcane growth. By screening these data values, key sugarcane growth characteristics, such as those related to drought, are highlighted, increasing the model's focus on these characteristics and thus more accurately reflecting sugarcane growth conditions.

[0066] The weight of the sugarcane growth characteristics of the sampled sugarcane is obtained, and the specific implementation process is as follows:

[0067] Gaussian fuzzy is used to quantify the membership of each feature in the sugarcane growth characteristics in each comment level in the comment set:

[0068]

[0069] Among them, f i,S represents the calculated membership, f i Indicates: the value of the i-th feature in the sugarcane growth characteristics, c i,j Indicates that the jth comment in the comment set corresponds to f i Typicality, for example, if the stem thickness index is "excellent", the corresponding stem thickness index typicality is 18. The typical value can be set according to the actual situation, σ i,j Means: f iThe standard deviation corresponding to the jth comment in the comment set is used for the fuzzy interval width. The comment set V = {v1, v2, v3, v4}, v1 is "excellent", v2 is "good", v3 is "medium", and v1 is "poor".

[0070] After obtaining the degree of membership of each feature to each evaluation level, several sugarcane experts were invited to conduct pairwise comparisons of the membership of each sugarcane growth feature. Based on their experience and expertise, the experts judged the relative importance of one feature relative to another at a given evaluation level and assigned a corresponding score. Scoring is typically performed on a 1-9 scale, where 1 indicates that both features are equally important, 3 indicates that one feature is slightly more important than the other, 5 indicates significantly more important, 7 indicates strongly important, and 9 indicates extremely important. The expert scores are aggregated to construct a judgment matrix. The elements in the mth row and nth column of the judgment matrix represent the relative importance of the mth feature relative to the nth feature at a given evaluation level. Each column of the judgment matrix is ​​normalized, and the normalized judgment matrices are then summed row-wise. Finally, the resulting vector is normalized to produce a weight vector, which includes the subjective weight of each feature.

[0071] The entropy weight method is used to calculate the objective weights of the subjective weights of sugarcane growth characteristics. Different weights are then assigned to the subjective and objective weights to obtain the weights of the sugarcane growth characteristics of the sampled sugarcane. The weights of the sugarcane growth characteristics of the sampled sugarcane are the sum of the product of the subjective weight and the corresponding weight, and the product of the objective weight and the corresponding weight. By obtaining the weights of sugarcane growth characteristics, key characteristics that have a significant impact on sugarcane growth status, such as those related to drought, insect pests, and nutrient deficiencies, can be accurately identified. This helps to more accurately judge the growth status of sugarcane and provides a scientific basis for timely implementation of appropriate management measures.

[0072] Among them, according to each sugarcane growth feature and the weight of each feature in each sugarcane growth feature, and using the sugarcane growth status recognition model, the sugarcane growth status of each sampled sugarcane is obtained. The specific implementation process is as follows:

[0073] Each feature in each sugarcane growth feature is quantile normalized to eliminate dimensional differences, and the feature normalization value and corresponding weight of each sugarcane growth feature are fused (which can be arranged in a preset order) to obtain a weighted feature.

[0074] Construct a deep learning model, which includes an input layer, a weight gating module, a feature interaction layer, and a multi-task output head. The input layer is used to receive weighted features. A weight gating module is established based on a dual-channel attention mechanism. The weight gating module includes a static weight channel, a dynamic weight channel, and a fusion gating signal acquisition unit. The static weight channel is used to directly receive the weight W in the weighted feature. The dynamic weight channel learns the adjustment factor ΔW of the weight received by the static weight channel through the fully connected layer. ΔW = MLP (F), where MLP (F) indicates that the fully connected layer learns W. The fusion gating signal acquisition unit obtains F through the following formula gated :

[0075] F gated =F·W final

[0076] Among them, W final =W gate W+(1-W gate )·ΔW,W gate =σ(MLP([W||ΔW])), where W||ΔW represents the concatenation of W and ΔW, MLP([W||ΔW]) represents the learning of [W||ΔW] through a fully connected layer, and σ represents the activation function used to compress MLP([W||ΔW]) to the interval [0,1] to generate the gating weight W gate , F gated represents: gated weighted feature vector, F represents: sugarcane growth characteristics, W final Represents an intermediate variable.

[0077] Among them, the feature interaction layer uses the deep cross network (DCN) to capture high-order interaction features. Specifically, F gated Enter the Deep Cross Network (DCN) to capture high-order interaction features.

[0078] The multi-task output head consists of a main task processing unit and an auxiliary task processing unit. The main task processing unit processes high-order interactive features through a regression layer to obtain a value representing the sugarcane growth condition. This value ranges from [0, 1], where 1 represents optimal growth and 0 represents the worst. The auxiliary task processing unit performs anomaly detection through a binary classification layer.

[0079] During the training process, the loss function corresponding to the main task processing unit and the loss function corresponding to the auxiliary task processing unit are different. For example, the loss function corresponding to the main task processing unit is Huber Loss, and the loss function corresponding to the auxiliary task processing unit is Focal Loss. This can not only ensure robustness, but also solve the problem of poor training effect caused by category imbalance of training samples.

[0080] By training the deep learning model, a trained deep learning model is obtained. The trained deep learning model is the sugarcane growth condition recognition model. The sugarcane growth condition recognition model is used to obtain the sugarcane growth condition of each sampled sugarcane.

[0081] S3. Determine an irrigation plan based on the growth status of each sampled sugarcane and by using artificial intelligence to regulate the growth status of sugarcane in the target sugarcane planting area through the irrigation plan.

[0082] Based on the growth status of each sampled sugarcane, and using artificial intelligence, the irrigation plan is determined. The specific implementation process is as follows:

[0083] Get the water stress response coefficient CWSI, Among them, CTD represents the difference between the mean canopy temperature of all sampled sugarcanes and the air temperature, CTD1 represents the baseline value of the fully irrigated area, and CTD2 represents the value of the drought stress area.

[0084] Establish a root water absorption capacity model, specifically:

[0085] Q=α·RTD β ·RHZR γ

[0086] Wherein, α, β, and γ are coefficients. In one embodiment, α=1, β=0.7, and γ=0.2. RTD represents the mean of the new root tip density of all sampled sugarcanes. RHZR represents the mean of the length ratio of the root hair zone of all sampled sugarcanes. Q represents the value used to characterize the water absorption capacity of the root system. A larger Q indicates a stronger water absorption capacity, and a smaller Q indicates a weaker water absorption capacity.

[0087] Calculate the total transpiration water consumption ET, Where T represents the total time in hours, and the value range of t is [1, T]. t represents the mean stem flow rate of all sampled sugarcanes at the tth hour, and A represents the mean duct cross-sectional area of ​​all sampled sugarcanes.

[0088] A convolutional water prediction network is constructed, specifically a deep convolutional neural network (DCNN). The input of the deep convolutional neural network (DCNN) is: a water stress response coefficient, a value used to characterize the water absorption capacity of the root system, total transpiration water consumption, soil moisture profile data, and evaporation per unit area (calculated using the Penman-Monteith formula). The output is: the water requirement of a single sugarcane within a preset time period in the future (such as 6 hours, 12 hours, or 24 hours). The deep convolutional neural network (DCNN) is trained using historical water stress response coefficients, historical values ​​used to characterize the water absorption capacity of the root system, historical total transpiration water consumption, historical soil moisture profile data, historical evaporation, and historical water demand to obtain a trained deep convolutional neural network (DCNN). The trained deep convolutional neural network (DCNN) is used to determine an initial irrigation plan. The initial irrigation plan includes: the initial irrigation plan includes the total water requirement within the preset time period in the future. After the water requirement of a single sugarcane is calculated, the total water requirement within the preset time period in the future can be calculated based on the sugarcane planting density and the area of ​​the target sugarcane planting area.

[0089] Calculate the mean value corresponding to the growth status of all sampled sugarcanes (the value that represents the good or bad growth status), recorded as ε, using the formula: B ′ =(1-ε)·B, correct the total water demand B within the future preset time period to obtain the corrected total water demand B within the future preset time period ′ , and obtain the final irrigation plan. By appropriately reducing the amount of irrigation, the soil saturation can be reduced, the soil loss and erosion caused by excessive irrigation can be reduced, and the soil fertility can be protected. Moreover, the energy consumption and equipment operating costs required for irrigation are reduced, thereby reducing the production cost of sugarcane planting.

[0090] Optionally, the method further includes: obtaining the mean value of the stem flow rate of each sampled sugarcane per hour in a day, obtaining time series data on the stem flow rate, performing data fitting on the time series data, obtaining a curve showing the change of the mean value of the stem flow rate over time in a day, and converting the total water demand B after correction within a preset time period into the total water demand B. ′ Allocation is performed according to this curve, resulting in a water demand curve that aligns with the mean stem flow rate curve. Irrigation is then performed based on this water demand curve. The final irrigation plan also includes the water demand curve. By monitoring changes in stem flow rate, we can more accurately understand water needs, allowing us to allocate irrigation water based on actual needs, meet sugarcane growth requirements, and improve irrigation precision.

[0091] In the present invention, the time series dataset can integrate monitoring information from different times and spatial locations, providing more comprehensive and continuous sugarcane growth dynamics data (i.e., time series datasets). This helps to more accurately understand the growth status of sugarcane. Moreover, through AI intelligent technology, large time series datasets can be quickly and efficiently processed and analyzed, accurately identifying the growth status of each sampled sugarcane and timely adjusting irrigation and fertilization plans based on actual changes. This dynamic management method can better adapt to various changes in the sugarcane growth process, ensuring that sugarcane receives appropriate water and nutrient supply at different growth stages, thereby improving sugarcane yield and quality. Moreover, the area of ​​the target sugarcane planting area is often large, making comprehensive monitoring of the growth status of each sugarcane unrealistic and costly. A representative sample of sugarcane can be selected for monitoring, greatly reducing the workload and the required manpower, material resources, and time.

[0092] Optionally, in the above technical solution, the following is further included:

[0093] According to the growth status of each sampled sugarcane, the growth status of the sugarcane in the target sugarcane planting area is predicted to obtain the sugarcane growth status prediction result.

[0094] The historical values ​​of each growth characteristic of sugarcane and the growth status of sugarcane, as well as the actual growth status in the corresponding future period are collected in advance, a sample set is constructed, and a preset deep learning model is trained to obtain a trained preset deep learning model. The trained preset deep learning model is used to predict the growth status of sugarcane in the target sugarcane planting area.

[0095] Among them, the preset deep learning model includes an input coding layer, a learnable sparse mask generator, a multi-core attention fusion layer, an aggregation layer and an output layer. The input coding layer is used to receive the historical value of each feature of each growth feature of sugarcane and the growth status of sugarcane. The learnable sparse mask generator can adaptively change the sparse attention according to the input data of the input coding layer, which can effectively reduce the amount of calculation while retaining key context associations. The aggregation layer is used to: generate low-dimensional features according to the output of the learnable sparse mask generator, and iterate the low-dimensional features according to the dynamic routing protocol to obtain high-semantic features for characterizing the sugarcane growth status prediction results. The aggregation layer can dynamically aggregate cross-layer features to enhance interpretability, and input the high-semantic features into the output layer to obtain the sugarcane growth status prediction results.

[0096] During the training of the preset deep learning model, the parameters in the training process can be passed into the quantum parameter optimizer, and the parameter update direction can be obtained through quantum simulation to avoid the situation of out-of-calibration local minima.

[0097] Another possible implementation involves segmented training of a pre-set deep learning model. In the first training phase, the parameters from the training process are passed to a quantum parameter optimizer, and the parameter update direction is obtained through quantum simulation. After a preset number of iterations (100 or 200, which can be set based on actual conditions), the second training phase is executed. In this second training phase, the parameters of the pre-set deep learning model are adjusted using the Adam optimizer until a trained pre-set deep learning model is obtained. The first training phase can quickly complete a wide-area search, preventing gradient descent from falling into local minima. The second training phase is highly adaptable to random noise and sparse gradients in the data, ensuring stability during the fine-tuning phase and effectively preventing overfitting.

[0098] The sugarcane growth status prediction result is represented by a value in the range of [0,1]. 1 indicates that the sugarcane growth status in the sugarcane growth status prediction result is the best, and 0 indicates that the sugarcane growth status in the sugarcane growth status prediction result is the worst. Intervention is carried out in the target sugarcane planting area based on the sugarcane growth status prediction result to prevent serious yield reduction.

[0099] Optionally, in the above technical solution, the following is further included:

[0100] According to the growth status of each sampled sugarcane and using artificial intelligence, a fertilization plan is determined to regulate the growth status of sugarcane in the target sugarcane planting area through the fertilization plan.

[0101] The new root tip density, root hair zone expansion rate, rhizosphere pH, O2 concentration, organic acid secretion, leaf nitrogen content (NDRE index), chlorophyll fluorescence parameters and sucrose transport rate (obtained by heat pulse stem flow meter) of sugarcane were obtained, and NH4 in the soil was obtained. + 、NO3 - and K + Plasma concentration is calculated, and a sample set is constructed in combination with the growth status of each sugarcane and the corresponding fertilization plan. After the spatiotemporal convolutional LSTM model is constructed, the spatiotemporal convolutional LSTM model is trained based on the sample set to obtain a trained spatiotemporal convolutional LSTM model.

[0102] According to the growth status of each sampled sugarcane, the density of new root tips, the expansion rate of root hair zone, rhizosphere pH, O2 concentration, organic acid secretion, leaf nitrogen content (NDRE index), chlorophyll fluorescence parameters and sucrose transport rate (obtained by heat pulse stem flow meter), and soil NH4 + 、NO3 - and K +The plasma concentration is input into the trained spatiotemporal convolutional LSTM model to obtain the initial fertilization plan, which includes the ratio of urea, superphosphate and potassium sulfate. The NH4 + 、NO3 - and K + The amount of urea, superphosphate and potassium sulfate can be deduced from the ratio, which can meet the requirements of NH4 + 、NO3 - and K + The amount is enough.

[0103] Optionally, data visualization technology is used to graphically display information such as time series data sets, growth status, and growth status prediction results, and a multi-level visualization method is used to achieve data drilling from macro to micro, resulting in an intuitive monitoring and analysis interface. Specifically, the photosynthetic rate data and light time distribution data of the sampled sugarcane are obtained; based on the photosynthetic rate data and light time distribution data, a line graph is used to display the trend of photosynthetic rate changes with light time; based on the trend of photosynthetic rate changes with light time, a visualization curve of the light compensation strategy is generated; soil moisture data and nutrient content data are obtained, and the results of the light compensation strategy are integrated with the soil moisture data and nutrient content data; for the integrated data, a bar graph and a line graph are used to display the dynamic adjustment process of irrigation amount and fertilizer allocation; leaf temperature data and transpiration rate data are obtained , combined with leaf temperature data and transpiration rate data, use heat maps to show leaf temperature changes in different time periods, and generate optimization trend charts for sprinkler frequency and sprinkler duration; obtain historical data and real-time monitoring information, and use ARIMA models to predict the frequency of pests and diseases based on historical data and real-time monitoring information, and use geographic information system tools to generate distribution maps of pest and disease prevention and control measures; use Tableau tools to achieve multi-level visualization, gradually drilling from the macro-assessment results of sugarcane growth conditions to the micro-optimization of sprinkler system parameters, forming a complete monitoring and analysis interface.

[0104] In the above embodiments, although the steps are numbered S1, S2, etc., these are only specific embodiments given by the present invention. Those skilled in the art may adjust the execution order of S1, S2, etc. according to actual conditions, which is also within the scope of protection of the present invention. It can be understood that in some embodiments, some or all of the above embodiments may be included.

[0105] like Figure 2 As shown, an intelligent monitoring and control system 200 for sugarcane growth conditions according to an embodiment of the present invention includes a data alignment module 201, a sugarcane growth condition acquisition module 202, and a solution determination module 203;

[0106] The data alignment and registration module 201 is used to obtain data of multiple indicators associated with each sampled sugarcane, and perform time alignment and spatial registration to obtain a time series dataset of each sampled sugarcane, wherein each sampled sugarcane is sampled from the target sugarcane planting area;

[0107] The sugarcane growth status acquisition module 202 is used to obtain the growth status of each sampled sugarcane based on the time series data set of each sampled sugarcane and using artificial intelligence;

[0108] The scheme determination module 203 is used to determine an irrigation scheme based on the growth status of each sampled sugarcane and by using artificial intelligence, so as to regulate the growth status of the sugarcane in the target sugarcane planting area through the irrigation scheme.

[0109] Optionally, in the above technical solution, the data alignment and registration module 201 is specifically used to:

[0110] The timestamp alignment method is used to time align the data of multiple indicators associated with each sampled sugarcane, and the spatial coordinate registration method is used to spatially register the data of multiple indicators associated with each sampled sugarcane.

[0111] Optionally, the above technical solution further includes a growth status prediction module, which is used to:

[0112] According to the growth status of each sampled sugarcane, the growth status of the sugarcane in the target sugarcane planting area is predicted to obtain the sugarcane growth status prediction result.

[0113] Optionally, in the above technical solution, the solution determination model is also used to: determine the fertilization solution based on the growth status of each sampled sugarcane and using artificial intelligence to regulate the growth status of sugarcane in the target sugarcane planting area through the irrigation solution.

[0114] Optionally, in the above technical solution, the data of multiple indicators include: sugarcane stem diameter, sugarcane plant height, leaf area, sugar content, effective accumulated temperature, plant height increment, soil nitrogen content, transpiration rate, soil EC value, stem flow rate and soil water deficit.

[0115] It should be noted that the beneficial effects of the intelligent sugarcane growth monitoring and control system 200 provided in the above-mentioned embodiment are the same as those of the intelligent sugarcane growth monitoring and control method described above, and will not be further elaborated here. Furthermore, the above-mentioned embodiment only illustrates the functional implementation of the system by dividing the functional modules described above. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to actual circumstances to perform all or part of the functions described above. Furthermore, the system and method embodiments provided in the above-mentioned embodiment are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be further elaborated here.

[0116] The intelligent monitoring and control system for sugarcane growth conditions of the present invention may be a computer program (including program code) running on a computer device. For example, the intelligent monitoring and control system for sugarcane growth conditions of the present invention is an application software that can be used to execute the corresponding steps of the intelligent monitoring and control method for sugarcane growth conditions of the present invention.

[0117] In some embodiments, the intelligent monitoring and control system for sugarcane growth of the present invention may be implemented using a combination of hardware and software. For example, the intelligent monitoring and control system for sugarcane growth of the present invention may be implemented using a hardware decoding processor programmed to execute the intelligent monitoring and control method for sugarcane growth of the present invention. For example, the hardware decoding processor may be implemented using one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0118] The modules described in the embodiments of the present invention may be implemented in software or hardware, and the name of a module does not necessarily limit the module itself.

[0119] An electronic device according to an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, any of the aforementioned methods for intelligently monitoring and controlling the growth of sugarcane is implemented. In other words, an electronic device according to an embodiment of the present invention may include, but is not limited to, a processor and a memory; the memory is configured to store the computer program; and the processor is configured to execute the method for intelligently monitoring and controlling the growth of sugarcane according to any of the embodiments of the present invention by invoking the computer program.

[0120] In an alternative embodiment, an electronic device is provided, such as Figure 3 As shown, Figure 3 The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data exchange between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the number of transceivers 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0121] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the present disclosure. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0122] Bus 4002 may include a path for transmitting information between the above components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. Bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3In the figure, only one thick line is used to represent the bus 4002, but this does not mean that there is only one bus or one type of bus.

[0123] The memory 4003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0124] The memory 4003 is used to store application code (computer program) for executing the solution of the present invention, and is controlled by the processor 4001. The processor 4001 is used to execute the application code stored in the memory 4003 to implement the content shown in the above method embodiment.

[0125] Among them, the electronic device can also be a terminal device, and the terminal device can be any device that can install applications, including at least one of a smartphone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a smart TV, and a smart car device.

[0126] It should be noted that Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0127] A computer-readable storage medium according to an embodiment of the present invention stores a computer program, which, when executed by a processor, implements any of the above-mentioned methods for intelligently monitoring and controlling the growth condition of sugarcane.

[0128] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, or the like.

[0129] In an exemplary embodiment, a computer program product or computer program is also provided. The computer program product or computer program includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to implement any of the aforementioned methods for intelligently monitoring and controlling sugarcane growth.

[0130] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0131] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0132] The computer-readable storage medium provided in the embodiment of the present invention may be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EEPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or component.

[0133] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0134] The above description is merely a preferred embodiment of the present invention and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present invention is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in the present invention.

[0135] It should be noted that the terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects and to define a specific order or precedence. Where appropriate, the order used for similar objects may be interchanged, such that the embodiments of the present application described herein can be implemented in an order other than the order shown or described.

[0136] Those skilled in the art will appreciate that the present invention may be implemented as a system, method, or computer program product. Therefore, the present invention may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, the present invention may be implemented in the form of a computer program product embodied in one or more computer-readable media containing computer-readable program code.

[0137] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A method for intelligent monitoring and control of sugarcane growth, characterized in that: include: Acquire data of multiple indicators associated with each sampled sugarcane, perform temporal alignment and spatial registration, and obtain a time series dataset of each sampled sugarcane, wherein each sampled sugarcane is sampled from the target sugarcane planting area; Based on the time series data set of each sampled sugarcane, and using artificial intelligence, the growth status of each sampled sugarcane is obtained; According to the growth status of each sampled sugarcane, and by using artificial intelligence, an irrigation plan is determined to regulate the growth status of the sugarcane in the target sugarcane planting area through the irrigation plan.

2. The method for intelligent monitoring and control of sugarcane growth according to claim 1, characterized in that: The implementation process of temporal alignment and spatial registration includes: The timestamp alignment method is used to time align the data of multiple indicators associated with each sampled sugarcane, and the spatial coordinate registration method is used to spatially register the data of multiple indicators associated with each sampled sugarcane.

3. The method for intelligent monitoring and control of sugarcane growth according to claim 1, characterized in that: Also includes: According to the growth status of each sampled sugarcane, the growth status of the sugarcane in the target sugarcane planting area is predicted to obtain the sugarcane growth status prediction result.

4. The method for intelligently monitoring and controlling the growth of sugarcane according to any one of claims 1 to 3, characterized in that: Also includes: According to the growth status of each sampled sugarcane, and by using artificial intelligence, a fertilization plan is determined to regulate the growth status of the sugarcane in the target sugarcane planting area through the fertilization plan.

5. The method for intelligently monitoring and controlling the growth of sugarcane according to any one of claims 1 to 3, characterized in that: The data of multiple indicators include: sugarcane stem diameter, sugarcane plant height, leaf area, sugar content, effective accumulated temperature, plant height increment, soil nitrogen content, transpiration rate, soil EC value, stem flow rate and soil water deficit.

6. An intelligent monitoring and control system for sugarcane growth, characterized in that: It includes data alignment module, sugarcane growth status acquisition module and solution determination module; The data alignment and registration module is used to: obtain data of multiple indicators associated with each sampled sugarcane, and perform time alignment and spatial registration to obtain a time series data set of each sampled sugarcane, wherein each sampled sugarcane is sampled and determined from a target sugarcane planting area; The sugarcane growth status acquisition module is used to obtain the growth status of each sampled sugarcane based on the time series data set of each sampled sugarcane and using artificial intelligence; The scheme determination module is used to determine an irrigation scheme based on the growth status of each sampled sugarcane and using artificial intelligence to regulate the growth status of the sugarcane in the target sugarcane planting area through the irrigation scheme.

7. The intelligent monitoring and control system for sugarcane growth according to claim 6, characterized in that: The data alignment module is specifically used for: The timestamp alignment method is used to time align the data of multiple indicators associated with each sampled sugarcane, and the spatial coordinate registration method is used to spatially register the data of multiple indicators associated with each sampled sugarcane.

8. The intelligent monitoring and control system for sugarcane growth according to claim 6, characterized in that: The invention also includes a growth status prediction module, wherein the growth status prediction module is used to: According to the growth status of each sampled sugarcane, the growth status of the sugarcane in the target sugarcane planting area is predicted to obtain the sugarcane growth status prediction result.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for intelligently monitoring and controlling the growth condition of sugarcane according to any one of claims 1 to 5 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for intelligently monitoring and controlling the growth condition of sugarcane according to any one of claims 1 to 5 is implemented.

Images