A corn field nitrogen element visualization method and platform based on unreal engine

Abstract

The application discloses a corn field nitrogen element visualization method and platform based on Unreal Engine, and relates to the technical field of intelligent agriculture. First, the application obtains and processes nitrogen element three-dimensional data of a target plot; a three-dimensional space model of the target plot is established in Unreal Engine; the nitrogen element three-dimensional data is imported into the three-dimensional space model, and different color particle systems representing the spatial distribution of different types of nitrogen elements are driven respectively, so as to realize the visualization of the nitrogen elements in the three-dimensional space model. The application obtains and processes multi-category nitrogen element three-dimensional data, and realizes visualization and diversified interactive presentation based on Unreal Engine, so that the collected nitrogen element data can be comprehensively and efficiently utilized, and the beneficial effect of visualization on data analysis and management decision-making can be exerted.

Description

Technical Field

[0001] This application relates to the field of smart agriculture technology, and in particular to a method and platform for visualizing nitrogen elements in maize fields based on Unreal Engine. Background Technology

[0002] Data visualization plays a vital role in smart agriculture. In agricultural production, the factors influencing changes in crop fertility are complex, with diverse data sources, large volumes of data, and rapid changes. With the maturity and application of new sensing technologies and digital twin technologies, how to comprehensively, efficiently, and intuitively present the collected data using appropriate methods to provide professionals and farmers with references for fertility management is a pressing issue that needs to be addressed in agricultural data visualization.

[0003] Existing soil fertility visualization research mainly focuses on data collection and model building techniques. The visualization is mostly limited to visual display and the display format is monotonous. This results in the collected fertility data not being used in a comprehensive and efficient manner, and it also fails to play a beneficial role in data analysis and management decision-making. Summary of the Invention

[0004] The purpose of this application is to provide a method and platform for visualizing nitrogen elements in maize fields based on Unreal Engine, so as to achieve diversified display of nitrogen fertilizer in maize.

[0005] To achieve the above objectives, this application provides the following solution.

[0006] Firstly, this application provides a method for visualizing nitrogen elements in maize fields based on Unreal Engine, including: The nitrogen element three-dimensional data of the target plot is acquired and processed; the nitrogen element three-dimensional data includes: three-dimensional data of available nitrogen, three-dimensional data of non-available nitrogen, three-dimensional data of nitrogen absorbed by crops, three-dimensional data of nitrogen lost through leaching, and three-dimensional data of nitrogen lost through volatilization.

[0007] A three-dimensional spatial model of the target plot is created in Unreal Engine; the three-dimensional spatial model includes: a soil three-dimensional model, a corn three-dimensional model, an air three-dimensional model, and a weather model.

[0008] The three-dimensional data of nitrogen element is imported into the three-dimensional spatial model, and different colored particle systems representing the spatial distribution of different types of nitrogen element are driven to realize the visualization of nitrogen element in the three-dimensional spatial model; different nitrogen elements include: available nitrogen, non-available nitrogen, nitrogen absorbed by crops, nitrogen lost through leaching, and nitrogen lost through volatilization.

[0009] Secondly, this application provides a maize field nitrogen element visualization platform based on Unreal Engine. The Unreal Engine-based maize field nitrogen element visualization platform applies the aforementioned Unreal Engine-based maize field nitrogen element visualization method. The Unreal Engine-based maize field nitrogen element visualization platform includes: The data processing layer is used to acquire and process the three-dimensional nitrogen data of the target plot; the three-dimensional nitrogen data includes: three-dimensional data of available nitrogen, three-dimensional data of non-available nitrogen, three-dimensional data of nitrogen absorbed by crops, three-dimensional data of nitrogen lost through leaching, and three-dimensional data of nitrogen lost through volatilization.

[0010] The scene building layer is used to create a three-dimensional spatial model of the target plot in Unreal Engine; the three-dimensional spatial model includes: a soil three-dimensional model, a corn three-dimensional model, an air three-dimensional model, and a weather model.

[0011] The visualization implementation layer is used to import the three-dimensional data of nitrogen elements into the three-dimensional spatial model, and drive different colored particle systems representing the spatial distribution of different types of nitrogen elements to realize the visualization of nitrogen elements in the three-dimensional spatial model; the different nitrogen elements include: available nitrogen, non-available nitrogen, nitrogen absorbed by crops, nitrogen lost through leaching, and nitrogen lost through volatilization.

[0012] According to the specific embodiments provided in this application, this application has the following technical effects.

[0013] This application provides a method and platform for visualizing nitrogen elements in maize fields based on Unreal Engine. First, it acquires and processes three-dimensional nitrogen data for the target plot, including: three-dimensional data of available nitrogen, non-available nitrogen, nitrogen absorbed by crops, nitrogen lost through leaching, and nitrogen lost through volatilization. Then, it establishes a three-dimensional spatial model of the target plot in Unreal Engine, including: a soil model, a maize model, an air model, and a weather model. The nitrogen three-dimensional data is imported into the three-dimensional spatial model, driving different colored particle systems representing the spatial distribution of different types of nitrogen elements, thereby visualizing nitrogen elements in the three-dimensional spatial model. By acquiring and processing multi-category three-dimensional nitrogen data and visualizing and presenting it in diverse interactive ways using Unreal Engine, this application enables multi-form display of maize nitrogen fertilizer, achieving comprehensive and efficient utilization of the collected nitrogen data and leveraging the beneficial role of visualization in data analysis and management decision-making. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This is a flowchart illustrating a method for visualizing nitrogen elements in a cornfield based on Unreal Engine, as provided in one embodiment of this application.

[0016] Figure 2 This is a schematic diagram illustrating a method for visualizing nitrogen elements in cornfields based on Unreal Engine, as provided in one embodiment of this application.

[0017] Figure 3 This is a schematic diagram of a particle system representing different spatial distributions of nitrogen element, provided as an embodiment of this application.

[0018] Figure 4 This is a schematic diagram of the structure of a maize field nitrogen element visualization platform based on Unreal Engine, provided as an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] The following are studies related to soil fertility visualization: A mobile platform for measuring soil fertility based on multi-channel ion-selective electrode method (CN 201110344124) integrates six ion-selective electrodes, including nitrate, ammonium, and potassium ions. Combined with GPS positioning and a vehicle-mounted system, it can detect indicators such as nitrate nitrogen and available phosphorus in real time in the field. The data is used to generate a fertility heat map through a cloud platform to guide variable fertilization.

[0022] A high-resolution soil scanning method and soil scanner (CN 202410837649) employs multi-point, multi-depth continuous scanning, integrating multi-source data from EC sensors, pH sensors, and other sources. It generates a three-dimensional attribute map through spatial interpolation and multi-source data synchronization technology. This method can quantify structural parameters such as soil porosity and aggregate distribution, and, combined with models such as the water retention index (WHold) and nutrient supply index (NSupply), visualize the correlation between fertility and maize growth.

[0023] A rapid field fertility detection method and system based on soil two-dimensional spectral data transfer learning (CN202310318143) converts one-dimensional spectra into two-dimensional spectrograms. Combined with an improved Inception-v4 neural network, the method achieves rapid prediction of soil nitrogen, phosphorus and potassium content in different regions through transfer learning of pre-trained models. The model can be optimized with only a small number of samples in new regions.

[0024] A method and platform for converting fertility points and surfaces at multiple depths in arable land (CN 116663779 A) combines a geographic detector model with the BPNN-Adaboost algorithm to establish fertility surface data models at multiple depths, such as 0-20cm and 20-40cm, through environmental similarity partitioning, and finally generates a three-dimensional fertility distribution map.

[0025] A spatial data visualization query method, system, and storage medium (CN 202311423418) combines multimodal input (voice, text, gesture) and grid storage technology to divide soil measurement point data into grid units according to latitude and longitude, dynamically generate fertility contour maps, nutrient profile maps, etc., and can overlay maize growth models to simulate the yield response of different fertilization schemes.

[0026] A machine learning-based hyperspectral detection and visualization method for nitrogen content in soil profiles (CN202211143677) uses hyperspectral imaging technology (400-2500nm) to acquire soil profile reflectance data, and combines PLSR, ANN and other models to predict the content of five forms of nitrogen, including total nitrogen and available nitrogen, and finally generates a pseudo-color distribution map, which can intuitively display the nitrogen leaching risk area.

[0027] The application of Unreal Engine in agriculture is studied as follows: A method, system, and electronic device for constructing an agricultural target detection dataset (Publication No.: 202310366283) utilizes Nanite micro-polygon geometry and Lumen dynamic global illumination technology from Unreal Engine to construct a virtual farmland with millimeter-level precision. By training the detection model with mixed real and virtual scene data, it solves the problems of high cost and insufficient samples in agricultural data collection.

[0028] A simulation system and method for multi-UAV self-organizing networks based on Unreal Engine (Publication No.: 202311529313) constructs a three-dimensional virtual farmland environment to simulate multi-UAV collaborative operation scenarios (such as pesticide spraying and crop inspection). The system supports UAV path planning and communication signal attenuation simulation, and reproduces the impact of airflow disturbances during UAV flight on crops through a physics engine.

[0029] A path planning and precision operation method for unmanned tractor operations (Publication No.: 202210110936) constructs a virtual training scenario for tractor operations based on UE4, simulating complex working conditions such as turning on slopes and harvesting lodged crops. The system simulates force feedback steering wheel and suspension vibration to provide real-time feedback on parameters such as tillage depth deviation and grain loss rate.

[0030] A method and system for generating agricultural park data based on digital twins (Publication No.: CN120374897A) is proposed. This method combines real-time rendering and machine learning in UE4 to construct a digital twin model of the agricultural park. By integrating data from soil sensors and weather stations, a three-dimensional visualization simulation of irrigation systems and agricultural machinery operations is achieved, and the impact of different management strategies on crop yields is predicted.

[0031] In the above patents, visualization is mainly used to display the collected data, and the display format is singular, which makes it impossible to comprehensively and efficiently utilize the collected soil fertility data.

[0032] Unreal Engine's applications in agriculture are mostly focused on building detection datasets and simulating equipment operation scenarios, with no application in crop fertility management yet.

[0033] Therefore, this application proposes a method and platform for visualizing nitrogen elements in maize fields based on Unreal Engine. It comprehensively and efficiently utilizes the collected fertility data to present the distribution and changes of nitrogen elements in the maize growing environment in a rich visualization format, thereby improving data analysis efficiency, enhancing data interactivity, supporting multi-dimensional analysis, and helping to provide a reference for fertility management.

[0034] In one exemplary embodiment, a method for visualizing nitrogen elements in corn fields based on Unreal Engine is provided, such as... Figure 1 and Figure 2 As shown, it includes the following steps 101-103.

[0035] Step 101: Acquire and process the three-dimensional nitrogen data of the target plot. The three-dimensional nitrogen data includes: three-dimensional data of available nitrogen, three-dimensional data of non-available nitrogen, three-dimensional data of nitrogen absorbed by crops, three-dimensional data of nitrogen lost through leaching, and three-dimensional data of nitrogen lost through volatilization. In this step, firstly, the nitrogen content data of the target plot is acquired and processed. Then, depending on the acquisition technology and the type of nitrogen element, it includes the nitrogen content value at a specific coordinate point in a three-dimensional space of a certain time series (hereinafter referred to as nitrogen three-dimensional data) and the nitrogen content value at a specific coordinate point in a two-dimensional space of a certain time series (hereinafter referred to as nitrogen two-dimensional data).

[0036] Step 102: Create a three-dimensional spatial model of the target plot in Unreal Engine; the three-dimensional spatial model includes: a soil three-dimensional model, a corn three-dimensional model, an air three-dimensional model, and a weather model.

[0037] Step 103: Import the three-dimensional nitrogen data into the three-dimensional spatial model, and drive different colored particle systems representing the spatial distribution of different types of nitrogen elements to visualize the nitrogen elements in the three-dimensional spatial model; the different nitrogen elements include: available nitrogen, non-available nitrogen, nitrogen absorbed by crops, nitrogen lost through leaching, and nitrogen lost through volatilization.

[0038] Implementing steps 101-103 above allows for the comprehensive and efficient use of collected fertility data, presenting the changes in nitrogen elements in the corn growing environment in a rich and visual format. This improves data analysis efficiency, enhances data interactivity, supports multi-dimensional analysis, and helps provide a reference for fertility management.

[0039] In another exemplary embodiment, nitrogen in the corn growing environment can be classified into the following categories: The total nitrogen element TN in the target soil space includes available nitrogen AN and other nitrogen elements nAN. Available nitrogen can be directly absorbed by corn, while other nitrogen elements cannot be absorbed by crops. TN = AN + nAN. Nitrogen (GN) absorbed by crops; Nitrogen (RN) lost through leaching from the target soil space; Nitrogen (VN) lost through volatilization from the target soil space; Increased nitrogen (FN) from fertilization; The relationship formulas for the above types of nitrogen elements are: TN 当前 =TN 原始 -GN-RN-VN+FN.

[0040] In another exemplary embodiment, the process of acquiring three-dimensional nitrogen element data includes: First, construct the data spatial grid for the target plot.

[0041] Select the target plot for visualization, set the origin and side length of the target soil space, and set the depth of the target soil space for visualization based on the nitrogen absorption of the corn roots.

[0042] For example, a square plot of land with sides of 450m (approximately 300 acres). Given that the absorption of nitrogen fertilizer by corn roots is mainly concentrated in the 0 to -600mm soil layer, the depth of the target soil space for visualization is set at 600mm. Furthermore, to represent nitrogen leaching, the visualization platform displays a soil depth of 800mm.

[0043] Using a Geographic Information System (GIS), a spatial network was constructed for the target plot, with longitude as the X-axis, latitude as the Y-axis, and depth as the Z-axis. Referring to the agronomical requirements for maize growth, such as row spacing of 500mm, plant spacing of 400mm, and nitrogen fertilizer absorption by maize roots, the required data grid density for visualization was set to 500mm intervals in the X-axis based on row spacing, 400mm intervals in the Y-axis based on plant spacing, and 200mm intervals in the Z-axis.

[0044] Then, acquire the data.

[0045] Using UAV remote sensing and soil sensor network technology, obtain the TN of the target plot. 获取 and AN 获取 Data. The data includes the X-axis coordinate (x), Y-axis coordinate (y), Z-axis coordinate (z), nitrogen content (v), and sampling time (t) for each sampling point. Data at depths from 0 to -600 mm are used as the target soil TN. 获取 and AN 获取 Data, total nitrogen data at a depth of 800 mm, was used to indirectly calculate the nitrogen element RN lost through leaching from the target soil space, denoted as TN800. 获取 .

[0046] Using UAV remote sensing technology combined with field sampling and detection technology, data on nitrogen uptake by corn was obtained. 获取 The data includes the X-axis coordinate (x), Y-axis coordinate (y), nitrogen content (v), and sampling time (t) for each sampling point.

[0047] Based on actual field fertilization practices, obtain the increased nitrogen (FN) from fertilization. 获取 The data includes the X-axis coordinate (x), Y-axis coordinate (y), nitrogen content (v), and sampling time (t) for each sampling point.

[0048] Using field sensors to obtain corn growth information C 获取 This data is used to control the growth of a maize model. The data includes the X-axis coordinate (x), Y-axis coordinate (y), maize plant height (h), and sampling time (t) for each sampling point.

[0049] Meteorological data, such as temperature, light, and precipitation, are obtained from field weather stations and used to simulate the real growing environment of corn.

[0050] Then, process the data.

[0051] 1. Rasterization processing.

[0052] The corresponding data grid is used to perform rasterization processing on the data in conjunction with a Geographic Information System (GIS), and the data types are unified into a user-friendly data format, such as CSV data.

[0053] The following data was obtained: TN 三维 and AN 三维 It contains xyzvt information; GN 二维 FN 二维 It contains xyvt information; C 二维 It contains xyht information.

[0054] 2. Obtain nitrogen element data through indirect calculation.

[0055] nAN in target soil space 三维 nAN can be indirectly calculated using the formula TN=AN+nAN. 三维 =TN 三维 -AN 三维 It contains xyzvt information.

[0056] Nitrogen RN lost through leaching from the target soil space 三维 Based on the spatial range set in the above embodiment and the TN data obtained at a depth of 800 mm, the nitrogen element data RN leached in the target soil space is indirectly calculated. 三维 , i.e., RN 三维 =TN 800 当前 -TN 800 原始 The data contains xyzvt information.

[0057] Nitrogen (VN) lost through volatilization from the target soil 三维 , for TN 三维 and RN 三维 The v-values ​​of the data are processed by dimensionality reduction and accumulation along the Z-axis to obtain TN. 二维 and RN 二维 Data. This leads to VN. 二维 =TN 二维原始 -TN 二维当前 -GN 二维 -RN 二维 +FN 二维The data includes xyvt information. Based on the nitrogen volatilization pattern, the concentration is highest within 0-2 meters, accounting for 60%-70% of the total content, while the concentration drops to the atmospheric background level above 10 meters. (Regarding VN...) 二维 The v value is mapped along the Z-axis, corresponding to the data grid density in the above embodiment, uniformly mapping 60% VN within 0-2 meters. 二维 The v value decreases uniformly to 0 within 2-10 meters, mapping 40% VN 二维 The value of v is used to obtain VN. 三维 It contains xyzvt information.

[0058] According to C 二维 and GN 二维 Data, will C 二维 The h is mapped along the data grid to obtain z-axis information, which is then considered as z-data for GN. For GN... 二维 The v value is mapped to the Z-axis uniformly to obtain GN. 三维 It contains xyzvt information.

[0059] After the above data processing steps, we obtain AN. 三维 nAN 三维 RN 三维 VN 三维 GN 三维 The data contains xyzvt information.

[0060] In another exemplary embodiment, step 101 described above can be replaced by steps 201-206.

[0061] Step 201: Use UAV remote sensing and / or soil sensor networks to acquire three-dimensional data of available nitrogen and total nitrogen in the target plot.

[0062] Step 202: Calculate the three-dimensional data of non-available nitrogen in the target plot based on the three-dimensional data of available nitrogen and total nitrogen in the target plot.

[0063] Step 203: Based on the three-dimensional data of the total nitrogen in the preset area below the maximum nitrogen absorption depth of the corn roots in the target plot, calculate the three-dimensional data of the leaching nitrogen loss of the target plot using the following formula. ; in, This provides three-dimensional data on nitrogen loss during leaching at sampling time t. This represents the three-dimensional data of total nitrogen in a preset region D below the maximum nitrogen absorption depth of maize roots at sampling time t. The three-dimensional data of total nitrogen in the preset region D below the maximum nitrogen absorption depth of maize roots at sampling time t-1; Step 204: Calculate the three-dimensional data of volatile nitrogen loss of the target plot based on the three-dimensional data of total nitrogen and leaching loss nitrogen of the target plot.

[0064] Step 205: Use UAV remote sensing to acquire two-dimensional data of nitrogen absorbed by crops in the target plot and use field sensors to acquire corn growth information in the target plot; the two-dimensional data is (x,y,v,t), and the corn growth information is (x,y,h,t), where h is the corn height.

[0065] Step 206: Using the corn growth information of the target plot, map the two-dimensional data of nitrogen absorbed by the crop into three-dimensional data of nitrogen absorbed by the crop.

[0066] In another exemplary embodiment, step 204 described above can be replaced by steps 301-303.

[0067] Step 301: The nitrogen element content of the three-dimensional data of total nitrogen and the three-dimensional data of nitrogen lost through leaching is accumulated along the Z-axis to obtain the two-dimensional data of total nitrogen and the two-dimensional data of nitrogen lost through leaching. Step 302: Based on the two-dimensional data of total nitrogen and the two-dimensional data of nitrogen loss from leaching, calculate the two-dimensional data of nitrogen loss from volatilization using the following formula; ; in, This provides two-dimensional data on nitrogen loss due to volatilization at sampling time t. and The two-dimensional data for total nitrogen at sampling time t-1 and t are respectively. This represents two-dimensional data on nitrogen absorbed by the crop at sampling time t. This is two-dimensional data of nitrogen loss during leaching at sampling time t. Two-dimensional data for nitrogen increase due to fertilization at sampling time t; Step 303: Using the volatilization law of nitrogen, the two-dimensional data of nitrogen loss due to volatilization is mapped along the z-axis to obtain the three-dimensional data of nitrogen loss due to volatilization.

[0068] In another exemplary embodiment, step 102 described above can be replaced by steps 401-404.

[0069] Step 401: In Unreal Engine, using the origin of Unreal Engine's world coordinate system as the origin of the geographic information system's world coordinate system, construct a box collision with a length of 450,000 mm in the X direction, a length of 450,000 mm in the Y direction, and a depth of -800 mm in the Z direction as the soil 3D model.

[0070] Step 402: In Unreal Engine, use Blender or 3ds Max to create individual corn plant models at different growth stages, and arrange the individual corn plant models according to the corn growth information of the target plot to obtain a three-dimensional corn model.

[0071] Step 403: In Unreal Engine, using the origin of Unreal Engine's world coordinate system as the origin of the geographic information system's world coordinate system, construct a box collision with a length of 450,000 mm in the X direction, a length of 450,000 mm in the Y direction, and a height of 10,000 mm in the Z direction as an air 3D model.

[0072] Step 404: In Unreal Engine, import meteorological data using the weather plugin and build a weather model.

[0073] In this embodiment, three-dimensional models are created or imported into the UE to build three-dimensional soil models, three-dimensional corn models, three-dimensional air models, and weather models.

[0074] 1. Create a 3D model of the soil.

[0075] In the spatial settings of the above embodiment, the origin of the UE's world coordinates is used as the origin, and a box collision is established with X = 450000mm, Y = 450000mm, and Z = -800mm.

[0076] 2. Create a 3D model of the corn.

[0077] Models of different growth stages of maize plants, such as seedling emergence, tasseling, and maturity, were created using modeling software such as Blender or 3ds Max, corresponding to the spatial settings and GN of the above embodiments. 三维 The XY data was imported and the corn model was arranged using the UE "Vegetation Tool".

[0078] 3. Create a 3D air model.

[0079] Based on the VN calculation principle and the corresponding soil model, a box collision is established with X = 450000mm, Y = 450000mm, and Z = 10000mm.

[0080] 4. Create a weather model.

[0081] Using a UE weather plugin, such as Sky Creator, import the meteorological data obtained in the above embodiments to simulate scene weather changes.

[0082] In another exemplary embodiment, step 103 described above can be replaced by steps 501-505.

[0083] Step 501: Create a structure variable in Unreal Engine and import the three-dimensional data of the target nitrogen element into the structure variable; the target nitrogen element is available nitrogen, non-available nitrogen, nitrogen absorbed by crops, nitrogen lost through leaching, or nitrogen lost through volatilization. Step 502: Create a blueprint for the particle system of the target nitrogen element, and create a blueprint for the particle system with a color material. Step 503: Use the ForEachLoop node to traverse all the three-dimensional coordinate information in the three-dimensional data of the target nitrogen element and build a spatial data grid in Unreal Engine. Step 504: Using the SpawnActor node, generate the corresponding number of particles according to the nitrogen content in the three-dimensional data of the target nitrogen element. Step 505: Using the AddTimeLine node, update the particle state according to the sampling time in the three-dimensional data of the target nitrogen element to perform dynamic three-dimensional visualization of the target nitrogen element.

[0084] In this embodiment, the AN obtained from the data processing layer 三维 nAN 三维 RN 三维 VN 三维 GN 三维 Data is imported into the UE to drive particle systems of different colors, such as... Figure 3 As shown, the particle system includes: particle system 1 for available nitrogen in the target soil space of the soil model; particle system 2 for non-available nitrogen; particle system 3 for nitrogen absorbed by crops in the maize model; particle system 4 for nitrogen lost through volatilization in the air model; and particle system 5 for nitrogen lost through leaching located below the target soil space in the soil model. These five particle systems enable dynamic three-dimensional visualization of nitrogen.

[0085] The advantage of this method is that: 1. The particle system's nitrogen element change process is driven by external data, eliminating the need for complex functions in the UE and helping to reduce the UE's computational load.

[0086] 2. Setting up separate particle systems allows you to enable or disable them in UE according to your needs, and set different levels of detail, rendering distances, and activation ranges, which also helps reduce computational load.

[0087] In another exemplary embodiment, in the above visualization method, for each nitrogen element particle system, a structure variable is created in the UE, and nitrogen element data (xyzvt) is imported into the structure variable; a particle system blueprint is created; a color material is created and assigned to the particle system blueprint; the ForEachLoop node is used to traverse the xyz coordinate information and establish the corresponding spatial data grid in the UE; the SpawnActor node is used to generate the corresponding number of particles according to the v value; and the AddTimeLine node is used to update the particle state according to the t value, thereby realizing dynamic three-dimensional visualization of nitrogen elements.

[0088] The available nitrogen particle system 1 and the non-available nitrogen particle system 2 are constrained within the 0 to -600 mm space of the soil model; the nitrogen particle system 3 absorbed by crops is constrained in the maize model, which is based on C 二维 The h value controls the growth height of the maize model; particle system 4 for volatile nitrogen loss is constrained in the air model; particle system 5 for leaching nitrogen loss is constrained in the soil model space from -601 to -800.

[0089] In another exemplary embodiment, step 103 above is followed by: Step 104: Import the three-dimensional nitrogen data into the three-dimensional spatial model. According to the needs of field management, control the particle system of different nitrogen elements to generate one or more of the following: two-dimensional heat map, three-dimensional heat map, and two-dimensional contour map.

[0090] In this embodiment, based on the above particle system, according to the needs of field management, the region and the types of nitrogen elements to be presented can be selected to form two-dimensional or three-dimensional heat maps, two-dimensional contour maps, etc., to present the changes of nitrogen elements in the corn growth environment in a diversified way, and provide a basis for field fertilization management.

[0091] 1. Generate a two-dimensional heat map.

[0092] 2D Heatmap: Create a heatmap material with a blue-green-red numerical gradient (0 for blue, 0.5 for green, and 1 for red); create a blueprint for the selected area and particle type; generate a 2D voxel plane by nesting ForLoop nodes twice; use ForEachLoop nodes to traverse the particles, count the number of particles projected into each voxel plane, store them in an array, and perform normalization; map the normalized value of each voxel to the corresponding heatmap color to generate a 2D heatmap.

[0093] 2. Generate a three-dimensional heat map.

[0094] 3D Heatmap: Create a heatmap material with a blue-green-red numerical gradient (0 for blue, 0.5 for green, and 1 for red); create a blueprint for the selected area and particle type; generate 3D mesh voxel cubes by nesting ForLoop nodes 3 times; use ForEachLoop nodes to traverse the particles, count the number of particles in each voxel cube, store them in an array, and perform normalization processing; map the normalized value of each voxel to the corresponding heatmap color to generate a 3D heatmap.

[0095] 3. Generate a two-dimensional contour map.

[0096] Create a heatmap material with a blue-green-red numerical gradient (0 for blue, 0.5 for green, and 1 for red); create a blueprint containing a spline curve component for the selected area and particle type; generate a 2D planar sampling mesh by nesting ForLoop nodes twice; traverse particles using ForEachLoop nodes, count the number of particles projected onto each voxel plane, store the count in an array, normalize it, and record it as a density value; set multiple density thresholds, collect sampling meshes with density values ​​close to different thresholds using ForEachLoop nodes, sort them by coordinates, connect the sampling meshes using a spline curve component to form closed or discontinuous curves, and pass the threshold parameters to the material to display the corresponding color; generate a 2D contour map.

[0097] The visualization methods described above can comprehensively and multidimensionally present information on nitrogen changes in the maize growing environment. They can intuitively and efficiently reflect the relationship between nitrogen content in the soil and maize growth status, and comprehensively reflect the impact of climatic conditions on nitrogen leaching and volatilization. Based on this, the relationship between maize growth and various nitrogen elements can be comprehensively analyzed, providing a reference for field fertilization management.

[0098] In another exemplary embodiment, the main data visualization functions described above can be implemented based on engines such as Unity 3D or Houdini.

[0099] In another exemplary embodiment, the interactive presentation layer can also generate pseudo-color images, surface views, cross-sectional views, etc.

[0100] In the above embodiments, the collected data is comprehensively and fully utilized to present the changes in nitrogen element in the corn growing environment in a diverse and intuitive way. By setting up pre-processing of data and driving the particle system separately, the computational load on the user interface (UE) is effectively reduced.

[0101] Based on the same inventive concept, this application also provides a Unreal Engine-based corn field nitrogen element visualization platform for implementing the aforementioned Unreal Engine-based corn field nitrogen element visualization method. The solution provided by this platform is similar to the implementation scheme described in the above method. Therefore, the specific limitations of the one or more Unreal Engine-based corn field nitrogen element visualization platform embodiments provided below can be found in the limitations of the Unreal Engine-based corn field nitrogen element visualization method described above, and will not be repeated here.

[0102] In one exemplary embodiment, a maize field nitrogen element visualization platform based on Unreal Engine is provided, such as... Figure 4 As shown, it includes: The data processing layer is used to acquire and process the three-dimensional nitrogen data of the target plot. This three-dimensional nitrogen data includes: three-dimensional data of available nitrogen, non-available nitrogen, nitrogen absorbed by crops, nitrogen lost through leaching, and nitrogen lost through volatilization. Specifically, nitrogen elements in the maize growing environment are categorized into six types: available and non-available nitrogen elements in the target soil, nitrogen absorbed by crops, nitrogen volatilized from the target soil, nitrogen leached from the target soil, and nitrogen applied through fertilization. Data information is acquired for each category. The target plot is spatially gridded using a Geographic Information System (GIS), and the acquired nitrogen data is matched with the spatial grid and standardized into a data format suitable for import into Unreal Engine (UE).

[0103] The scene building layer is used to create a 3D spatial model of the target plot in Unreal Engine. This 3D spatial model includes: a soil 3D model, a corn 3D model, an air 3D model, and a weather model. Specifically, it creates the necessary 3D models for visualization in Unreal Engine. The soil, corn, and air 3D models are used to constrain and present nitrogen element variations, while the weather 3D model simulates the real growing environment of the corn.

[0104] The visualization layer imports the 3D nitrogen data into the 3D spatial model and drives different colored particle systems representing the spatial distribution of different nitrogen elements, thus visualizing nitrogen elements within the 3D spatial model. These different nitrogen elements include: available nitrogen, non-available nitrogen, nitrogen absorbed by crops, nitrogen lost through leaching, and nitrogen lost through volatilization. The processed nitrogen data is imported into the UE (User Equipment) and drives the corresponding particle systems for each nitrogen element. These include particle systems for available and non-available nitrogen in the target soil space of the soil model, particle systems for nitrogen absorbed by crops in the maize model, particle systems for volatilized nitrogen in the air model, and particle systems for leached nitrogen located below the target soil space in the soil model. Dynamic 3D visualization of nitrogen elements is achieved through these five particle systems.

[0105] In another exemplary embodiment, such as Figure 4 As shown, the aforementioned Unreal Engine-based visualization platform for nitrogen elements in corn fields also includes: The interactive presentation layer is used to import the three-dimensional nitrogen data into the three-dimensional spatial model. Based on field management needs, it controls the nitrogen particle system of different colors to generate one or more of the following: two-dimensional heatmap, three-dimensional heatmap, and two-dimensional contour map. In other words, based on the above particle system, according to field management needs, regions and the types of nitrogen to be presented can be selected to form three-dimensional or two-dimensional heatmaps or contour maps, providing a diversified representation of nitrogen changes in the maize growing environment and offering a basis for field fertilization management.

[0106] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0107] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for visualizing nitrogen elements in maize fields based on Unreal Engine, characterized in that, include: Acquire and process the three-dimensional nitrogen data of the target plot; The three-dimensional nitrogen data includes: three-dimensional data of available nitrogen, three-dimensional data of non-available nitrogen, three-dimensional data of nitrogen absorbed by crops, three-dimensional data of nitrogen lost through leaching, and three-dimensional data of nitrogen lost through volatilization. A three-dimensional spatial model of the target plot is created in Unreal Engine; the three-dimensional spatial model includes: a soil three-dimensional model, a corn three-dimensional model, an air three-dimensional model, and a weather model; The three-dimensional nitrogen data is imported into the three-dimensional spatial model, and different colored particle systems representing the spatial distribution of different types of nitrogen elements are driven to visualize the nitrogen elements in the three-dimensional spatial model. The different nitrogen elements include: available nitrogen, non-available nitrogen, nitrogen absorbed by crops, nitrogen lost through leaching, and nitrogen lost through volatilization. The process of acquiring and processing the 3D nitrogen data of the target site includes, prior to which, the construction of a spatial grid for the target site's data is also required. Select the target plot for visualization, set the origin and side length of the target soil space, and set the depth of the target soil space for visualization based on the nitrogen absorption of the corn roots. Using a geographic information system, a spatial network is constructed for the target plot. The longitude direction is set as the X-axis, the latitude direction as the Y-axis, and the depth direction as the Z-axis. Referring to the agronomical requirements for maize growth and the absorption of nitrogen fertilizer by maize roots, the data grid density required for visualization is set to 500mm interval in the X-axis based on row spacing, 400mm interval in the Y-axis based on plant spacing, and 200mm interval in the Z-axis. The process of acquiring and processing the three-dimensional nitrogen data of the target site includes: Using UAV remote sensing and / or soil sensor networks, acquire three-dimensional data of available nitrogen and total nitrogen in the target plot; Based on the three-dimensional data of total nitrogen in the preset area below the maximum nitrogen absorption depth of corn roots in the target plot, the three-dimensional data of leaching nitrogen loss in the target plot are calculated using the following formula. ； in, This provides three-dimensional data on nitrogen loss during leaching at sampling time t. This represents the three-dimensional data of total nitrogen in a preset region D below the maximum nitrogen absorption depth of maize roots at sampling time t. The three-dimensional data of total nitrogen in the preset region D below the maximum nitrogen absorption depth of maize roots at sampling time t-1; Based on the three-dimensional data of total nitrogen and leaching loss nitrogen of the target site, calculate the three-dimensional data of volatile nitrogen loss of the target site. Two-dimensional data of nitrogen absorbed by crops in a target plot are obtained using drone remote sensing, and corn growth information of the target plot is obtained using field sensors; the two-dimensional data is (x,y,v,t), and the corn growth information is (x,y,h,t), where v is the nitrogen content and h is the corn height. Using the corn growth information of the target plot, the two-dimensional data of nitrogen absorbed by the crop is mapped into three-dimensional data of nitrogen absorbed by the crop.

2. The method for visualizing nitrogen elements in maize fields based on Unreal Engine according to claim 1, characterized in that, The three-dimensional data is (x, y, z, v, t), where x, y, and z are the coordinates of the X-axis, Y-axis, and Z-axis in the geographic information system, respectively, v is the nitrogen content, and t is the sampling time.

3. The method for visualizing nitrogen elements in maize fields based on Unreal Engine according to claim 2, characterized in that, Based on the three-dimensional data of total nitrogen and leaching loss nitrogen of the target site, the three-dimensional data of volatile nitrogen loss of the target site are calculated, specifically including: The nitrogen element content of the three-dimensional data of total nitrogen and the three-dimensional data of nitrogen lost through leaching is accumulated along the Z-axis to obtain the two-dimensional data of total nitrogen and nitrogen lost through leaching. Based on the two-dimensional data of total nitrogen and the two-dimensional data of nitrogen loss from leaching, the two-dimensional data of nitrogen loss from volatilization are calculated using the following formula; ； in, This provides two-dimensional data on nitrogen loss due to volatilization at sampling time t. and The two-dimensional data for total nitrogen at sampling time t-1 and t are respectively. This represents two-dimensional data on nitrogen absorbed by the crop at sampling time t. This is two-dimensional data of nitrogen loss during leaching at sampling time t. Two-dimensional data for nitrogen increase due to fertilization at sampling time t; By utilizing the volatilization characteristics of nitrogen, the two-dimensional data of nitrogen loss due to volatilization are mapped along the z-axis to obtain the three-dimensional data of nitrogen loss due to volatilization.

4. The method for visualizing nitrogen elements in maize fields based on Unreal Engine according to claim 1, characterized in that, Creating a 3D spatial model of the target land parcel in Unreal Engine includes: In Unreal Engine, the origin of Unreal Engine's world coordinate system is used as the origin of the world coordinate system of the geographic information system. A boxcollision with a length of 450,000 mm in the X-axis direction, a length of 450,000 mm in the Y-axis direction, and a depth of -800 mm in the Z-axis direction is constructed as a 3D soil model. In Unreal Engine, use Blender or 3ds Max to create individual corn plant models at different growth stages, and arrange the individual corn plant models according to the corn growth information of the target plot to obtain a three-dimensional corn model. In Unreal Engine, the origin of Unreal Engine's world coordinate system is used as the origin of the world coordinate system of the geographic information system. A boxcollision with a length of 450,000 mm in the X-axis direction, a length of 450,000 mm in the Y-axis direction, and a height of 10,000 mm in the Z-axis direction is constructed as an air 3D model. In Unreal Engine, weather data is imported using a weather plugin to build a weather model.

5. The method for visualizing nitrogen elements in maize fields based on Unreal Engine according to claim 1, characterized in that, The three-dimensional data of nitrogen element is imported into the three-dimensional spatial model, and particle systems of different colors representing the spatial distribution of different types of nitrogen element are driven respectively to realize the visualization of nitrogen element in the three-dimensional spatial model, specifically including: Create a structure variable in Unreal Engine and import the three-dimensional data of the target nitrogen element into the structure variable; the target nitrogen element is available nitrogen, non-available nitrogen, nitrogen absorbed by crops, nitrogen lost through leaching, or nitrogen lost through volatilization. Create a blueprint for the particle system containing the target nitrogen element, and create a blueprint for the particle system that assigns a color material to the particle system; By using the ForEachLoop node to traverse all the three-dimensional coordinate information in the three-dimensional data of the target nitrogen element, a spatial data grid is built in Unreal Engine. Using the SpawnActor node, generate the corresponding number of particles based on the nitrogen content in the three-dimensional data of the target nitrogen element; By using the AddTimeLine node, the particle state is updated according to the sampling time in the three-dimensional data of the target nitrogen element, and dynamic three-dimensional visualization of the target nitrogen element is performed.

6. The method for visualizing nitrogen elements in maize fields based on Unreal Engine according to claim 1, characterized in that, The particle systems of available nitrogen and non-available nitrogen are constrained within a space of 0 to -600 mm in the soil model; The particle system that absorbs nitrogen from crops is constrained in a three-dimensional model of maize; The particle system that loses nitrogen through volatilization is constrained in an air model; The particle system of nitrogen loss due to leaching is constrained within a space of -601 mm to -800 mm in the soil model.

7. The method for visualizing nitrogen elements in maize fields based on Unreal Engine according to claim 1, characterized in that, The particle system that absorbs nitrogen from crops uses the corn height information to control the growth height of a 3D corn model.

8. The method for visualizing nitrogen elements in maize fields based on Unreal Engine according to claim 1, characterized in that, The three-dimensional data of nitrogen element is imported into the three-dimensional spatial model. Different nitrogen element particle systems are used to drive the three-dimensional data of different nitrogen elements to visualize the nitrogen element in the three-dimensional spatial model. This process also includes: The three-dimensional nitrogen data is imported into the three-dimensional spatial model. Based on field management needs, the particle systems of different nitrogen elements are processed to generate one or more of the following: two-dimensional heat map, three-dimensional heat map, and two-dimensional contour map.

9. A visualization platform for nitrogen elements in maize fields based on Unreal Engine, characterized in that, The Unreal Engine-based maize field nitrogen element visualization platform is applied to the Unreal Engine-based maize field nitrogen element visualization method according to any one of claims 1-8, wherein the Unreal Engine-based maize field nitrogen element visualization platform comprises: The data processing layer is used to acquire three-dimensional nitrogen data of the target plot; the three-dimensional nitrogen data includes: three-dimensional data of available nitrogen, three-dimensional data of non-available nitrogen, three-dimensional data of nitrogen absorbed by crops, three-dimensional data of nitrogen lost through leaching, and three-dimensional data of nitrogen lost through volatilization. The scene building layer is used to create a 3D spatial model of the target plot in Unreal Engine; the 3D spatial model includes: a soil 3D model, a corn 3D model, an air 3D model, and a weather model; The visualization implementation layer is used to import the three-dimensional data of nitrogen elements into the three-dimensional spatial model, and drive different colored particle systems representing the spatial distribution of different types of nitrogen elements to realize the visualization of nitrogen elements in the three-dimensional spatial model; the different nitrogen elements include: available nitrogen, non-available nitrogen, nitrogen absorbed by crops, nitrogen lost through leaching, and nitrogen lost through volatilization.

10. The maize field nitrogen element visualization platform based on Unreal Engine according to claim 9, characterized in that, The Unreal Engine-based field nitrogen visualization platform for cornfields also includes: An interactive presentation layer is used to import the three-dimensional data of nitrogen element into the three-dimensional spatial model, and control the particle system of different nitrogen elements according to field management needs to generate one or more of two-dimensional heat maps, three-dimensional heat maps, and two-dimensional contour maps.

Images