Grassland recovery state dynamic monitoring system and method based on multi-scale fusion

Abstract

The invention provides a grassland recovery state dynamic monitoring system and method based on multi-scale fusion, and the system comprises a multi-scale data obtaining module which is used for obtaining macro monitoring data of a grassland through a satellite remote sensing technology, and obtaining micro monitoring data of the grassland through an unmanned plane; the long-time sequence data analysis module is used for collecting macroscopic monitoring data and microscopic monitoring data in a long time, forming a time sequence, performing fusion analysis, and determining an actual growth state and a recovery effect of the grassland; and the prediction and strategy adjustment module is used for predicting the grassland growth trend and adjusting the grassland recovery strategy based on the grassland actual growth and recovery effects in combination with the actual grassland environment data and the historical time sequence. A dynamic monitoring system is established by combining macro monitoring of satellite remote sensing and micro monitoring of an unmanned aerial vehicle, precise monitoring and prediction of the grassland growth trend are achieved, and timely and accurate data support is provided for management personnel to adjust a recovery strategy.

Description

Technical Field

[0001] The present invention relates to the field of satellite navigation positioning monitoring technology, and in particular to a grassland restoration status dynamic monitoring system and method based on multi-scale fusion. Background Art

[0002] As a vital component of terrestrial ecosystems, grassland ecological restoration is crucial for maintaining ecological balance and promoting the development of animal husbandry. Traditional grassland monitoring methods suffer from limited coverage and insufficient accuracy, making them inadequate for comprehensive, dynamic monitoring and accurate prediction of grassland restoration. Advances in satellite remote sensing and drone technology have provided new avenues for grassland monitoring. However, effectively integrating these diverse data scales to enable scientific assessment and accurate prediction of grassland restoration remains a pressing challenge. Summary of the Invention

[0003] The present invention provides a system and method for dynamic monitoring of grassland restoration status based on multi-scale fusion. By combining macro-monitoring through satellite remote sensing and micro-monitoring through drones, a dynamic monitoring system is established to achieve accurate monitoring and prediction of grassland growth trends, providing reliable data support for the adjustment of grassland restoration strategies.

[0004] The present invention provides a grassland restoration status dynamic monitoring system based on multi-scale fusion, comprising:

[0005] Multi-scale data acquisition module, used to obtain macro-monitoring data of grasslands using satellite remote sensing technology, and simultaneously obtain micro-monitoring data of grasslands using drones;

[0006] A long-term data series analysis module is used to collect macro-monitoring data and micro-monitoring data over a long period of time to form a time series, and to perform fusion analysis on the data in the current time series to determine the actual growth status and restoration effect of the grassland;

[0007] The prediction and strategy adjustment module is used to predict grassland growth trends based on the actual growth and restoration effects of grasslands, combined with actual grassland environmental data and historical time series, and adjust grassland restoration strategies based on the predictions.

[0008] Preferably, a grassland restoration status dynamic monitoring system based on multi-scale fusion includes:

[0009] A macro data acquisition unit is used to collect panoramic images of grasslands and non-panoramic large-area grassland images using satellite remote sensing technology to generate macro monitoring data;

[0010] The micro-data acquisition unit is used to use drones to collect detailed images of local areas of the grassland and generate micro-monitoring data.

[0011] Preferably, in a grassland restoration status dynamic monitoring system based on multi-scale fusion, the multi-scale data acquisition module includes:

[0012] A time series generation unit is used to store macro-monitoring data and micro-monitoring data based on the time axis sequence and generate a time series;

[0013] The sequence data fusion unit is used to extract features from the macro-monitoring data and micro-monitoring data in the time series respectively to obtain grassland landform features and vegetation features. Based on the corresponding relationship of the collection area, the grassland landform features and vegetation features are fused to obtain the current fused feature image;

[0014] A fusion data analysis unit is used to analyze the current fusion feature image to determine the actual growth situation and growth status of grassland vegetation;

[0015] The actual growth of grassland vegetation is compared with the actual growth corresponding to the previous fused feature image to determine the restoration effect of the grassland.

[0016] Preferably, in a grassland restoration status dynamic monitoring system based on multi-scale fusion, the sequence data fusion unit includes:

[0017] The macro feature extraction subunit is used to perform edge detection processing on the grassland panoramic image and the non-panoramic large area image in the macro monitoring data, and obtain the texture features and color features of the grassland panoramic image and the non-panoramic large area image respectively;

[0018] The macro feature fusion subunit is used to fuse the texture features and color features of the non-panoramic large area image with the grassland panoramic image based on the acquisition area of ​​the non-panoramic large area image to obtain a primary panoramic image;

[0019] The micro-feature extraction subunit is used to extract features from the detail images corresponding to the micro-monitoring data to obtain grassland landforms and vegetation detail features;

[0020] The macro feature extraction subunit is used to determine the regional correspondence between the detail image and the primary panoramic image based on the texture features of the primary panoramic image and the shooting position of the micro monitoring data. Based on the prime number region correspondence, the grassland landform and vegetation detail features of the detail image are fused with the corresponding area of ​​the primary panoramic image to obtain a fused feature image.

[0021] Preferably, in a grassland restoration status dynamic monitoring system based on multi-scale fusion, the fusion data analysis unit includes:

[0022] The grassland feature extraction unit is used to extract features from the current fused feature image to obtain the landform features and vegetation features of the grassland;

[0023] The vegetation determination unit is used to determine the landform distribution of grassland based on grassland landform characteristics, and to determine the vegetation information corresponding to different landforms in combination with grassland management data;

[0024] a growth analysis unit, configured to determine the main vegetation types in each area of ​​the grassland based on the vegetation information and landform distribution, and obtain standard vegetation growth data corresponding to different vegetation types from a database based on the vegetation types;

[0025] Determine vegetation sub-features corresponding to each area of ​​the grassland respectively, determine the actual growth status of vegetation in each area based on the vegetation sub-features, and determine the growth status of vegetation in each area of ​​the grassland according to the actual vegetation conditions and standard vegetation growth data corresponding to the vegetation;

[0026] The effect determination unit is used to compare the actual growth of grassland vegetation with the actual growth corresponding to the previous fusion feature image, and obtain the growth differences corresponding to different grassland landforms;

[0027] Based on the growth differences and the actual growth status of each area, it is determined whether the vegetation growth trend of the grassland is good. If so, it is determined that the restoration effect of the current area is good;

[0028] Otherwise, based on the current solar term changes in the grassland and the corresponding vegetation growth data of each area, it is judged whether the current area's vegetation growth trend is normal;

[0029] If not, it is determined that the recovery effect of the current area is poor;

[0030] If so, the vegetation coverage rate of the current area is determined based on the fused feature image corresponding to the optimal vegetation growth state of the current area, and combined with the preset coverage rate threshold of the landform corresponding to the current area, it is judged whether the coverage rate of the current area meets the standard;

[0031] If the coverage rate of the current area meets the standard, it is determined that the recovery effect of the current area is good;

[0032] Otherwise, it is determined that the recovery effect of the current area is poor.

[0033] Preferably, in a grassland restoration status dynamic monitoring system based on multi-scale fusion, the prediction and strategy adjustment module includes:

[0034] The growth trend prediction unit is used to obtain the actual environmental data of the grassland and the historical time series. Based on the vegetation growth conditions of each area of ​​the grassland in the historical time series, the unit generates vegetation growth curves for each area and determines the vegetation growth dynamics of each area.

[0035] Based on the vegetation curve graph, combined with the current vegetation growth status, the growth trend of vegetation in each area of ​​the grassland and the change of grassland coverage are predicted;

[0036] The intelligent strategy adjustment unit is used to adjust the current grassland restoration strategy based on the growth trend and the change in grassland coverage, combined with the actual environmental data of the grassland.

[0037] Preferably, in a grassland restoration status dynamic monitoring system based on multi-scale fusion, the growth trend prediction unit includes:

[0038] The growth curve generation subunit is used to determine the vegetation height and vegetation color based on the vegetation growth situation, and predict the peak point corresponding to the optimal vegetation growth state of the vegetation in the corresponding area based on the vegetation height change and the reference height range corresponding to the optimal vegetation growth state of the corresponding vegetation;

[0039] Taking the peak point as the predicted peak value of the vegetation growth curve diagram of the corresponding area, and determining the time interval corresponding to the predicted peak value in combination with the time series generation time interval;

[0040] Based on the change in vegetation height, combined with the predicted peak value and its corresponding time interval, a vegetation growth curve for the corresponding area is generated, and the vegetation color at each point corresponding to the vegetation growth curve is marked;

[0041] The trend prediction subunit is used to obtain the direction vector corresponding to the end of the vegetation growth curve corresponding to each area, and obtain the predicted vegetation growth trend direction;

[0042] At the same time, target growth data corresponding to the target grassland vegetation is obtained based on the big data, and based on the target growth data, a first average growth rate or a second average decay rate of the target vegetation under the current solar term is determined;

[0043] Determining an actual average growth rate or an actual decay rate of the actual vegetation based on a vegetation growth curve corresponding to the target grassland vegetation, and comparing the first average growth rate with the actual average growth rate or the first average decay rate to obtain an environmental impact growth difference;

[0044] Intercepting a plurality of target curve segments corresponding to similar vegetation growth trends from the vegetation growth curve in the corresponding area, and calculating a second average growth rate or a second average decay rate corresponding to the plurality of target curve segments;

[0045] Based on the second average growth rate or the second average decay rate, combined with the environmental impact growth difference, the change of vegetation in the corresponding area in the predicted vegetation growth trend direction is determined to obtain the vegetation growth trend prediction result of the corresponding area.

[0046] The present invention provides a method for dynamic monitoring of grassland restoration status based on multi-scale fusion, comprising:

[0047] Step 1: Use satellite remote sensing technology to obtain macro-monitoring data of grasslands, and use drones to obtain micro-monitoring data of grasslands;

[0048] Step 2: Collect macro- and micro-monitoring data over a long period of time to form a time series, and perform fusion analysis on the data in the current time series to determine the actual growth status of the grassland and the restoration effect;

[0049] Step 3: Based on the actual growth and restoration effects of grasslands, combined with actual grassland environmental data and historical time series, predict grassland growth trends and adjust grassland restoration strategies based on the predictions.

[0050] Preferably, in a method for dynamic monitoring of grassland restoration status based on multi-scale fusion, step 2 includes:

[0051] Based on the time axis sequence, the macro-monitoring data and micro-monitoring data are stored to generate time series;

[0052] Feature extraction is performed on the macro-monitoring data and micro-monitoring data in the time series to obtain grassland landform features and vegetation features. Based on the corresponding relationship of the collection area, the grassland landform features and vegetation features are fused to obtain the current fused feature image;

[0053] Analyze the current fused feature image to determine the actual growth and status of grassland vegetation;

[0054] The actual growth of grassland vegetation is compared with the actual growth corresponding to the previous fused feature image to determine the restoration effect of the grassland.

[0055] Preferably, in a dynamic monitoring method for grassland restoration status based on multi-scale fusion, the current fused feature image is analyzed to determine the actual growth situation and growth status of grassland vegetation; and the actual growth situation of grassland vegetation is compared with the actual growth situation corresponding to the previous fused feature image to determine the restoration effect of the grassland, including:

[0056] Perform feature extraction on the current fused feature image to obtain the landform and vegetation features of the grassland;

[0057] Based on grassland landform characteristics, determine the landform distribution of grasslands, and combine grassland management data to determine the vegetation information corresponding to different landforms;

[0058] Based on the vegetation information and landform distribution, determining the main vegetation types in each area of ​​the grassland, and based on the vegetation types, obtaining standard vegetation growth data corresponding to different vegetation in a database;

[0059] Determine vegetation sub-features corresponding to each area of ​​the grassland respectively, determine the actual growth status of vegetation in each area based on the vegetation sub-features, and determine the growth status of vegetation in each area of ​​the grassland according to the actual vegetation conditions and standard vegetation growth data corresponding to the vegetation;

[0060] Compare the actual growth of grassland vegetation with the actual growth corresponding to the previous fusion feature image to obtain the growth differences corresponding to different grassland landforms;

[0061] Based on the growth differences and the actual growth status of each area, it is determined whether the vegetation growth trend of the grassland is good. If so, it is determined that the restoration effect of the current area is good;

[0062] Otherwise, based on the current solar term changes in the grassland and the corresponding vegetation growth data of each area, it is judged whether the current area's vegetation growth trend is normal;

[0063] If not, it is determined that the recovery effect of the current area is poor;

[0064] If so, the vegetation coverage rate of the current area is determined based on the fused feature image corresponding to the optimal vegetation growth state of the current area, and combined with the preset coverage rate threshold of the landform corresponding to the current area, it is judged whether the coverage rate of the current area meets the standard;

[0065] If the coverage rate of the current area meets the standard, it is determined that the recovery effect of the current area is good;

[0066] Otherwise, it is determined that the recovery effect of the current area is poor.

[0067] Compared with the prior art, the present invention has at least the following beneficial effects:

[0068] The present invention combines macroscopic monitoring by satellite remote sensing with microscopic monitoring by drones to conduct multi-scale, all-encompassing dynamic monitoring of grassland restoration. It collects macroscopic and microscopic monitoring data over a long period of time to form a time series. This data is then fused and analyzed to determine the actual growth status and recovery effect of the grassland. This comprehensive monitoring and automatic analysis of grassland restoration allows managers to quickly determine the actual growth status and recovery effect of the grassland. Finally, based on the actual growth and recovery effect of the grassland, combined with actual grassland environmental data and historical time series, grassland growth trends are predicted. This facilitates the timely identification of factors adverse to grassland restoration, provides timely and accurate data support for managers to adjust restoration strategies, and helps improve the efficiency and quality of grassland restoration, promoting the sustainable development of grassland ecosystems.

[0069] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in this application document.

[0070] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0072] Figure 1 This is a structural diagram of a grassland restoration status dynamic monitoring system based on multi-scale fusion according to the present invention;

[0073] Figure 2 This is a structural diagram of a multi-scale data acquisition module of a grassland restoration status dynamic monitoring system based on multi-scale fusion according to the present invention;

[0074] Figure 3 This is a structural diagram of a long-time series data analysis module of a grassland restoration status dynamic monitoring system based on multi-scale fusion according to the present invention;

[0075] Figure 4 This is a structural diagram of a prediction and strategy adjustment module of a grassland restoration status dynamic monitoring system based on multi-scale fusion according to the present invention;

[0076] Figure 5 This is a flow chart of a method for dynamic monitoring of grassland restoration status based on multi-scale fusion in the present invention. DETAILED DESCRIPTION

[0077] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0078] Example 1:

[0079] The present invention provides a grassland restoration status dynamic monitoring system based on multi-scale fusion, such as Figure 1 As shown, including:

[0080] Multi-scale data acquisition module, used to obtain macro-monitoring data of grasslands using satellite remote sensing technology, and simultaneously obtain micro-monitoring data of grasslands using drones;

[0081] A long-term data series analysis module is used to collect macro-monitoring data and micro-monitoring data over a long period of time to form a time series, and to perform fusion analysis on the data in the current time series to determine the actual growth status and restoration effect of the grassland;

[0082] The prediction and strategy adjustment module is used to predict grassland growth trends based on the actual growth and restoration effects of grasslands, combined with actual grassland environmental data and historical time series, and adjust grassland restoration strategies based on the predictions.

[0083] In this embodiment, a long time refers to a period of time that is greater than or equal to 72 hours.

[0084] The beneficial effects of the above technical solution are as follows: The present invention combines macroscopic monitoring by satellite remote sensing with microscopic monitoring by drones to conduct multi-scale, all-encompassing dynamic monitoring of grassland restoration. It also collects macroscopic and microscopic monitoring data over a long period of time to form a time series, and then performs a fusion analysis of the data within the current time series to determine the actual growth status and recovery effect of the grassland. This achieves comprehensive monitoring and simultaneous automatic analysis of grassland recovery, obtaining the actual growth status and recovery effect of the grassland, making it easier for managers to quickly determine the actual recovery status of the grassland. Finally, based on the actual growth and recovery effect of the grassland, combined with actual grassland environmental data and historical time series, grassland growth trends are predicted. This facilitates the timely identification of factors adverse to grassland recovery, provides timely and accurate data support for managers to adjust restoration strategies, helps improve the efficiency and quality of grassland restoration, and promotes the sustainable development of grassland ecosystems.

[0085] Example 2:

[0086] On the basis of Example 1, in a grassland restoration status dynamic monitoring system based on multi-scale fusion, a multi-scale data acquisition module, such as Figure 2 As shown, including:

[0087] A macro data acquisition unit is used to collect panoramic images of grasslands and non-panoramic large-area grassland images using satellite remote sensing technology to generate macro monitoring data;

[0088] The micro-data acquisition unit is used to use drones to collect detailed images of local areas of the grassland and generate micro-monitoring data.

[0089] The beneficial effects of the above technical solution are as follows: the present invention uses a macro data acquisition unit to collect panoramic images of grasslands and non-panoramic large-area grassland images with the help of satellite remote sensing technology to generate macro monitoring data. The wide field of view of satellite remote sensing can cover a large area of ​​grassland from a macro level, providing a basis for overall grasp of the grassland's topography, vegetation distribution, land use and other conditions. For example, the panoramic image can clearly understand the boundary range, overall form, and relationship with the surrounding geographical environment of the grassland; the non-panoramic large-area image can more carefully observe the characteristic differences of different areas of the grassland, such as the distribution areas of different vegetation types, providing comprehensive data support for macro ecological analysis and planning. At the same time, the micro data acquisition unit uses drones to collect detailed images of local areas of the grassland to generate micro monitoring data. The high flexibility of drones can go deep into the characteristics of specific local areas of the grassland, obtain high-resolution detailed images, focus on tiny elements in the grassland ecosystem, and contribute to in-depth research on the microstructure and ecological processes of the grassland ecosystem.

[0090] Example 3:

[0091] Based on Example 1, the multi-scale data acquisition module, such as Figure 3 As shown, including:

[0092] A time series generation unit is used to store macro-monitoring data and micro-monitoring data based on the time axis sequence and generate a time series;

[0093] The sequence data fusion unit is used to extract features from the macro-monitoring data and micro-monitoring data in the time series respectively to obtain grassland landform features and vegetation features. Based on the corresponding relationship of the collection area, the grassland landform features and vegetation features are fused to obtain the current fused feature image;

[0094] A fusion data analysis unit is used to analyze the current fusion feature image to determine the actual growth situation and growth status of grassland vegetation;

[0095] The actual growth of grassland vegetation is compared with the actual growth corresponding to the previous fused feature image to determine the restoration effect of the grassland.

[0096] The beneficial effects of the above technical solution: the present invention collects macro-monitoring data and micro-monitoring data of grassland in chronological order, and fuses the macro-monitoring data and the micro-monitoring data through a sequence data fusion unit, thereby improving the accuracy of grassland monitoring data, which is beneficial for managers to have a more comprehensive and in-depth understanding of grassland vegetation recovery, and also provides a more comprehensive and accurate data basis for determining grassland restoration effects. Finally, the fusion data analysis unit is used to analyze the current fused feature image to determine the actual growth conditions and growth status of grassland vegetation; and the actual growth conditions of grassland vegetation are compared with the actual growth conditions corresponding to the previous fused feature image to determine the restoration effect of the grassland, thereby realizing automatic analysis of grassland restoration conditions, reducing the monitoring workload of managers, and effectively improving the efficiency of grassland restoration monitoring feedback.

[0097] Example 4:

[0098] Based on Example 3, the sequence data fusion unit includes:

[0099] The macro feature extraction subunit is used to perform edge detection processing on the grassland panoramic image and the non-panoramic large area image in the macro monitoring data, and obtain the texture features and color features of the grassland panoramic image and the non-panoramic large area image respectively;

[0100] The macro feature fusion subunit is used to fuse the texture features and color features of the non-panoramic large area image with the grassland panoramic image based on the acquisition area of ​​the non-panoramic large area image to obtain a primary panoramic image;

[0101] The micro-feature extraction subunit is used to extract features from the detail images corresponding to the micro-monitoring data to obtain grassland landforms and vegetation detail features;

[0102] The macro feature extraction subunit is used to determine the regional correspondence between the detail image and the primary panoramic image based on the texture features of the primary panoramic image and the shooting position of the micro monitoring data. Based on the prime number region correspondence, the grassland landform and vegetation detail features of the detail image are fused with the corresponding area of ​​the primary panoramic image to obtain a fused feature image.

[0103] The beneficial effects of the above technical solution: the present invention first fuses the image features of the grassland panoramic image and the non-panoramic large-area image through the macro-feature extraction subunit and the macro-feature fusion subunit, so that the image information at the macro level is more complete and rich, and combines the overall field of view of the panoramic image and the local detailed features of the non-panoramic large-area image, which can more comprehensively reflect the macro state of the grassland and lay the foundation for the subsequent fusion with micro features; then based on the texture features of the primary panoramic image and combined with the shooting position of the micro monitoring data, the regional correspondence between the detail image and the primary panoramic image is determined, and then the grassland landform and vegetation detail features of the detail image are fused with the corresponding area of ​​the primary panoramic image to obtain a fused feature image, which organically combines the macro and micro features, retains the overall macro information of the grassland, and incorporates the micro details of the key areas, so that the generated fused feature image can comprehensively and meticulously reflect the real situation of the grassland.

[0104] Example 5:

[0105] Based on Example 3, the fusion data analysis unit includes:

[0106] The grassland feature extraction unit is used to extract features from the current fused feature image to obtain the landform features and vegetation features of the grassland;

[0107] The vegetation determination unit is used to determine the landform distribution of grassland based on grassland landform characteristics, and to determine the vegetation information corresponding to different landforms in combination with grassland management data;

[0108] a growth analysis unit, configured to determine the main vegetation types in each area of ​​the grassland based on the vegetation information and landform distribution, and obtain standard vegetation growth data corresponding to different vegetation types from a database based on the vegetation types;

[0109] Determine vegetation sub-features corresponding to each area of ​​the grassland respectively, determine the actual growth status of vegetation in each area based on the vegetation sub-features, and determine the growth status of vegetation in each area of ​​the grassland according to the actual vegetation conditions and standard vegetation growth data corresponding to the vegetation;

[0110] The effect determination unit is used to compare the actual growth of grassland vegetation with the actual growth corresponding to the previous fusion feature image, and obtain the growth differences corresponding to different grassland landforms;

[0111] Based on the growth differences and the actual growth status of each area, it is determined whether the vegetation growth trend of the grassland is good. If so, it is determined that the restoration effect of the current area is good;

[0112] Otherwise, based on the current solar term changes in the grassland and the corresponding vegetation growth data of each area, it is judged whether the current area's vegetation growth trend is normal;

[0113] If not, it is determined that the recovery effect of the current area is poor;

[0114] If so, the vegetation coverage rate of the current area is determined based on the fused feature image corresponding to the optimal vegetation growth state of the current area, and combined with the preset coverage rate threshold of the landform corresponding to the current area, it is judged whether the coverage rate of the current area meets the standard;

[0115] If the coverage rate of the current area meets the standard, it is determined that the recovery effect of the current area is good;

[0116] Otherwise, it is determined that the recovery effect of the current area is poor.

[0117] The beneficial effects of the above technical solution: the present invention first extracts features from the current fused feature image to obtain the geomorphic features and vegetation features of the grassland, then determines the geomorphic distribution based on the geomorphic features of the grassland, and clarifies the vegetation information corresponding to different geomorphologies in combination with grassland management data, establishes a close connection between geomorphology and vegetation, determines the vegetation types suitable for growth or planting under different geomorphic conditions, and provides an accurate basis for subsequent grassland vegetation growth analysis, and then determines the main vegetation types in each area of ​​the grassland based on the vegetation information and geomorphic distribution, and obtains standard vegetation growth data corresponding to different vegetation in the database based on the vegetation types; determines the vegetation sub-features corresponding to each area of ​​the grassland respectively, and determines the actual vegetation growth situation in each area based on the vegetation sub-features, and determines the actual vegetation growth situation according to the actual vegetation situation and the standard vegetation growth data corresponding to the vegetation. Quasi-vegetation growth data can determine the growth status of vegetation in each area of ​​the grassland respectively, and can objectively and accurately evaluate the growth status of vegetation in each area. Finally, by comparing the actual growth of vegetation corresponding to the current and previous fusion feature images, the growth differences of different landforms are obtained, which intuitively reflects the growth and change trend of grassland vegetation over a period of time, helps to timely discover abnormal conditions in the vegetation growth process, and provides an important basis for evaluating the restoration effect. The growth difference and actual growth status are combined to judge the vegetation growth trend, consider the impact of solar term changes on vegetation growth, and comprehensively judge the restoration effect. It fully considers the complexity and dynamics of the grassland ecosystem. Combining solar terms and vegetation growth data can effectively avoid misjudgment. In addition, by comparing the current regional vegetation coverage with the preset threshold to finally determine the restoration effect, the scientificity and accuracy of the evaluation are further improved. The present invention can clearly understand the restoration effect of different areas of the grassland, which is conducive to the rational allocation of grassland management resources and the adjustment of subsequent grassland restoration strategies.

[0118] Example 6:

[0119] Based on Example 5, the prediction and strategy adjustment module, such as Figure 4 As shown, including:

[0120] The growth trend prediction unit is used to obtain the actual environmental data of the grassland and the historical time series. Based on the vegetation growth conditions of each area of ​​the grassland in the historical time series, the unit generates vegetation growth curves for each area and determines the vegetation growth dynamics of each area.

[0121] Based on the vegetation curve graph, combined with the current vegetation growth status, the growth trend of vegetation in each area of ​​the grassland and the change of grassland coverage are predicted;

[0122] The intelligent strategy adjustment unit is used to adjust the current grassland restoration strategy based on the growth trend and the change in grassland coverage, combined with the actual environmental data of the grassland.

[0123] In this embodiment, the intelligent policy adjustment unit includes:

[0124] The first adjustment subunit is used to obtain the growth trend of vegetation in each area of ​​the grassland and the change of grassland coverage, and to determine whether the vegetation growth in each area is tending to be good. If so, the current grassland restoration strategy corresponding to the current area is maintained;

[0125] Otherwise, the current area is taken as the target area, and combined with the current grassland environmental data, it is determined whether the target area is the cause of environmental impact. If so, the optimal environmental data for vegetation growth in the target area is compared with the current grassland environmental data to determine the influencing environmental factors;

[0126] Based on the environmental impact data, artificial intervention methods are screened to obtain the best intervention plan, and the current grassland restoration strategy is adjusted based on the best intervention plan;

[0127] The second adjustment subunit is used to obtain biological activity data in the target area when the target area is not affected by environmental factors, determine all areas involved in the biological activity, compare the growth trends of regional vegetation and grassland coverage rates in multiple areas corresponding to the same biological activity, and determine the impact of various biological activities on grassland restoration;

[0128] Determine the target biological activities contained in the target area based on the biological activity data corresponding to the target area, and generate a restriction strategy for the target biological activities;

[0129] Adjust current grassland restoration strategies based on the stated restriction strategies;

[0130] If the growth trend of vegetation and grassland coverage changes in the target area do not improve after biological activities are restricted, the preset database will be screened based on the environmental data of the target area and the growth data of different vegetation in the target area to determine the optimal growth vegetation in the target area, and the current grassland restoration strategy will be adjusted based on the optimal growth vegetation and its corresponding planting method.

[0131] In this embodiment, biological activity data refers to animal activity data on grasslands, including grassland data changes caused by human grazing.

[0132] The present invention decides whether to adjust the strategy by judging the growth of vegetation in each area, maintains the existing strategy for areas with good vegetation growth, avoids unnecessary adjustments, ensures the stability and continuity of the management work, and sets areas with poor growth as target areas, and makes targeted adjustments to the grassland restoration strategy in the target area, realizing zoning management of the entire grassland, making strategy adjustments more accurate, and being able to concentrate resources in areas that really need improvement. When it is determined that the target area is affected by environmental factors, the influencing factors are found by comparing the optimal environmental data with the current environmental data, and the best intervention plan is screened accordingly to adjust the restoration strategy, realizing accurate analysis of the environmental factors in the target area, and being able to quickly identify and solve vegetation growth problems caused by environmental unsuitability. For example, if it is found that insufficient soil fertility in a certain area affects vegetation growth, the fertilization plan can be adjusted in a targeted manner to improve soil fertility and promote healthy vegetation growth. When the target area is affected by non-environmental factors, by obtaining biological activity data and comparing the vegetation growth trends and grassland coverage rates of multiple areas involved in the same biological activity, the impact of various biological activities on grassland restoration can be comprehensively determined. This will help to gain a deeper understanding of the complex relationship between biological activities and grassland vegetation growth, and provide a basis for formulating reasonable biological activity management strategies. For example, by analyzing and finding that excessive gnawing of a certain type of animal has inhibited vegetation growth, targeted measures can be taken to limit the activity range or number of the animal, and the target biological activity can be determined based on the biological activity data of the target area, and a restriction strategy can be generated, and then the restoration strategy can be adjusted, thus realizing the customization of restoration strategies for areas affected by biological activities, which can effectively control the negative impact of biological activities on grassland vegetation and protect grassland ecosystems. Balance, for example, for some harmful biological activities that damage vegetation, formulate corresponding restriction strategies, such as setting up guardrails, adopting biological control measures, etc., to reduce their damage to vegetation. If the vegetation growth in the target area does not improve after restricting biological activities, further combine environmental data and different vegetation growth data, screen the best growth vegetation and planting methods in the preset database to adjust the strategy, adopt a multi-dimensional comprehensive adjustment method, fully consider the complexity of the grassland ecosystem, and analyze from multiple aspects such as environmental adaptability, biological activity impact and vegetation selection to ensure that the restoration strategy can promote the growth and recovery of grassland vegetation to the greatest extent. For example, when it is found that the existing vegetation is difficult to grow well in the current environment, select more suitable vegetation varieties for planting to improve the survival rate and growth quality of vegetation. The present invention adjusts the grassland restoration strategy based on actual conditions and comprehensive consideration of multiple factors. It can effectively solve various problems encountered in the growth process of grassland vegetation, significantly improve the management effect of grassland restoration work, promote the health and sustainable development of grassland ecosystems, and carry out zoning management of grasslands, thereby improving the accuracy of grassland restoration strategy adjustment, avoiding blind investment of resources, improving resource utilization efficiency, and achieving optimal allocation of resources.

[0133] The beneficial effects of the above technical solution: the present invention generates a vegetation growth curve for each area by acquiring the actual environmental data and historical time series of the grassland, which intuitively shows the growth of vegetation at different time points, so that managers can clearly observe the dynamic changes in vegetation growth. Moreover, the slope of the curve can be used to judge the growth rate of vegetation in a certain time period, and then analyze the activeness of vegetation growth in the area, which helps to gain a deep understanding of the inherent laws of vegetation growth in different areas, provide a solid foundation for subsequent growth trend prediction, and improve the accuracy of the prediction. Subsequently, the vegetation growth curve and the current vegetation growth status are combined to predict the growth trend of vegetation in each area of ​​the grassland and the change in grassland coverage. Due to differences in environmental factors such as topography, soil, and light, vegetation growth dynamics may vary across regions. By fully considering historical vegetation growth data and current conditions, the system can more accurately predict future vegetation growth trends and the macro-development trends of grassland vegetation. Based on these growth trends and changes in grassland coverage, combined with actual grassland environmental data, current grassland restoration strategies can be adjusted. This is conducive to the rational allocation of grassland restoration resources and improves the efficiency and quality of grassland management. For example, for areas where vegetation growth is predicted to be slow and coverage may decrease, restoration strategies can be adjusted to increase irrigation frequency, improve soil fertility, or adjust the types of vegetation planted to promote vegetation growth and increase coverage. Adjusting strategies based on actual grassland environmental data ensures that restoration strategies can adapt to dynamic changes in the grassland environment, making them more tailored to current environmental conditions and improving their effectiveness and sustainability. For example, in drought years, irrigation strategies can be adjusted based on actual environmental data of reduced precipitation to optimize water resource utilization and ensure normal vegetation growth.

[0134] Example 7:

[0135] Based on Example 5, the growth trend prediction unit includes:

[0136] The growth curve generation subunit is used to determine the vegetation height and vegetation color based on the vegetation growth situation, and predict the peak point corresponding to the optimal vegetation growth state of the vegetation in the corresponding area based on the vegetation height change and the reference height range corresponding to the optimal vegetation growth state of the corresponding vegetation;

[0137] Taking the peak point as the predicted peak value of the vegetation growth curve diagram of the corresponding area, and determining the time interval corresponding to the predicted peak value in combination with the time series generation time interval;

[0138] Based on the change in vegetation height, combined with the predicted peak value and its corresponding time interval, a vegetation growth curve for the corresponding area is generated, and the vegetation color at each point corresponding to the vegetation growth curve is marked;

[0139] The trend prediction subunit is used to obtain the direction vector corresponding to the end of the vegetation growth curve corresponding to each area, and obtain the predicted vegetation growth trend direction;

[0140] At the same time, target growth data corresponding to the target grassland vegetation is obtained based on the big data, and based on the target growth data, a first average growth rate or a second average decay rate of the target vegetation under the current solar term is determined;

[0141] Determining an actual average growth rate or an actual decay rate of the actual vegetation based on a vegetation growth curve corresponding to the target grassland vegetation, and comparing the first average growth rate with the actual average growth rate or the first average decay rate to obtain an environmental impact growth difference;

[0142] Intercepting a plurality of target curve segments corresponding to similar vegetation growth trends from the vegetation growth curve in the corresponding area, and calculating a second average growth rate or a second average decay rate corresponding to the plurality of target curve segments;

[0143] Based on the second average growth rate or the second average decay rate, combined with the environmental impact growth difference, the change of vegetation in the corresponding area in the predicted vegetation growth trend direction is determined to obtain the vegetation growth trend prediction result of the corresponding area.

[0144] In this embodiment, the growth trend prediction unit further includes:

[0145] The coverage prediction subunit is used to determine the vegetation-covered pixels and non-vegetation-covered pixels in each area of ​​the grassland based on the color features of the current fused feature image;

[0146] According to the number of pixels corresponding to the vegetation-covered pixels and non-vegetation-covered pixels in each area, the current vegetation coverage rate of each area is obtained respectively;

[0147] Based on the vegetation features corresponding to the current fused feature image, the amount of vegetation in each area of ​​the grassland is determined, and combined with the vegetation growth trend prediction results of the corresponding area, the vegetation coverage prediction trend corresponding to each area is determined respectively;

[0148] Based on the current vegetation coverage rate and combined with the predicted trend of vegetation coverage rate corresponding to each area, the changes in vegetation coverage rate corresponding to each area are determined respectively, and the predicted results of vegetation coverage rate corresponding to each area of ​​the grassland are obtained.

[0149] The present invention determines the vegetation coverage pixels and non-vegetation coverage pixels in each area of ​​the grassland based on the color characteristics of the current fused feature image, and then calculates the current vegetation coverage rate according to the number of pixels, so as to achieve accurate quantification of the grassland vegetation coverage status. Then, the vegetation quantity in each area of ​​the grassland is determined based on the vegetation characteristics corresponding to the current fused feature image, and the vegetation coverage rate prediction trend is determined in combination with the vegetation growth trend prediction results of the corresponding area. Not only the actual quantity of current vegetation is taken into account, but also the dynamic trend of vegetation growth, and the influence of multiple factors on the change of vegetation coverage rate is comprehensively considered, so that the prediction is more scientific and reasonable. For example, when predicting the future vegetation coverage rate of a certain area, if the current vegetation quantity in the area is large and the growth trend is good, the prediction result will tend to show an increase in vegetation coverage rate; on the contrary, if the vegetation quantity decreases and the growth trend is not good, the vegetation coverage rate is predicted to decrease. The multi-factor comprehensive prediction method can more accurately reflect the future development trend of grassland vegetation and provide strong support for the formulation of response strategies in advance. Finally, based on the current vegetation coverage rate and combined with the predicted vegetation coverage trends for each region, the changes in vegetation coverage rates for each region are determined. This results in the predicted vegetation coverage rates for each grassland region, enabling timely understanding of the dynamic changes in grassland vegetation coverage rates and identifying potential problems in advance. For example, if the predicted results indicate that the vegetation coverage rate in a certain area will continue to decline, managers can quickly take measures, such as adjusting grazing strategies and strengthening vegetation protection, to prevent further declines in vegetation coverage rates, thereby effectively maintaining the ecological balance of the grassland. Real-time monitoring and prediction of vegetation coverage changes will help achieve the sustainable use of grassland resources and the stable development of the ecosystem.

[0150] The beneficial effects of the above technical solution: The present invention predicts the peak point based on the change in vegetation height and refers to the height interval corresponding to the optimal vegetation growth state, takes the predicted peak point as the predicted peak, and determines its corresponding time interval in combination with the time series generation time interval, which provides an important time frame for the construction of the entire growth curve, helps to more intuitively understand the stage characteristics of the vegetation growth cycle, and provides a basis for the curvature transformation of the curve of natural growth and decay of vegetation. Then, the vegetation growth curve is generated based on the vegetation height change, the predicted peak value and its time interval, and the vegetation color of each point is marked on the curve, wherein the vegetation height change reflects the vertical dimension of growth, and the vegetation color can be used to judge the health status of vegetation, growth stage, etc., and can comprehensively and intuitively display the comprehensive growth of vegetation at different time points. It can provide managers with rich data visualization expressions and facilitate in-depth analysis of the vegetation growth process; obtain the direction vector of the vegetation growth curve end through the trend prediction subunit to determine the predicted vegetation growth trend direction, and then compare the target growth data of the target grassland vegetation (such as the average growth or decay rate under the current solar term) with the average growth or decay rate of the actual vegetation to obtain the environmental impact growth difference and determine the degree of influence of the current environmental factors on vegetation growth. Then, the target curve segment with similar vegetation growth trend is intercepted and its average growth or decay rate is calculated. The change of vegetation in the predicted trend direction is determined in combination with the environmental impact growth difference, which fully considers the impact of grassland environment on vegetation growth. It can more comprehensively and accurately predict the future growth trend of vegetation and provide strong support for grassland management decision-making.

[0151] Example 8:

[0152] The present invention provides a method for dynamic monitoring of grassland restoration status based on multi-scale fusion, such as Figure 5 As shown, including:

[0153] Step 1: Use satellite remote sensing technology to obtain macro-monitoring data of grasslands, and use drones to obtain micro-monitoring data of grasslands;

[0154] Step 2: Collect macro- and micro-monitoring data over a long period of time to form a time series, and perform fusion analysis on the data in the current time series to determine the actual growth status of the grassland and the restoration effect;

[0155] Step 3: Based on the actual growth and restoration effects of grasslands, combined with actual grassland environmental data and historical time series, predict grassland growth trends and adjust grassland restoration strategies based on the predictions.

[0156] The beneficial effects of the above technical solution are as follows: The present invention combines macroscopic monitoring by satellite remote sensing with microscopic monitoring by drones to conduct multi-scale, all-encompassing dynamic monitoring of grassland restoration. It also collects macroscopic and microscopic monitoring data over a long period of time to form a time series, and then performs a fusion analysis of the data within the current time series to determine the actual growth status and recovery effect of the grassland. This achieves comprehensive monitoring and simultaneous automatic analysis of grassland recovery, obtaining the actual growth status and recovery effect of the grassland, making it easier for managers to quickly determine the actual recovery status of the grassland. Finally, based on the actual growth and recovery effect of the grassland, combined with actual grassland environmental data and historical time series, grassland growth trends are predicted. This facilitates the timely identification of factors adverse to grassland recovery, provides timely and accurate data support for managers to adjust restoration strategies, helps improve the efficiency and quality of grassland restoration, and promotes the sustainable development of grassland ecosystems.

[0157] Example 9:

[0158] Based on Example 8, step 2 includes:

[0159] Based on the time axis sequence, the macro-monitoring data and micro-monitoring data are stored to generate time series;

[0160] Feature extraction is performed on the macro-monitoring data and micro-monitoring data in the time series to obtain grassland landform features and vegetation features. Based on the corresponding relationship of the collection area, the grassland landform features and vegetation features are fused to obtain the current fused feature image;

[0161] Analyze the current fused feature image to determine the actual growth and status of grassland vegetation;

[0162] The actual growth of grassland vegetation is compared with the actual growth corresponding to the previous fused feature image to determine the restoration effect of the grassland.

[0163] The beneficial effects of the above technical solution: The present invention collects macro-monitoring data and micro-monitoring data of grasslands based on time sequence, and integrates the macro-monitoring data and the micro-monitoring data to improve the accuracy of grassland monitoring data, which is conducive to managers to have a more comprehensive and in-depth understanding of grassland vegetation recovery, and also provides a more comprehensive and accurate data basis for determining grassland restoration effects. Finally, the current fused feature image is analyzed to determine the actual growth conditions and growth status of grassland vegetation; and the actual growth conditions of grassland vegetation are compared with the actual growth conditions corresponding to the previous fused feature image to determine the restoration effect of grassland, realizing automatic analysis of grassland restoration conditions, reducing the monitoring workload of managers, and effectively improving the efficiency of grassland restoration monitoring feedback.

[0164] Example 10:

[0165] Based on Example 9, the current fused feature image is analyzed to determine the actual growth and growth status of grassland vegetation; and the actual growth of grassland vegetation is compared with the actual growth corresponding to the previous fused feature image to determine the restoration effect of the grassland, including:

[0166] Perform feature extraction on the current fused feature image to obtain the landform and vegetation features of the grassland;

[0167] Based on grassland landform characteristics, determine the landform distribution of grasslands, and combine grassland management data to determine the vegetation information corresponding to different landforms;

[0168] Based on the vegetation information and landform distribution, determining the main vegetation types in each area of ​​the grassland, and based on the vegetation types, obtaining standard vegetation growth data corresponding to different vegetation in a database;

[0169] Determine vegetation sub-features corresponding to each area of ​​the grassland respectively, determine the actual growth status of vegetation in each area based on the vegetation sub-features, and determine the growth status of vegetation in each area of ​​the grassland according to the actual vegetation conditions and standard vegetation growth data corresponding to the vegetation;

[0170] Compare the actual growth of grassland vegetation with the actual growth corresponding to the previous fusion feature image to obtain the growth differences corresponding to different grassland landforms;

[0171] Based on the growth differences and the actual growth status of each area, it is determined whether the vegetation growth trend of the grassland is good. If so, it is determined that the restoration effect of the current area is good;

[0172] Otherwise, based on the current solar term changes in the grassland and the corresponding vegetation growth data of each area, it is judged whether the current area's vegetation growth trend is normal;

[0173] If not, it is determined that the recovery effect of the current area is poor;

[0174] If so, the vegetation coverage rate of the current area is determined based on the fused feature image corresponding to the optimal vegetation growth state of the current area, and combined with the preset coverage rate threshold of the landform corresponding to the current area, it is judged whether the coverage rate of the current area meets the standard;

[0175] If the coverage rate of the current area meets the standard, it is determined that the recovery effect of the current area is good;

[0176] Otherwise, it is determined that the recovery effect of the current area is poor.

[0177] The beneficial effects of the above technical solution: the present invention first extracts features from the current fused feature image to obtain the geomorphic features and vegetation features of the grassland, then determines the geomorphic distribution based on the geomorphic features of the grassland, and clarifies the vegetation information corresponding to different geomorphologies in combination with grassland management data, establishes a close connection between geomorphology and vegetation, determines the vegetation types suitable for growth or planting under different geomorphic conditions, and provides an accurate basis for subsequent grassland vegetation growth analysis, and then determines the main vegetation types in each area of ​​the grassland based on the vegetation information and geomorphic distribution, and obtains standard vegetation growth data corresponding to different vegetation in the database based on the vegetation types; determines the vegetation sub-features corresponding to each area of ​​the grassland respectively, and determines the actual vegetation growth situation in each area based on the vegetation sub-features, and determines the actual vegetation growth situation according to the actual vegetation situation and the standard vegetation growth data corresponding to the vegetation. Quasi-vegetation growth data can determine the growth status of vegetation in each area of ​​the grassland respectively, and can objectively and accurately evaluate the growth status of vegetation in each area. Finally, by comparing the actual growth of vegetation corresponding to the current and previous fusion feature images, the growth differences of different landforms are obtained, which intuitively reflects the growth and change trend of grassland vegetation over a period of time, helps to timely discover abnormal conditions in the vegetation growth process, and provides an important basis for evaluating the restoration effect. The growth difference and actual growth status are combined to judge the vegetation growth trend, consider the impact of solar term changes on vegetation growth, and comprehensively judge the restoration effect. It fully considers the complexity and dynamics of the grassland ecosystem. Combining solar terms and vegetation growth data can effectively avoid misjudgment. In addition, by comparing the current regional vegetation coverage with the preset threshold to finally determine the restoration effect, the scientificity and accuracy of the evaluation are further improved. The present invention can clearly understand the restoration effect of different areas of the grassland, which is conducive to the rational allocation of grassland management resources and the adjustment of subsequent grassland restoration strategies.

[0178] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A grassland restoration status dynamic monitoring system based on multi-scale fusion, characterized by: include: Multi-scale data acquisition module, used to obtain macro-monitoring data of grasslands using satellite remote sensing technology, and simultaneously obtain micro-monitoring data of grasslands using drones; A long-term data series analysis module is used to collect macro-monitoring data and micro-monitoring data over a long period of time to form a time series, and to perform fusion analysis on the data in the current time series to determine the actual growth status and restoration effect of the grassland; The prediction and strategy adjustment module is used to predict grassland growth trends based on the actual growth and restoration effects of grasslands, combined with actual grassland environmental data and historical time series, and adjust grassland restoration strategies based on the predictions.

2. A grassland restoration status dynamic monitoring system based on multi-scale fusion according to claim 1, characterized in that: Multi-scale data acquisition module, including: A macro data acquisition unit is used to collect panoramic images of grasslands and non-panoramic large-area grassland images using satellite remote sensing technology to generate macro monitoring data; The micro-data acquisition unit is used to use drones to collect detailed images of local areas of the grassland and generate micro-monitoring data.

3. The grassland restoration status dynamic monitoring system based on multi-scale fusion according to claim 1 is characterized in that: Multi-scale data acquisition module, including: A time series generation unit is used to store macro-monitoring data and micro-monitoring data based on the time axis sequence and generate a time series; The sequence data fusion unit is used to extract features from the macro-monitoring data and micro-monitoring data in the time series respectively to obtain grassland landform features and vegetation features. Based on the corresponding relationship of the collection area, the grassland landform features and vegetation features are fused to obtain the current fused feature image; A fusion data analysis unit is used to analyze the current fusion feature image to determine the actual growth situation and growth status of grassland vegetation; The actual growth of grassland vegetation is compared with the actual growth corresponding to the previous fused feature image to determine the restoration effect of the grassland.

4. The grassland restoration status dynamic monitoring system based on multi-scale fusion according to claim 3 is characterized in that: Sequence data fusion unit, including: The macro feature extraction subunit is used to perform edge detection processing on the grassland panoramic image and the non-panoramic large area image in the macro monitoring data, and obtain the texture features and color features of the grassland panoramic image and the non-panoramic large area image respectively; The macro feature fusion subunit is used to fuse the texture features and color features of the non-panoramic large area image with the grassland panoramic image based on the acquisition area of ​​the non-panoramic large area image to obtain a primary panoramic image; The micro-feature extraction subunit is used to extract features from the detail images corresponding to the micro-monitoring data to obtain grassland landforms and vegetation detail features; The macro feature extraction subunit is used to determine the regional correspondence between the detail image and the primary panoramic image based on the texture features of the primary panoramic image and the shooting position of the micro monitoring data. Based on the prime number region correspondence, the grassland landform and vegetation detail features of the detail image are fused with the corresponding area of ​​the primary panoramic image to obtain a fused feature image.

5. The grassland restoration status dynamic monitoring system based on multi-scale fusion according to claim 3 is characterized in that: Fusion data analysis unit, including: The grassland feature extraction unit is used to extract features from the current fused feature image to obtain the landform features and vegetation features of the grassland; The vegetation determination unit is used to determine the landform distribution of grassland based on grassland landform characteristics, and to determine the vegetation information corresponding to different landforms in combination with grassland management data; a growth analysis unit, configured to determine the main vegetation types in each area of ​​the grassland based on the vegetation information and landform distribution, and obtain standard vegetation growth data corresponding to different vegetation types from a database based on the vegetation types; Determine vegetation sub-features corresponding to each area of ​​the grassland respectively, determine the actual growth status of vegetation in each area based on the vegetation sub-features, and determine the growth status of vegetation in each area of ​​the grassland according to the actual vegetation conditions and standard vegetation growth data corresponding to the vegetation; The effect determination unit is used to compare the actual growth of grassland vegetation with the actual growth corresponding to the previous fusion feature image, and obtain the growth differences corresponding to different grassland landforms; Based on the growth differences and the actual growth status of each area, it is determined whether the vegetation growth trend of the grassland is good. If so, it is determined that the restoration effect of the current area is good; Otherwise, based on the current solar term changes in the grassland and the corresponding vegetation growth data of each area, it is judged whether the current area's vegetation growth trend is normal; If not, it is determined that the recovery effect of the current area is poor; If so, the vegetation coverage rate of the current area is determined based on the fused feature image corresponding to the optimal vegetation growth state of the current area, and combined with the preset coverage rate threshold of the landform corresponding to the current area, whether the coverage rate of the current area meets the standard is judged; If the coverage rate of the current area meets the standard, it is determined that the recovery effect of the current area is good; Otherwise, it is determined that the recovery effect of the current area is poor.

6. The grassland restoration status dynamic monitoring system based on multi-scale fusion according to claim 1 is characterized in that: Forecasting and strategy adjustment modules, including: The growth trend prediction unit is used to obtain the actual environmental data of the grassland and the historical time series. Based on the vegetation growth conditions of each area of ​​the grassland in the historical time series, the unit generates vegetation growth curves for each area and determines the vegetation growth dynamics of each area. Based on the vegetation curve graph, combined with the current vegetation growth status, the growth trend of vegetation in each area of ​​the grassland and the change of grassland coverage are predicted; The intelligent strategy adjustment unit is used to adjust the current grassland restoration strategy based on the growth trend and the change in grassland coverage, combined with the actual environmental data of the grassland.

7. The grassland restoration status dynamic monitoring system based on multi-scale fusion according to claim 6 is characterized in that: Growth trend prediction unit, including: The growth curve generation subunit is used to determine the vegetation height and vegetation color based on the vegetation growth situation, and predict the peak point corresponding to the optimal vegetation growth state of the vegetation in the corresponding area based on the vegetation height change and the reference height range corresponding to the optimal vegetation growth state of the corresponding vegetation; Taking the peak point as the predicted peak value of the vegetation growth curve diagram of the corresponding area, and determining the time interval corresponding to the predicted peak value in combination with the time series generation time interval; Based on the change in vegetation height, combined with the predicted peak value and its corresponding time interval, a vegetation growth curve for the corresponding area is generated, and the vegetation color at each point corresponding to the vegetation growth curve is marked; The trend prediction subunit is used to obtain the direction vector corresponding to the end of the vegetation growth curve corresponding to each area, and obtain the predicted vegetation growth trend direction; At the same time, target growth data corresponding to the target grassland vegetation is obtained based on the big data, and based on the target growth data, a first average growth rate or a second average decay rate of the target vegetation under the current solar term is determined; determining an actual average growth rate or an actual decay rate of the actual vegetation based on a vegetation growth curve corresponding to the target grassland vegetation, and comparing the first average growth rate with the actual average growth rate or the first average decay rate to obtain an environmental impact growth difference; Intercepting a plurality of target curve segments corresponding to similar vegetation growth trends from the vegetation growth curve in the corresponding area, and calculating a second average growth rate or a second average decay rate corresponding to the plurality of target curve segments; Based on the second average growth rate or the second average decay rate, combined with the environmental impact growth difference, the change of vegetation in the corresponding area in the predicted vegetation growth trend direction is determined to obtain the vegetation growth trend prediction result of the corresponding area.

8. A method for dynamic monitoring of grassland restoration status based on multi-scale fusion, characterized in that: include: Step 1: Use satellite remote sensing technology to obtain macro-monitoring data of grasslands, and use drones to obtain micro-monitoring data of grasslands; Step 2: Collect macro- and micro-monitoring data over a long period of time to form a time series, and perform fusion analysis on the data in the current time series to determine the actual growth status of the grassland and the restoration effect; Step 3: Based on the actual growth and restoration effects of grasslands, combined with actual grassland environmental data and historical time series, predict grassland growth trends and adjust grassland restoration strategies based on the predictions.

9. The method for dynamic monitoring of grassland restoration status based on multi-scale fusion according to claim 8, characterized in that: Step 2 includes: Based on the time axis sequence, the macro-monitoring data and micro-monitoring data are stored to generate time series; Feature extraction is performed on the macro-monitoring data and micro-monitoring data in the time series to obtain grassland landform features and vegetation features. Based on the corresponding relationship of the collection area, the grassland landform features and vegetation features are fused to obtain the current fused feature image; Analyze the current fused feature image to determine the actual growth and status of grassland vegetation; The actual growth of grassland vegetation is compared with the actual growth corresponding to the previous fused feature image to determine the restoration effect of the grassland.

10. The method for dynamic monitoring of grassland restoration status based on multi-scale fusion according to claim 9, characterized in that: Analyze the current fused feature image to determine the actual growth and status of grassland vegetation; The actual growth of grassland vegetation is compared with the actual growth corresponding to the previous fused feature image to determine the grassland restoration effect, including: Perform feature extraction on the current fused feature image to obtain the landform and vegetation features of the grassland; Based on grassland landform characteristics, determine the landform distribution of grasslands, and combine grassland management data to determine the vegetation information corresponding to different landforms; Based on the vegetation information and landform distribution, determining the main vegetation types in each area of ​​the grassland, and based on the vegetation types, obtaining standard vegetation growth data corresponding to different vegetation in a database; Determine vegetation sub-features corresponding to each area of ​​the grassland respectively, determine the actual growth status of vegetation in each area based on the vegetation sub-features, and determine the growth status of vegetation in each area of ​​the grassland according to the actual vegetation conditions and standard vegetation growth data corresponding to the vegetation; Compare the actual growth of grassland vegetation with the actual growth corresponding to the previous fusion feature image to obtain the growth differences corresponding to different grassland landforms; Based on the growth differences and the actual growth status of each area, it is determined whether the vegetation growth trend of the grassland is good. If so, it is determined that the restoration effect of the current area is good; Otherwise, based on the current solar term changes in the grassland and the corresponding vegetation growth data of each area, it is judged whether the current area's vegetation growth trend is normal; If not, it is determined that the recovery effect of the current area is poor; If so, the vegetation coverage rate of the current area is determined based on the fused feature image corresponding to the optimal vegetation growth state of the current area, and combined with the preset coverage rate threshold of the landform corresponding to the current area, whether the coverage rate of the current area meets the standard is judged; If the coverage rate of the current area meets the standard, it is determined that the recovery effect of the current area is good; Otherwise, it is determined that the recovery effect of the current area is poor.

Images