Method and system for topographic analysis based on unmanned aerial vehicle remote sensing monitoring decision

Abstract

The present application belongs to the field of agricultural topography decision, and particularly relates to a topography analysis method and system based on unmanned aerial vehicle remote sensing monitoring decision, comprising: firstly, obtaining various data of a region to be exploited, constructing a three-dimensional terrain visualization and planting simulation model, configuring a crop planting attribute library and simulating planting to obtain a score; secondly, screening crops according to a score threshold, and if the condition is met, planting is planned again; if a region needs to be transformed, the region is transformed according to attributes and the difficulty is evaluated; then, configuring a transformation difficulty threshold according to user planting requirements and cost, and if the condition is met, the crop is planted, transformed and planned according to the situation; if the crop does not meet the requirements but the transformation difficulty is appropriate, a crop with a small estimated cost is selected for transformation and planting; finally, when the crop planting difficulty is great and the growth is poor, whether to transform and plant is determined according to the condition by analyzing the attributes, so as to provide accurate decision for agricultural planting planning.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of agricultural topography decision-making, and particularly relates to a topography analysis method and system based on unmanned aerial vehicle remote sensing monitoring decision-making. BACKGROUND

[0002] In precision agriculture, topography analysis is one of the key links, which involves the understanding and application of farmland topographic features such as slope, aspect, and elevation. Reasonable topography analysis can help farmers optimize irrigation system layout, select appropriate crop types, and plan agricultural operation paths, thereby achieving optimal resource allocation and environmentally friendly agricultural practices. However, traditional topography analysis methods often rely on ground measurements or satellite imagery, which have problems such as slow data update, low spatial resolution, and high cost. How to analyze topographic features to monitor and analyze different types of land for agriculture, and design reasonable agricultural development strategies and plant the most suitable crops is one of the main problems in existing agricultural development.

[0003] A method for extracting mountain front water system based on optical remote sensing data and digital elevation model is disclosed in Chinese patent with authorization announcement number CN118503658B. First, the optical remote sensing and digital elevation model data of the mountain front area are obtained and preprocessed. Then, water body and terrain feature datasets are extracted to obtain corresponding extraction indexes. The extraction indexes are analyzed comprehensively to obtain precision indexes, which are compared with threshold values to optimize the preprocessing state of mountain front water system data extraction.

[0004] The above existing technology has the following problems: There are still many areas that can be developed for agriculture, but have not been developed. Traditional manual measurement methods are inefficient, have limited accuracy, and are greatly limited by manpower and geographical environment. In terms of regional topography modeling, intelligent means are lacking to accurately simulate and analyze complex terrain, and it is difficult to comprehensively consider the comprehensive interactive influence of multiple factors such as soil type and hydrological conditions on topography, making it difficult to accurately match the direction of agricultural development, and easily causing resource mismatch and low agricultural production efficiency. Therefore, the present application provides a topography analysis method and system based on unmanned aerial vehicle remote sensing monitoring decision-making. SUMMARY

[0005] In view of the deficiencies of the prior art, the present application provides a topography analysis method and system based on unmanned aerial vehicle remote sensing monitoring decision, which comprises the following steps: firstly, obtaining various data of the region to be exploited, constructing a three-dimensional terrain visualization and planting simulation model, configuring a crop planting attribute library and simulating planting to obtain a score; secondly, screening crops according to the score threshold value, and if the conditions are met, the crops are planted again; if the region needs to be transformed, the region is transformed according to the attributes and the difficulty is evaluated; then, according to the user's planting requirements and cost, the transformation difficulty threshold value is configured, and if the conditions are met, the crops are planted, transformed and planned according to the situation; if the crops do not meet the requirements but the transformation difficulty is appropriate, crops with a small estimated cost are selected for transformation and planting; finally, when the crop planting difficulty is great and the growth is poor, the attributes are analyzed to determine whether to transform and plant according to the conditions, so as to provide accurate decision for agricultural planting planning.

[0006] To achieve the above object, the present application provides the following technical scheme:

[0007] The topography analysis method based on unmanned aerial vehicle remote sensing monitoring decision comprises the following steps:

[0008] S1, obtaining multi-angle topographic images, laser measurement data, meteorological data and hydrological data of the current region, user planting requirements and estimated cost data, constructing a three-dimensional terrain planting simulation model with hydrological and meteorological data by means of a simulation algorithm and a three-dimensional generation algorithm;

[0009] S2, configuring a crop planting attribute library, and according to the planting requirement parameters of each crop in the crop planting attribute library, performing planting simulation and evaluation by means of the three-dimensional terrain planting simulation model with hydrological and meteorological data and a crop segmented growth period growth factor function, to obtain a planting difficulty score and a simulation growth score of each crop in the current region;

[0010] S3, setting a planting difficulty score threshold value and a simulation growth score threshold value When there is a crop whose planting difficulty score is less than and whose simulation growth score is greater than the simulation growth score threshold value , and the number of such crops is greater than or equal to 1, the crops meeting the conditions are selected as the crops planted in the current region, and according to the user's planting requirements, the current region is subjected to secondary planting planning according to the number of crop types meeting the conditions, the crop planting attributes and the current region;

[0011] S4, when the planting difficulty scores of all crops are greater than or equal to the planting difficulty score threshold value , but there is a crop whose simulation growth score is greater than the simulation growth score threshold value , the current region is subjected to transformation evaluation and judgment according to the crop planting attributes meeting the condition of being greater than the simulation growth score threshold value , to obtain the current region after transformation, and secondary planting planning is performed.

[0012] Specifically, the step of performing the transformation evaluation and discrimination on the current area includes:

[0013] S5, setting a transformation difficulty threshold according to the user planting demand and the estimated cost data, and evaluating the difficulty of the corresponding environmental transformation of the corresponding crop planted in the current area that meets the condition in S4, to obtain the environmental transformation difficulty of the corresponding crop;

[0014] S6, when there is at least one crop that meets the user planting demand and the environmental transformation difficulty is less than the transformation difficulty threshold, the crop that meets the condition is selected for planting, and the current area is secondarily transformed according to the number of crop types that meet the condition, the corresponding crop planting attribute and the current area environmental attribute, and the S3 process is repeated for secondary planting planning in the transformed current area;

[0015] S7, when all crops do not meet the user planting demand, but there is a crop that meets the corresponding environmental transformation difficulty less than the transformation difficulty threshold, the corresponding crop with the minimum estimated cost is selected as the corresponding planting crop of the current area, and the S6 process is repeated to perform environmental transformation and planting planning of the current area according to the planting demand parameters of the crops that meet the user planting demand condition;

[0016] S8, when the planting difficulty score of all crops is greater than or equal to the planting difficulty score threshold , and the simulation growth score is less than or equal to the simulation growth score threshold , analyze all crop attributes, when there is a crop with the minimum planting difficulty score and the maximum simulation growth score corresponding to the type of crop that is the user planting demand crop and the transformation cost is less than or equal to the estimated cost, transform and plant the current area, otherwise do not perform planting planning for the current area.

[0017] Specifically, the steps of constructing a three-dimensional terrain planting simulation model of the area with hydro-meteorological data include:

[0018] S101, according to the slope and terrain height data in the obtained multi-angle terrain image and laser measurement data of the current area, a three-dimensional terrain sub-model of the current area is generated through a three-dimensional generation algorithm;

[0019] S102, according to the obtained meteorological data of the current area, a pre-trained meteorological prediction model is configured to obtain a regional meteorological simulation sub-model, and the simulated meteorological state of the current area at each time period is output;

[0020] S103, according to the hydrological data of the current area, a hydrological model is trained to obtain a regional hydrological simulation sub-model, and the distance between the water source and the current area, the water flow path and the soil moisture are simulated;

[0021] S104, integrate the current regional three-dimensional terrain sub-model, the regional meteorological simulation sub-model and the regional hydrological simulation sub-model through an integration algorithm to obtain a regional three-dimensional terrain model with hydro-meteorology;

[0022] S105, construct a segmented growth period growth factor function according to the planting environment conditions and simulated meteorological state of each growth period of the crop, the distance between the water source and the current region, the water flow path and the soil moisture, and train the segmented growth period growth factor function into the constructed crop segmented growth simulation sub-model to obtain the corresponding growth state of each crop under different growth conditions;

[0023] S106, integrate the pre-trained crop segmented growth simulation sub-model into the regional three-dimensional terrain model with hydro-meteorology to obtain a regional three-dimensional terrain planting simulation model with hydro-meteorology, and when the current region changes, repeat the process of S101-S106 to obtain a regional three-dimensional terrain planting simulation model with hydro-meteorology after fine-tuning for each region, and dynamically label the simulated meteorology, hydrology and crop growth state according to the time dimension.

[0024] Specifically, the construction step of the segmented growth period growth factor function is:

[0025] S201, set the crop growth period stages to include the seeding period, the seedling period, the vegetative growth period, the reproductive growth period and the mature period, and according to the parameters between each crop in different growth period stages and meteorology and hydrology, analyze the meteorology and hydrology parameter space with a contribution degree greater than a contribution threshold value through a factor analysis algorithm;

[0026] S202, according to the meteorology and hydrology parameter space with a contribution degree greater than a contribution threshold value, construct a segmented growth period growth factor function corresponding to each crop through a multiple regression algorithm combined with a genetic optimization algorithm.

[0027] Specifically, the obtaining step of the crop planting difficulty score includes:

[0028] S211, obtain a comprehensive terrain modification difficulty score according to the slope, terrain height difference and terrain complexity obtained through the evaluation algorithm of the current region;

[0029] S212, obtain a current regional meteorological adaptability score through an evaluation algorithm according to the average temperature, precipitation and wind speed of the current region;

[0030] S213, obtain a current regional hydrological adaptability score through an evaluation algorithm according to the distance between the water source and the current region, the water flow path and the soil moisture information;

[0031] S214, according to the current regional comprehensive terrain transformation difficulty score, meteorological adaptability score and hydrological adaptability score, the current regional crop planting difficulty score is obtained by weighted average method.

[0032] Specifically, the step of S3 of planning secondary planting in the current region comprises:

[0033] S301, when the crop meeting the condition is one kind, then directly plant the corresponding type of crop in the current region;

[0034] S302, when the crop meeting the condition is more than one kind, then according to the number of crop types meeting the condition, obtain the shade tolerance, drought tolerance and lodging resistance of each type of crop, as well as the terrain height, slope, soil moisture, distance from water source, water flow path direction, historical wind speed and direction, and the planning planting proportion of the crop type meeting the user's planting demand, divide the current region by the grid algorithm of particle swarm optimization, and obtain the crop planting sub-region in the corresponding type;

[0035] S303, plant the corresponding crop in the crop planting sub-region, and obtain the crop growth score and corresponding yield in the corresponding planting period;

[0036] S304, feed back the corresponding type of crop growth score and corresponding yield to the grid algorithm of particle swarm optimization, and adjust the crop planting area in real time.

[0037] The terrain analysis system based on unmanned aerial vehicle remote sensing monitoring decision-making comprises a simulation module, an initial decision discrimination module and a secondary decision discrimination module.

[0038] The simulation module comprises a data acquisition unit, a model construction unit and a simulation evaluation unit.

[0039] The data acquisition unit is used to acquire multi-angle terrain images, laser measurement data, meteorological data and hydrological data of the current region, and user planting demand and estimated cost data.

[0040] The model construction unit is used to construct a three-dimensional terrain planting simulation model with hydrological and meteorological data of the region by simulation algorithm and three-dimensional generation algorithm according to the data acquired by the data acquisition unit.

[0041] The simulation evaluation unit is used to perform planting simulation and evaluation by the three-dimensional terrain planting simulation model with hydrological and meteorological data of the region and the crop segmented growth period growth factor function according to the corresponding crop in the crop planting attribute library, and obtain the planting difficulty score and simulation growth score of each crop in the current region.

[0042] Specifically, the initial decision discrimination module comprises a first initial decision unit and a second initial decision unit.

[0043] a first initial decision unit configured to select a crop meeting a first initial decision condition as a crop to be planted in the current region according to the set planting difficulty score threshold and a simulated growth score threshold and perform secondary planting planning in the current region according to the number of crop types meeting the condition and the planting attributes of the crops in the current region according to the user planting requirements;

[0044] The first initial decision condition is that there are at least one type of crop with a planting difficulty score less than and a simulated growth score greater than .

[0045] A second initial decision unit is configured to select a crop meeting a second initial decision condition as a crop to be planted in the current region, and perform reconstruction evaluation and discrimination on the current region according to the planting attributes of the crops meeting the second initial decision condition, to obtain a reconstructed current region and perform secondary planting planning.

[0046] The second initial decision condition is that all crop planting difficulty scores are greater than or equal to but there is at least one type of crop with a simulated growth score greater than .

[0047] Specifically, the secondary decision discrimination module includes a reconstruction evaluation unit, a first reconstruction decision unit, a second reconstruction decision unit, and a third reconstruction decision unit.

[0048] The reconstruction evaluation unit is configured to set a reconstruction difficulty threshold according to the user planting requirements and the estimated cost data, and evaluate the difficulty of corresponding environmental reconstruction of the corresponding crops meeting the second initial decision condition in the current region, to obtain the environmental reconstruction difficulty of the corresponding crops.

[0049] The first reconstruction decision unit is configured to select a crop meeting a first reconstruction decision condition for planting according to the first reconstruction decision condition, and perform secondary reconstruction on the current region according to the number of crop types meeting the condition, the planting attributes of the corresponding crops, and the environmental attributes of the current region, while repeating the process of S3 to perform secondary planting planning on the reconstructed current region.

[0050] The first reconstruction decision condition is that at least one crop meets the user planting requirements and has an environmental reconstruction difficulty less than the reconstruction difficulty threshold.

[0051] The second reconstruction decision unit is configured to select a corresponding crop with the minimum estimated cost as a corresponding crop to be planted in the current region according to a second reconstruction decision condition, and repeat the process of S6 to perform environmental reconstruction and planting planning in the current region.

[0052] The second transformation decision condition is that all crops do not meet the user planting requirements, but there is a crop that meets the environmental transformation difficulty less than the transformation difficulty threshold;

[0053] The third transformation decision unit is configured to select, according to the third transformation decision condition, a crop with the minimum crop planting difficulty score, the maximum simulation growth score, the corresponding type crop being the user planting requirement crop and the transformation cost being less than or equal to the estimated cost as the current region planting crop, and transform and plant the current region according to the selected planting crop;

[0054] The third transformation decision condition is that all crop planting difficulty scores are greater than or equal to the planting difficulty score threshold, and the simulation growth score is less than or equal to the simulation growth score threshold.

[0055] Compared with the prior art, the present application has the following advantages:

[0056] The present application overcomes the problems of low efficiency and limited precision of traditional manual measurement by constructing a high-precision regional three-dimensional terrain planting simulation model with hydrology and meteorology based on unexplored area multi-angle topographic images, laser measurement data, meteorological data and hydrological data, combined with simulation and three-dimensional generation algorithm. Secondly, the planting simulation is carried out by combining the configured crop planting attribute library, the regional three-dimensional terrain planting simulation model with hydrology and meteorology and the crop segmented growth period growth factor function, the planting difficulty and simulation growth score of each crop at each growth stage in the unexplored area are accurately evaluated, and accurate analysis results are provided for scientific selection and current regional agricultural development. Dynamic threshold setting selects suitable crops to ensure the selection of the most suitable crops, while considering user planting requirements and budget constraints. For regions that do not meet the direct planting conditions, an environmental transformation optimization scheme is proposed to make the originally unsuitable planting area also efficient within the budget. Through this process, not only is resource mismatch avoided, but also agricultural production efficiency is further improved. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 The present application is based on the topographic analysis method flowchart of unmanned aerial vehicle remote sensing monitoring decision of embodiment 1;

[0058] Figure 2 The present application is based on the regional transformation discrimination flowchart of embodiment 1;

[0059] Figure 3 The present application is based on the topographic analysis system module diagram of unmanned aerial vehicle remote sensing monitoring decision of embodiment 2. DETAILED DESCRIPTION

[0060] Embodiment 1:

[0061] Please refer to Figure 1The application provides a topographic analysis method based on unmanned aerial vehicle remote sensing monitoring decision, which is used for crop planting planning evaluation in an agricultural development area.

[0062] S1, obtain current regional multi-angle topographic images, laser measurement data, meteorological data and hydrological data, and user planting demand and estimated cost data, construct a regional three-dimensional terrain planting simulation model with hydrological and meteorological data by a simulation simulation algorithm combined with a three-dimensional generation algorithm;

[0063] Further, in the embodiment, the current regional multi-angle topographic images are measured by DJI M3M (Mavic 3 multi-spectral version), the main angle of the route can be adjusted to align the long side, and the other parameters are set to default. When planning the shooting task boundary, attention should be paid to the surrounding high-altitude obstacles such as high-voltage lines, windmills and other obstacles, and whether they have an impact within the flight height. When planning the land, attention should be paid to, because the elevation map is viewed, if there are other factors outside the field, the noise segmentation algorithm is used to automatically plan to remove, such as high-voltage lines, working agricultural machinery, field ridges, etc., if not planned out, it will affect the local elevation judgment. After shooting, image and point cloud splicing are carried out, and a high-precision farmland digital terrain model is generated to perform elevation analysis on the target field. Further, in the embodiment, the meteorological data and hydrological data and the user planting demand and estimated cost data are used to further refine the accuracy of the land topography analysis while performing the elevation analysis.

[0064] Further, in the embodiment, the steps of constructing the regional three-dimensional terrain planting simulation model with hydrological and meteorological data include:

[0065] S101, according to the slope and topographic height data measured in the obtained current regional multi-angle topographic images and laser data, a three-dimensional terrain sub-model of the current region is generated by a three-dimensional generation algorithm; the three-dimensional generation algorithm is preferably a Delaunay triangulation algorithm combined with a multi-view stereo (MVS) reconstruction algorithm;

[0066] S102, according to the obtained current regional meteorological data, a pre-trained meteorological forecast model is configured to obtain a regional meteorological simulation sub-model, and the simulated meteorological state of each time period in the current region is output; the meteorological forecast model is preferably constructed by a statistical downscaling model or a mesoscale meteorological model;

[0067] S103, according to the current regional hydrological data, a hydrological model is configured to be trained to obtain a regional hydrological simulation sub-model, and the distance of water source from the current region, the water flow path and the soil moisture are simulated; the hydrological model is preferably a distributed hydrological model SWAT;

[0068] S104, integrate the current regional three-dimensional terrain sub-model, the regional meteorological simulation sub-model and the regional hydrological simulation sub-model through an integration algorithm to obtain a regional three-dimensional terrain model with hydro-meteorology;

[0069] S105, construct a segmented growth period growth factor function according to the planting environment conditions and simulated meteorological state of each growth period of the crops, the distance between the water source and the current region, the water flow path and the soil humidity, and train the segmented growth period growth factor function into the constructed crop segmented growth simulation sub-model to obtain the corresponding growth state of each crop under different growth conditions;

[0070] S106, integrate the pre-trained crop segmented growth simulation sub-model into the regional three-dimensional terrain model with hydro-meteorology to obtain a regional three-dimensional terrain planting simulation model with hydro-meteorology, and when the current region changes, repeat the process of S101-S106 to obtain a fine-tuned regional three-dimensional terrain planting simulation model with hydro-meteorology for each region, and dynamically label the simulated meteorology, hydrology and crop growth state according to the time dimension.

[0071] The process generates a high-precision three-dimensional terrain sub-model by obtaining multi-angle terrain images and laser measurement data, overcoming the problems of low efficiency and limited precision of traditional manual measurement. Secondly, the pre-trained meteorological prediction model and hydrological model are used to obtain the regional meteorological simulation sub-model and the regional hydrological simulation sub-model, which can accurately predict the meteorological changes and water flow path in the region, providing a scientific basis for irrigation system design. On this basis, the three sub-models are integrated through an integration algorithm to form a comprehensive three-dimensional terrain model, which comprehensively considers the interactive influence of soil type, hydrological conditions and other factors on terrain. Further, the segmented growth period growth factor function is introduced in step S105, which is trained with the specific environmental conditions of each growth period of the crops to ensure accurate simulation of different growth stages. Finally, the crop segmented growth simulation sub-model is integrated into the overall model to realize dynamic labeling of the crop growth state. When the current region changes, the above process can be repeated for fine-tuning and optimization.

[0072] S2, configure a crop planting attribute library, and perform planting simulation and evaluation on each crop in the crop planting attribute library according to the planting demand parameters of each crop through the regional three-dimensional terrain planting simulation model with hydro-meteorology and the crop segmented growth period growth factor function to obtain the planting difficulty score and the simulated growth score of each crop in the current region;

[0073] Further, in the embodiment, the construction step of the segmented growth period growth factor function is as follows:

[0074] S201, setting the crop growth stage includes the sowing period, seedling stage, vegetative growth period, reproductive growth period and mature period, according to the parameters between each crop in different growth stages and meteorology, hydrology, through factor analysis algorithm, the meteorological and hydrological parameter space with contribution greater than the contribution threshold is obtained by analysis;

[0075] S202, according to the meteorological and hydrological parameter space with contribution greater than the contribution threshold, the segmented growth period growth factor function corresponding to each crop is constructed by multivariate regression algorithm combined with genetic optimization algorithm.

[0076] Further, the segmented growth period growth factor function corresponding to each crop in the embodiment is constructed by multivariate regression algorithm combined with genetic optimization algorithm and the meteorological and hydrological parameter space with contribution greater than the contribution threshold in each growth period.

[0077] It needs to be further explained that the specific implementation process of multivariate regression algorithm combined with genetic optimization algorithm in the embodiment includes:

[0078] After the meteorological and hydrological parameters with contribution greater than the contribution threshold in each growth period are screened out based on the factor analysis algorithm, the dimensionality of the screened parameters is reduced by principal component analysis algorithm, the multicollinearity between variables is eliminated, and the principal component variables are obtained; then the ordinary least squares algorithm is used, the growth factor is taken as the dependent variable, and the principal component variable is taken as the independent variable, the initial model of multivariate linear regression is constructed, and the quantitative relationship between the parameters and the growth factor is initially established; then the genetic optimization algorithm is introduced, the determination coefficient (R²) of the model is taken as the fitness function, and the coefficients of the regression model are iteratively optimized by genetic operations such as selection, crossover and mutation; in the iteration process, for parameters with nonlinear relationship, such as wind speed and water source distance, the logarithmic transformation or polynomial expansion algorithm is used to convert them into linear form and include them in the regression model; after several rounds of genetic iteration, the regression coefficients with the optimal fitting effect are obtained until the fitness function value converges, and the segmented growth period growth factor function containing the key meteorological and hydrological parameters in each growth period and corresponding to the biological mechanism of crop growth is finally constructed.

[0079] Further, the specific reasons for selecting the parameters corresponding to the segmented growth period growth factor function corresponding to each crop in the embodiment include:

[0080] At the sowing stage, the parameters of the growth factor function corresponding to the segmented growth period include temperature, moisture, and soil humidity, and the like, because the seed germination requires suitable temperature, moisture, and soil aeration; at this time, temperature and soil humidity are the key factors, and excessively high or low temperature can lead to a decrease in the seed germination rate, and excessively dry or wet soil can affect seed water absorption and respiration; in addition, at the sowing stage, the drought-tolerant crop varieties still have a certain germination capacity when the soil humidity is low, which is reflected by the interaction term of the drought tolerance of the crop and the soil humidity; when the soil humidity is low, the drought-tolerant crop variety has a larger value, and the contribution of the interaction term of the drought tolerance of the crop and the soil humidity to the growth factor is relatively large, that is, the drought-tolerant crop variety can alleviate the inhibition of low soil humidity on germination to a certain extent; on the contrary, the drought-intolerant crop variety has a smaller value, and the alleviating capacity of the corresponding crop variety to the soil humidity lower than the corresponding required growth humidity is low, so that the growth state of the corresponding crop variety is inhibited to a greater extent. represents the drought resistance score of the ith crop, and the embodiment is comprehensively evaluated by a comprehensive evaluation algorithm combined with the drought property parameters of the corresponding crop;

[0081] At the seedling stage, the parameters of the growth factor function corresponding to the segmented growth period include photoperiod, soil humidity, wind speed, shade-tolerant variety attribute, light and soil humidity interaction term, for the photoperiod-sensitive crop, the photoperiod function of each crop adjusts the influence of light on the growth factor; for long-day crops, when the light duration exceeds the threshold value, the growth is promoted, because the long day meets the growth and development needs, promotes photosynthesis and seedling morphological development; for short-day crops, the growth is promoted when the light duration is lower than the threshold value; soil humidity continues to affect root growth and nutrient absorption; the growth factor function corresponding to the segmented growth period at the seedling stage has an inverse relationship with the wind speed, because strong wind is not conducive to the seedling, and the greater the wind speed, the more obvious the inhibition of the seedling growth. For the light and soil humidity interaction term, when the light is sufficient, suitable soil humidity promotes photosynthesis, and insufficient soil humidity limits light use efficiency, and vice versa, and the interaction term reflects this mutual restraint relationship; the shade-tolerant variety can still maintain a certain growth when the light is weak, and when the light is insufficient, the basic growth maintenance parameter value of the shade-tolerant variety is larger, and the contribution of the light and soil humidity interaction term to the growth factor is relatively large; this means that the shade-tolerant variety can maintain the growth trend by enhancing the compensation effect of soil humidity under low light conditions; and the contribution of the interaction term of the non-shade-tolerant variety is smaller, and the growth is more dependent on sufficient light conditions.

[0082] ​​From the biological mechanism, shade-tolerant varieties increase the content of chlorophyll b in low light environment, improve weak light absorption efficiency, and allocate more photosynthetic products to the root system to enhance the interactive effect by enhancing water and nutrient absorption capacity. In the mathematical model, shade-tolerant varieties have larger interaction coefficients and basic growth maintenance parameters. This feature has important application value in agricultural production, such as optimizing intercropping mode, reducing energy consumption of facility agriculture light supplement, and providing index reference for shade-tolerant variety breeding.

[0083] During the vegetative growth period, the parameters corresponding to the segmented growth period growth factor function include: under the condition that other variables remain unchanged, the distance to water source is increased, and a large amount of water is needed during the growth stage. If the distance to water source is far, water transportation is difficult, and growth is limited. The limiting effect is reflected by the distance to water source;

[0084] During the reproductive growth period, the segmented growth period growth factor function adds a water flow path complexity parameter. The parameter is quantified by combining indicators such as the number of tributaries, tortuosity, and water flow bifurcation coefficient with a fuzzy evaluation algorithm. The water flow path complexity parameter affects the uniformity of water and nutrient distribution, and then acts on the development of reproductive organs. Too many tributaries will cause terminal water flow attenuation, too large tortuosity will easily cause water shortage on convex banks and water accumulation on concave banks, and high water flow bifurcation coefficient will lead to differences in nutrient concentration gradient, all of which will cause uneven development of reproductive organs, such as unfilled grains and low fruit setting rate. Therefore, the water flow path needs to be optimized, and the number of tributaries, tortuosity, and water flow bifurcation coefficient need to be controlled within a reasonable threshold, in order to achieve uniform distribution of water and nutrients in the field, reduce the risk of flower and fruit drop, and ensure normal development of reproductive organs;

[0085] At the mature stage, the parameters of the segmented growth period growth factor function include radiation intensity, precipitation, soil humidity, wind speed, and water source distance, each parameter affects the maturation process through specific physiological mechanisms, radiation intensity and temperature cooperatively regulate the material conversion and accumulation in the crop maturation process, the principle is that radiation as the energy source of photosynthesis, its intensity directly affects the amount of photosynthetic product, and temperature controls the synthesis and conversion rate of storage materials such as sugar and starch by regulating enzyme activity; Precipitation has a dual effect on crop quality in a linear relationship, and appropriate precipitation can maintain the cell turgor pressure of the plant and promote the transportation of metabolic substances, while excessive precipitation will cause the breeding of pathogenic bacteria due to high field humidity, the principle is that high humidity environment provides suitable breeding conditions for fungi, bacteria and other pests; Soil humidity acts on the late physiological activity of crops in a linear form, the principle is that appropriate soil humidity can guarantee the water absorption function of the root system, maintain the balance of leaf transpiration and nutrient transportation, and then affect the maturation process such as grain filling or fruit enlargement; Wind speed and water source distance inhibit the maturation in the form of inverse, among them, strong wind in the maturation period is easy to cause crop lodging, the principle is that the mechanical tissue of the plant stem is aging at the maturation stage, the wind resistance decreases, when the mechanical stress generated by strong wind exceeds the threshold value of the stem, lodging is caused, and too far water source distance will affect water supply, the principle is that the resistance of soil water transportation to the root system increases with the increase of distance, which leads to the decrease of available water amount of the plant, and affects the water metabolism balance in the late maturation period. These parameters regulate physiological processes such as material accumulation efficiency and environmental stress resistance, and jointly affect the yield and quality formation of crops at the mature stage;

[0086] Among the above variables, all variables do not affect crops alone, therefore, corresponding interaction factors are added here to reflect the relationship between each variable.

[0087] Further, in the embodiment, the obtaining step of the crop planting difficulty score comprises:

[0088] S211, obtaining a comprehensive terrain modification difficulty score according to the current regional slope, terrain height difference, and terrain complexity obtained by the evaluation algorithm;

[0089] It should be further pointed out that in the embodiment, one implementation manner of the comprehensive terrain modification difficulty score is specifically:

[0090] Based on the regional DEM data, the slope value of each sampling point is extracted by the terrain analysis algorithm, and then the minimum-maximum normalization algorithm is used to map the slope to the interval of 0-1 to obtain the slope normalization feature. Then, the elevation difference between the highest point and the lowest point is calculated, and the height difference is converted into the corresponding reconstruction difficulty coefficient based on the threshold segmentation function algorithm. Secondly, the gully density, ridge relief and other terrain feature parameters are extracted from the current regional digital elevation model data, and the fractal dimension is calculated by the box dimension algorithm to quantify the terrain complexity. Finally, the slope normalization value, height difference difficulty coefficient and terrain complexity fractal dimension are linearly weighted and summed according to the preset weight, and the terrain reconstruction difficulty score is obtained through the comprehensive evaluation model.

[0091] Further, in the present embodiment, the terrain reconstruction difficulty is graded according to the size of the slope S; when , the terrain reconstruction difficulty coefficient , indicating that the terrain is relatively flat, and the reconstruction difficulty is low; when , the terrain reconstruction difficulty coefficient ; when , the terrain reconstruction difficulty coefficient , indicating that the slope is large, and the reconstruction difficulty is high, such as the need to build terraces and other large-scale engineering; when , the terrain reconstruction difficulty coefficient , indicating that the terrain is steep, and the reconstruction is extremely difficult, which may require special engineering measures and high-cost investment.

[0092] Further, in the present embodiment, the terrain height difference between the highest point and the lowest point in the region is calculated from the laser measurement data, denoted as ;

[0093] When m, the terrain height difference difficulty coefficient ; when m, the terrain height difference difficulty coefficient ; when m, the terrain height difference difficulty coefficient ; when m, the terrain height difference difficulty coefficient ; the larger the height difference, the more complex the reconstruction work such as land leveling and irrigation and drainage facilities, and the difficulty coefficient increases accordingly.

[0094] Further, in the present embodiment, the terrain complexity is calculated by using the fractal dimension method on the multi-angle terrain image, denoted as ;

[0095] When , the terrain complexity difficulty coefficient ; when , the terrain complexity difficulty coefficient ; when , the terrain complexity difficulty coefficient ; when , the terrain complexity difficulty coefficient The more complex the terrain, such as the presence of a large number of gullies, undulating, etc. In the land planning, mechanical operation and other aspects of the greater difficulty.

[0096] S212, according to the current regional average temperature, precipitation, wind speed, through the evaluation algorithm to obtain the current regional weather adaptability score;

[0097] It should be further explained that, in the embodiment, one implementation of the current regional weather adaptability score is specifically:

[0098] Based on the current regional average temperature, precipitation, wind speed and other meteorological parameters, first, the deviation degree of the actual temperature value and the optimum temperature of the crop is calculated by the Gaussian membership function algorithm, and the temperature suitability score is obtained; secondly, the precipitation is evaluated by using the piecewise linear transformation algorithm, when the precipitation is lower than the lower limit or higher than the upper limit, the precipitation suitability score is obtained by using the linear decreasing function; the wind speed is converted into adaptability index by using the reciprocal transformation algorithm, the greater the wind speed, the lower the score, and the wind speed suitability score is obtained; then the minimum-maximum standardization algorithm is used to normalize the factor score, and the dimension influence is eliminated; finally, the weight of each meteorological factor is calculated based on the entropy weight method algorithm, and the linear weighted aggregation model is used to multiply and accumulate the standardized factor score and the corresponding weight, and the weather adaptability score is obtained.

[0099] In the embodiment, according to the current regional historical meteorological data output by the regional weather simulation sub-model, such as multi-year average temperature, precipitation, wind speed and the like; and the future forecast meteorological data, the suitable range of meteorological conditions of crops in the crop planting attribute library is compared; the temperature difference absolute value, that is, the absolute value of the difference between the crop suitable temperature range and the actual average temperature, the precipitation difference absolute value, that is, the absolute value of the difference between the crop suitable precipitation range and the actual average precipitation, and the wind speed influence coefficient are calculated, and the wind damage tolerance of crops is determined, such as wind-sensitive crops, when the wind speed exceeds a certain threshold, the wind speed influence coefficient takes a larger value.

[0100] S213, according to the distance between the water source and the current region, the water flow path and the soil moisture information, through the evaluation algorithm to obtain the current regional hydrological adaptability score;

[0101] It should be further explained that, in the embodiment, one implementation of the current regional hydrological adaptability score is specifically:

[0102] Based on the actual distance data between the water source and the region, the distance is converted into the water supply convenience index through the inverse distance decay algorithm; based on the branch number and river channel bending degree of the water flow path and other characteristic parameters, the path complexity index is calculated through the network complexity analysis algorithm in graph theory; based on the measured value of soil moisture and the threshold of field water holding capacity, the humidity fit score of the actual humidity and the suitable interval is calculated through the linear membership function algorithm; the water supply convenience index, the path complexity index and the humidity fit score are subjected to non-dimensionalization processing through the minimum-maximum standardization algorithm, and then the objective weights of the indexes are determined based on the entropy weight method, and finally the hydrological adaptability score is obtained through the linear weighted aggregation algorithm.

[0103] In this embodiment, the distance between the water source and the current region, the water flow path and the soil moisture information obtained by the regional hydrological simulation sub-model are utilized. The water source distance difficulty coefficient is calculated, which is greater when the distance is farther, and different coefficient values can be set according to the distance range; the water flow path complexity coefficient is determined according to the tortuosity of the water flow path, whether there are obstacles and other conditions, and the water flow path complexity coefficient is greater when the water flow path is more complex; the soil moisture difference absolute value, i.e. the absolute value of the difference between the actual soil moisture and the suitable soil moisture range of crops, is obtained by using the evaluation algorithm according to the calculated data to obtain the current regional hydrological adaptability score.

[0104] S214, according to the current regional comprehensive terrain modification difficulty score, the meteorological adaptability score and the hydrological adaptability score, the current regional crop planting difficulty score is obtained through the weighted average method.

[0105] It needs to be further explained that one implementation manner of the current regional crop planting difficulty score in this embodiment is specifically:

[0106] Based on the terrain modification difficulty score, the meteorological adaptability score and the hydrological adaptability score, first, a judgment matrix is constructed through the analytic hierarchy process, and the index weight system is obtained after eigenvalue calculation and consistency check; then, considering the positive correlation between the terrain modification difficulty score and the planting difficulty, the negative correlation between the meteorological adaptability score and the hydrological adaptability score and the planting difficulty, the three scores are linearly combined through the weighted aggregation algorithm, wherein the meteorological adaptability score and the hydrological adaptability score need to be adjusted to be positively correlated with the planting difficulty through the polarity conversion algorithm; finally, the comprehensive score is mapped to the 0-100 score interval through the linear transformation algorithm, forming the crop planting difficulty score quantitatively representing the severity of the planting conditions.

[0107] Further, in this embodiment, the weighting coefficients of the corresponding variables in the weighted average method are obtained through a large number of actual case analysis and expert experience judgment.

[0108] The process ensures the accuracy and applicability of the model by setting the parameter space between crops at different growth stages and meteorology and hydrology, and constructing a segmented growth factor function corresponding to each crop. These functions comprehensively consider temperature, humidity, precipitation, light intensity, wind speed, water source distance and water flow path, as well as the drought tolerance, photoperiod function and shade tolerance of crops, to accurately assess the growth status of crops at different growth stages; further, on the basis of configuring the crop planting attribute library, the planting simulation and evaluation are carried out through the regional three-dimensional terrain planting simulation model with hydrology and meteorology and the crop segmented growth factor function, to obtain the planting difficulty score and the simulation growth score of the current regional crops. This process not only comprehensively considers the terrain modification difficulty, meteorological adaptability and hydrological adaptability, but also ensures the comprehensiveness and accuracy of the evaluation results through weighted average method; specifically, the terrain modification difficulty score is graded according to slope, terrain height difference and terrain complexity, to ensure the feasibility of the terrain modification scheme; the meteorological adaptability score is calculated by comparing the historical meteorological data with the crop suitable range, calculating the temperature difference absolute value, precipitation difference absolute value and wind speed influence coefficient, to ensure the adaptability of crops to meteorological conditions; the hydrological adaptability score is calculated by water source distance, water flow path and soil moisture information, to calculate the water source distance difficulty coefficient, water flow path complexity coefficient and soil moisture difference absolute value, to ensure the adaptability of crops to water conditions; finally, the planting difficulty score and the simulation growth score of the current regional crops are obtained through weighted average method, to provide intelligent and personalized decision support for farmers and promote the fine development of modern agricultural management.

[0109] S3, setting a planting difficulty score threshold and a simulation growth score threshold When there is a crop with a planting difficulty score less than the planting difficulty score threshold and a simulation growth score greater than the simulation growth score threshold , and the number of crops meeting the conditions is greater than or equal to 1, the crop meeting the conditions is selected as the current regional crop, and the current region is planned for secondary planting according to the crop type number and crop planting attributes that meet the conditions; it should be noted that the current region in this embodiment is the to-be-developed region in the user planting demand;

[0110] S4, when all crop planting difficulty scores are greater than or equal to the planting difficulty score threshold , but there is a crop with a simulation growth score greater than the simulation growth score threshold , the current region is evaluated and judged for modification according to the crop planting attributes that meet the condition of being greater than the simulation growth score threshold , to obtain the modified current region and carry out secondary planting planning.

[0111] Further, the step of planning secondary planting in the current area in the embodiment includes:

[0112] S301, when the crop meeting the condition is one, then directly plant the corresponding type of crop in the current area;

[0113] S302, when the crop meeting the condition is more than one, then according to the number of crop types meeting the condition, obtain the shade tolerance, drought tolerance and lodging resistance of each type of crop, as well as the terrain height, slope, soil moisture, distance from water source, water flow path direction, historical wind speed and direction, and the planning planting proportion of the crop type meeting the user's planting demand, divide the current area by the grid algorithm of particle swarm optimization, and obtain the crop planting sub-area in the corresponding type;

[0114] It should be further explained that the specific implementation mode of the grid algorithm of particle swarm optimization for dividing the current area in the embodiment is:

[0115] Firstly, the current region is divided into regular grid cells, and based on the environmental parameters of each grid cell, such as the average slope and soil moisture obtained by spatial interpolation algorithm, the matching degree score of each environmental parameter and crop attribute is calculated using the analytic hierarchy process to construct the environment-crop matching matrix; secondly, the particle swarm is initialized, each particle represents a regional division scheme, the particle position corresponds to the planting allocation of different crops in each grid cell, and the particle velocity represents the adjustment direction and amplitude of the allocation scheme; in the iteration process, according to the planning planting proportion constraint condition, the fitness of each particle is obtained through the objective function; thirdly, based on the historical optimal position of the particle itself and the global optimal position, the velocity-position update formula of the particle swarm optimization algorithm is used to iteratively update the particle to adjust the crop planting allocation of each grid cell; when the iteration reaches the preset number or the fitness converges, the optimal crop sub-regional division scheme is output; in the actual planting stage, based on the crop growth monitoring data, such as the vegetation index obtained by the unmanned aerial vehicle multi-spectral image analysis algorithm, and the yield estimation model, the growth score and yield of each crop are obtained, and these feedback data are used as new constraint conditions or optimization objectives, and the particle swarm optimization algorithm is used to dynamically adjust the planting area again, so as to realize the continuous optimization of the planting scheme. The objective function is constructed by maximizing the overall crop yield and minimizing the weighted value of environmental risk combined with the least square method, which is: based on the historical yield data and the current planting area environmental parameters, the yield estimation model of each crop is constructed by using the random forest regression algorithm to obtain the expected yield of each crop in different sub-regions; at the same time, for environmental parameters such as terrain height, slope, and soil moisture, the environmental risk of planting different crops in each sub-region is evaluated by fuzzy comprehensive evaluation algorithm, such as the risk of soil erosion caused by planting drought-tolerant crops in high-slope areas, the risk of lodging caused by planting weak lodging-resistant crops in high-wind areas, etc., and the corresponding weight is given according to the risk type; secondly, the least square method is used to maximize the overall crop yield and minimize the weighted value of environmental risk as the optimization direction to construct the objective function; specifically, the sum of the expected yield of each sub-region crop is taken as the yield optimization item, and the sum of the product of the environmental risk value and the corresponding weight is taken as the risk penalty item, the model parameters are adjusted by the least square method to maximize the weighted difference between the yield optimization item and the risk penalty item, and finally the objective function balancing yield and risk is formed.

[0116] It needs to be further explained that the lodging resistance in the embodiment refers to the ability of crops to resist stem lodging caused by strong wind, which is combined with historical wind speed and direction data to plan the planting of crops with strong lodging resistance in high-wind areas to reduce the risk of lodging at maturity.

[0117] The terrain height refers to the regional altitude parameter, which affects the vertical distribution of temperature, light duration and drainage conditions. High terrain areas may have lower temperature, large diurnal temperature difference, and are suitable for planting cool-loving crops.

[0118] Slope reflects the degree of ground inclination, affecting water flow speed, soil erosion risk and mechanical operation convenience. Regions with high slope need to match crops with developed root systems or drought-tolerant crops to reduce water and soil loss.

[0119] The planning planting proportion refers to the planting area proportion of each crop set by the user according to market demand, rotation plan, etc., which is used as a constraint condition of the particle swarm optimization algorithm to ensure that the optimized regional division result meets the planting planning target.

[0120] S303, planting the corresponding crop in the crop planting sub-region, and obtaining the growth score and corresponding yield of the crop in the corresponding planting period;

[0121] S304, feeding the growth score and corresponding yield of the corresponding type of crop to the particle swarm optimization grid algorithm to adjust the crop planting area in real time.

[0122] This process accurately selects crops suitable for planting in the current region by setting planting difficulty scores and simulating growth score thresholds, and conducts secondary planting planning according to user planting needs, significantly improving the scientific nature and economic benefits of agricultural production. First, when there is only one crop that meets the conditions, directly planting this crop simplifies the decision-making process and improves efficiency. When there are multiple crops that meet the conditions, the particle swarm optimization grid algorithm is used to combine crop characteristics such as shade tolerance and drought tolerance, and environmental factors such as terrain height, slope, and soil moisture, to finely divide the region and ensure that each crop can grow in the most suitable environment. This not only optimizes space utilization, but also enhances the stress resistance and yield stability of crops. Further, by obtaining the growth score and yield of the crop in the corresponding planting period and feeding it back to the particle swarm optimization grid algorithm, the planting area is dynamically adjusted to enable real-time optimization of the model according to actual growth conditions. This method not only improves the accuracy of crop growth prediction, but also enhances the adaptive ability of the system, ensuring long-term stable high yield and efficiency.

[0123] Further, please refer to Figure 2 In this embodiment, the step of evaluating and discriminating the current region for modification includes:

[0124] S5, according to the user's planting needs and estimated cost data, set the modification difficulty threshold, and evaluate the difficulty of corresponding environmental modification for the corresponding crop in the current region that meets the conditions in S4, to obtain the environmental modification difficulty of the corresponding crop;

[0125] S6, when there is at least one crop satisfying the user planting demand and the environmental modification difficulty is less than the modification difficulty threshold value, the crop satisfying the condition is selected for planting, and the current area is secondarily modified according to the number of crop types satisfying the condition, the corresponding crop planting attribute and the current area environment attribute, and the S3 process is repeated for secondary planting planning of the modified current area;

[0126] S7, when all crops do not satisfy the user planting demand, but there is a crop satisfying the corresponding environmental modification difficulty less than the modification difficulty threshold value, the corresponding crop with the minimum estimated cost is selected as the corresponding planting crop of the current area, and the S6 process is repeated for the current area environmental modification and planting planning according to the planting demand parameters of the crops satisfying the user planting demand condition;

[0127] S8, when all crop planting difficulty scores are greater than or equal to the planting difficulty score threshold value , and the simulation growth score is less than or equal to the simulation growth score threshold value , analyze all crop attributes, when there is a crop with the minimum planting difficulty score and the maximum simulation growth score corresponding to the type of crop as the user planting demand crop and the modification cost is less than or equal to the estimated cost, modify and plant the current area, otherwise do not plant the current area.

[0128] It should be further pointed out that one implementation way of the current area modification evaluation and discrimination in the embodiment is as follows:

[0129] Based on the user planting demand parameters and historical estimated cost data, a judgment matrix is constructed and the weight is calculated by the analytic hierarchy process to obtain a scientific reconstruction difficulty threshold. At the same time, based on the terrain reconstruction difficulty evaluation algorithm, hydrological adaptability evaluation algorithm, etc., the environmental parameters required for crop growth are compared with the current regional measured data, and the environmental reconstruction difficulty score of the corresponding crop is obtained through a linear weighted model. When there is at least one crop that meets the planting requirements and the reconstruction difficulty is lower than the threshold, based on the shade tolerance, lodging resistance and other planting properties of the crops that meet the conditions and the environmental properties such as regional slope and soil humidity, the region is divided into grids through a multi-objective particle swarm optimization algorithm to determine the crop planting sub-region, and then based on the three-dimensional terrain planting simulation model and the regional meteorological simulation sub-model, the S3 process is repeated for secondary planting planning. If all crops do not meet the planting requirements but there are crops with reconstruction difficulty lower than the threshold, based on the material cost, labor cost and other data of the environmental reconstruction of each crop, the crop with the minimum estimated cost is selected through a greedy algorithm, and then the reconstruction and planning are performed according to the S6 process. When the difficulty score of all crops exceeds the threshold and the growth score is lower than the threshold, based on the TOPSIS multi-attribute decision-making algorithm, the crop planting difficulty, simulated growth, reconstruction cost and other attributes are standardized and weighted sorted to select the crop with the smallest planting difficulty and the largest growth score. If the crop meets the user's planting requirements and the reconstruction cost does not exceed the estimated amount, the region is reconstructed and planting planning is performed based on the hydrological model and terrain reconstruction algorithm, otherwise the planning process is terminated.

[0130] This process sets the reconstruction difficulty threshold according to the user's planting requirements and estimated cost, and evaluates the environmental reconstruction difficulty of crops that meet the conditions, ensuring the feasibility and economy of the reconstruction scheme. When there is at least one crop that meets the user's planting requirements and has a lower environmental reconstruction difficulty than the reconstruction difficulty threshold, the crop is selected for planting, and the crop characteristics and environmental attributes are combined for secondary reconstruction and planting planning, achieving optimal allocation and efficient use of resources. For the case where all crops do not completely meet the user's planting requirements but the reconstruction difficulty meets the conditions, the crop with the minimum estimated cost is selected for reconstruction and planting, reducing the cost risk and improving the flexibility of decision-making. Finally, when the planting difficulty and simulated growth score of all crops are not ideal, the crop with the optimal overall performance within the budget is selected for reconstruction and planting planning by analyzing all crop attributes, avoiding blind investment and ensuring the sustainability of the project. This method not only optimizes the planting planning process, but also enhances the adaptive ability of the system, which can dynamically adjust the scheme according to different conditions, accurately match user requirements, reasonably control reconstruction costs and maximize crop growth potential.

[0131] Example 2:

[0132] Please refer to Figure 3The application provides another embodiment: a topographic analysis system based on unmanned aerial vehicle remote sensing monitoring decision, comprising: a simulation module, an initial decision discrimination module and a secondary decision discrimination module;

[0133] The simulation module is used for simulation analysis and simulation of the current regional planting state, and obtains a crop planting difficulty score and a simulation growth score of the current region.

[0134] The simulation module comprises a data acquisition unit, a model construction unit and a simulation evaluation unit.

[0135] The data acquisition unit is used for acquiring multi-angle topographic images, laser measurement data, meteorological data and hydrological data of the current region, and user planting requirements and estimated cost data.

[0136] The model construction unit is used for constructing a regional three-dimensional terrain planting simulation model with hydrological and meteorological data by using a simulation algorithm and a three-dimensional generation algorithm according to the data acquired by the data acquisition unit.

[0137] The simulation evaluation unit is used for performing planting simulation and evaluation by using the regional three-dimensional terrain planting simulation model with hydrological and meteorological data and a crop segmented growth period growth factor function according to the corresponding crops in a crop planting attribute library, so as to obtain a crop planting difficulty score and a simulation growth score of each crop in the current region.

[0138] The initial decision discrimination module is used for making planting and reconstruction decisions of the current region according to the crop planting difficulty score and the simulation growth score of each crop in the current region and a set decision threshold.

[0139] The initial decision discrimination module comprises a first initial decision unit and a second initial decision unit.

[0140] The first initial decision unit is used for selecting a crop meeting a first initial decision condition as a crop planted in the current region according to a set planting difficulty score threshold and a simulation growth score threshold , and making secondary planting planning of the current region according to the number of crops meeting the condition, crop planting attributes and the user planting requirements; the first initial decision condition is that there is a crop type with a crop planting difficulty score less than and a simulation growth score greater than , and the number of the crop type is greater than or equal to 1.

[0141] The second initial decision unit is used for selecting a crop meeting a second initial decision condition as a crop planted in the current region, making reconstruction evaluation and discrimination of the current region according to the planting attributes of the crop meeting the second initial decision condition, obtaining a reconstructed current region and making secondary planting planning.

[0142] the second initial decision condition is that all crop planting difficulty scores are greater than or equal to , but there is a crop whose simulated growth score is greater than .

[0143] The secondary decision discrimination module is configured to evaluate the difficulty of transforming the current area and to discriminate the transformation of the area.

[0144] The secondary decision discrimination module includes a transformation evaluation unit, a first transformation decision unit, a second transformation decision unit, and a third transformation decision unit.

[0145] The transformation evaluation unit is configured to set a transformation difficulty threshold according to the user planting demand and the estimated cost data, to evaluate the difficulty of transforming the corresponding environment for the corresponding crop that meets the second initial decision condition in the current area, and to obtain the environmental transformation difficulty of the corresponding crop.

[0146] The first transformation decision unit is configured to select crops that meet the conditions for planting according to the first transformation decision condition, to perform secondary transformation on the current area according to the number of crop types that meet the conditions, the corresponding crop planting attributes, and the current area environmental attributes, and to repeat the S3 process to perform secondary planting planning on the transformed current area.

[0147] The first transformation decision condition is that there is at least one crop that meets the user planting demand and has an environmental transformation difficulty less than the transformation difficulty threshold.

[0148] The second transformation decision unit is configured to select a corresponding crop with the minimum estimated cost as the corresponding planting crop of the current area according to the second transformation decision condition, and to repeat the S6 process to perform environmental transformation and planting planning of the current area.

[0149] The second transformation decision condition is that all crops do not meet the user planting demand, but there is a crop that has an environmental transformation difficulty less than the transformation difficulty threshold.

[0150] The third transformation decision unit is configured to select a crop with the minimum crop planting difficulty score, the maximum simulated growth score, the corresponding type of crop being the user planting demand crop, and the transformation cost being less than or equal to the estimated cost as the planting crop of the current area according to the third transformation decision condition, and to perform transformation and planting planning of the current area according to the selected planting crop, or not to perform planting planning of the current area.

[0151] The third transformation decision condition is that all crop planting difficulty scores are greater than or equal to the planting difficulty score threshold, and the simulated growth score is less than or equal to the simulated growth score threshold.

[0152] The embodiments of the present application are described above with reference to the accompanying drawings, but the present application is not limited to the above-described specific embodiments, and the above-described specific embodiments are merely illustrative, but not restrictive, and a person of ordinary skill in the art can make changes, modifications, replacements and variations to the above-described embodiments without departing from the purpose of the present application and the scope protected by the claims under the inspiration of the present application, and these are all within the protection of the present application.

Claims

1. A topographic analysis method based on unmanned aerial vehicle remote sensing monitoring decision, characterized by the steps of include: S1. Obtain multi-angle terrain images, laser measurement data, meteorological data, hydrological data, and user planting requirements and estimated cost data for the current area. Build a regional 3D terrain planting simulation model with hydrological and meteorological data by combining simulation algorithms with 3D generation algorithms. S2. Configure a crop planting attribute library. Based on the planting requirement parameters of each crop in the library, perform planting simulation and evaluation using a regional three-dimensional terrain planting simulation model with hydrological and meteorological data and a crop growth factor function for each growth period. This results in a planting difficulty score and simulated growth score for each crop in the current region. S3, set planting difficulty score threshold and simulate growth score threshold When there is a crop whose planting difficulty score is less than and whose simulate growth score is greater than the simulate growth score threshold and the number of crop types meeting the conditions is greater than or equal to 1, then select the crop meeting the conditions as the current region planting crop, and according to the user planting demand, perform secondary planting planning on the current region according to the number of crop types meeting the conditions and the crop planting attribute. S4, when all crop planting difficulty scores are greater than or equal to the planting difficulty score threshold but there are crop simulation growth scores greater than the simulation growth score threshold , then the current area is evaluated and distinguished according to the crop planting attributes that meet the condition of being greater than the simulation growth score threshold , the current area after the reconstruction is obtained, and secondary planting planning is performed. The steps of evaluating and judging the transformation of the current area include: S5. Set a transformation difficulty threshold based on the user's planting needs and estimated cost data, and evaluate the difficulty of environmental transformation for the crops that meet the conditions in S4 when planted in the current area, to obtain the environmental transformation difficulty for the crops. S6. When there is at least one crop that meets the user's planting requirements and the environmental transformation difficulty is less than the transformation difficulty threshold, the crop that meets the conditions is selected for planting, and the current area is secondary transformed based on the number of crop types that meet the conditions, the corresponding crop planting attributes, and the current area's environmental attributes. At the same time, the S3 process is repeated to perform secondary planting planning on the transformed current area. S7. When all crops do not meet the user's planting requirements, but there are crops that meet the corresponding environmental modification difficulty and are less than the modification difficulty threshold, the crop with the lowest estimated cost is selected as the corresponding crop for the current area, and the S6 process is repeated to perform environmental modification and planting planning for the current area based on the planting requirement parameters corresponding to the crops that meet the user's planting requirements. S8、when all crop planting difficulty scores are greater than or equal to the planting difficulty score threshold value , and the simulated growth vigor score is less than or equal to the simulated growth vigor score threshold value , analyze all crop attributes, when there is a type of crop corresponding to the crop planting difficulty score minimum and the simulated growth vigor score maximum, which is the user planting demand crop and the reconstruction cost is less than or equal to the estimated cost, reconstruct and plant the current area, otherwise do not plant the current area. 2.The method of claim 1, wherein, The steps of constructing the regional three-dimensional terrain planting simulation model with hydrological and meteorological features include: S101, generating a three-dimensional terrain sub-model of the current area using a three-dimensional generation algorithm based on the acquired multi-angle terrain image of the current area and the slope and terrain height data in the laser measurement data; S102: Pre-train the configured weather forecast model based on the acquired current regional weather data to obtain a regional weather simulation sub-model, and output the simulated weather status for each time period in the current region; S103. Based on the current regional hydrological data, the configured hydrological model is trained to obtain a regional hydrological simulation sub-model, and the distance between the water source and the current region, the water flow path, and the soil moisture are simulated. S104, integrating the current regional three-dimensional terrain sub-model, the regional meteorological simulation sub-model, and the regional hydrological simulation sub-model through an integration algorithm to obtain a regional three-dimensional terrain model with hydrological and meteorological features; S105: constructing a segmented growth period growth factor function based on the planting environment conditions and simulated meteorological conditions of each crop growth period, the distance between the water source and the current area, the water flow path, and the soil moisture. The segmented growth period growth factor function is embedded in the constructed crop segmented growth simulation sub-model for training to obtain the corresponding growth state of each crop under different growth conditions. S106, integrate the pre-trained crop segmented growth simulation sub-model into the regional three-dimensional terrain model with hydro-meteorology, obtain a regional three-dimensional terrain planting simulation model with hydro-meteorology, and when the current region changes, repeat the process of S101-S106 to obtain a fine-tuned regional three-dimensional terrain planting simulation model with hydro-meteorology for each region, and dynamically label the simulated meteorology, hydrology and crop growth state according to the time dimension. 3.The method of claim 2, wherein, The construction step of the segmented growth period growth factor function is: S201, set the crop growth period stage to include the sowing period, seedling period, vegetative growth period, reproductive growth period and mature period, and obtain the meteorological and hydrological parameter space with a contribution degree greater than a contribution threshold value through factor analysis algorithm according to the parameters between each crop in different growth period stages and meteorology and hydrology; S202, according to the meteorological and hydrological parameter space with a contribution degree greater than a contribution threshold value, a segmented growth period growth factor function corresponding to each crop is constructed by a multiple regression algorithm combined with a genetic optimization algorithm. 4.The method of claim 3, wherein, The obtaining step of the crop planting difficulty score includes: S211, obtain a comprehensive terrain modification difficulty score according to the current regional slope, terrain height difference and terrain complexity obtained by the evaluation algorithm; S212, obtain a current regional meteorological adaptability score by the evaluation algorithm according to the current regional average temperature, precipitation and wind speed; S213, obtain a current regional hydrological adaptability score by the evaluation algorithm according to the distance between the water source and the current region, the water flow path and the soil moisture information; S214, obtain the current regional crop planting difficulty score by weighted average method according to the current regional comprehensive terrain modification difficulty score, meteorological adaptability score and hydrological adaptability score. 5.The method of topographic analysis based on UAV remote sensing monitoring decision according to claim 4, wherein, The step of secondary planting planning of the current region in S3 includes: S301, when the crop meeting the condition is one, the current region is directly planted with the corresponding type of crop; S302, when the crop meeting the condition is more than one, the shade tolerance, drought tolerance and lodging resistance of each type of crop, as well as the terrain height, slope, soil moisture, distance from the water source, water flow path direction, historical wind speed and direction, and planning planting proportion of the crop type meeting the user's planting demand are obtained according to the number of crop types meeting the condition, and a particle swarm optimization grid algorithm is used to divide the current region to obtain a crop planting sub-region of the corresponding type; S303, plant the corresponding crop in the crop planting sub-region, and obtain the crop growth score and corresponding yield in the corresponding planting period; S304, feed back the corresponding type of crop growth score and corresponding yield to the particle swarm optimization grid algorithm to adjust the crop planting area in real time.

6. A topographic analysis system based on UAV remote sensing monitoring decision, for implementing the topographic analysis method based on UAV remote sensing monitoring decision according to any one of claims 1-5, characterized in that, It includes: a simulation simulation module, an initial decision discrimination module and a secondary decision discrimination module; The simulation simulation module includes a data acquisition unit, a model construction unit and a simulation evaluation unit; The data acquisition unit is used to acquire current regional multi-angle terrain images, laser measurement data, meteorological data and hydrological data, and user planting demand and estimated cost data; The model construction unit is configured to construct a three-dimensional terrain planting simulation model with hydro-meteorological conditions of a region according to data obtained by the data acquisition unit, through a simulation algorithm and a three-dimensional generation algorithm. The simulation evaluation unit is configured to perform planting simulation and evaluation on the three-dimensional terrain planting simulation model with hydro-meteorological conditions of the region and a crop segmented growth period growth factor function according to a corresponding crop in the crop planting attribute library, to obtain a current region crop planting difficulty score and a simulation growth score of each crop. 7.The topographic analysis system based on UAV remote sensing monitoring decision of claim 6, wherein, The initial decision discrimination module includes a first initial decision unit and a second initial decision unit. The first initial decision unit is used to determine the planting difficulty score threshold according to the set planting difficulty score threshold. and simulated growth score threshold , select the crops that meet the first initial decision condition as the crops to be planted in the current area, and according to the user's planting needs, perform secondary planting planning for the current area based on the number of crop types that meet the conditions and the crop planting attributes; the first initial decision condition is: there are crops with a planting difficulty score less than And the simulated growth score is greater than types, and the number of types is greater than or equal to 1; The second initial decision unit is configured to select a crop satisfying a second initial decision condition as a current region crop, and perform reconstruction evaluation discrimination on the current region according to planting attributes of the crop satisfying the second initial decision condition, to obtain a reconstructed current region and perform secondary planting planning. The second initial decision condition is that all of the crop planting difficulty scores are greater than or equal to but there is a crop whose simulated growth score is greater than the threshold value.

8. The terrain analysis system based on UAV remote sensing monitoring and decision-making according to claim 7, characterized in that: The secondary decision discrimination module includes a reconstruction evaluation unit, a first reconstruction decision unit, a second reconstruction decision unit, and a third reconstruction decision unit. The reconstruction evaluation unit is configured to set a reconstruction difficulty threshold according to user planting requirements and estimated cost data, and evaluate a difficulty of corresponding environmental reconstruction of the corresponding crop in the current region, to obtain an environmental reconstruction difficulty of the corresponding crop. The first reconstruction decision unit is configured to select a crop satisfying a first reconstruction decision condition for planting according to the first reconstruction decision condition, and perform secondary reconstruction on the current region according to a number of crop types satisfying the condition, corresponding crop planting attributes, and current region environmental attributes, while repeating the process of S3 to perform secondary planting planning on the reconstructed current region. The first reconstruction decision condition is that there is at least one crop satisfying the user planting requirements and having an environmental reconstruction difficulty less than the reconstruction difficulty threshold. The second reconstruction decision unit is configured to select a corresponding crop with the minimum estimated cost as a corresponding crop of the current region according to a second reconstruction decision condition, and repeat the process of S6 to perform current region environmental reconstruction and planting planning. The second reconstruction decision condition is that all crops do not satisfy the user planting requirements, but there is a crop satisfying an environmental reconstruction difficulty less than the reconstruction difficulty threshold. The third reconstruction decision unit is configured to select a crop with the minimum crop planting difficulty score, the maximum simulation growth score, the corresponding type crop being the user planting requirement crop, and the reconstruction cost being less than or equal to the estimated cost as a crop of the current region according to a third reconstruction decision condition, and perform reconstruction and planting planning on the current region according to the selected crop. The third reconstruction decision condition is that all crop planting difficulty scores are greater than or equal to a planting difficulty score threshold, and the simulation growth scores are less than or equal to a simulation growth score threshold.

Images