A precision irrigation and fertilization system based on crop accumulated temperature

Abstract

This invention discloses a precision irrigation and fertilization system based on crop accumulated temperature, belonging to the field of intelligent agricultural planting technology. The system includes an accumulated temperature acquisition module, an environmental sensing module, a crop growth status monitoring module, a data processing module, an intelligent decision-making module, an irrigation and fertilization execution module, and a remote monitoring module. Driven by accumulated temperature, this invention collects temperature, environmental, and crop growth data collaboratively through multiple modules. After data processing and intelligent decision-making, it generates a precision irrigation and fertilization plan matched to the crop's growth stage. Simultaneously, closed-loop control and remote monitoring ensure the accurate execution of the plan, solving the problems of traditional irrigation and fertilization relying on experience, resource waste, and insufficient targeting of existing systems, thereby improving water and fertilizer utilization and crop yield and quality.

Description

Technical Field

[0001] This invention relates to the field of intelligent agricultural planting technology, specifically to a precision irrigation and fertilization system based on crop accumulated temperature. Background Technology

[0002] Irrigation and fertilization are core aspects of agricultural planting that affect crop growth and yield. Traditional methods rely on growers' experience, which leads to problems such as inaccurate irrigation and fertilization amounts and improper timing. This not only wastes water and fertilizer resources but also easily causes soil compaction and water pollution. Furthermore, it cannot meet the precise needs of crops at different growth stages, affecting quality and yield.

[0003] Accumulated temperature directly determines the growth stage and speed of crops, and the water and fertilizer requirements of different crops at each growth stage are closely related to accumulated temperature. Although existing precision irrigation and fertilization systems incorporate some environmental parameter monitoring, most do not use accumulated temperature as the core driving factor, failing to accurately match the correspondence between crop growth stages and water and fertilizer requirements, resulting in insufficient targeting and accuracy of decision-making solutions. Therefore, there is an urgent need for a precision irrigation and fertilization system that uses accumulated temperature as the core and combines multi-dimensional data to improve the level of agricultural intelligence, save resources, and increase crop yield and quality. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a precision irrigation and fertilization system based on crop accumulated temperature to solve the problems mentioned in the background section.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] In a first aspect, the present invention provides a precision irrigation and fertilization system based on crop accumulated temperature, comprising the following functional modules:

[0007] The system includes a temperature accumulation acquisition module, an environmental sensing module, a crop growth status monitoring module, a data processing module, an intelligent decision-making module, an irrigation and fertilization execution module, and a remote monitoring module.

[0008] in,

[0009] The accumulated temperature acquisition module is used to collect temperature data of the crop growing area and calculate the cumulative accumulated temperature according to the active accumulated temperature method, covering the entire crop growing area and ensuring the uniformity and accuracy of temperature data acquisition.

[0010] The environmental sensing module is used to collect environmental data, including soil moisture content, soil nitrogen, phosphorus and potassium content, air temperature and humidity, and light intensity.

[0011] The crop growth status monitoring module monitors the crop status through a high-definition camera (installed above the crop growth area to take growth images at regular intervals) and physiological sensors.

[0012] The data processing module is used to receive and process data from the accumulated temperature acquisition module, the environmental sensing module, and the crop growth status monitoring module.

[0013] The intelligent decision-making module uses built-in fertilization models for different crops to match the crop growth stage and optimize irrigation and fertilization plans by combining environmental and crop growth data.

[0014] The irrigation and fertilization execution module is used to adjust the on / off status and power of the irrigation valve and fertilizer pump according to the irrigation and fertilization plan, and to provide feedback on the operating data during execution.

[0015] The remote monitoring module allows users to view real-time data (accumulated temperature, soil moisture, crop height, etc.), system operating status (whether each module is online), and irrigation and fertilization plans via computer or mobile terminal.

[0016] To further optimize this technical solution, the accumulated temperature acquisition module is equipped with multiple distributed temperature sensors to collect temperature data of the crop growth area at least once per hour. The accumulated temperature is calculated using the active accumulated temperature method (accumulating the daily average temperature above the biological lower limit temperature of the crop). The biological lower limit temperature of different crops can be set in advance (e.g., 3℃ for wheat, 10℃ for corn), and the accumulated temperature data is transmitted to the data processing module.

[0017] To further optimize this technical solution, the environmental sensing module includes a soil parameter monitoring submodule and an air and light monitoring submodule;

[0018] in,

[0019] The soil parameter monitoring submodule includes soil moisture sensors and soil nitrogen, phosphorus, and potassium sensors;

[0020] The air and light monitoring submodule includes an air temperature and humidity sensor and a light sensor;

[0021] Data on soil moisture content, soil nitrogen, phosphorus and potassium content, air temperature and humidity, and light intensity are collected and transmitted to the data processing module in real time.

[0022] To further optimize this technical solution, the crop growth status monitoring module includes physiological sensors such as chlorophyll sensors and leaf water content sensors. The physiological sensors employ a combination of fixed-point and mobile monitoring, performing both fixed monitoring and random sampling. Morphological parameters such as plant height and leaf area index are extracted using machine vision algorithms, and combined with the chlorophyll content and leaf water content data collected by the physiological sensors, the data is transmitted to the data processing module.

[0023] To further optimize this technical solution, the data processing module uses the 3σ criterion to remove outliers and linear interpolation to fill in missing values. It establishes a multi-dimensional data association model through a data fusion algorithm, extracts data on water and fertilizer requirements, including accumulated temperature, soil moisture content, and chlorophyll content, and generates a standardized data matrix.

[0024] To further optimize this technical solution, the intelligent decision-making module includes different crop fertilization models, such as the accumulated temperature-growth stage correspondence model and the water and fertilizer requirement model for each growth stage.

[0025] The model of the relationship between accumulated temperature and growth stage for different crops, such as wheat: 120-150℃·d is required from sowing to germination, and 250-300℃·d is required from germination to tillering; corn: 200-550℃·d is required from emergence to jointing, and 550-750℃·d is required from jointing to large trumpet stage.

[0026] Water and fertilizer requirement models clearly define the suitable soil moisture content range, nutrient supply level, and corresponding irrigation and fertilization amounts for different crops at each growth stage. For example, the suitable soil moisture content for wheat at the jointing stage is 70%-80% of field capacity, and the nitrogen requirement is 15-20 kg / mu. The suitable soil moisture content for corn at the jointing stage is 65%-75% of field capacity.

[0027] The intelligent decision-making module iteratively optimizes the model each quarter based on historical irrigation and fertilization data, crop growth data, and yield data using a random forest algorithm.

[0028] To further optimize this technical solution, the model for the correspondence between accumulated temperature and growth stages of different crops is constructed by including:

[0029] Feature selection: Accumulated temperature is the core feature, supplemented by crop morphological parameters as auxiliary features;

[0030] Model selection: The K-means clustering algorithm is used to divide the crop growth process into stages based on the accumulated temperature and morphological parameter data in the training set;

[0031] Model optimization: Validate the model using test set data and calculate the stage split accuracy; if the accuracy is not up to standard, adjust the K value or supplement feature parameters and retrain the model.

[0032] To further optimize this technical solution, the water and fertilizer requirement models for each growth stage are constructed by including:

[0033] Feature selection: growth stage, soil moisture, soil nutrients, crop physiological indicators, and light intensity are used as input features; irrigation amount, fertilizer type, and fertilizer amount are used as output targets.

[0034] Model selection: The random forest regression algorithm is adopted to build a model based on the training set data. The hyperparameters of the model are optimized by grid search method. The goal is to minimize the mean square error between the model prediction and the actual irrigation and fertilization amount.

[0035] Model validation: Evaluate model performance using test set data, requiring irrigation prediction error ≤8% and fertilizer prediction error ≤10%; if the target is not met, supplement with more training data under different soil types and climatic conditions, and retrain the model.

[0036] To further optimize this technical solution, the irrigation and fertilization execution module includes an intelligent irrigation valve, an intelligent fertilization pump, a flow sensor, and a pressure sensor;

[0037] After receiving the irrigation and fertilization plan from the intelligent decision-making module, the intelligent irrigation valve and intelligent fertilization pump start according to the preset time, opening degree / flow rate. The flow sensor and pressure sensor monitor the operating data in real time. If the actual flow rate is found to be 10% lower than the preset value or the pressure is 20% higher than the preset value, the data is immediately fed back to the intelligent decision-making module, which adjusts the opening degree of the intelligent irrigation valve or the power of the intelligent fertilization pump in real time.

[0038] To further optimize this technical solution, the remote monitoring module is built on a B / S architecture and has a built-in manual intervention function. When encountering extreme weather, the user can manually adjust the irrigation amount within ±20% and the fertilizer amount within ±15%. The adjustment command is directly transmitted to the intelligent decision-making module and executed first.

[0039] In a second aspect, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, they implement the steps of a precision irrigation and fertilization system based on crop accumulated temperature as described in the first aspect of the present invention.

[0040] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, they implement the steps of a precision irrigation and fertilization system based on crop accumulated temperature as described in the first aspect of the present invention.

[0041] The steps of this precision irrigation and fertilization system based on crop accumulated temperature are as follows:

[0042] System initialization: Based on the type of crop being planted, set the biological lower limit temperature (e.g., 3℃ for wheat, 10℃ for corn) in the intelligent decision-making module, and import the corresponding accumulated temperature-growth stage correspondence model and water and fertilizer requirement model parameters.

[0043] Data acquisition: The accumulated temperature acquisition module collects temperature every hour and calculates the accumulated temperature; the environmental sensing module collects soil moisture, nutrients, air temperature and humidity and light data in real time; the crop growth status monitoring module collects crop growth data on a regular basis (images every 24 hours, physiological indicators every 3 days), and all data are transmitted to the data processing module in real time.

[0044] Data processing: The data processing module removes outliers and fills in missing values ​​in the collected data. Through data fusion and feature extraction, it generates a standardized data matrix and transmits it to the intelligent decision-making module.

[0045] Intelligent Decision-Making: The intelligent decision-making module matches the crop growth stage with a standardized data matrix, optimizes the water and fertilizer requirement model by combining environmental and crop growth data, and generates a precise irrigation and fertilization plan (including irrigation amount, irrigation time, fertilizer type, fertilizer amount, and fertilization time).

[0046] Execution and Feedback: The irrigation and fertilization execution module starts the irrigation valve and fertilization pump according to the plan, and the flow and pressure sensors provide real-time feedback of operating data; if the data deviates from the preset value, the intelligent decision-making module immediately adjusts the control command to form a closed-loop control.

[0047] Remote monitoring: Users can view system operation data and plan execution status through the remote monitoring module, and can manually intervene and adjust in special circumstances.

[0048] Compared with existing technologies, this invention provides a precision irrigation and fertilization system based on crop accumulated temperature, which has the following beneficial effects:

[0049] This precision irrigation and fertilization system, based on crop accumulated temperature, uses accumulated temperature as its core driver and combines multi-dimensional environmental and crop growth data to accurately match the water and fertilizer requirements of crops at each growth stage. This improves water and fertilizer utilization by 20%-30%, reduces water and fertilizer waste, and lowers the risk of environmental pollution. It integrates data acquisition, processing, decision-making, execution, and remote monitoring throughout the entire process, achieving intelligent control of irrigation and fertilization. This reduces growers' labor intensity by more than 40% and is suitable for large-scale farmland planting scenarios. The intelligent decision-making module has self-optimization capabilities, iteratively optimizing parameters through historical data to adapt to different crops (wheat, corn, rice, etc.), different soil types (loam, sandy soil), and different climatic conditions, demonstrating strong adaptability. Employing a closed-loop control mechanism and remote manual intervention function, it ensures the accuracy of irrigation and fertilization execution (error ≤5%), while also handling extreme conditions to ensure stable crop growth, contributing to a 10%-15% increase in yield and significant quality improvement. Attached Figure Description

[0050] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is a schematic diagram of the functional modules of a precision irrigation and fertilization system based on crop accumulated temperature proposed in this invention. Detailed Implementation

[0052] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0053] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0054] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0055] Example 1:

[0056] Reference Figure 1 This is the first embodiment of the present invention, which provides a precision irrigation and fertilization system based on crop accumulated temperature, including the following functional modules:

[0057] The system includes a temperature accumulation acquisition module, an environmental sensing module, a crop growth status monitoring module, a data processing module, an intelligent decision-making module, an irrigation and fertilization execution module, and a remote monitoring module.

[0058] The precision irrigation and fertilization system based on crop accumulated temperature provided in this embodiment has the following module functions, hardware architecture, composition, and collaborative relationships:

[0059] (a) Accumulated Temperature Acquisition Module

[0060] Hardware composition: The core uses a DS18B20 digital temperature sensor (measurement range -55℃~+125℃, accuracy ±0.5℃), paired with an STM8L151K4 microcontroller as the local computing unit, supplemented by a 5V solar power supply module (including a 1000mAh lithium battery for energy storage), a LoRa wireless communication module (SX1278 chip, communication distance 1-3km), and a waterproof encapsulation shell (IP67 rating).

[0061] Hardware deployment: Distribute sensors evenly in the crop growth area at a density of one sensor per 5-10 acres. Bury the sensor probes 5cm deep (to avoid the influence of surface temperature fluctuations). Install the solar power supply module on a bracket 1.2m high to ensure sufficient sunlight.

[0062] Functionality: The sensor collects temperature data once per hour and transmits it to the local computing unit. The computing unit calculates the daily average temperature according to the formula "Daily average temperature = (Daily maximum temperature + Daily minimum temperature) / 2", compares it with the preset lower limit temperature for crop biology, accumulates effective accumulated temperature data, and transmits it to the data processing module in real time through the LoRa module.

[0063] (II) Environmental Perception Module

[0064] Soil parameter monitoring submodule:

[0065] Hardware components: Soil moisture sensor (TDR-300 type, measurement range 0-100%Vol, accuracy ±2%), soil nitrogen, phosphorus and potassium sensor (ES-2 type, measurement range 0-2000mg / kg, accuracy ±5%), equipped with signal conditioning circuit (AD8232 chip) and data acquisition module (STM32F103C8T6 microcontroller).

[0066] Deployment method: The sensors are buried in the main distribution layer of the crop root system (20-30cm deep), with one group per 15 mu. Each group contains one soil moisture sensor and one nitrogen, phosphorus and potassium sensor, with a spacing of 5m.

[0067] Air and light monitoring submodule:

[0068] Hardware components: an air temperature and humidity sensor (SHT30 chip, measurement range -40℃~+125℃, 0-100%RH, accuracy ±0.3℃, ±2%RH) and a light sensor (BH1750 chip, measurement range 0-65535lx, accuracy ±1lx), integrated into an integrated monitoring box, equipped with a 5V DC power supply module and a LoRa communication module.

[0069] Deployment method: Install on a rust-proof bracket with a height of 1.5m, facing south (to ensure the accuracy of light sensor data collection), with one monitoring box placed for every 30 acres.

[0070] Data transmission: After all sensor data is collected by the local data acquisition module, it is transmitted to the data processing module in real time via LoRa wireless communication. The transmission cycle is 30 minutes / time (soil parameters) and 15 minutes / time (air and light parameters).

[0071] (III) Crop Growth Status Monitoring Module

[0072] Morphological parameter monitoring submodule:

[0073] Hardware components: 2-megapixel high-definition camera (IMX307 sensor, supports 1080P resolution, 30 frames / second shooting), gimbal (supports 360° horizontal and -30° to +90° vertical rotation, control precision 0.1°), network video server (HiSilicon HI3518EV300 chip, supports H.265 encoding) and PoE power supply module (IEEE802.3af standard).

[0074] Deployment method: Install on poles 3-5m high, with one set for every 50 acres. The camera lens should be facing the crop growth area to ensure a coverage radius of not less than 15m.

[0075] Functionality: Triggers one shooting session every 24 hours, acquiring three sets of images from different angles through gimbal rotation. After being encoded by a network video server, the images are transmitted to the data processing module via Ethernet. Then, morphological parameters such as plant height, leaf area index, and number of flowers and fruits are extracted using machine vision algorithms (edge ​​detection, threshold segmentation).

[0076] Physiological indicator monitoring submodule:

[0077] Hardware components: chlorophyll sensor (SPAD-502Plus type, measurement range 0-99.9SPAD, accuracy ±0.1SPAD), leaf water content sensor (MS700 type, measurement range 0-100%, accuracy ±1%), supports Bluetooth 5.0 wireless communication (communication distance 10m), equipped with a rechargeable lithium battery (7 days of battery life / charge).

[0078] Deployment method: A combination of fixed and mobile monitoring is adopted. Three fixed monitoring points are set up for every 20 mu, and one handheld monitoring terminal is also equipped for random sampling and testing. The sensors at the fixed monitoring points are installed 10cm below the crop canopy to avoid direct sunlight.

[0079] Functionality: Data is collected every 3 days. Data is automatically collected at fixed monitoring points and transmitted via Bluetooth to the nearest environmental sensing module, which then synchronizes it to the data processing module. Data from handheld terminals is manually uploaded by the user to the remote monitoring platform and finally aggregated in the data processing module.

[0080] (iv) Data Processing Module

[0081] Hardware architecture: The core uses an industrial-grade STM32H743VIT6 microcontroller (480MHz main frequency, built-in 2MB Flash and 1MB RAM), paired with a high-speed SD card (64GB, for data caching), an Ethernet network interface (DM9051 chip, supporting 10 / 100M Ethernet), a LoRa concentrator module (SX1308 chip, capable of receiving 8 LoRa signals simultaneously) and a 220V AC power supply module (including surge and overvoltage protection circuits).

[0082] Hardware deployment: Installed in a field control box (IP54 protection level), the control box is placed in the center of the planting area to ensure that the communication distance with each sensor module is within the effective range; the control box is equipped with a cooling fan (which automatically starts when the temperature exceeds 40℃) to ensure stable hardware operation.

[0083] Functionality: The LoRa concentrator module receives data from each acquisition module, and the STM32H743VIT6 microcontroller executes data processing algorithms. First, outliers exceeding the range of "mean ± 3 standard deviations" are identified and removed using the 3σ criterion, and missing sensor data are supplemented using linear interpolation. Then, a weighted fusion algorithm is used to correlate accumulated temperature data, environmental parameters, and crop growth data to establish a multi-dimensional data model. Finally, feature parameters related to water and fertilizer requirements, such as accumulated temperature, relative soil moisture content, soil nitrogen content, and chlorophyll SPAD value, are extracted to generate a 10×N dimensional standardized data matrix (N is the number of acquisition cycles), which is then transmitted to the intelligent decision-making module via Ethernet.

[0084] (v) Intelligent Decision Module

[0085] Hardware architecture: The NVIDIA Jetson Nano development board adopts the ARM Cortex-A9 architecture (1.43GHz clock speed, built-in 4GB LPDDR4 RAM, supports GPU acceleration), equipped with a SATA interface solid-state drive (512GB, used for storing models and historical data), a gigabit Ethernet interface (used for communication with the data processing module and remote monitoring module), a USB 3.0 interface (used for connecting external debugging devices), and a 12V DC power supply module (supports wide voltage input 9-24V).

[0086] Hardware deployment: The development board is placed in the same field control box as the data processing module and is directly connected to the data processing module via gigabit Ethernet to ensure data transmission rate and stability; the development board is equipped with an external heat sink and a small cooling fan to prevent overheating during long-term operation.

[0087] Core model construction (self-built based on actual data):

[0088] Data preparation stage:

[0089] Collect basic data: For the target crop (such as wheat, corn, rice), collect basic data for 2-3 complete growth cycles under the local planting environment, including: accumulated temperature data (1 record per hour, including daily average temperature and cumulative accumulated temperature), environmental data (soil moisture, nitrogen, phosphorus and potassium content, air temperature and humidity, light intensity, recorded according to the corresponding collection cycle), crop growth data (plant height, leaf area index, chlorophyll content, leaf water content, etc., recorded according to the corresponding collection cycle), irrigation and fertilization records (irrigation amount, irrigation time, fertilizer type, fertilizer amount, fertilization time), and final yield and quality data (yield kg / mu, protein content, starch content, etc.).

[0090] Data preprocessing: The collected raw data is cleaned to remove extreme outliers (such as invalid data caused by sensor failure), and missing data is filled in using linear interpolation; the data is standardized (such as converting soil moisture content to relative moisture content and normalizing accumulated temperature data according to the growth cycle) to eliminate dimensional differences; the training set and test set are divided in an 8:2 ratio (the training set is used for model building, and the test set is used for model validation).

[0091] Construction of the model for the correspondence between accumulated temperature and growth stage:

[0092] Feature selection: Accumulated temperature is the core feature, supplemented by crop morphological parameters (plant height, leaf area index) as auxiliary features.

[0093] Model selection: The K-means clustering algorithm is used to divide the crop growth process into stages based on the accumulated temperature and morphological parameter data in the training set. For example, for wheat, cluster analysis is used to determine the accumulated temperature threshold ranges for growth stages such as "sowing-germination", "germination-tillering", and "tillering-jointing", forming an initial model of the correspondence between accumulated temperature and growth stages.

[0094] Model optimization: Validate the model using test set data and calculate the stage splitting accuracy (target ≥ 95%). If the accuracy does not meet the target, adjust the K value (number of clusters) or supplement feature parameters (such as adding cumulative illumination data), and retrain the model until the accuracy requirements are met.

[0095] Water and fertilizer requirement model construction:

[0096] Feature selection: The input features are growth stage (output by the accumulated temperature-growth stage model), soil moisture (relative soil water content), soil nutrients (nitrogen, phosphorus and potassium content), crop physiological indicators (chlorophyll SPAD value, leaf water content) and light intensity; the output targets are irrigation amount, fertilizer type and fertilizer amount.

[0097] Model selection: A random forest regression algorithm was adopted to build the model based on the training set data. The model hyperparameters (such as the number of decision trees, maximum tree depth, feature sampling ratio, etc.) were optimized using a grid search method, with the goal of minimizing the mean squared error (MSE) between the model's predicted values ​​and the actual irrigation and fertilization amounts.

[0098] Model validation: Evaluate model performance using test set data, requiring irrigation prediction error ≤8% and fertilizer prediction error ≤10%; if the standard is not met, supplement with more training data under different soil types and climatic conditions, and retrain the model until the accuracy requirements are met.

[0099] Model self-optimization: After the model is deployed, historical data (including irrigation and fertilization data, crop growth data and yield and quality data for that quarter) is automatically extracted every quarter. Following the above data preprocessing and model training process, the accumulated temperature-growth stage correspondence model and the water and fertilizer requirement model are iteratively updated to continuously optimize model parameters and improve decision-making accuracy.

[0100] Functionality: After receiving the standardized data matrix transmitted by the data processing module, the system first matches the current growth stage of the crop by accumulating temperature, and then combines soil moisture, nutrients and crop physiological indicators to call the water and fertilizer requirement model to optimize parameters and generate a personalized irrigation and fertilization plan (including irrigation amount, irrigation time, fertilizer type, fertilizer amount and fertilization time). The plan is then transmitted to the irrigation and fertilization execution module via gigabit Ethernet and simultaneously synchronized to the remote monitoring module.

[0101] (vi) Irrigation and Fertilization Execution Module

[0102] Hardware components:

[0103] Irrigation control unit: Intelligent electromagnetic irrigation valve (DN50 specification, supports 0-100% opening adjustment, adjustment accuracy ±1%, working pressure 0.1-1.0MPa), valve controller (STM32F030C8T6 microcontroller, used to receive control commands and drive valve action).

[0104] Fertilizer control unit: centrifugal pump (flow rate adjustable range 0-5L / min, accuracy ±0.1L / min), fertilizer controller (communications with valve controller via I2C, synchronously receiving control commands).

[0105] Monitoring and feedback unit: flow sensor (turbine type, measurement range 0.1-10m³ / h, accuracy ±1%), pressure sensor (strain gauge type, range 0-1MPa, accuracy ±0.5%FS), paired with signal acquisition circuit (ADS1115 chip, 16-bit AD conversion).

[0106] Auxiliary units: 220V AC power supply module (powers valves and fertilizer pumps), relay module (used to control equipment start and stop, with photoelectric isolation protection).

[0107] Hardware deployment: The intelligent irrigation valve is installed at the branch of the main irrigation pipeline, the intelligent fertilizer pump is connected to the fertilizer tank, the flow sensor is connected in series inside the irrigation pipeline (near the outlet of the irrigation valve), and the pressure sensor is installed on the inner wall of the irrigation pipeline (at a distance of not less than 1m from the flow sensor); all control units and sensors are waterproofed (IP65 protection level) to avoid damage from moisture.

[0108] Functionality: After receiving the irrigation and fertilization plan from the intelligent decision-making module, the valve controller and fertilization controller drive the irrigation valve and fertilization pump to start according to the preset time, opening degree / flow rate; the flow and pressure sensors collect operating data in real time, which is converted by the signal acquisition circuit and transmitted to the controller, which then feeds back to the intelligent decision-making module via Ethernet; if the actual flow rate is found to be 10% lower than the preset value or the pressure is 20% higher than the preset value, the intelligent decision-making module immediately issues an adjustment command, and the controller adjusts the opening degree of the irrigation valve or the power of the fertilization pump in real time to ensure execution accuracy.

[0109] (vii) Remote monitoring module

[0110] Hardware architecture: An industrial-grade router (Huawei AR502H, supporting 4G / 5G dual-mode communication and gigabit Ethernet) is used, paired with a WiFi module (ESP8266 chip, supporting 802.11b / g / n protocol) as a data transmission hub; the hardware is deployed in the field control box, and a 4G / 5G data card is inserted into the router to ensure communication with the cloud server; the WiFi module is used for local debugging and short-range access.

[0111] Software support (in collaboration with hardware): A remote monitoring platform is built based on a B / S architecture and deployed in the cloud. The minimum requirements for an ECS instance are 4 cores, 8GB of memory, and 500GB of SSD cloud disk. Users can log in via a computer browser or mobile APP to view real-time data (accumulated temperature, soil moisture, crop height, etc.), system operation status (whether each module is online and the working status of hardware devices), and irrigation and fertilization plans. Manual intervention is supported. When encountering extreme weather (such as heavy rain or high temperature), users can manually adjust the irrigation amount (±20%) and fertilization amount (±15%). The adjustment command is transmitted to the industrial-grade router via 4G / 5G network and then forwarded to the intelligent decision-making module for priority execution.

[0112] The system's workflow is as follows:

[0113] System initialization: Based on the type of crop, set the biological lower limit temperature (e.g., 3℃ for wheat, 10℃ for corn) in the intelligent decision module, and import the accumulated temperature-growth stage correspondence model and water and fertilizer requirement model parameters based on local actual data; complete the power-on and communication tests of each hardware module to ensure normal data transmission between sensors, controllers, and decision modules.

[0114] Data acquisition: The accumulated temperature acquisition module collects temperature every hour and calculates the accumulated temperature; the environmental sensing module collects soil moisture, nutrients, air temperature and humidity and light data according to a preset cycle; the crop growth status monitoring module collects crop growth data at regular intervals (images every 24 hours, physiological indicators every 3 days), and all data are transmitted to the data processing module in real time through the corresponding communication module.

[0115] Data processing: The data processing module removes outliers and fills in missing values ​​in the collected data. Through data fusion and feature extraction, it generates a standardized data matrix and transmits it to the intelligent decision-making module.

[0116] Intelligent Decision Making: The intelligent decision making module matches the current growth stage of the crop with a standardized data matrix, and optimizes the water and fertilizer requirement model by combining environmental and crop growth data to generate a precise irrigation and fertilization plan (including irrigation amount, irrigation time, fertilizer type, fertilizer amount, and fertilization time).

[0117] Execution and Feedback: The irrigation and fertilization execution module starts the irrigation valve and fertilization pump according to the plan, and the flow and pressure sensors provide real-time feedback of operating data; if the data deviates from the preset value, the intelligent decision-making module immediately adjusts the control command to form a closed-loop control.

[0118] Remote monitoring: Users can view system operation data and plan execution status through the remote monitoring module, and can manually intervene and adjust in special circumstances.

[0119] Example 2:

[0120] Based on the precision irrigation and fertilization system based on crop accumulated temperature described in Example 1, taking corn as an example, we will manage the precision irrigation and fertilization scheme for corn.

[0121] Before designing the irrigation and fertilization plan, carry out fertilization management during the sowing preparation period (30 days before sowing) to create a suitable starting point for growth and ensure a high-yield foundation.

[0122] Soil nutrient determination: core indicators include organic matter (≥3.0%), total nitrogen, available nitrogen, available phosphorus, available potassium, and pH value.

[0123] Develop personalized base fertilizer plans:

[0124] Calculation formula: Base fertilizer application rate = Target yield fertilizer requirement × Base fertilizer ratio - Soil available nutrients

[0125] Base fertilizer ratio: Based on the principle of "deep application of phosphate fertilizer, phased application of nitrogen fertilizer, and combination of base and topdressing of potassium fertilizer", it is recommended that 20% of nitrogen fertilizer, 100% of phosphate fertilizer, and 50% of potassium fertilizer be used as base fertilizer.

[0126] Soil nutrient supply calibration: If the content of available phosphorus and potassium in the soil reaches the "extremely high" level, the amount of phosphorus and potassium base fertilizer can be reduced by 10%-20% as appropriate.

[0127] Seed and fertilizer co-sowing technique: It is recommended to use high-phosphorus slow-release compound fertilizer (such as N-P2O5-K2O=15-25-10) to ensure a stable supply of nutrients during the seedling stage.

[0128] A scheme for constructing a dynamic model for intelligent fertilization of maize based on Growing Degree-Days (GDD). This scheme abandons traditional calendar time and uses ≥10℃ GDD as a unified "physiological clock" for maize, precisely binding agronomic measures such as fertilization management with the crop's inherent physiological processes, thus enabling the scheme to have high adaptability across regions.

[0129] Model foundation: Effective accumulated temperature (GDD) calculation and data foundation;

[0130] 1. Calculation formula:

[0131] Daily GDD = [(Daily High Temperature + Daily Low Temperature) / 2] - 10℃

[0132] If the calculation result is negative, it will be calculated as 0.

[0133] Cumulative GDD = ∑ Daily GDD (calculated from the day after emergence)

[0134] 2. Data Source and Security:

[0135] Temperature data: sourced from small weather stations deployed in the fields, ensuring real-time and accurate data.

[0136] Physiological baseline: The GDD thresholds for each stage of the model were derived from publicly available research data on spring maize in Northeast China and summer maize in the Huang-Huai-Hai Plain, with major cultivated varieties such as Zhengdan 958 and Xianyu 335 as references. Different varieties have different accumulated temperature requirements, necessitating localized calibration for practical applications.

[0137] Construction of the water and fertilizer requirement model:

[0138] Table 1 below is the core decision table of the model, which details the operations to be performed at each growth stage as defined by GDD.

[0139] Table 1

[0140] growth stage GDD range (≥10℃) Morphological / physiological characteristics Fertilizer Management Plan Remark Seedling stage - early jointing stage 0~200℃ From emergence to the beginning of elongation of the basal internodes. At the 3-leaf stage, the milk stops flowing and the root system is established. Requirements: Promote root growth and strong seedlings. Base fertilizer: Completed before GDD=0. Apply all phosphate fertilizer, 20% nitrogen fertilizer, and 50% potassium fertilizer. Dynamic assessment: When GDD reaches 150, if NDVI<0.5, lightly supplement with 3% total nitrogen. During the seedling stage, nitrogen should be controlled to promote root growth; phosphorus fertilizer can promote deep root development. Jointing - Small trumpet mouth 200~550℃ Internodes elongate rapidly, plant growth accelerates, and female ears begin to differentiate. Requirements: Stabilize stems and promote leaf growth. First topdressing (stem-boosting fertilizer): Begin when GDD reaches 250℃. Apply 25% of the total nitrogen and zinc micronutrient fertilizer (500-1000g / mu). Nutritional demand surges at the beginning of the jointing stage; fertilization at this time is to store nutrients for ear differentiation. Big trumpet mouth - before male extraction 550~750℃ The upper leaves are trumpet-shaped, and the male spikelet is visible when the base is pinched. This is the critical period for the differentiation of female spike florets. Requirements: Determine the number of grains per ear. Second topdressing (ear-boosting fertilizer): Begin when GDD reaches 600℃. Apply 40% of the total nitrogen and boron micronutrient fertilizer (500-1000g / mu). Foliar spray with 0.3% potassium dihydrogen phosphate (200g / mu). Dynamic adjustment: If NDVI < 0.7, increase the fertilizer application rate by 5%. Nitrogen deficiency at this stage directly leads to a reduction in the number of grains per ear; growth vigor is closely related to yield. Male extraction - initial stage of grouting 750~1100℃ The male tassel emerges, pollen is released, and the silks extend. The growth center shifts to the grains, and grain filling begins. Requirements: Preserve flowers and increase grain size, initiate grain filling. Third topdressing (grain-boosting fertilizer): When GDD reaches 800℃ (after silking stage), apply all remaining nitrogen and potassium fertilizers (50%). Potassium is needed during the grain-filling stage to promote grain filling; increasing grain weight is crucial. peak grouting period 1100~1500℃ The grains gain weight rapidly, and milk lines form and move downwards. Requirements: Preserve leaf weight and increase plant weight. Foliar fertilization: When GDD reaches 1300℃, spray the leaves with 0.3% potassium dihydrogen phosphate (200g / mu). Growth maintenance: Ensure NDVI > 0.7 to prevent premature aging. Foliar potassium supplementation in the later stages can increase the thousand-grain weight by 4.0g. Maturity 1500℃~1800℃+ The nipple lines disappear, the melanin layer appears, and physiological maturity is achieved. Requirements: Harvest at the appropriate time. Stop irrigation when GDD reaches 1800℃.

[0141] Calculation of basic fertilizer application:

[0142] Formula: Basic fertilizer application rate (kg / mu) = Target yield (kg / mu) × Fertilizer requirement per unit yield (kg / kg)

[0143] Parameters: The fertilizer requirements per unit yield are based on the general reference values ​​in the "Crop Nutrient Management Manual" jointly maintained by the Food and Agriculture Organization of the United Nations (FAO) and the International Institute of Plant Nutrition (IPNI): Approximately 18-24 kg of N, 12-15 kg of P2O5, and 16-20 kg of K2O are required to produce 1 ton of maize kernels. For ease of calculation, the midpoints are used: N: 21 kg / t, P2O5: 13.5 kg / t, K2O: 18 kg / t.

[0144] If the target yield is 1.2 tons / mu, then the basic nitrogen requirement is 1.2 × 21 = 25.2 kg / mu.

[0145] If the target yield is 1.2 tons / mu, then the basic phosphorus requirement is 1.2 × 13.5 = 16.2 kg / mu.

[0146] If the target yield is 1.2 tons / mu, then the basic potassium requirement is 1.2 × 18 = 21.6 kg / mu.

[0147] The irrigation and fertilization execution module starts the irrigation valve and fertilizer pump according to the above scheme, and the flow and pressure sensors provide real-time feedback of operating data. If the data deviates from the preset value, the intelligent decision-making module immediately adjusts the control commands to form a closed-loop control. Users can view the system operating data and scheme execution status through the remote monitoring module and can manually intervene and adjust in special circumstances.

[0148] Example 3:

[0149] This embodiment also provides a computer device applicable to a precision irrigation and fertilization system based on crop accumulated temperature, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize a precision irrigation and fertilization system based on crop accumulated temperature as proposed in the above embodiment.

[0150] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements a precision irrigation and fertilization system based on crop accumulated temperature as proposed in the above embodiment.

[0151] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0152] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0153] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0154] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0155] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0156] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A precision irrigation and fertilization system based on crop accumulated temperature, characterized in that, Includes the following functional modules: The system includes a temperature accumulation acquisition module, an environmental sensing module, a crop growth status monitoring module, a data processing module, an intelligent decision-making module, an irrigation and fertilization execution module, and a remote monitoring module. in, The accumulated temperature acquisition module is used to collect temperature data of the crop growing area and calculate the accumulated temperature using the active accumulated temperature method. The environmental sensing module is used to collect environmental data, including soil moisture content, soil nitrogen, phosphorus and potassium content, air temperature and humidity and light intensity. The crop growth status monitoring module monitors the status of crops using high-definition cameras and physiological sensors; The data processing module is used to receive and process data from the accumulated temperature acquisition module, the environmental sensing module, and the crop growth status monitoring module; The intelligent decision-making module uses built-in different crop fertilization models to match the crop growth stage and combine environmental and crop growth data to optimize and generate irrigation and fertilization plans. The irrigation and fertilization execution module is used to adjust the on / off status and power of the irrigation valve and fertilizer pump according to the irrigation and fertilization plan, and to provide feedback on the operating data during execution. The remote monitoring module allows users to view the system's operating status, collected data, and irrigation and fertilization plans via computer or mobile device.

2. The precision irrigation and fertilization system based on crop accumulated temperature according to claim 1, characterized in that, The accumulated temperature acquisition module has multiple built-in distributed temperature sensors to collect temperature data of the crop growth area at least once per hour and transmit the calculated accumulated temperature to the data processing module; at the same time, it sets the biological lower limit temperature for different crops.

3. The precision irrigation and fertilization system based on crop accumulated temperature according to claim 1, characterized in that, The environmental sensing module includes a soil parameter monitoring submodule and an air and light monitoring submodule. in, The soil parameter monitoring submodule includes soil moisture sensors and soil nitrogen, phosphorus, and potassium sensors; The air and light monitoring submodule includes an air temperature and humidity sensor and a light sensor.

4. The precision irrigation and fertilization system based on crop accumulated temperature according to claim 1, characterized in that, The physiological sensors in the crop growth status monitoring module include chlorophyll sensors and leaf water content sensors. The physiological sensors use a combination of fixed-point and mobile monitoring to perform fixed monitoring and random sampling detection.

5. The precision irrigation and fertilization system based on crop accumulated temperature according to claim 1, characterized in that, The data processing module uses the 3σ criterion to remove outliers and linear interpolation to fill in missing values. It establishes a multi-dimensional data association model through a data fusion algorithm, extracts data on water and fertilizer requirements, including accumulated temperature, soil moisture content, and chlorophyll content, and generates a standardized data matrix.

6. The precision irrigation and fertilization system based on crop accumulated temperature according to claim 1, characterized in that, The intelligent decision-making module includes different crop fertilization models, such as the accumulated temperature-growth stage correspondence model and the water and fertilizer requirement model for each growth stage. The intelligent decision-making module iteratively optimizes the model each quarter based on historical irrigation and fertilization data, crop growth data, and yield data using a random forest algorithm.

7. A precision irrigation and fertilization system based on crop accumulated temperature according to claim 6, characterized in that, The model for the correspondence between accumulated temperature and growth stages of different crops is constructed by including: Feature selection: Accumulated temperature is the core feature, supplemented by crop morphological parameters as auxiliary features; Model selection: The K-means clustering algorithm is used to divide the crop growth process into stages based on the accumulated temperature and morphological parameter data in the training set; Model optimization: Validate the model using test set data and calculate the stage split accuracy; if the accuracy is not up to standard, adjust the K value or supplement feature parameters and retrain the model.

8. A precision irrigation and fertilization system based on crop accumulated temperature according to claim 6, characterized in that, The water and fertilizer requirement models for each growth stage are constructed by including: Feature selection: growth stage, soil moisture, soil nutrients, crop physiological indicators, and light intensity are used as input features; irrigation amount, fertilizer type, and fertilizer amount are used as output targets. Model selection: The random forest regression algorithm is adopted to build a model based on the training set data. The hyperparameters of the model are optimized by grid search method. The goal is to minimize the mean square error between the model prediction and the actual irrigation and fertilization amount. Model validation: Evaluate model performance using test set data, requiring irrigation prediction error ≤8% and fertilizer prediction error ≤10%; if the target is not met, supplement with more training data under different soil types and climatic conditions, and retrain the model.

9. A precision irrigation and fertilization system based on crop accumulated temperature according to claim 1, characterized in that, The irrigation and fertilization execution module includes an intelligent irrigation valve, an intelligent fertilization pump, a flow sensor, and a pressure sensor; After receiving the irrigation and fertilization plan from the intelligent decision-making module, the intelligent irrigation valve and intelligent fertilization pump start according to the preset time, opening degree / flow rate. The flow sensor and pressure sensor monitor the operating data in real time. If the actual flow rate is found to be 10% lower than the preset value or the pressure is 20% higher than the preset value, the data is immediately fed back to the intelligent decision-making module, which adjusts the opening degree of the intelligent irrigation valve or the power of the intelligent fertilization pump in real time.

10. A precision irrigation and fertilization system based on crop accumulated temperature according to claim 1, characterized in that, The remote monitoring module is built on a B / S architecture and has a built-in manual intervention function. When encountering extreme weather, users can manually adjust the irrigation amount within ±20% and the fertilizer amount within ±15%. The adjustment instructions are directly transmitted to the intelligent decision-making module and executed with priority.

Images