Intelligent desert vegetation recovery planning and monitoring system and method thereof

Abstract

The invention relates to the technical field of desert vegetation recovery planning and monitoring systems, in particular to an intelligent desert vegetation recovery planning and monitoring system and method. And the planning optimization module is used for comparing and analyzing the image data of each time node in the data set to obtain the current ecological situation, carrying out simulation experiments based on different vegetation restoration schemes, and planning and designing vegetation restoration according to simulation experiment results. Obtaining a planning design scheme including a vegetation recovery type, a vegetation recovery region, different plant configuration, regional environment simulation and regional water system simulation; the monitoring module is used for monitoring the planning and design scheme, obtaining a vegetation image through an infrared sensor, and processing the vegetation image to obtain vegetation parameters; the service layer carries an artificial intelligence engine, undertakes core algorithm functions of data processing, change detection, growth prediction and the like, and provides an intelligent brain for scheme generation and problem diagnosis.

Description

Technical Field

[0001] The invention relates to the technical field of desert vegetation restoration planning and monitoring systems, and in particular to an intelligent desert vegetation restoration planning and monitoring system and a method thereof. Background Art

[0002] In recent years, with the impact of global warming and unreasonable human activities, the problem of desertification has become increasingly serious. Desertification not only leads to land degradation and a sharp decline in biodiversity, but also seriously threatens human survival and development. Therefore, how to effectively control deserts and restore desert vegetation has become a major issue that needs to be solved urgently around the world.

[0003] At present, scholars at home and abroad have carried out a lot of fruitful work on desert control. Some studies focus on the investigation and analysis of natural characteristics such as desert micrometeorology, hydrology, and geology, in order to find the root cause of vegetation degradation from the perspective of environmental factors. Other scholars explore engineering measures such as artificial afforestation and aerial seeding to promote vegetation restoration. These studies and practices have undoubtedly greatly promoted the cause of desert control, but objectively speaking, there are still some problems that need to be solved.

[0004] First, the current monitoring of desert ecology is not comprehensive and systematic enough. Although meteorological and hydrological data can reflect local environmental conditions, it is difficult to meet the needs of full coverage and normal monitoring. Satellite remote sensing technology can make up for this shortcoming, but it is still difficult to accurately and timely grasp the dynamic process of vegetation recovery in the region due to the limitations of traditional land object classification and change detection methods.

[0005] Secondly, the pertinence and operability of existing desert control planning schemes need to be strengthened. Due to the limited understanding of desert environment and the lack of strong simulation methods, planning and design are often extensive, making it difficult to carry out vegetation layout and configuration according to local conditions. In particular, insufficient consideration of the key factor of water resources makes it difficult to guarantee the effect of vegetation restoration.

[0006] Furthermore, there is a lack of process control in the implementation of desert control. Vegetation restoration is a long-term systematic project, but there is currently a lack of full-process, refined dynamic supervision measures, making it difficult to effectively track the survival and growth of seedlings, and it is also impossible to discover and deal with sudden problems in a timely manner, making it difficult to consolidate the results of control.

[0007] In addition, the safe sharing mechanism of governance data is still imperfect. As it involves multiple departments such as environment, forestry, and water conservancy, the collection, transmission, and storage of desert governance data are not standardized enough, and lack the necessary security measures. The authenticity and reliability of the data are at risk, and the data value cannot be fully activated. Summary of the invention

[0008] In response to the above problems, the present invention proposes an intelligent desert vegetation restoration planning and monitoring system and method. The system cleverly integrates cutting-edge technologies such as artificial intelligence, the Internet of Things, and blockchain, and builds a set of intelligent solutions that integrate data collection, planning and design, dynamic monitoring, comprehensive analysis, and irrigation decision-making, truly realizing the digital transformation and intelligent upgrading of the entire process of desert management.

[0009] The present invention proposes an intelligent desert vegetation restoration planning and monitoring system, comprising: a data collection module, which is used to collect historical satellite remote sensing data and unmanned aerial vehicle infrared laser scanning data, and obtain a data set through processing and calculation; a planning optimization module, which is used to compare and analyze the image data of each time node in the data set to obtain the current ecological status, and to conduct simulation experiments based on different vegetation restoration schemes, and to plan and design vegetation restoration according to the simulation experiment results, so as to obtain a planning and design scheme including vegetation restoration types, vegetation restoration areas, different plant configurations, regional environmental simulations, and regional water system simulations; a monitoring module, which is used to monitor the planning and design scheme, obtain vegetation images through infrared sensors, and process the vegetation images to obtain vegetation parameters; and a comprehensive analysis module, which is used to analyze the changing laws of the vegetation parameters based on comprehensive historical data, establish a vegetation growth change related model, obtain growth change information, and obtain growth change evaluation results based on the growth change information and standard growth change trends.

[0010] Preferably, it also includes an irrigation module, which makes judgments based on the vegetation parameters and the growth change information to obtain the irrigation area, irrigation type and irrigation amount, and sets water pipes according to the irrigation type; wherein the regional environmental simulation includes performing simulation experiments on temperature, moisture, wind, and light data to obtain simulation test results, and obtaining an optimized environmental simulation plan through the simulation test results; the regional water system simulation includes performing simulation experiments on different water resources required for the different vegetation types to obtain an optimized water system simulation plan.

[0011] Preferably, it also includes a blockchain system, which is used for data storage and data query of the collected vegetation restoration data; wherein, the data collection module also includes: preprocessing the historical satellite remote sensing data and the drone infrared laser scanning data, performing feature selection on the preprocessed data, and obtaining a current condition data set.

[0012] Preferably, the planning optimization module compares and analyzes the image data of each time node in the data set to obtain the current ecological status, including: constructing a time node database; comparing the data of the current time node with the data of the previous time node to obtain a difference image; pre-marking the difference image manually, determining the real significant area through a difference detection algorithm, and extracting features from the real significant area; inputting the features into a prediction model to obtain a predicted current ecological status.

[0013] The method of an intelligent desert vegetation restoration planning and monitoring system comprises the following steps: first, historical satellite remote sensing data and unmanned aerial vehicle infrared laser scanning data are processed to obtain a desert current condition data set; then, a desert planning data set is obtained, and the current ecological status and planning design scheme are obtained through a planning optimization algorithm and a terrain comparison algorithm; then, the planning design scheme is monitored, vegetation images of different growth cycles are obtained, and the vegetation images are processed to obtain vegetation parameters; thereafter, a data set is constructed for the changes of the vegetation images of different growth cycles, and a vegetation growth change related model is established through a fitting curve algorithm to obtain growth change information; finally, an optimization model is established according to the growth change information and a preset original growth change trend to obtain a growth change evaluation result.

[0014] Preferably, the step of obtaining the current ecological status and planning design scheme through planning optimization algorithm and terrain comparison algorithm includes: acquiring historical data, processing the historical data through optimization algorithm to obtain a historical desert data feature library; performing image simulation on the historical desert data feature library through terrain comparison algorithm; comparing the current ecological status image with the image simulation to obtain a current ecological status comment; establishing a planning model according to the current ecological status comment, evaluating and scoring the planning model, and screening out planning schemes with high scores as planning design schemes.

[0015] Preferably, the data set is constructed for the changes in the vegetation images of the different growth cycles, and a vegetation growth change correlation model is established through a fitting curve algorithm. The steps of obtaining growth change information include: time node construction, constructing time node data for the vegetation images of the different growth cycles and the vegetation parameters; constructing a historical vegetation change data set; fitting a curve algorithm for the historical vegetation change data set to obtain vegetation trend directions; and predicting the vegetation growth trend for the next year based on the vegetation trend directions to obtain growth change evaluation results.

[0016] Preferably, the step of establishing an optimization model based on the growth change information and the preset original growth change trend to obtain a growth change evaluation result includes: obtaining current vegetation growth change information, obtaining a change trend graph of the current planting area based on the vegetation growth change information, obtaining standard growth change trend information, comparing the current vegetation growth change information with the standard growth change trend information to obtain a growth trend difference ratio; establishing an optimization model based on the growth trend difference ratio to obtain an optimization trend graph; when the optimization trend graph and the standard growth change trend are consistent, determining that the vegetation growth is normal; when the optimization trend graph and the standard growth change trend are inconsistent, determining that the vegetation growth is abnormal; when the growth trend difference ratio is greater than the preset change ratio, sending a warning message to a designated terminal.

[0017] Preferably, the method further includes a detection node construction step: constructing a detection node composed of multiple detection units; the detection node interacts with a central processing unit through a communication network; the central processing unit generates an irrigation plan based on the vegetation parameters and the growth change information, and sends the irrigation plan to the corresponding detection node through the communication network; the detection node obtains a regional difference ratio based on the water resource utilization and the water resource amount of the irrigation plan, and judges whether the irrigation area needs irrigation through the regional difference ratio to obtain a judgment result; the irrigation type and irrigation amount of the area to be irrigated are obtained according to the judgment result, and water pipes are arranged in the area corresponding to the irrigation type through the irrigation plan.

[0018] Preferably, it also includes an environmental simulation step: building a virtual environmental climate, and conducting a simulation test in the virtual environmental climate; obtaining vegetation growth pictures and vegetation parameters in the virtual environmental climate under different environments, and the detection node is set in the virtual environmental climate; processing the vegetation growth pictures and the vegetation parameters, calculating the vegetation change speed in different environments according to the vegetation growth pictures and the vegetation parameters, comparing the vegetation change speed with the preset vegetation change speed, and obtaining the simulation test results; according to the simulation test results, optimizing the virtual environmental climate, and using the optimized virtual environmental climate as an optimized environmental simulation scheme.

[0019] The beneficial technical effects brought by the technical solution of the present invention are:

[0020] From a macro perspective, the system consists of three parts: data layer, service layer, and application layer. The data layer brings together heterogeneous data from multiple sources such as satellites, drones, and ground stations, and uses blockchain technology to build a secure and reliable governance big data resource pool, laying a solid foundation for subsequent processes. The service layer is equipped with an artificial intelligence engine, which undertakes core algorithm functions such as data processing, change detection, and growth prediction, and gives solution generation and problem diagnosis an intelligent brain. The application layer designs a visual intelligent portal to facilitate users to carry out one-stop self-service monitoring and early warning, remote control and other governance practices. The three levels are organically connected and collaboratively efficient, effectively solving the shortcomings of incomplete governance data, unintelligent methods, and unintegrated means in the past.

[0021] From a microscopic perspective, each functional module of the system also has many highlights. The data acquisition module introduces computer vision technology, which greatly improves the accuracy of remote sensing image interpretation; the planning and optimization module innovatively embeds the niche suitability model, which can accurately estimate the restoration effect under different vegetation configurations; the monitoring module applies a multi-sensor data fusion strategy to achieve a full-time, multi-factor three-dimensional depiction of the vegetation growth process; the irrigation module integrates the crop water consumption model and hydraulic calculation method, which can finely regulate the regional water resource allocation and maximize the water utilization efficiency on the basis of ensuring the water demand of vegetation. In addition, the system has also developed a virtual vegetation growth simulation test platform, which optimizes the governance process at low cost and high efficiency through the regulation of environmental parameters and the construction of scenarios, making the governance plan more economical and applicable.

[0022] In summary, the present invention starts from cutting-edge technologies such as ecological big data, artificial intelligence, and blockchain, takes desert geographical conditions as the basis, vegetation restoration goals as the guide, and efficient use of water resources as the starting point, and systematically designs an intelligent desert vegetation restoration planning and monitoring system, which responds well to the key technical problems faced by current desert governance, such as insufficient information acquisition, inaccurate auxiliary decision-making, and opaque governance process, and provides a set of effective overall solutions for the construction of ecological civilization in the new era. The technical system framework created by the system is complete, the modules are tightly coupled, and the functions are complementary and superimposed. It not only greatly improves the scientificity, refinement, and automation level of governance, but also opens up a new intelligent implementation path for governance work, which will surely have a positive and far-reaching impact in my country and even in the world. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is the overall logic block diagram of the system of the present invention.

[0024] Figure 2 It is a logic block diagram of the data collection module of the present invention.

[0025] Figure 3 It is a logic block diagram of the planning optimization module of the present invention.

[0026] Figure 4 It is a flow chart of the monitoring module of the present invention.

[0027] Figure 5 It is a flow chart of the comprehensive analysis module of the present invention.

[0028] Figure 6 It is a flow chart of the irrigation module of the present invention. DETAILED DESCRIPTION

[0029] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects thereof are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0030] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0031] See also Figure 1-6 The present invention provides an intelligent desert vegetation restoration planning and monitoring system and method thereof. The system comprises a data collection module 1, a planning optimization module 2, a monitoring module 3, and a comprehensive analysis module 4.

[0032] First, the data collection module 1 is used to collect historical satellite remote sensing data and drone infrared laser scanning data, and obtain a data set through processing and calculation. Specifically, the data collection module 1 also includes preprocessing the historical satellite remote sensing data and drone infrared laser scanning data, performing feature selection on the preprocessed data, and obtaining a current condition data set. In this way, more comprehensive and accurate current status data can be obtained, providing a good foundation for subsequent analysis.

[0033] Secondly, the planning optimization module 2 is used to compare and analyze the image data of each time node in the data set to obtain the current ecological status, and conduct simulation experiments based on different vegetation restoration schemes. According to the results of the simulation experiments, the vegetation restoration is planned and designed to obtain a planning and design scheme including vegetation restoration type, vegetation restoration area, different plant configurations, regional environmental simulation, and regional water system simulation. Preferably, in one embodiment of the present invention, the steps of comparing and analyzing the image data of each time node in the data set to obtain the current ecological status include: constructing a time node database; comparing the data of the current time node with the data of the previous time node to obtain a difference image; pre-marking the difference image manually, determining the real significant area through a difference detection algorithm, and extracting features from the real significant area; inputting the features into the prediction model to obtain the predicted current ecological status. For example, by building a satellite remote sensing image database for different months such as January, February, and March 2021, and comparing the images of February and January 2021, we found that some new green areas appeared in the February images. By manually pre-marking these areas, we used the difference detection algorithm to determine which were the real vegetation restoration areas, extracted the features of these areas, and input them into the prediction model to determine the current ecological restoration situation. This comparative analysis of time series can accurately grasp the dynamic changes in ecological restoration.

[0034] Thirdly, the monitoring module 3 is used to monitor the planning and design scheme, obtain vegetation images through infrared sensors, and process the vegetation images to obtain vegetation parameters. For example, one year after the implementation of vegetation restoration, the restoration area is photographed using an infrared sensor carried by a drone to obtain a series of vegetation images, extract parameters such as the color, density, and height of the vegetation in the image, and evaluate the restoration effect. Through continuous monitoring, problems can be discovered and the restoration plan can be dynamically optimized.

[0035] Finally, the comprehensive analysis module 4 is used to analyze the changing rules of vegetation parameters based on comprehensive historical data, establish a vegetation growth change related model, obtain growth change information, and obtain growth change evaluation results based on the growth change information and the standard growth change trend. Preferably, in one embodiment of the present invention, the step of establishing an optimization model based on the growth change information and the preset original growth change trend to obtain the growth change evaluation result includes: obtaining the current vegetation growth change information, obtaining the change trend diagram of the current planting area based on the vegetation growth change information, obtaining the standard growth change trend information, comparing the current vegetation growth change information with the standard growth change trend information, and obtaining the growth trend difference ratio; establishing an optimization model based on the growth trend difference ratio to obtain an optimization trend diagram; when the optimization trend diagram and the standard growth change trend are consistent, it is determined that the vegetation growth is normal; when the optimization trend diagram and the standard growth change trend are inconsistent, it is determined that the vegetation growth is abnormal; when the growth trend difference ratio is greater than the preset change ratio such as 0.2, a warning message is sent to the terminal of the manager. By comprehensively analyzing historical data and current monitoring data and establishing a dynamic growth model, we can more accurately grasp the vegetation growth status and issue timely warnings.

[0036] In addition, the present invention also provides a method for the above system, comprising the following steps:

[0037] Firstly, the historical satellite remote sensing data and UAV infrared laser scanning data were processed to obtain the desert status data set;

[0038] Then, obtain the desert planning data set, and obtain the current ecological status and planning design scheme through planning optimization algorithm and terrain comparison algorithm; specifically, obtain historical data, process the historical data through optimization algorithm, and obtain the historical desert data feature library; perform image simulation on the historical desert data feature library through terrain comparison algorithm; compare the current ecological status image with the image simulation to obtain the current ecological status comment; establish a planning model based on the current ecological status comment, evaluate and score the planning model, and select the planning scheme with a score of 0.9 or above as the final design scheme. In this way, the value of historical data can be fully utilized, and the planning scheme can be optimized based on big data analysis;

[0039] Next, the planning and design scheme is monitored, vegetation images of different growth periods are obtained, and vegetation images are processed to obtain vegetation parameters;

[0040] Afterwards, a dataset is constructed for the changes in vegetation images of different growth cycles, and a vegetation growth change related model is established through a curve fitting algorithm to obtain growth change information; specifically, it includes: time node construction, time node data construction for vegetation images and vegetation parameters of different growth cycles; construction of a historical vegetation change dataset; fitting curve algorithms are performed on the historical vegetation change dataset to obtain vegetation trends; based on the vegetation trends, the vegetation growth trend for the next year is predicted to obtain growth change evaluation results. This can scientifically predict future growth conditions and provide a basis for the next step of optimization;

[0041] Finally, an optimization model is established based on the growth change information and the preset original growth change trend to obtain the growth change evaluation results.

[0042] Furthermore, the present invention may also include an irrigation module 5 and a blockchain system 6. Among them, the irrigation module 5 makes a judgment based on the vegetation parameters and growth change information to obtain the irrigation area, irrigation type and irrigation amount, and sets the water pipe according to the irrigation type. For example, when the vegetation growth in a certain area is lower than the expected 0.2, it is determined that it needs irrigation. According to specific parameters such as soil moisture and temperature, it is determined that micro-sprinkler irrigation or drip irrigation is needed, and the irrigation intensity is controlled at 2L / ㎡. Regional environmental simulation includes conducting simulation experiments on temperature, moisture, wind, and light data to obtain simulation test results, and obtaining an optimized environmental simulation scheme through the simulation test results. For example, by setting different temperature gradients (20℃-40℃), humidity gradients (40%-80%), etc., the vegetation growth is simulated. When the temperature is 28-35℃ and the humidity is 60%-70%, the growth effect is the best, and the parameter setting of the environmental simulation scheme is optimized accordingly. Regional water system simulation includes conducting simulation experiments on different water resources required by different vegetation types to obtain an optimized water system simulation scheme. According to the water consumption characteristics of different plants, different water system layout schemes are simulated, such as 3 schemes. Scheme 1 has a daily water supply of 5000m 3 , coverage rate 65%; plan 2 daily water supply 6000m 3 , coverage rate 70%; water supply of scheme 3 8000m 3 , coverage rate is 85%. Through comparison of input-output ratio, environmental benefits, etc., Scheme 2 is preferred. Irrigation model and water resource utilization efficiency are key factors affecting vegetation restoration, which need to be focused on design and optimization. Blockchain system 6 is used for data storage and data query of collected vegetation restoration data. Using blockchain technology to build a database can ensure the security and immutability of data, and facilitate the tracing and query of historical data, providing a reliable data foundation for desert control.

[0043] The present invention also constructs a detection node 10 composed of multiple detection units, and the detection node 10 interacts with a central processing unit such as a cloud platform through a communication network such as the Internet and GPRS; the central processing unit generates an irrigation plan according to vegetation parameters and growth change information, and sends the irrigation plan to the corresponding detection node through the communication network; the detection node obtains a regional difference ratio according to the water resource utilization and the water resource amount of the irrigation plan, and judges whether the irrigation area needs irrigation through the regional difference ratio to obtain a judgment result; the irrigation type and irrigation amount of the area to be irrigated are obtained according to the judgment result, and the irrigation type corresponding area is arranged with water pipes through the irrigation plan. For example, 10 detection units are set in the desert control area, each unit covers a 1km*1km area, and the water content, vegetation growth and other data of the area are collected and uploaded to the cloud platform for processing and calculation. When the water content of a certain area is lower than the critical value of 0.002, the cloud platform analyzes that it needs irrigation, generates an irrigation plan, and sends it to the corresponding detection unit, and the unit starts irrigation, and at the same time feeds back the actual water consumption to the cloud platform to dynamically optimize the irrigation strategy. Through this distributed, Internet of Things-based intelligent irrigation control, water resources can be used more accurately and efficiently.

[0044] In addition, the present invention also conducts an environmental simulation test, and the specific steps are: building a virtual environmental climate, and conducting a simulation test in the virtual environmental climate; obtaining vegetation growth pictures and vegetation parameters in the virtual environmental climate under different environments, and the detection node 10 is also set in the virtual environmental climate; processing the vegetation growth pictures and vegetation parameters, and calculating the vegetation change speed in different environments according to the vegetation growth pictures and vegetation parameters, and comparing the vegetation change speed with a preset vegetation change speed such as 0.01% / day to obtain the simulation test results; according to the simulation test results, optimizing the virtual environmental climate, and using the optimized virtual environmental climate as an optimized environmental simulation scheme. For example, for a target plant, fescue, we set up five different virtual growth environments: environment 1 with 6h / d light and 350ppm carbon dioxide concentration, environment 2 with 4h / d light and 380ppm carbon dioxide concentration, etc. A certain amount of fescue was planted in each environment and continuously monitored for 30 days. Growth data was collected through video monitoring and sensors, and the growth rate was calculated. It was found that environment 3 with 5h / d light and 400ppm carbon dioxide concentration grew fastest, with an average daily growth of 0.03%, which was much higher than other environments. Therefore, the indicators of environment 3 were selected as the optimal growth environment model. Through computer simulation, the environmental parameters of vegetation growth can be optimized at low cost and high efficiency, shortening the experimental cycle.

[0045] The intelligent desert vegetation restoration planning and monitoring system and method thereof comprehensively improve the intelligent level of desert vegetation restoration through the collaborative work of multiple modules such as data collection, planning and design, dynamic monitoring, and comprehensive analysis. Compared with the existing technology, it has the following beneficial effects:

[0046] 1. Data collection is more comprehensive and accurate, covering multiple data sources such as satellite remote sensing and ground monitoring, and has been intelligently processed, which has greatly improved the scientific nature of ecological status assessment and planning and design;

[0047] 2. Make full use of modern information technologies such as artificial intelligence and big data analysis to optimize vegetation restoration plans, making them more accurate and targeted;

[0048] 3. A dynamic monitoring system covering the entire region has been built based on the Internet of Things, which can monitor regional ecological changes in real time and provide data support for decision-making optimization;

[0049] 4. An intelligent irrigation system has been established to allocate water resources according to local conditions, promoting vegetation growth while achieving the economical and intensive use of water resources;

[0050] 5. Carry out growth simulation in virtual environment, obtain scientific knowledge of vegetation growth laws under different ecological environments at low cost, and greatly shorten the optimization cycle.

[0051] 6. The use of blockchain technology for data management effectively ensures data security and improves traceability and audit efficiency.

[0052] To sum up, the present invention starts from ecological big data, artificial intelligence, the Internet of Things, blockchain and other aspects to construct a set of intelligent solutions for desert vegetation restoration that integrates monitoring, analysis, early warning, decision-making and management, realizes the intelligence of the entire process, and promotes the overall leap in the level of desert ecological governance. It is of great significance for building a desert ecological safety barrier and achieving harmonious coexistence between man and nature.

[0053] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. Intelligent desert vegetation restoration planning and monitoring system, characterized by: include: The data collection module is used to collect historical satellite remote sensing data and drone infrared laser scanning data, and obtain data sets through processing and calculation; A planning and optimization module is used to compare and analyze the image data at each time node in the data set to obtain the current ecological status, and to conduct simulation experiments based on different vegetation restoration schemes. According to the simulation experiment results, the vegetation restoration is planned and designed to obtain a planning and design scheme including vegetation restoration type, vegetation restoration area, different plant configurations, regional environmental simulation, and regional water system simulation; a monitoring module is used to monitor the planning and design scheme, obtain vegetation images through infrared sensors, and process the vegetation images to obtain vegetation parameters; The comprehensive analysis module is used to analyze the changing rules of the vegetation parameters based on comprehensive historical data, establish a vegetation growth change related model, obtain growth change information, and obtain growth change evaluation results based on the growth change information and standard growth change trends.

2. The intelligent desert vegetation restoration planning and monitoring system according to claim 1 is characterized in that: It also includes an irrigation module, which makes judgments based on the vegetation parameters and the growth change information to obtain the irrigation area, irrigation type and irrigation amount, and sets water pipes according to the irrigation type; wherein the regional environmental simulation includes performing simulation experiments on temperature, moisture, wind, and light data to obtain simulation test results, and obtaining an optimized environmental simulation plan through the simulation test results; the regional water system simulation includes performing simulation experiments on different water resources required by the different vegetation types to obtain an optimized water system simulation plan.

3. The intelligent desert vegetation restoration planning and monitoring system according to claim 2 is characterized in that: It also includes a blockchain system, which is used for data storage and data query of the collected vegetation restoration data; wherein the data collection module also includes: preprocessing the historical satellite remote sensing data and the drone infrared laser scanning data, performing feature selection on the preprocessed data, and obtaining a current condition data set.

4. The intelligent desert vegetation restoration planning and monitoring system according to claim 1 is characterized in that: The planning optimization module compares and analyzes the image data of each time node in the data set to obtain the current ecological status, including the following steps: constructing a time node database; comparing the data of the current time node with the data of the previous time node to obtain a difference image; pre-marking the difference image manually, determining the real significant area through a difference detection algorithm, and extracting features from the real significant area; and inputting the features into a prediction model to obtain a predicted current ecological status.

5. A method based on the intelligent desert vegetation restoration planning and monitoring system according to any one of claims 1 to 4, characterized in that: The method comprises the following steps: first, processing historical satellite remote sensing data and unmanned aerial vehicle infrared laser scanning data to obtain a desert status data set; then, obtaining a desert planning data set, and obtaining the current ecological status and planning design scheme through a planning optimization algorithm and a terrain comparison algorithm; then, monitoring the planning design scheme, obtaining vegetation images of different growth cycles, and processing the vegetation images to obtain vegetation parameters; thereafter, constructing a data set for the changes in the vegetation images of different growth cycles, establishing a vegetation growth change related model through a fitting curve algorithm, and obtaining growth change information; finally, establishing an optimization model according to the growth change information and a preset original growth change trend, and obtaining a growth change evaluation result.

6. The method of the intelligent desert vegetation restoration planning and monitoring system according to claim 5 is characterized in that: The steps of obtaining the current ecological status and planning design schemes through the planning optimization algorithm and the terrain comparison algorithm include: obtaining historical data, processing the historical data through the optimization algorithm, and obtaining a historical desert data feature library; performing image simulation on the historical desert data feature library through the terrain comparison algorithm; comparing the current ecological status image with the image simulation to obtain a current ecological status comment; establishing a planning model according to the current ecological status comment, evaluating and scoring the planning model, and selecting planning schemes with high scores as planning design schemes.

7. The method of the intelligent desert vegetation restoration planning and monitoring system according to claim 5, characterized in that: The steps of constructing a data set for the changes in the vegetation images of different growth cycles, establishing a vegetation growth change related model through a fitting curve algorithm, and obtaining growth change information include: time node construction, constructing time node data for the vegetation images of different growth cycles and the vegetation parameters; constructing a historical vegetation change data set; fitting a curve algorithm for the historical vegetation change data set to obtain vegetation trend trends; and predicting the vegetation growth trend for the next year based on the vegetation trend trends to obtain growth change evaluation results.

8. The method of the intelligent desert vegetation restoration planning and monitoring system according to claim 7 is characterized in that: The step of establishing an optimization model based on the growth change information and the preset original growth change trend to obtain a growth change evaluation result includes: obtaining current vegetation growth change information, obtaining a change trend graph of the current planting area based on the vegetation growth change information, obtaining standard growth change trend information, comparing the current vegetation growth change information with the standard growth change trend information to obtain a growth trend difference ratio; establishing an optimization model based on the growth trend difference ratio to obtain an optimization trend graph; when the optimization trend graph is consistent with the standard growth change trend, determining that the vegetation growth is normal; when the optimization trend graph is inconsistent with the standard growth change trend, determining that the vegetation growth is abnormal; when the growth trend difference ratio is greater than the preset change ratio, sending a warning message to a designated terminal.

9. The method of the intelligent desert vegetation restoration planning and monitoring system according to claim 5, characterized in that: The method also includes a detection node construction step: constructing a detection node composed of a plurality of detection units; the detection node interacts with a central processing unit through a communication network; the central processing unit generates an irrigation plan according to the vegetation parameters and the growth change information, and sends the irrigation plan to a corresponding detection node through the communication network; The detection node obtains a regional difference ratio based on the water resource utilization and the water resource amount of the irrigation plan, and judges whether the irrigation area needs irrigation through the regional difference ratio to obtain a judgment result; the irrigation type and irrigation amount of the area to be irrigated are obtained based on the judgment result, and water pipes are arranged in the area corresponding to the irrigation type through the irrigation plan.

10. The method of the intelligent desert vegetation restoration planning and monitoring system according to claim 9, characterized in that: The method also includes an environmental simulation step: building a virtual environmental climate, and conducting a simulation test in the virtual environmental climate; obtaining vegetation growth pictures and vegetation parameters in the virtual environmental climate under different environments, wherein the detection node is set in the virtual environmental climate; processing the vegetation growth pictures and the vegetation parameters, and calculating the vegetation change speed in different environments according to the vegetation growth pictures and the vegetation parameters, and comparing the vegetation change speed with a preset vegetation change speed to obtain the simulation test result; According to the simulation test results, the virtual environment climate is optimized, and the optimized virtual environment climate is used as an optimized environment simulation scheme.

Images