CN-121998789-A - Planting method and system based on summer vegetables in plateau region

CN121998789ACN 121998789 ACN121998789 ACN 121998789ACN-121998789-A

Abstract

The invention relates to the technical field of intelligent agriculture, and discloses a planting method and system based on summer vegetables in a plateau area. The method comprises the steps of continuously collecting soil and meteorological multi-parameter data through a sensor array deployed in a target planting area, forming a standardized data set after verification processing, analyzing planting suitability by utilizing the data set to generate a spatial distribution map, building a crop growth prediction model by combining historical data and real-time data, outputting growth expectations of different planting schemes, making a detailed planting plan comprising time, density and position according to the map and expected results, controlling planting equipment to plant according to the plan, continuously monitoring growth, dynamically adjusting management measures according to growth variation, and forming closed-loop regulation. The invention realizes the refinement of planting planning and the intellectualization of growth management, and improves the resource utilization efficiency and the output stability of Gao Yuanxia vegetable planting.

Inventors

ZHAO YANRONG
WANG XUXIN
HU ZHIXIA

Assignees

金昌海量陇丰农牧科技发展有限公司
金昌市农业技术推广服务中心

Dates

Publication Date: 20260508
Application Date: 20260408

Claims (10)

1. The planting method of the summer vegetables based on the plateau region is characterized by comprising the following steps of: Continuously acquiring soil multi-parameter data and meteorological multi-parameter data through a sensor array deployed in a target planting area, and performing quality check and outlier rejection processing on the acquired soil multi-parameter data and meteorological multi-parameter data to form a standardized environment monitoring data set; performing planting suitability analysis by using the standardized environment monitoring data set to generate a planting suitability map containing spatial distribution characteristics; Combining historical planting record data with real-time environment monitoring data, establishing a crop growth prediction model, and outputting a growth expected result under different planting schemes through the crop growth prediction model; A detailed planting operation plan is established according to the planting suitability map and the expected growth result, and the planting operation plan comprises planting time schedule, planting density plan and planting position distribution; Controlling planting equipment to execute sowing operation according to the planting operation plan, and continuously monitoring crop growth vigor change in a crop growth period; and dynamically adjusting management measures according to the monitored crop growth condition change to form a closed-loop planting regulation strategy.
2. The planting method based on the plateau region summer vegetable according to claim 1, wherein the soil multi-parameter data and the meteorological multi-parameter data are continuously collected through a sensor array deployed in a target planting area, and specifically comprises the following steps: arranging soil sensor nodes and meteorological sensor nodes according to a preset grid pattern in a target planting area, wherein the soil sensor nodes measure soil humidity, soil temperature and soil pH value, and the meteorological sensor nodes measure air temperature, air humidity and illumination intensity; Setting data acquisition frequency, synchronously acquiring environmental parameters by each sensor node according to the set frequency, and transmitting acquired data to a data sink node through a wireless sensor network; The data sink node performs time stamp alignment and format unified processing on the received sensor data to form an original environment data set; Carrying out data cleaning on the original environment data set, and identifying and removing abnormal data points generated by sensor faults or transmission interference; And performing spatial interpolation processing on the cleaned environmental data to generate a continuous environmental parameter distribution map covering the whole target planting area.
3. The method for planting summer vegetables in a plateau region according to claim 1, wherein the planting suitability analysis is performed by using the standardized environmental monitoring dataset to generate a planting suitability map including spatial distribution characteristics, and the method specifically comprises: Extracting spatial distribution data of all environmental parameters from a standardized environmental monitoring data set, and establishing an environmental parameter spatial database; determining the threshold values of the proper ranges of different summer vegetable varieties on all environmental parameters, and constructing a crop environment suitability evaluation standard; carrying out matching analysis on the spatial distribution data of each environmental parameter and the crop environmental suitability evaluation standard by adopting a spatial superposition analysis method; calculating the coincidence degree of the environmental parameters and the suitable range of each spatial position, and generating a suitability degree scoring layer of each environmental parameter; weighting and fusing the scoring layers of the suitability of each environmental parameter to obtain a comprehensive planting suitability distribution map; And carrying out space smoothing treatment on the comprehensive planting suitability distribution map, and eliminating a local abnormal region to form a final planting suitability distribution map.
4. The planting method based on the plateau region summer vegetable of claim 1, wherein the combination of the historical planting record data and the real-time environment monitoring data establishes a crop growth prediction model, and specifically comprises: Collecting historical planting record data of a plurality of past growth cycles of a target planting area, wherein the historical planting record data comprises planting time, planting varieties, environmental data and final yield data; The historical planting record data are arranged and standardized, and a historical planting database is established; Analyzing the correlation between the environmental parameters and crop growth indexes in the historical planting database, and determining key influence factors; selecting a neural network as a model infrastructure, and constructing a growth prediction network structure comprising an input layer, a hidden layer and an output layer; Training a growth prediction network by using a historical planting database, and adjusting network weight parameters to minimize errors between prediction output and actual growth data; and inputting the real-time environment monitoring data into a growth prediction model after training, and obtaining the expected growth results under different planting schemes.
5. The planting method based on the plateau region summer vegetable according to claim 1, wherein the making of the detailed planting operation plan according to the planting suitability map and the expected growth result specifically comprises: Determining the distribution conditions of a high-fitness area and a low-fitness area according to the planting fitness map; Determining the planting priority of each area by combining the expected yield data of different areas in the expected growth result; Considering crop rotation requirements and soil restoration requirements, reasonably arranging planting time sequences of different areas; determining the planting density and the planting mode of each area according to the characteristics and the expected growth conditions of the planted varieties; Combining the spatial distribution, the time schedule and the planting parameters to form a planting operation plan containing specific operation instructions; and decomposing the planting operation plan into an executable task list, and defining the time node and the execution requirement of each task.
6. The method for planting summer vegetables in a plateau-based area according to claim 1, wherein said controlling the planting equipment performs a planting operation according to said planting operation plan and continuously monitors a change in crop growth vigor during a crop growth cycle, specifically comprising: Converting the planting operation plan into a control instruction sequence which can be identified by planting equipment; the planting equipment automatically completes the control of the sowing depth, the adjustment of the sowing spacing and the control of the sowing quantity according to the control instruction sequence; After sowing is completed, starting multispectral imaging equipment to periodically acquire crop canopy image data; extracting crop leaf area index, chlorophyll content, plant height and other parameters from the canopy image through an image processing technology; establishing a crop growth time sequence database, and recording the growth change track of the whole growth period of crops; When abnormal change of the growth parameters is monitored, an early warning mechanism is automatically triggered and abnormal conditions are recorded.
7. The planting method based on the plateau region summer vegetable according to claim 1, wherein the dynamic adjustment of the management measures according to the monitored crop growth variation forms a closed-loop planting control strategy, and specifically comprises: Setting a threshold value of a normal range of growth parameters of each growth stage of crops; comparing and analyzing the crop growth parameters monitored in real time with normal range thresholds, and identifying the growth deviation condition; According to the degree and type of the growth deviation, a targeted regulation and control scheme is automatically generated, wherein the regulation and control scheme comprises irrigation regulation, fertilization regulation and pest control measures; converting the regulation scheme into a specific equipment control instruction, and automatically adjusting working parameters of an irrigation system and a fertilizer application device; After the regulation measures are implemented, continuously monitoring the growth condition change of crops, and evaluating the regulation effect; And optimizing the regulation strategy parameters according to the regulation effect feedback to form a self-adaptive closed-loop regulation system.
8. The planting method based on the plateau region summer vegetable of claim 6, wherein the method for extracting the crop leaf area index, chlorophyll content and plant height and other long-term parameters from the canopy image by the image processing technology comprises the following steps: preprocessing the acquired multispectral canopy image, including radiation calibration, atmospheric correction and geometric correction; Separating crop canopy from background soil by adopting an image segmentation algorithm, and extracting a pure crop canopy region; Calculating spectral reflectivities of the canopy region in different wavebands, and constructing a crop spectral characteristic curve; Inverting the leaf area index through spectral feature analysis, and calculating a normalized vegetation index by utilizing the reflectivity ratio of the near infrared band to the red band; Calculating chlorophyll content index based on red-edge band characteristics, and measuring plant height by stereoscopic vision technology; and correlating the extracted growth parameters with corresponding position information to generate a spatialization growth distribution map.
9. The planting method based on the plateau region summer vegetable of claim 3, wherein the weighting and fusion are carried out on the fitness scoring layers of all the environmental parameters to obtain a comprehensive planting fitness distribution map, and the planting method specifically comprises the following steps: Determining weight coefficients of all environmental parameters based on the growth requirements of target summer vegetable varieties by a hierarchical analysis method, wherein the environmental parameters comprise soil humidity, soil temperature, soil pH value, air temperature, air humidity and illumination intensity; Converting the suitability degree scoring layers of all the environmental parameters into grid data with the same spatial resolution, and ensuring that each grid unit corresponds to a consistent geographic position; calculating the sum of products of the fitness scores of the environmental parameters and the corresponding weight coefficients for each grid unit to obtain a weighted fitness score of the grid unit; performing linear normalization processing on weighted fitness scores of all grid units, mapping score values to a range from 0 to 1, and generating a comprehensive planting fitness distribution map; And verifying the accuracy of the comprehensive planting suitability distribution map, and carrying out consistency test by comparing the suitability scores of the historical planting success areas.
10. A plateau region summer vegetable-based planting system comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor, when executing the computer program, performs the steps of a plateau region summer vegetable-based planting method as claimed in any one of claims 1 to 9.

Description

Planting method and system based on summer vegetables in plateau region Technical Field The invention relates to the technical field of intelligent agriculture, in particular to a planting method and system based on summer vegetables in a plateau area. Background The planting of summer vegetables in plateau areas mainly depends on traditional farming experience and fixed planting modes. In the planting planning stage, farmers generally decide according to the overall impression and history habit of the field, and lack accurate grasp of the spatial variability of key environmental elements such as soil moisture content, nutrients, temperature and the like in the planting area. In the prior art, the land condition is usually estimated by adopting a mode of combining limited point position sampling detection with manual investigation, the data acquired by the method is sparse and has hysteresis, and the space cognition of the whole planting area is difficult to form. This results in a large blindness in terms of planting position selection, variety collocation, etc., and cannot realize optimal allocation of agricultural resources in the spatial dimension. In the crop growth management process, the prior art scheme mainly performs operations such as irrigation, fertilization and the like according to preset and unified lunar calendar, and the management strategy is static and universal. Because the microclimate characteristics of the plateau areas are obvious, the meteorological conditions are complex and changeable, and the fixed management mode is difficult to adapt to the actual demands of crops in different land areas in different growth stages. The application of the crop growth model is mostly in scientific research or post analysis, but cannot be combined with real-time environment monitoring and farm operation depth, and prospective simulation cannot be performed on different planting schemes to assist decision making. Management adjustment in the growth process also depends on manual inspection and experience judgment seriously, response is not timely and lacks quantitative basis, and the whole planting process does not form an optimized closed loop based on data feedback. Disclosure of Invention The invention aims to provide a planting method and system based on summer vegetables in a plateau area, which are used for solving the problems in the background technology. In order to achieve the above purpose, the invention provides a planting method of summer vegetables based on a plateau region, which comprises the following steps: Continuously acquiring soil multi-parameter data and meteorological multi-parameter data through a sensor array deployed in a target planting area, and performing quality check and outlier rejection processing on the acquired soil multi-parameter data and meteorological multi-parameter data to form a standardized environment monitoring data set; performing planting suitability analysis by using the standardized environment monitoring data set to generate a planting suitability map containing spatial distribution characteristics; Combining historical planting record data with real-time environment monitoring data, establishing a crop growth prediction model, and outputting a growth expected result under different planting schemes through the crop growth prediction model; A detailed planting operation plan is established according to the planting suitability map and the expected growth result, and the planting operation plan comprises planting time schedule, planting density plan and planting position distribution; Controlling planting equipment to execute sowing operation according to the planting operation plan, and continuously monitoring crop growth vigor change in a crop growth period; and dynamically adjusting management measures according to the monitored crop growth condition change to form a closed-loop planting regulation strategy. Preferably, the method for continuously collecting soil multi-parameter data and meteorological multi-parameter data by using the sensor array deployed in the target planting area specifically includes: arranging soil sensor nodes and meteorological sensor nodes according to a preset grid pattern in a target planting area, wherein the soil sensor nodes measure soil humidity, soil temperature and soil pH value, and the meteorological sensor nodes measure air temperature, air humidity and illumination intensity; Setting data acquisition frequency, synchronously acquiring environmental parameters by each sensor node according to the set frequency, and transmitting acquired data to a data sink node through a wireless sensor network; The data sink node performs time stamp alignment and format unified processing on the received sensor data to form an original environment data set; Carrying out data cleaning on the original environment data set, and identifying and removing abnormal data points generated by sensor faults or transmission interferenc