A lake time series data prediction method based on unmanned aerial vehicle laser radar point cloud

Abstract

The application discloses a kind of lake time series data prediction methods based on unmanned aerial vehicle laser radar point cloud, applied to lake data prediction technical field.The application includes the following steps: by unmanned aerial vehicle carrying laser radar collection lake and surrounding terrain and water level point cloud data;Point cloud data is converted into DEM elevation map;DEM elevation map is re-discretized to obtain new discrete point cloud map;Screening lake terrain feature points;Combining the elevation data of lake terrain feature points and the elevation data of water level, obtain database and pretreatment;Based on database training time series prediction model, multivariate seasonal trend prediction is carried out;The elevation data of prediction result is visualized.The application can predict multivariate seasonal data, and finally visualized, which can predict lake geological structure change, water level fluctuation and water storage size, help to carry out lake development, geological structure research record and other work.

Description

Technical Field

[0001] The present invention relates to the technical field of lake data prediction, and more particularly to a lake time series data prediction method based on unmanned aerial vehicle (UAV) lidar point cloud. Background Art

[0002] Lakes are an important component of surface water and play a vital role in maintaining hydrological balance and a healthy environment. However, climate change and human interference in the lake environment have caused significant changes in lake morphology, resulting in adverse ecological and environmental impacts. This has greatly affected the availability of freshwater resources, leading to a series of regional ecological and environmental problems and restricting regional sustainable development. Changes in lake parameters generally indicate environmental changes. Therefore, extracting lake water information, reflecting changes in lake water volume, understanding its impact, and proposing solutions in a timely manner are of great practical significance. Existing lake water storage estimation methods are mainly based on traditional water level station measurement and remote sensing technology. The overall engineering workload is large, the maintenance cost of fixed-site instruments is high, and the accuracy of remote sensing data is low. In many application scenarios, many lakes do not have professional water level stations and supporting equipment, and the cost of mobilizing personnel and materials is high. Therefore, how to provide a lake time series data prediction method based on drone lidar point clouds is a problem that technicians in this field urgently need to solve. Summary of the Invention

[0003] In view of this, the present invention provides a lake time series data prediction method based on UAV lidar point cloud. The lake block point cloud data of the UAV lidar can be used to establish a digital elevation model of the lake block and measure the water level. The time series prediction model is used to predict the changes in the lake basin and surrounding geological structure, and to estimate and predict the lake water storage and water level time series data.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] A lake time series data prediction method based on UAV lidar point cloud includes the following steps:

[0006] S1. Use a drone equipped with a lidar to collect point cloud data of the lake, surrounding terrain, and water level;

[0007] S2, converting the point cloud data of the lake and surrounding terrain and water level into a DEM elevation map;

[0008] S3, re-discretize the DEM elevation map to obtain a new discrete point cloud map;

[0009] S4. Screening lake terrain feature points in the new discrete point cloud image;

[0010] S5. Combining the elevation data of the lake terrain feature points with the elevation data of the water level to obtain a database, and preprocessing the database;

[0011] S6. Train a time series prediction model based on the database, and use the trained time series prediction model to predict multivariate seasonal trends;

[0012] S7. Visualize the elevation data of the prediction results.

[0013] Optionally, S1 specifically includes: using a drone equipped with a lidar combined with an inertial measurement unit and a GPS module to collect point cloud data of the lake and surrounding terrain and water level at certain time intervals, and performing multi-cycle measurement.

[0014] Optionally, S4 is:

[0015] S41, performing sparse grid equal distance screening on the new discrete point cloud image;

[0016] S42, further screening by joint time domain filtering method;

[0017] S43. Calculate the gradient value corresponding to each data point and set a dynamic threshold value of the gradient modulus for screening.

[0018] Optionally, S41 specifically includes: selecting one data point from every four data points as a feature point to reduce the point cloud density.

[0019] Optionally, S42 specifically includes: calculating the coefficient of variation CV of the Z coordinate of the data point:

[0020]

[0021]

[0022] Where, X i represents the elevation data Z of the i-th period of the geographical location point X, N is the total number of measurement cycles, and ε represents X i The mean of the samples, S is the sample standard deviation, CV < 10% indicates that the data are very concentrated, 10% ≤ CV < 30% indicates that the data are relatively concentrated, 30% ≤ CV < 50% indicates that the data are moderately dispersed, and CV ≥ 50% indicates that the data are highly dispersed. Data points with CV ≥ 10% are selected and entered into S43.

[0023] Optionally, S43 specifically includes: calculating the gradient value corresponding to each data point, calculating the angle between the gradient vector and the unit vector perpendicular to the XY plane, setting a dynamic threshold value of the gradient modulus, taking data points exceeding the dynamic threshold range of the gradient modulus as inflection points, and repeatedly setting the dynamic threshold value for multiple rounds of screening.

[0024] Optionally, the preprocessing in S5 includes outlier processing and data set expansion. The outlier processing adopts one of the isolation forest algorithm, the local outlier factor algorithm, the standard deviation-based detection algorithm, and the interquartile range method. The data set expansion method includes time series interpolation, synthetic data generation, and data enhancement.

[0025] It can be seen from the above technical solution that compared with the existing technology, the present invention provides a lake time series data prediction method based on UAV lidar point cloud, which has the following beneficial effects: the present invention can predict multivariate seasonal data, and finally visualize it to predict changes in lake geological structure, water level fluctuations and water storage size, and help carry out lake area development, geological structure research and recording and other tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0027] Figure 1 This is a flow chart of the lake time series data prediction method of the present invention;

[0028] Figure 2 This is a schematic diagram of characteristic points before screening in the present invention;

[0029] Figure 3 This is a schematic diagram of feature points after screening in the present invention;

[0030] Figure 4 The DEM elevation map of the first period in the embodiment of the present invention;

[0031] Figure 5 is a point cloud map of the first cycle in an embodiment of the present invention;

[0032] Figure 6 This is a 3D geological structure map of the first period in an embodiment of the present invention;

[0033] Figure 7 A DEM elevation map for a new period in the future according to an embodiment of the present invention;

[0034] Figure 8 A point cloud map of a new period in the future in an embodiment of the present invention;

[0035] Figure 9 A 3D geological structure map of a new period in the future in an embodiment of the present invention;

[0036] Figure 10This is a schematic diagram of the water area in a new cycle in the future according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0038] The embodiment of the present invention discloses a lake time series data prediction method based on UAV lidar point cloud, such as Figure 1 As shown, the following steps are included:

[0039] S1. Use a drone equipped with a lidar to collect point cloud data of the lake, surrounding terrain, and water level;

[0040] S2, converting the point cloud data of the lake and surrounding terrain and water level into a DEM elevation map;

[0041] S3. Re-discretize the DEM elevation map to obtain a new discrete point cloud map; discretization can maintain the single value of elevation while sparsely sparse the point cloud for subsequent processing;

[0042] S4. Screening lake terrain feature points in the new discrete point cloud image;

[0043] In order to predict terrain data and reduce the amount of calculation to improve the efficiency of the time series prediction model, it is necessary to perform multi-step lake terrain feature point screening. The feature points before and after screening are as follows: Figure 2 and Figure 3 As shown;

[0044] S5. Combining the elevation data of the lake terrain feature points with the elevation data of the water level to obtain a database, and preprocessing the database;

[0045] S6. Train a time series prediction model based on the database, and use the trained time series prediction model to predict multivariate seasonal trends;

[0046] S7. Visualize the elevation data of the prediction results.

[0047] A time series, also known as a dynamic series, is a series of values ​​​​of the same statistical indicator arranged in the order of their occurrence. The main purpose of time series analysis is to predict the future based on existing historical data. Depending on the observation time, the time in the time series can be a year, quarter, month, or any other time format. In this embodiment of the present invention, the lake time series data includes the coordinate information of the geological structure of the lake and its vicinity, as well as the lake water level and lake water storage.

[0048] Furthermore, S1 specifically involves performing multi-cycle measurements using a drone-mounted LiDAR, in conjunction with an inertial measurement unit and GPS module, to collect point cloud data of the lake, surrounding terrain, and water levels at regular intervals. LiDAR point clouds offer high accuracy, with an error range of up to centimeters even in deep water. Furthermore, a long-hover drone equipped with LiDAR collects point cloud data of lake terrain within a radius of hundreds of meters.

[0049] In the embodiment of the present invention, when using a drone equipped with a lidar for multi-cycle measurement, geological structure and water level sampling needs to be carried out at long time intervals. This is mainly due to the slowness of geological structure changes and the convenience of sampling. Taking a half-month cycle as an example, the long period ensures the significance of geological structure changes while ignoring temporary water level anomalies caused by short-term factors such as weather.

[0050] During multiple cycles of data collection, the terrain height at the same longitude and latitude, or geographic location, will shift differently along the z-axis over time. The time-varying patterns of these shifts can be used to predict the geological structure of lakes. Here, a change in the z-axis coordinate at the same (X, Y) coordinate is considered a displacement of that (X, Y) point along the z-axis.

[0051] A Digital Elevation Model (DEM) is a method for digitally representing the Earth's surface morphology. It uses a limited amount of terrain elevation data to construct a ground model presented in the form of an ordered numerical matrix. It is a type of Digital Terrain Model (DTM). A DTM covers multiple aspects of terrain, including but not limited to the spatial distribution of attributes such as elevation, slope, aspect, and slope change rate. In contrast, a DEM focuses on providing zero-order, single-dimensional information on terrain height, while other terrain features can be obtained through further analysis of the DEM data.

[0052] The data structure of digital elevation models mainly includes two forms: regular grids and triangulated irregular networks (TINs):

[0053] 1. Regular Grid: This format, based on a Gaussian projection system, arranges topographic points at regular intervals on the XY plane, forming an array consisting of coordinate values ​​and their corresponding elevation values. The location of a given point P{i,j} can be determined by its row number i and column number j in the DEM, as well as basic information stored in the DEM file. The advantage of a regular grid is that it requires less data storage and supports effective data compression techniques, thus simplifying data processing and maintenance.

[0054] 2. Triangulated Irregular Network: TIN is a method for depicting terrain features using a non-uniformly distributed network of triangles. In a TIN, each node represents an original survey data point, ensuring accurate reproduction of terrain features and being particularly advantageous for modeling complex terrain. However, TINs are data-intensive; in addition to storing 3D coordinates, they also record the connectivity between nodes, making them more suitable for processing large-scale remote sensing imagery.

[0055] In the embodiment of the present invention, in order to facilitate point cloud data processing, a regular grid is used for subsequent calculations.

[0056] The resolution of DEM is one of the key parameters for evaluating its terrain representation capabilities, and it also affects the choice of its applicable scenarios. DEM resolution specifically refers to the basic unit that constitutes the model - the grid size. As discretized geographic spatial information, each (X, Y) position actually corresponds to a small grid with a specific elevation value, and the size of these grids is the DEM resolution. Generally speaking, the smaller the resolution value, the higher the detail retention ability and the finer the surface description, but it also leads to a significant increase in the data size. Therefore, when creating or selecting a DEM, it is necessary to weigh the relationship between accuracy and data management according to actual needs in order to achieve the best application effect.

[0057] In an embodiment of the present invention, the discretization adopts the equal-width binning method, which is a simple and intuitive data discretization method. The continuous data interval is evenly divided into several subintervals, each of which has an equal width. The interval width is adjusted according to the accuracy requirements. Since most DEM maps maintain the continuity of elevation data through interpolation, it is necessary to re-discretize it to facilitate subsequent data processing. By selecting different interval widths, the DEM map is divided into several blocks, and the elevation value corresponding to the block center point is taken as the block characteristic elevation value. Through this discretization process, a preliminary uniformly distributed point cloud is obtained.

[0058] Furthermore, S4 is specifically:

[0059] S41, performing sparse grid equal distance screening on the new discrete point cloud image;

[0060] S42, further screening by joint time domain filtering method;

[0061] S43. Calculate the gradient value corresponding to each data point and set a dynamic threshold value of the gradient modulus for screening.

[0062] In order to predict terrain data and reduce the amount of calculation to improve the efficiency of the time series prediction model, a multi-step screening of lake terrain feature points is required.

[0063] Furthermore, S41 is specifically as follows: one data point is selected from every four data points as a feature point to reduce the point cloud density.

[0064] Furthermore, S42 is specifically as follows: calculating the coefficient of variation CV of the Z coordinate of the data point:

[0065]

[0066] Where, X i represents the elevation data Z of the i-th period of the geographical location point X, N is the total number of measurement cycles, and ε represents X i The mean of the samples, S is the sample standard deviation, CV < 10% indicates that the data are very concentrated, 10% ≤ CV < 30% indicates that the data are relatively concentrated, 30% ≤ CV < 50% indicates that the data are moderately dispersed, and CV ≥ 50% indicates that the data are highly dispersed. Data points with CV ≥ 10% are selected and entered into S43.

[0067] Furthermore, S43 is specifically as follows: calculating the gradient value corresponding to each data point, calculating the angle between the gradient vector and the unit vector perpendicular to the XY plane, setting a dynamic threshold value of the gradient modulus, taking data points exceeding the dynamic threshold range of the gradient modulus as inflection points, and repeatedly setting the dynamic threshold value for multiple rounds of screening.

[0068] In this embodiment, a dynamic threshold for the gradient modulus is selected based on the terrain. For example, relatively small angles such as 15° or 30° can be used to reduce the number of inflection points, thereby reducing the model's time complexity. This filtering logic is then followed to perform multiple rounds of data point screening, reducing computational effort while preserving the lake's primary geological structure.

[0069] The joint time-domain filtering method used in S42 can screen out terrain feature points that have undergone obvious time-varying displacements, and the time-varying coefficient of variation exceeds the threshold. The inflection point gradient in S43 screens out its terrain feature points. Simply put, many points in some blocks simultaneously show the same trend of time-varying displacement, and the overall trend is smooth. At this time, we only need to know how the edge points of this part of the block change to describe the time-varying displacement of the entire plane.

[0070] In this embodiment of the present invention, since different inflection points may occur between multiple cycles, a weight factor is introduced to determine the logical order of the prediction model to further optimize the time complexity of the model:

[0071]

[0072] Where N is the total amount of data and the total number of measurement cycles, k i is the total number of inflection points that appear in all cycles.

[0073] By arranging the weight factors in reverse order and giving priority to calculating important inflection points with more occurrences, the main characteristic points of the predicted geological structure can be obtained as quickly as possible.

[0074] The filtered point cloud elevation values ​​are saved and, along with the water level elevation data, form the complete time-varying elevation dataset. A time series prediction model is then used for the next step. A time series prediction model is a statistical or machine learning method used to predict future values ​​based on past data points. These models are widely used in fields such as finance, economics, weather forecasting, and sales forecasting. Various types of time series prediction models can be used depending on specific needs and data characteristics. Due to the varying complexity of lake terrains, cross-validation can be used to select the optimal model for each type of terrain. For example, using the LSTM model, an attention mechanism can be added to further enhance the accuracy of time series predictions.

[0075] Furthermore, the preprocessing in S5 includes outlier processing and data set expansion. The outlier processing adopts one of the isolation forest algorithm, local outlier factor algorithm, standard deviation-based detection algorithm, and interquartile range method. The data set expansion method includes time series interpolation, synthetic data generation, and data enhancement.

[0076] Outliers refer to data points that deviate significantly from the rest of the observations. These data points may be caused by measurement errors, recording errors, or unusual events. Their existence may have a negative impact on model training, leading to overfitting or decreased generalization ability. Therefore, effectively identifying and processing outliers is an important part of time series analysis. Since lake waters are not always closed and may be subject to artificial changes or large-scale dam breaches, if abnormal point clouds appear in two adjacent detections, the point cloud block needs to be preprocessed and not included in the prediction model. If the original abnormal point cloud block stabilizes again in the new detection and a new small-scale evolution process occurs, it will be re-included in the time series prediction model.

[0077] Dataset augmentation is a technique that increases the size of a training dataset by adding additional data points. This is particularly important for avoiding overfitting and improving model generalization. Since sampling over long intervals inevitably results in relatively small amounts of data, methods are necessary to increase and augment the dataset.

[0078] In an embodiment of the present invention, time series interpolation can fill missing values ​​or create new data points using techniques such as linear interpolation and spline interpolation. This method can maintain the original trend and seasonal characteristics of the time series. Synthetic data generation uses models such as ARIMA and LSTM to generate new time series data based on existing data. This method can create new samples with similar statistical properties to the original data, helping to enhance the model's learning ability. Data augmentation is similar to data augmentation techniques in image processing. It can modify the original data by adding noise, transforming the time scale, etc. to generate new training samples.

[0079] After preprocessing the data, the dataset is used to train and predict various time series models. Visualization yields DEM elevation maps or point cloud maps for multiple future periods. Calculations can also be used to predict changes in water reserves and water area. The data here is multivariate and exhibits seasonal trends, so the characteristics of the dataset must be considered when selecting a time series prediction model to ensure effective predictions.

[0080] After the visualization operation matches the LSTM predicted elevation value to the corresponding two-dimensional position coordinates, a three-dimensional spatial coordinate data is formed. These spatial coordinates are redrawn to obtain the predicted point cloud map and DEM map, which is convenient for intuitive analysis. In the embodiment of the present invention, the DEM elevation map, point cloud map and 3D geological structure map of the first cycle obtained by the visualization simulation are shown as follows: Figure 4 、 Figure 5 and Figure 6 As shown in the figure, the DEM elevation map, point cloud map and 3D geological structure map of the next cycle are as follows: Figure 7 、 Figure 8 and Figure 9 As shown in the figure, the water area in the next cycle will be as follows: Figure 10 As shown, the coordinate zero point in the figure is a selected fixed observation point. Since multi-period time-series terrain data requires the coordinate information of each feature point to be coordinateized to simplify calculations, a point corresponding to a specific longitude and latitude is selected as the fixed zero point as the coordinate reference. Fixed coordinate axes are also required. In this embodiment of the present invention, east is selected as the positive x-axis direction, and north is selected as the positive y-axis direction.

[0081] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0082] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A lake time series data prediction method based on UAV lidar point cloud, characterized in that: The following steps are involved: S1. Use a drone equipped with a lidar to collect point cloud data of the lake, surrounding terrain, and water level; S2, converting the point cloud data of the lake and surrounding terrain and water level into a DEM elevation map; S3, re-discretize the DEM elevation map to obtain a new discrete point cloud map; S4. Screening lake terrain feature points in the new discrete point cloud image; S5. Combining the elevation data of the lake terrain feature points with the elevation data of the water level to obtain a database, and preprocessing the database; S6. Train a time series prediction model based on the database, and use the trained time series prediction model to predict multivariate seasonal trends; S7. Visualize the elevation data of the prediction results; S4 is specifically: S41, performing sparse grid equal distance screening on the new discrete point cloud image; S42, further screening by joint time domain filtering method; S43, calculating the gradient value corresponding to each data point, and setting a dynamic threshold value of the gradient modulus for screening; S41 specifically includes: selecting one data point from every four data points as a feature point to reduce the point cloud density; S42 is specifically: Calculate the coefficient of variation of the Z coordinate of the data point CV : Where, Represents a geographic location point X No. i Elevation data Z of a period, N is the total number of measurement cycles, express The mean of S is the sample standard deviation, CV <10% indicates that the data is very concentrated, 10%≤CV<30% indicates that the data is relatively concentrated, 30%≤CV<50% indicates that the data is moderately dispersed, and CV≥50% indicates that the data is highly dispersed. CV ≥10% of the data points entered S43; S43 specifically includes: calculating the gradient value corresponding to each data point, calculating the angle between the gradient vector and the unit vector perpendicular to the XY plane, setting a dynamic threshold for the gradient modulus, taking data points that exceed the dynamic threshold range of the gradient modulus as inflection points, and repeatedly setting the dynamic threshold for multiple rounds of screening.

2. The lake time series data prediction method based on UAV lidar point cloud according to claim 1 is characterized in that: S1 specifically involves using a drone equipped with a lidar, inertial measurement unit, and GPS module to collect point cloud data of the lake, surrounding terrain, and water level at certain time intervals for multi-cycle measurement.

3. The lake time series data prediction method based on UAV lidar point cloud according to claim 1 is characterized in that: The preprocessing in S5 includes outlier processing and data set expansion. Outlier processing uses one of the isolation forest algorithm, local outlier factor algorithm, standard deviation-based detection algorithm, and interquartile range method. Data set expansion methods include time series interpolation, synthetic data generation, and data enhancement.

Images