Grassland restoration intelligent decision system and method based on satellite remote sensing and internet of things

Abstract

The present application provides a kind of grassland recovery intelligent decision system and method based on satellite remote sensing and internet of things, its system includes: data integration module is used to obtain the satellite remote sensing data of the region to be governed and the grassland environment data of internet of things sensor, and according to data integration, obtain the grassland topography data of the region to be governed;Intelligent decision module is used to simulate different grassland recovery management schemes based on grassland topography data through dynamic grassland recovery prediction model, respectively obtain the management effect of each grassland recovery management scheme;Decision screening module is used to evaluate each grassland recovery management scheme based on management effect, obtain the best grassland recovery management scheme and the best combination scheme, and recommend to management personnel, provide scientific decision basis for management personnel, help precise planning, implementation and management grassland recovery project, realize the purpose of resource optimization configuration and grassland management scheme according to local conditions, improve grassland recovery efficiency and success rate.

Description

Technical Field

[0001] This invention relates to the field of grassland restoration management decision optimization technology, and in particular to an intelligent decision-making system and method for grassland restoration based on satellite remote sensing and the Internet of Things. Background Technology

[0002] Grassland ecological functions refer to the inherent habitat, biological properties, or ecological processes of a grassland ecosystem. These are prerequisites for grasslands to provide ecological resources and mainly include primary productivity, carbon sequestration, climate regulation, water conservation, windbreak and nutrient fixation, environmental purification, and biodiversity conservation. Grassland degradation leads to reduced vegetation cover and primary productivity, imbalances in the carbon cycle source-sink relationship, decreased climate regulation capacity, reduced soil nutrient and water retention capacity, river drying, lake shrinkage, reduced biodiversity, and frequent natural disasters such as insect and rodent infestations and sandstorms. With the advocacy of green development, people's awareness of environmental protection is increasing, and they are paying more and more attention to grassland management. However, due to the differences in grassland geographical environment, grassland restoration and management need to be tailored to local conditions, making grassland management decisions particularly difficult. Therefore, this invention proposes an intelligent decision-making system and method for grassland restoration based on satellite remote sensing and the Internet of Things. Summary of the Invention

[0003] This invention provides an intelligent decision-making system and method for grassland restoration based on satellite remote sensing and the Internet of Things. By constructing an intelligent decision support system, it provides managers with scientific decision-making basis, helps to accurately plan, implement and manage grassland restoration projects, achieves optimal resource allocation, and improves the efficiency and success rate of grassland restoration.

[0004] This invention provides an intelligent decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things, comprising:

[0005] The data integration module is used to acquire satellite remote sensing data and grassland environmental data from IoT sensors in the area to be treated, and to integrate the data to obtain grassland landform data of the area to be treated.

[0006] The intelligent decision-making module is used to simulate different grassland restoration and management schemes based on grassland geomorphology data and through a dynamic grassland restoration prediction model, and obtain the governance effect of each grassland restoration and management scheme respectively.

[0007] The decision screening module is used to evaluate each grassland restoration and management plan based on the governance effect, obtain the best grassland restoration and management plan and the best combination plan, and recommend them to the managers.

[0008] Preferably, in a smart decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things, the data integration module includes:

[0009] The remote sensing data storage unit is used to collect satellite remote sensing data of the area to be governed at a first preset frequency and store the satellite remote sensing data in chronological order.

[0010] The sensor data storage unit is used to collect IoT sensor data of the managed area at a second preset frequency, and store the IoT sensor data based on the time axis order and the type of IoT sensor.

[0011] The real-time data integration unit is used to determine the time correspondence between satellite remote sensing data and Internet of Things sensor data based on the frequency time difference between the first preset frequency and the second preset frequency.

[0012] Based on the aforementioned time correspondence, the correspondence between the storage files corresponding to satellite remote sensing data and IoT sensor data is determined, thereby obtaining grassland landform data for different time periods in the treated area.

[0013] Preferably, in a smart decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things, the smart decision-making module includes:

[0014] The scheme input unit is used by managers to input grassland restoration management schemes and generate preset grassland restoration management scheme information.

[0015] The environmental data analysis unit is used to determine the current grassland land parameters and vegetation data of the treated area based on the latest grassland geomorphology data.

[0016] The decision simulation unit is used to simulate grassland restoration based on current grassland land parameters and vegetation data, and through a dynamic grassland restoration prediction model, simulate grassland restoration according to different preset grassland restoration management schemes, obtain grassland restoration trends corresponding to different preset grassland restoration management schemes, and determine the final grassland management effect based on the grassland restoration trends.

[0017] Preferably, in a smart decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things, the decision simulation unit includes:

[0018] The scene data acquisition subunit is used to collect data from various IoT sensors, biological activity data, grassland remote sensing full images, and local remote sensing images of each sub-region in the area to be managed.

[0019] The information extraction subunit is used to perform grayscale processing on the whole image of the grassland remote sensing and the local remote sensing images corresponding to each sub-region to obtain grayscale processed images, and to extract grassland vegetation information based on the grayscale processed images and the original color images to obtain grassland vegetation information.

[0020] Based on big data, environmental change data of the treated area within a preset number of years is obtained, and meteorological change data corresponding to various weather conditions under different solar terms in the treated area are determined.

[0021] The model establishes a sub-unit, which is used to determine the species information, their corresponding distribution, and species migration within the governed area based on biological activity data.

[0022] Based on grassland vegetation information, species information and their corresponding distribution, the point cloud distribution of each sub-region within the treated area is determined, and a three-dimensional grassland scene is established.

[0023] The system acquires global remote sensing images of the treated area within a preset number of years. Based on these images, it determines the impact of meteorological changes on grassland species migration and grassland vegetation growth. Simultaneously, it acquires changes in various grassland IoT sensors corresponding to different grassland vegetation growth states. The system then determines and sets the correlation of the dynamic parameters of the original three-dimensional scene to generate a dynamic grassland model.

[0024] Based on the target grassland restoration data, a dynamic grassland model is restored, and a dynamic grassland restoration prediction model is generated.

[0025] Preferably, in a smart decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things, the model building subunit further includes:

[0026] The dynamic model refinement sub-unit is used to collect historical grassland management plans and their corresponding historical grassland management and restoration data based on big data.

[0027] Based on the geographical location data and environmental data of the grasslands corresponding to the historical grassland management schemes, the historical grassland restoration data are clustered to obtain multiple grassland restoration data groups. The grassland restoration data group with the highest similarity to the geographical location data and environmental data of the managed area is taken as the target data group.

[0028] Based on historical grassland management plans, the target data group was divided into multiple target sub-data groups;

[0029] The historical IoT data corresponding to the target data subgroups are input into the dynamic grassland restoration prediction model for simulation training to obtain grassland simulated restoration data. The grassland simulated restoration data is then compared with the grassland vegetation change data of the target data group to obtain data for improving the solution.

[0030] Multiple target sub-data groups are obtained to obtain scheme improvement data, a training set is established, and the dynamic grassland model is iteratively trained based on the training set to obtain the dynamic grassland restoration prediction model corresponding to the treated area.

[0031] Preferably, in a smart decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things, the decision filtering module includes:

[0032] The first evaluation unit is used to compare the governance effects of different grassland restoration and management schemes, obtain a ranking sequence of effects, and score each different grassland restoration and management scheme in the ranking sequence according to the expected governance effects to obtain the scheme score results.

[0033] The second evaluation unit is used to evaluate the sustainable development rate of the governance effect based on the changes in grassland land parameters during the simulation process, and obtain the effect maintenance score.

[0034] The decision screening unit is used to screen and combine grassland restoration management plans based on the plan scoring results and the effect maintenance score, to obtain the best grassland restoration management plan and the best combination plan, and recommend them to the managers.

[0035] Preferably, in a smart decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things, the first evaluation unit includes:

[0036] The sorting subunit is used to sort the governance effects of different grassland restoration and management schemes based on the grassland coverage corresponding to different grassland restoration and management schemes, and obtain the effect ranking sequence.

[0037] The scheme evaluation subunit is used to obtain the expected governance effect of the treated area at different governance stages. According to the stage allocation of the expected quality effect, the governance process of different grassland restoration management schemes is divided into multiple stages, and the grassland restoration sub-effect corresponding to each stage is determined. The grassland restoration sub-effect is compared with its corresponding expected governance effect to obtain the difference in vegetation coverage and the difference in vegetation growth status.

[0038] The differences in vegetation coverage and vegetation growth status are respectively divided into percentages to obtain vegetation coverage scores and vegetation growth status scores. These scores are then added together to obtain grassland restoration scores for each stage of different grassland restoration management schemes. The average score of grassland restoration scores for each stage of the same grassland restoration management scheme is calculated as the scheme score corresponding to the grassland restoration management scheme.

[0039] Preferably, in a smart decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things, the second evaluation unit includes:

[0040] The effect assignment sub-unit is used to obtain the changes in grassland land parameters at different stages of different grassland restoration and management schemes. Any treatment stage is taken as the target treatment stage, and the initial grassland land parameters of the target treatment stage are compared with the final grassland land parameters to determine whether the grassland soil quality corresponding to the target treatment stage has improved.

[0041] If so, then assign a value of 1 to the sustainable development status of the target governance stage;

[0042] Otherwise, the sustainable development status of the target governance stage will be assigned a value of 1 to 0;

[0043] The effect evaluation sub-unit is used to obtain all target governance stages with a value of 1, determine the sustainable development rate corresponding to different grassland restoration and management schemes, obtain the maximum number of consecutive target governance stages with a value of 1 for different grassland restoration and management schemes, and obtain the maximum improvement duration ratio.

[0044] Based on the maximum improvement duration ratio and combined with the preset effective index list, the effective index of different grassland restoration and management schemes is determined respectively.

[0045] Based on the effectiveness index and sustainable development rate of the proposed schemes, the effectiveness maintenance scores corresponding to different grassland restoration and management schemes are obtained.

[0046] Preferably, in a smart decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things, the decision screening unit includes:

[0047] The recommended filtering sub-unit is used to obtain the preset weights corresponding to the scheme scoring results and the effect maintenance score, respectively. Based on the scheme scoring results and their corresponding preset weights and the effect maintenance score and their corresponding preset weights for each grassland restoration management scheme, the final score for each grassland restoration management scheme is obtained.

[0048] The grassland restoration and management plan with the highest final score will be considered the best grassland restoration and management plan.

[0049] The decision-making intelligent combination subunit is used to obtain the grassland restoration score and sustainable development status assignment results corresponding to each stage of different grassland restoration management schemes, and compare and filter them to obtain a preset number of high-quality grassland restoration schemes corresponding to each governance stage.

[0050] Based on the conversion cost between different grassland restoration and management schemes, a preset number of high-quality grassland restoration schemes for each governance stage are intelligently combined to generate the optimal combination scheme.

[0051] The recommended interactive sub-unit is used to send the best grassland restoration management plan, the scoring results of each grassland restoration management plan, and the best combination plan to the managers.

[0052] This invention provides a smart decision-making method for grassland restoration based on satellite remote sensing and the Internet of Things, comprising:

[0053] Acquire satellite remote sensing data and grassland environmental data from IoT sensors in the area to be treated, and integrate the data to obtain grassland landform data of the area to be treated.

[0054] Based on grassland geomorphological data, a dynamic grassland restoration prediction model was used to simulate different grassland restoration and management schemes, and the governance effects of each grassland restoration and management scheme were obtained.

[0055] Based on the governance effects, each grassland restoration and management plan was evaluated to obtain the best grassland restoration and management plan and the best combination plan, which were then recommended to the managers.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] This invention acquires satellite remote sensing data and grassland environmental data from IoT sensors in the treated area through a data integration module. By integrating this data, it obtains grassland geomorphological data for the treated area, achieving automatic data processing and ensuring the accuracy of data correspondences and the comprehensiveness and integrity of the data. This provides a rich data foundation for subsequent grassland decision-making simulations. Based on the grassland geomorphological data, the intelligent decision-making module simulates different grassland restoration management schemes using a dynamic grassland restoration prediction model. The invention obtains the governance effects of each scheme and allows for a comprehensive comparison of the effects of each scheme across different dimensions, such as vegetation restoration speed and soil improvement. This helps managers clearly understand the advantages and disadvantages of each scheme. The advantages include providing intuitive data support for selecting the best solution, helping to formulate restoration strategies that better suit the actual geological and environmental conditions of the grassland, and avoiding the waste of resources and time caused by blind attempts; finally, the decision screening module evaluates each grassland restoration management plan based on the governance effect, obtains the best grassland restoration management plan and the best combination plan, and recommends them to managers, which greatly reduces the information burden and uncertainty in the decision-making process, provides managers with a scientific basis for decision-making, helps to accurately plan, implement and manage grassland restoration projects, achieves the goal of optimizing resource allocation and adapting grassland governance plans to local conditions, improves grassland restoration efficiency and success rate, effectively improves the efficiency and quality of grassland governance decision-making, and achieves the sustainable development of grassland ecosystems.

[0058] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in this application.

[0059] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0060] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0061] Figure 1 This is a structural diagram of an intelligent decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things according to the present invention;

[0062] Figure 2 This is a structural diagram of the data integration module of an intelligent decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things, according to the present invention.

[0063] Figure 3 This is a structural diagram of the intelligent decision-making module of an intelligent decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things, according to the present invention.

[0064] Figure 4 This is a structural diagram of the decision screening module of the intelligent decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things according to the present invention;

[0065] Figure 5 This is a flowchart of an intelligent decision-making method for grassland restoration based on satellite remote sensing and the Internet of Things, according to the present invention. Detailed Implementation

[0066] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0067] Example 1: This invention provides an intelligent decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things, such as... Figure 1 As shown, it includes:

[0068] The data integration module is used to acquire satellite remote sensing data and grassland environmental data from IoT sensors in the area to be treated, and to integrate the data to obtain grassland landform data of the area to be treated.

[0069] The intelligent decision-making module is used to simulate different grassland restoration and management schemes based on grassland geomorphology data and through a dynamic grassland restoration prediction model, and obtain the governance effect of each grassland restoration and management scheme respectively.

[0070] The decision screening module is used to evaluate each grassland restoration and management plan based on the governance effect, obtain the best grassland restoration and management plan and the best combination plan, and recommend them to the managers.

[0071] The beneficial effects of the above technical solution are as follows: This invention acquires satellite remote sensing data and grassland environmental data from IoT sensors in the treated area through a data integration module, and then integrates the data to obtain grassland geomorphological data of the treated area. This achieves automatic organization of grassland geomorphological data in the treated area, ensuring the accuracy of the correspondence between data and the comprehensiveness and integrity of the data, providing a rich data foundation for subsequent grassland decision-making simulations. Furthermore, based on the grassland geomorphological data, the intelligent decision-making module simulates different grassland restoration management schemes using a dynamic grassland restoration prediction model, obtaining the governance effects of each scheme. This allows for a comprehensive comparison of the governance effects of each scheme under different dimensions, such as vegetation restoration speed and soil improvement, which is beneficial for managers to clearly understand the situation. The advantages and disadvantages of each option provide intuitive data support for selecting the best option, helping to formulate restoration strategies that are more in line with the actual geological and environmental conditions of the grassland, avoiding the waste of resources and time caused by blind attempts. Finally, the decision screening module evaluates each grassland restoration and management option based on the governance effect, obtains the best grassland restoration and management option and the best combination option, and recommends them to managers. This greatly reduces the information burden and uncertainty in the decision-making process, provides managers with a scientific basis for decision-making, helps to accurately plan, implement and manage grassland restoration projects, achieve the goal of optimizing resource allocation and adapting grassland governance options to local conditions, improve grassland restoration efficiency and success rate, effectively improve the efficiency and quality of grassland governance decision-making, and achieve sustainable development of grassland ecosystems.

[0072] Example 2: Based on Example 1, the data integration module, such as Figure 2 As shown, it includes:

[0073] The remote sensing data storage unit is used to collect satellite remote sensing data of the area to be governed at a first preset frequency and store the satellite remote sensing data in chronological order.

[0074] The sensor data storage unit is used to collect IoT sensor data of the managed area at a second preset frequency, and store the IoT sensor data based on the time axis order and the type of IoT sensor.

[0075] The real-time data integration unit is used to determine the time correspondence between satellite remote sensing data and Internet of Things sensor data based on the frequency time difference between the first preset frequency and the second preset frequency.

[0076] Based on the aforementioned time correspondence, the correspondence between the storage files corresponding to satellite remote sensing data and IoT sensor data is determined, thereby obtaining grassland landform data for different time periods in the treated area.

[0077] In this embodiment, the first preset frequency and the second preset frequency can be the same or different, and the administrator can set them according to the monitoring needs.

[0078] In this embodiment, the IoT sensor data includes ambient temperature, ambient humidity, and soil data (humidity, content of a certain element, etc.).

[0079] The beneficial effects of the above technical solution are as follows: The present invention collects and stores satellite remote sensing data and IoT sensor data according to a preset acquisition frequency through remote sensing data storage unit and sensor data storage unit, respectively, and realizes automatic sorting of grassland landform data in the treated area through real-time data integration unit, ensuring the accuracy of the correspondence between data and the comprehensiveness and integrity of the data, so as to provide a rich data foundation for improving subsequent grassland decision simulation.

[0080] Example 3: Based on Example 1, the intelligent decision-making module, such as Figure 3 As shown, it includes:

[0081] The scheme input unit is used by managers to input grassland restoration management schemes and generate preset grassland restoration management scheme information.

[0082] The environmental data analysis unit is used to determine the current grassland land parameters and vegetation data of the treated area based on the latest grassland geomorphology data.

[0083] The decision simulation unit is used to simulate grassland restoration based on current grassland land parameters and vegetation data, and through a dynamic grassland restoration prediction model, simulate grassland restoration according to different preset grassland restoration management schemes, obtain grassland restoration trends corresponding to different preset grassland restoration management schemes, and determine the final grassland management effect based on the grassland restoration trends.

[0084] The beneficial effects of the above technical solution are as follows: In this invention, managers input grassland restoration management plans through the plan input unit, generating preset grassland restoration management plan information to provide a basis for macro-simulation. The environmental data analysis unit, based on the latest grassland geomorphological data, determines the current grassland land parameters and vegetation data of the managed area, achieving the parsing and preliminary analysis of grassland ground data. Subsequently, the decision simulation unit, based on the current grassland land parameters and vegetation data, uses a dynamic grassland restoration prediction model to simulate grassland restoration according to different preset grassland restoration management plans, obtaining the grassland restoration trends corresponding to different preset grassland restoration management plans. Based on these grassland restoration trends, the final grassland management effect can be determined. A comprehensive comparison of the management effects of each plan under different dimensions, such as vegetation restoration speed and soil improvement degree, is possible. This helps managers clearly understand the advantages and disadvantages of each plan, providing intuitive data support for selecting the best plan. It also helps to formulate restoration strategies that better suit the actual geological and environmental conditions of the grassland, avoiding the waste of resources and time caused by blind attempts.

[0085] Example 4: Based on Example 3, the decision simulation unit includes:

[0086] The scene data acquisition subunit is used to collect data from various IoT sensors, biological activity data, grassland remote sensing full images, and local remote sensing images of each sub-region in the area to be managed.

[0087] The information extraction subunit is used to perform grayscale processing on the whole image of the grassland remote sensing and the local remote sensing images corresponding to each sub-region to obtain grayscale processed images, and to extract grassland vegetation information based on the grayscale processed images and the original color images to obtain grassland vegetation information.

[0088] Based on big data, environmental change data of the treated area within a preset number of years is obtained, and meteorological change data corresponding to various weather conditions under different solar terms in the treated area are determined.

[0089] The model establishes a sub-unit, which is used to determine the species information, their corresponding distribution, and species migration within the governed area based on biological activity data.

[0090] Based on grassland vegetation information, species information and their corresponding distribution, the point cloud distribution of each sub-region within the treated area is determined, and a three-dimensional grassland scene is established.

[0091] The system acquires global remote sensing images of the treated area within a preset number of years. Based on these images, it determines the impact of meteorological changes on grassland species migration and grassland vegetation growth. Simultaneously, it acquires changes in various grassland IoT sensors corresponding to different grassland vegetation growth states. The system then determines and sets the correlation of the dynamic parameters of the original three-dimensional scene to generate a dynamic grassland model.

[0092] Based on the target grassland restoration data, a dynamic grassland model is restored, and a dynamic grassland restoration prediction model is generated.

[0093] The beneficial effects of the above technical solution are as follows: This invention collects data from various IoT sensors, biological activity data, and full and partial remote sensing images of grassland through a scene data acquisition subunit, covering environmental perception, biological dynamics, and macroscopic and microscopic geomorphological information. This provides a more comprehensive understanding of the treated area and a rich data foundation for subsequent analysis. Furthermore, the information extraction subunit processes the remote sensing images in grayscale and combines them with the original color images to extract grassland vegetation information. This processing method highlights vegetation characteristics and improves the accuracy of information extraction. Grayscale processing enhances the contrast between vegetation and background, enabling more accurate identification of vegetation types and coverage, providing crucial data for subsequent grassland ecosystem assessments. Big data analysis of environmental changes within a predetermined timeframe in the managed area, along with meteorological data for different seasons and weather conditions, helps to understand the long-term dynamics of grassland environmental changes and meteorological variations under different seasons, providing a basis for developing targeted management measures. By establishing sub-units based on biological activity data to determine species information, distribution, and migration patterns, the health of the ecosystem and the impact of biological activity factors on grassland restoration are assessed. Subsequently, grassland vegetation and species information are used to determine the point cloud distribution of each sub-region, creating a three-dimensional grassland scene. This provides an effective means to visually represent the grassland ecosystem, more realistically reflecting its spatial structure and helping decision-makers to make more comprehensive assessments. Understanding the current state of grasslands provides visual support for developing reasonable governance plans. Then, by acquiring global remote sensing images within a preset timeframe, the impact of meteorological changes on species migration and vegetation growth is analyzed. Furthermore, by combining data from IoT sensors, the correlation of dynamic grassland model parameters is determined, enabling the model to simulate the dynamic processes of grassland ecosystem changes over time and the environment. This allows for more accurate prediction of grassland development trends under different conditions, providing a powerful tool for developing scientific governance strategies. Finally, based on target grassland governance and restoration data, the dynamic grassland model is restored to generate a dynamic grassland restoration prediction model. This model provides a foundation for simulating different grassland restoration and management schemes. It can predict the effects of grassland restoration based on different governance schemes, helping decision-makers to assess the feasibility and expected outcomes of various schemes in advance, thereby selecting the optimal governance strategy. This improves the efficiency and success rate of grassland governance and effectively promotes the restoration and protection of the grassland ecological environment.

[0094] Example 5: Based on Example 4, the model establishes sub-units, which also include:

[0095] The dynamic model refinement sub-unit is used to collect historical grassland management plans and their corresponding historical grassland management and restoration data based on big data.

[0096] Based on the geographical location data and environmental data of the grasslands corresponding to the historical grassland management schemes, the historical grassland restoration data are clustered to obtain multiple grassland restoration data groups. The grassland restoration data group with the highest similarity to the geographical location data and environmental data of the managed area is taken as the target data group.

[0097] Based on historical grassland management plans, the target data group was divided into multiple target sub-data groups;

[0098] The historical IoT data corresponding to the target data subgroups are input into the dynamic grassland restoration prediction model for simulation training to obtain grassland simulated restoration data. The grassland simulated restoration data is then compared with the grassland vegetation change data of the target data group to obtain data for improving the solution.

[0099] Multiple target sub-data groups are obtained to obtain scheme improvement data, a training set is established, and the dynamic grassland model is iteratively trained based on the training set to obtain the dynamic grassland restoration prediction model corresponding to the treated area.

[0100] In this embodiment, the improved data refers to the difference between the grassland landform data and the historical grassland management schemes, which are considered non-interference data (historical IoT data corresponding to the target data subgroup).

[0101] The beneficial effects of the above technical solution are as follows: This invention collects historical grassland management schemes and their corresponding historical grassland management and restoration data based on big data; based on the geographical location data and environmental data of the grasslands corresponding to the historical grassland management schemes, the historical grassland restoration data is clustered to obtain multiple grassland restoration data groups; the grassland restoration data group with the highest similarity to the geographical location data and environmental data corresponding to the managed area is selected as the target data group; and according to the historical grassland management schemes, the target data group is further divided into multiple target sub-data groups; the historical IoT data corresponding to each target data sub-group is input into a dynamic grassland restoration prediction model for simulation training to obtain simulated grassland restoration data. The data is obtained by comparing simulated grassland restoration data with grassland vegetation change data of the target data group to obtain scheme improvement data; scheme improvement data corresponding to multiple target sub-data groups are obtained respectively, and a training set is established. Based on the training set, the dynamic grassland model is iteratively trained to obtain a dynamic grassland restoration prediction model corresponding to the managed area. This provides a basis for simulating different grassland restoration management schemes. The model can predict the effect of grassland restoration according to different management schemes, helping decision-makers to assess the feasibility and expected results of various schemes in advance, thereby selecting the optimal management strategy, which is conducive to improving the efficiency and success rate of grassland management and effectively promoting the restoration and protection of grassland ecological environment.

[0102] Example 6: Based on Example 1, the decision filtering module, such as Figure 4As shown, it includes:

[0103] The first evaluation unit is used to compare the governance effects of different grassland restoration and management schemes, obtain a ranking sequence of effects, and score each different grassland restoration and management scheme in the ranking sequence according to the expected governance effects to obtain the scheme score results.

[0104] The second evaluation unit is used to evaluate the sustainable development rate of the governance effect based on the changes in grassland land parameters during the simulation process, and obtain the effect maintenance score.

[0105] The decision screening unit is used to screen and combine grassland restoration management plans based on the plan scoring results and the effect maintenance score, to obtain the best grassland restoration management plan and the best combination plan, and recommend them to the managers.

[0106] The beneficial effects of the above technical solution are as follows: The present invention compares the governance effects of different grassland restoration and management schemes through the first evaluation unit, generates an effect ranking sequence, makes the advantages and disadvantages of each scheme clear at a glance, and provides a clear framework for subsequent evaluation, helping decision-makers to quickly determine the position of different grassland restoration and management schemes in the overall governance effect evaluation, and score the ranked schemes according to the expected governance effects to obtain the scheme scoring results. This quantitative assessment method makes comparisons between schemes more precise, avoiding the ambiguity of subjective judgment. Simultaneously, the second assessment unit evaluates the sustainability rate of the restoration effect based on changes in grassland land parameters during the simulation process, thus obtaining an effect maintenance score. It goes beyond short-term restoration results, considering the long-term stability of grassland restoration management schemes for grassland ecosystem restoration. For example, by monitoring changes in land parameters such as soil fertility and soil structure, it determines whether the restoration scheme will have a long-term positive impact on grassland land or only bring short-term superficial improvements, ensuring the comprehensiveness and long-term nature of the assessment. Finally, the decision-making screening unit selects and combines grassland restoration management schemes based on the scheme score and effect maintenance score. Through a comprehensive evaluation of the scheme's effectiveness and sustainability, schemes that are both effective in the short term and guarantee long-term sustainable development can be selected. Managers no longer need to spend a lot of time and energy analyzing the advantages and disadvantages of numerous schemes; they can directly refer to the recommended results, greatly improving decision-making efficiency and quality, ensuring that grassland restoration work proceeds in the most favorable direction, and effectively promoting the healthy development of the grassland ecosystem.

[0107] Example 7: Based on Example 6, the first evaluation unit includes:

[0108] The sorting subunit is used to sort the governance effects of different grassland restoration and management schemes based on the grassland coverage corresponding to different grassland restoration and management schemes, and obtain the effect ranking sequence.

[0109] The scheme evaluation subunit is used to obtain the expected governance effect of the treated area at different governance stages. According to the stage allocation of the expected quality effect, the governance process of different grassland restoration management schemes is divided into multiple stages, and the grassland restoration sub-effect corresponding to each stage is determined. The grassland restoration sub-effect is compared with its corresponding expected governance effect to obtain the difference in vegetation coverage and the difference in vegetation growth status.

[0110] The differences in vegetation coverage and vegetation growth status are respectively divided into percentages to obtain vegetation coverage scores and vegetation growth status scores. These scores are then added together to obtain grassland restoration scores for each stage of different grassland restoration management schemes. The average score of grassland restoration scores for each stage of the same grassland restoration management scheme is calculated as the scheme score corresponding to the grassland restoration management scheme.

[0111] The beneficial effects of the above technical solution are as follows: This invention sorts the governance effects of different grassland restoration management schemes according to the grassland coverage rate through a sorting sub-unit, generating an effect ranking sequence. This allows managers and decision-makers to quickly and intuitively understand the relative performance of each scheme in increasing grassland coverage, and rapidly identify the schemes that are more effective in increasing vegetation cover area. This provides a clear preliminary framework for subsequent evaluation and decision-making. The scheme evaluation sub-unit refines the governance process of each scheme into multiple stages based on the expected governance effects of the governed area at different stages, and determines the grassland restoration sub-effects of each stage. This fully considers the dynamic and stage-specific characteristics of grassland restoration, avoiding the problem of ignoring the actual progress of each stage while only evaluating the overall situation (for example, in the early stage of grassland restoration, more attention is paid to the germination and survival of vegetation; while in the later stage, more attention may be paid to the healthy growth of vegetation and community stability). This allows for a more accurate grasp of each aspect. This study examines the implementation of the plan at different stages and compares the sub-effects of grassland restoration at each stage with the expected results. It obtains the differences in vegetation coverage and vegetation growth status, comprehensively reflecting the grassland restoration situation from both quantitative and qualitative perspectives. These two differences are then percentage-processed to obtain vegetation coverage and vegetation growth status scores, which are summed to derive the grassland restoration score for each stage. This quantitative assessment of grassland restoration provides a clear and quantitative result of the effectiveness of different grassland restoration management measures at different stages, effectively avoiding the ambiguity of subjective judgment. It comprehensively and meticulously reflects the overall performance of the plan in promoting vegetation coverage growth and ensuring healthy vegetation growth. Finally, by calculating the average score of grassland restoration at each stage of the same grassland restoration management plan, the assessment results from different stages are integrated to form a unified quantitative indicator, providing a basis for selecting the plan that best meets the needs and expectations of the managed area.

[0112] Example 8: Based on Example 6, the second evaluation unit includes:

[0113] The effect assignment sub-unit is used to obtain the changes in grassland land parameters at different stages of different grassland restoration and management schemes. Any treatment stage is taken as the target treatment stage, and the initial grassland land parameters of the target treatment stage are compared with the final grassland land parameters to determine whether the grassland soil quality corresponding to the target treatment stage has improved.

[0114] If so, then assign a value of 1 to the sustainable development status of the target governance stage;

[0115] Otherwise, the sustainable development status of the target governance stage will be assigned a value of 1 to 0;

[0116] The effect evaluation sub-unit is used to obtain all target governance stages with a value of 1, determine the sustainable development rate corresponding to different grassland restoration and management schemes, obtain the maximum number of consecutive target governance stages with a value of 1 for different grassland restoration and management schemes, and obtain the maximum improvement duration ratio.

[0117] Based on the maximum improvement duration ratio and combined with the preset effective index list, the effective index of different grassland restoration and management schemes is determined respectively.

[0118] Based on the effectiveness index and sustainable development rate of the proposed schemes, the effectiveness maintenance scores corresponding to different grassland restoration and management schemes are obtained.

[0119] In this embodiment, the sustainable development rate refers to the ratio of the target governance stage with a sustainable development status value of 1 to the total number of governance stages of the corresponding grassland restoration and management scheme.

[0120] In this embodiment, the maximum improvement duration ratio refers to the ratio of the maximum consecutive number to the total number of governance stages corresponding to the same grassland restoration management plan. The maximum consecutive number refers to the maximum number of consecutive governance stages with a value of 1 adjacent to the target governance stage.

[0121] In this embodiment, the preset effective index list refers to the reference list of effective indices of schemes stored in the system in advance. Different ranges of maximum improvement duration ratio correspond to different effective indices of schemes. The index can be set according to the requirements of the sustainability of grassland management effect. For example, when the maximum improvement duration ratio is between (0, 0.5], the effective index of scheme is 0.75; when the maximum improvement duration ratio is between (0.5, 0.8], the effective index of scheme is 1.2; and when the maximum improvement duration ratio is between (0.8, 1], the effective index of scheme is 1.5.

[0122] The beneficial effects of the above technical solution are as follows: This invention compares grassland land parameters at the beginning and end of the target governance stage through an effect assignment sub-unit to determine whether the grassland soil quality has improved, and assigns a value of 0-1 accordingly. This transforms the complex ecological phenomenon of soil quality change into a simple and intuitive quantitative indicator, making it easy to identify and compare soil quality improvement at different governance stages. Then, through the effect evaluation sub-unit, the target governance stages assigned a value of 1 are statistically analyzed to determine the sustainable development rate of different grassland restoration and management schemes. This reflects the proportion of soil quality improvement stages in the entire governance process of different grassland restoration and management schemes, and can intuitively demonstrate the degree of contribution of the scheme to the sustainable development of the grassland ecosystem. A higher sustainable development rate means that the scheme can achieve soil quality improvement in most stages, which is conducive to maintaining the long-term stability of the grassland ecosystem. Subsequently, the maximum continuity number of target governance stages assigned a value of 1 for different grassland restoration and management schemes is obtained, yielding the maximum improvement duration ratio, emphasizing the continuity of soil quality improvement. Compared with the simple sustainable development rate, this better reflects the stability and effectiveness of the scheme in the actual implementation process. For example, two schemes may have the same sustainable development rate, but one scheme's soil quality improvement phases are more dispersed, while the other's are concentrated and continuous. Obviously, the latter has a greater advantage in maintaining the trend of grassland ecological improvement. The maximum improvement duration ratio can effectively distinguish this difference. Then, based on the maximum improvement duration ratio and the pre-set scheme effectiveness index list, the scheme effectiveness index corresponding to different grassland restoration and management schemes is determined. Taking into account the continuity of improvement and the pre-set scheme evaluation criteria, a comprehensive evaluation of the schemes' overall performance in soil quality improvement is achieved within a relatively unified framework. Finally, based on the scheme effectiveness index and sustainable development rate, the effect maintenance score corresponding to different grassland restoration and management schemes is obtained. This comprehensively considers multiple key factors such as the continuity of soil quality improvement, overall sustainability, and conformity with pre-set standards, ensuring that schemes that can not only improve grassland soil quality in the short term but also maintain it in the long term and have good implementation continuity can be selected from among many grassland restoration and management schemes, thereby improving the quality and long-term benefits of grassland restoration work.

[0123] Example 9: Based on Example 6, the decision screening unit includes:

[0124] The recommended filtering sub-unit is used to obtain the preset weights corresponding to the scheme scoring results and the effect maintenance score, respectively. Based on the scheme scoring results and their corresponding preset weights and the effect maintenance score and their corresponding preset weights for each grassland restoration management scheme, the final score for each grassland restoration management scheme is obtained.

[0125] The grassland restoration and management plan with the highest final score will be considered the best grassland restoration and management plan.

[0126] The decision-making intelligent combination subunit is used to obtain the grassland restoration score and sustainable development status assignment results corresponding to each stage of different grassland restoration management schemes, and compare and filter them to obtain a preset number of high-quality grassland restoration schemes corresponding to each governance stage.

[0127] Based on the conversion cost between different grassland restoration and management schemes, a preset number of high-quality grassland restoration schemes for each governance stage are intelligently combined to generate the optimal combination scheme.

[0128] The recommended interactive sub-unit is used to send the best grassland restoration management plan, the scoring results of each grassland restoration management plan, and the best combination plan to the managers.

[0129] In this embodiment, the preset weights can be flexibly set, and the emphasis on different short-term effects and long-term sustainability can be adjusted flexibly, so that the evaluation results can better meet the complex needs of grassland management. For example, in grassland areas with fragile ecosystems and in urgent need of short-term improvement, the weight of the scheme scoring results can be appropriately increased; while in areas that focus on long-term ecological balance, the weight of the effect maintenance score can be increased.

[0130] In this embodiment, a high-quality grassland restoration plan refers to a comprehensive evaluation of the sub-plans at each stage of different grassland restoration management plans based on grassland restoration scores and sustainable development status assignments. Then, multiple sub-plans at each governance stage are compared, and a predetermined number (greater than or equal to 3) of sub-plans with high comprehensive scores are selected as the high-quality grassland restoration plan for the corresponding governance stage.

[0131] The beneficial effects of the above technical solution are as follows: This invention sets preset weights for the scheme scoring results and effect maintenance scores by recommending and screening sub-units, and calculates the final score of each grassland restoration management scheme based on these weights. It comprehensively considers the short-term effectiveness (scheme scoring results) and long-term sustainability (effect maintenance score) of the schemes, avoiding the one-sidedness of making decisions based solely on a single indicator. Finally, the scheme with the highest final score is determined as the optimal grassland restoration management scheme, providing decision-makers with a scientific and quantitative optimal choice. Furthermore, by comparing and screening the grassland restoration scores and sustainable development status assignments of different grassland restoration management schemes at various stages through the decision-making intelligent combination sub-unit, a preset number of high-quality grassland restoration schemes are obtained for each governance stage. This fully considers the stage-specific characteristics of the grassland restoration process, as different stages may have different focuses and needs, ensuring that a relatively optimal scheme is selected at each stage. Then, based on the conversion costs between different schemes, the high-quality schemes at each stage are intelligently combined to generate the optimal combination scheme, making the generated optimal combination scheme more practical and economical. For example, while some solutions may perform well in a single phase, the cost of switching to solutions in other phases may be too high. By comprehensively considering the switching costs, such solutions can be avoided, thus forming an optimal combination solution that is seamlessly integrated across phases, cost-effective, and yields excellent overall results. Through the recommendation and interaction sub-unit, the best grassland restoration management solution, the scoring results of each solution, and the optimal combination solution are sent to managers. Managers do not need to manually organize and analyze large amounts of complex data to fully understand the advantages and disadvantages of each solution and the overall optimal choice. This one-stop information delivery method greatly improves decision-making efficiency, enabling managers to make scientific decisions quickly based on accurate and comprehensive information. At the same time, the detailed scoring results also facilitate managers in explaining the basis of their decisions, ensuring the smooth progress of grassland restoration management.

[0132] Example 10: This invention provides a smart decision-making method for grassland restoration based on satellite remote sensing and the Internet of Things, such as... Figure 5 As shown, it includes:

[0133] Acquire satellite remote sensing data and grassland environmental data from IoT sensors in the area to be treated, and integrate the data to obtain grassland landform data of the area to be treated.

[0134] Based on grassland geomorphological data, a dynamic grassland restoration prediction model was used to simulate different grassland restoration and management schemes, and the governance effects of each grassland restoration and management scheme were obtained.

[0135] Based on the governance effects, each grassland restoration and management plan was evaluated to obtain the best grassland restoration and management plan and the best combination plan, which were then recommended to the managers.

[0136] The beneficial effects of the above technical solution are as follows: First, this invention acquires satellite remote sensing data and grassland environmental data from IoT sensors in the treated area. Then, it integrates this data to obtain grassland geomorphological data for the treated area, achieving automatic data processing and ensuring the accuracy of data correspondences and the comprehensiveness and integrity of the data. This provides a rich data foundation for subsequent grassland decision-making simulations. Next, based on the grassland geomorphological data, a dynamic grassland restoration prediction model is used to simulate different grassland restoration management schemes, obtaining the governance effects of each scheme. This allows for a comprehensive comparison of the governance effects of each scheme across different dimensions, such as vegetation restoration speed and soil improvement, which helps managers clearly understand the effects of each scheme. The advantages and disadvantages of each plan provide intuitive data support for selecting the best solution, helping to formulate restoration strategies that are more in line with the actual geological and environmental conditions of the grassland, avoiding the waste of resources and time caused by blind attempts. Finally, based on the governance effect, each grassland restoration management plan is evaluated to obtain the best grassland restoration management plan and the best combination plan, which are recommended to managers. This greatly reduces the information burden and uncertainty in the decision-making process, provides managers with a scientific basis for decision-making, helps to accurately plan, implement and manage grassland restoration projects, achieve the goal of optimizing resource allocation and adapting grassland governance plans to local conditions, improve grassland restoration efficiency and success rate, and effectively improve the efficiency and quality of grassland governance decision-making to achieve the sustainable development of grassland ecosystems.

[0137] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A smart decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things, characterized in that, include: The data integration module is used to acquire satellite remote sensing data and grassland environmental data from IoT sensors in the treated area, and to integrate the data to obtain grassland landform data of the treated area. The intelligent decision-making module is used to simulate different grassland restoration and management schemes based on grassland geomorphological data and a dynamic grassland restoration prediction model, obtaining the governance effects of each scheme, including: The scheme input unit is used by managers to input grassland restoration management schemes and generate preset grassland restoration management scheme information. The environmental data analysis unit is used to determine the current grassland land parameters and vegetation data of the treated area based on the latest grassland geomorphology data. The decision simulation unit is used to simulate grassland restoration based on current grassland land parameters and vegetation data, using a dynamic grassland restoration prediction model to simulate grassland restoration according to different preset grassland restoration management schemes, obtain grassland restoration trends corresponding to different preset grassland restoration management schemes, and determine the final grassland management effect based on the grassland restoration trends, including: The scene data acquisition subunit is used to collect data from various IoT sensors, biological activity data, grassland remote sensing full images, and local remote sensing images of each sub-region in the area to be managed. The information extraction subunit is used to perform grayscale processing on the whole image of the grassland remote sensing and the local remote sensing images corresponding to each sub-region to obtain grayscale processed images, and to extract grassland vegetation information based on the grayscale processed images and the original color images to obtain grassland vegetation information. Based on big data, environmental change data of the treated area within a preset number of years is obtained, and meteorological change data corresponding to various weather conditions under different solar terms in the treated area are determined. The model establishes a sub-unit, which is used to determine the species information, their corresponding distribution, and species migration within the governed area based on biological activity data. Based on grassland vegetation information, species information and their corresponding distribution, the point cloud distribution of each sub-region within the treated area is determined, and a three-dimensional grassland scene is established. Global remote sensing images of the treated area within a preset number of years are acquired. Based on the remote sensing images, the impact of meteorological changes on grassland species migration and grassland vegetation growth is determined. At the same time, changes of various grassland IoT sensors corresponding to different grassland vegetation generation states are acquired. The correlation of dynamic parameters of grassland three-dimensional scene is determined and set to generate a dynamic grassland model. Based on the target grassland restoration data, a dynamic grassland model is restored, and a dynamic grassland restoration prediction model is generated. The decision-making and screening module is used to evaluate various grassland restoration and management schemes based on their governance effects, obtain the optimal grassland restoration and management scheme and the best combination scheme, and recommend them to managers, including: The first evaluation unit is used to compare the governance effects of different grassland restoration and management schemes, obtain a ranking sequence of effects, and score each different grassland restoration and management scheme in the ranking sequence according to the expected governance effects to obtain the scheme score results. The second evaluation unit is used to evaluate the sustainable development rate of the governance effect based on the changes in grassland land parameters during the simulation process, and obtain the effect maintenance score. The decision screening unit is used to screen and combine grassland restoration management plans based on the plan scoring results and effect maintenance scores, to obtain the best grassland restoration management plan and the best combination plan, and recommend them to the managers.

2. The intelligent decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things as described in claim 1, characterized in that, The data integration module includes: The remote sensing data storage unit is used to collect satellite remote sensing data of the area to be governed at a first preset frequency and store the satellite remote sensing data in chronological order. The sensor data storage unit is used to collect IoT sensor data of the managed area at a second preset frequency, and store the IoT sensor data based on the time axis order and the type of IoT sensor. The real-time data integration unit is used to determine the time correspondence between satellite remote sensing data and Internet of Things sensor data based on the frequency time difference between the first preset frequency and the second preset frequency. Based on the time correspondence, the correspondence between the storage files corresponding to satellite remote sensing data and IoT sensor data is determined, and grassland landform data corresponding to different time periods in the treated area are obtained.

3. The intelligent decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things as described in claim 1, characterized in that, The model building sub-units also include: The dynamic model refinement sub-unit is used to collect historical grassland management plans and their corresponding historical grassland management and restoration data based on big data. Based on the geographical location data and environmental data of the grasslands corresponding to the historical grassland management schemes, the historical grassland management and restoration data are clustered to obtain multiple grassland restoration data groups. The grassland restoration data group with the highest similarity to the geographical location data and environmental data corresponding to the managed area is taken as the target data group. Based on historical grassland management plans, the target data group was divided into multiple target sub-data groups; The historical IoT data corresponding to the target sub-data group are input into the dynamic grassland restoration prediction model for simulation training to obtain grassland simulated restoration data. The grassland simulated restoration data is then compared with the grassland vegetation change data of the target data group to obtain data for improving the solution. Multiple target sub-data groups are obtained to obtain scheme improvement data, a training set is established, and the dynamic grassland model is iteratively trained based on the training set to obtain the dynamic grassland restoration prediction model corresponding to the treated area.

4. The intelligent decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things as described in claim 1, characterized in that, The first evaluation unit includes: The sorting subunit is used to sort the governance effects of different grassland restoration and management schemes based on the grassland coverage corresponding to different grassland restoration and management schemes, and obtain the effect ranking sequence. The scheme evaluation subunit is used to obtain the expected governance effect of the treated area at different governance stages. According to the stage allocation of the expected quality effect, the governance process of different grassland restoration management schemes is divided into multiple stages, and the grassland restoration sub-effect corresponding to each stage is determined. The grassland restoration sub-effect is compared with its corresponding expected governance effect to obtain the difference in vegetation coverage and the difference in vegetation growth status. The differences in vegetation coverage and vegetation growth status are respectively divided into percentages to obtain vegetation coverage scores and vegetation growth status scores. These scores are then added together to obtain grassland restoration scores for each stage of different grassland restoration management schemes. The average score of grassland restoration scores for each stage of the same grassland restoration management scheme is calculated as the scheme score corresponding to the grassland restoration management scheme.

5. The intelligent decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things as described in claim 1, characterized in that, The second evaluation unit includes: The effect assignment sub-unit is used to obtain the changes in grassland land parameters at different stages of different grassland restoration and management schemes. Any treatment stage is taken as the target treatment stage, and the initial grassland land parameters of the target treatment stage are compared with the final grassland land parameters to determine whether the grassland soil quality corresponding to the target treatment stage has improved. If so, then assign a value of 1 to the sustainable development status of the target governance stage; Otherwise, the sustainable development status of the target governance stage will be assigned a value of 0; The effect evaluation sub-unit is used to obtain all target governance stages with a value of 1, determine the sustainable development rate corresponding to different grassland restoration and management schemes, obtain the maximum number of consecutive target governance stages with a value of 1 for different grassland restoration and management schemes, and obtain the maximum improvement duration ratio. Based on the maximum improvement duration ratio and combined with the preset effective index list, the effective index of different grassland restoration and management schemes is determined respectively. Based on the effectiveness index and sustainable development rate of the proposed schemes, the effectiveness maintenance scores corresponding to different grassland restoration and management schemes are obtained.

6. The intelligent decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things according to claim 1, characterized in that, The decision screening unit includes: The recommended filtering sub-unit is used to obtain the preset weights corresponding to the scheme scoring results and the effect maintenance score, respectively. Based on the scheme scoring results and their corresponding preset weights and the effect maintenance score and their corresponding preset weights for each grassland restoration management scheme, the final score for each grassland restoration management scheme is obtained. The grassland restoration and management plan with the highest final score will be considered the best grassland restoration and management plan. The decision-making intelligent combination subunit is used to obtain the grassland restoration score and sustainable development status assignment results corresponding to each stage of different grassland restoration management schemes, and compare and filter them to obtain a preset number of high-quality grassland restoration schemes corresponding to each governance stage. Based on the conversion cost between different grassland restoration and management schemes, a preset number of high-quality grassland restoration schemes for each governance stage are intelligently combined to generate the optimal combination scheme. The recommended interactive sub-unit is used to send the best grassland restoration management plan, the scoring results of each grassland restoration management plan, and the best combination plan to the managers.

7. A smart decision-making method for grassland restoration based on satellite remote sensing and the Internet of Things, applied to the smart decision-making system for grassland restoration based on satellite remote sensing and the Internet of Things as described in claim 1, characterized in that, include: Acquire satellite remote sensing data and grassland environmental data from IoT sensors in the area to be treated, and integrate the data to obtain grassland landform data of the area to be treated. Based on grassland geomorphological data, a dynamic grassland restoration prediction model was used to simulate different grassland restoration and management schemes, and the governance effects of each grassland restoration and management scheme were obtained. Based on the effectiveness of the restoration efforts, each grassland restoration and management plan was evaluated to determine the optimal grassland restoration and management plan and the best combination of plans, which were then recommended to managers. These included: The governance effects of different grassland restoration and management schemes are compared to obtain a ranking sequence of effects. Based on the expected governance effects, each different grassland restoration and management scheme in the ranking sequence is scored to obtain the scheme scoring results. Based on the changes in grassland land parameters during the simulation process, the sustainable development rate of the governance effect is evaluated, and an effect maintenance score is obtained. Based on the scheme scoring results and the effect retention score, grassland restoration management schemes are screened and combined to obtain the best grassland restoration management scheme and the best combination scheme, which are then recommended to the managers.

Images