Multi-element feature coupled archaeological site prediction method and device

Abstract

The invention relates to an archaeological site prediction method and device coupled with multi-element characteristics, and belongs to the technical field of data processing.The archaeological site prediction method coupled with the multi-element characteristics comprises the steps that geographic element data and remote sensing image data of a target area are obtained, the geographic element data comprises DEM, land utilization types and river system data; determining a target feature vector based on the preprocessed geographic element data and remote sensing image data; the target feature vector serves as input of an archaeological site prediction model, the archaeological site distribution probability of the target area is predicted based on output of the archaeological site prediction model, and the archaeological site prediction model is obtained based on training of a real archaeological site position carrying a feature tag. According to the method, archaeological site prediction is carried out by coupling multi-element features, and the accuracy and flexibility of archaeological site prediction are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an archaeological site prediction method and device coupling multi-factor features. Background Art

[0002] The archaeological site prediction model is a tool based on the combination of Geographic Information System (GIS), remote sensing technology, archaeological knowledge and statistical methods. It uses a variety of data such as historical documents, topography, land use, and water distribution to analyze the relationship between sites and environmental, ecological, and cultural variables, thereby predicting and evaluating the potential distribution of archaeological sites in specific areas. It plays a vital role in the discovery and protection of sites, and has positive significance for the protection and inheritance of cultural heritage.

[0003] Most existing archaeological site prediction schemes only focus on the prediction of a single feature (such as geographic elements or image data), which is limited in prediction accuracy and scope of application. Summary of the invention

[0004] In view of this, it is necessary to provide an archaeological site prediction method and device that couples multi-factor features to solve the limitations of existing archaeological site prediction schemes in prediction accuracy and application scope.

[0005] In order to solve the above problems, the present invention provides an archaeological site prediction method coupling multi-factor features, comprising: Acquire geographic element data and remote sensing image data of the target area, wherein the geographic element data includes DEM, land use type and river system data; Determine the target feature vector based on the preprocessed geographic element data and remote sensing image data; The target feature vector is used as the input of an archaeological site prediction model, and the distribution probability of archaeological sites in the target area is predicted based on the output of the archaeological site prediction model, wherein the archaeological site prediction model is trained based on the locations of real archaeological relics carrying feature labels.

[0006] In a possible implementation, determining the target feature vector based on the preprocessed geographic element data and remote sensing image data includes: Determine the geographic element characteristics, remote sensing image data characteristics and time series characteristics of the target area based on the preprocessed geographic element data and remote sensing image data; Determining the target feature vector based on the geographic element features, remote sensing image data features and time series features of the target area; The geographical element characteristics of the target area include the topographic characteristics and hydrological characteristics of the target area, the remote sensing image data characteristics of the target area include the normalized vegetation index and the normalized water body index, and the time series characteristics of the target area include the vegetation change rate and the surface temperature change rate.

[0007] In a possible implementation, the terrain features of the target area include the elevation, slope and slope direction of each preset location in the target area, and the hydrological features of the target area include the distance to the water source of each preset location in the target area, and the water system density of the target area.

[0008] In a possible implementation, the preprocessing of the geographic element data and remote sensing image data of the target area includes: Performing outlier elimination and denoising processing on the geographic element data and remote sensing image data of the target area to obtain a first data set; Performing data format conversion on the first data set so that the spatial resolution and spatial coordinate system of all data in the first data set are the same, thereby obtaining a second data set; The remote sensing image data in the second data set is corrected to obtain pre-processed geographic element data and remote sensing image data of the target area.

[0009] In a possible implementation manner, the correcting the remote sensing image data in the second data set includes: The remote sensing image data in the second data set is subjected to geometric correction, radiation correction and atmospheric correction.

[0010] In a possible implementation, determining the target feature vector based on the geographic element features, remote sensing image data features and time series features of the target area includes: The target feature vector is obtained by performing feature dimensionality reduction on the geographic feature, remote sensing image data and time series features of the target area, and performing feature fusion on the geographic feature, remote sensing image data and time series features of the target area after feature dimensionality reduction.

[0011] In one possible implementation, the archaeological site prediction model is obtained by training a random forest model using real archaeological site locations as positive samples, real non-archaeological site locations as negative samples, and the geographic element features, remote sensing image data features, and time series features of the positive and negative samples as labels.

[0012] The present invention also provides an archaeological site prediction device coupling multiple factor features, comprising: An acquisition module is used to acquire geographic element data and remote sensing image data of a target area, wherein the geographic element data includes DEM, land use type and river system data; A determination module, used for determining a target feature vector based on preprocessed geographic element data and remote sensing image data; A prediction module is used to use the target feature vector as the input of an archaeological site prediction model, and to predict the distribution probability of archaeological sites in the target area based on the output of the archaeological site prediction model, wherein the archaeological site prediction model is trained based on the location of real archaeological relics carrying feature labels.

[0013] The present invention also provides an electronic device, including a memory and a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the archaeological site prediction method coupling multiple factor features as described above is implemented.

[0014] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the archaeological site prediction method of coupling multiple factor features as described above.

[0015] The beneficial effects of the present invention are as follows: the method and device for predicting archaeological sites by coupling multi-factor features provided by the present invention extract the geographical element features, remote sensing image data features and time series features of the target area through the geographical element data and remote sensing image data of the target area, thereby realizing the multi-factor feature extraction of the target area, and then predicting the distribution probability of archaeological sites in the target area based on the geographical element features, remote sensing image data features and time series features of the target area. Taking multi-factor features into consideration, the accuracy of archaeological site prediction can be effectively improved. The present invention improves the accuracy and flexibility of archaeological site prediction by coupling multi-factor features to predict archaeological sites. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a flow chart of an embodiment of an archaeological site prediction method coupling multiple factor features provided by the present invention; Figure 2 A schematic diagram of a process flow of an embodiment of an archaeological site prediction process provided by the present invention; Figure 3 A schematic diagram of the structure of an embodiment of an archaeological site prediction device coupled with multiple element features provided by the present invention; Figure 4 A schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0018] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0019] In the description of the present invention, reference to an "embodiment" means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive of other embodiments. It is explicitly and implicitly understood by those skilled in the art that the described embodiments may be combined with other embodiments.

[0020] The archaeological site prediction model is a tool based on the combination of GIS, remote sensing technology, archaeological knowledge and statistical methods. It uses a variety of data such as historical documents, topography, land use, and water distribution to analyze the relationship between sites and environmental, ecological, and cultural variables, thereby predicting and evaluating the potential distribution of archaeological sites in specific areas. It plays a vital role in the discovery and protection of sites, and has positive significance for the protection and inheritance of cultural heritage.

[0021] Most existing archaeological site prediction schemes only focus on the prediction of a single feature (such as geographic elements or image data), which is limited in prediction accuracy and scope of application.

[0022] In order to solve the above problems, the present invention provides an archaeological site prediction method coupling multi-factor features.

[0023] The specific embodiments are described in detail below: A specific embodiment of the present invention discloses an archaeological site prediction method that couples multiple factor features. Figure 1 Come and see, Figure 1 The flowchart of an embodiment of the method for predicting archaeological sites by coupling multiple elements provided by the present invention includes steps S101 to S103, wherein: In step S101, the geographic element data and remote sensing image data of the target area are obtained, wherein the geographic element data includes DEM, land use type and river system data; In step S102, a target feature vector is determined based on the preprocessed geographic element data and remote sensing image data; In step S103, the target feature vector is used as the input of an archaeological site prediction model, and the distribution probability of archaeological sites in the target area is predicted based on the output of the archaeological site prediction model, wherein the archaeological site prediction model is trained based on the locations of real archaeological relics carrying feature labels.

[0024] During implementation, the geographic element data and remote sensing image data of the target area can be obtained first. The geographic element data can be obtained from public or proprietary GIS databases, and the remote sensing image data can be obtained through the Google Earth Engine (GEE) platform. The geographic element data can include digital elevation models (DEM), land use types, and river system data. Through the geographic element data and remote sensing image data of the target area, the spatial characteristics of the target area can be fully understood, providing support for subsequent archaeological remains prediction.

[0025] After obtaining the geographic element data and remote sensing image data of the target area, the target feature vector can be determined based on the preprocessed geographic element data and remote sensing image data. The target feature vector can be used to characterize the spatial characteristics of the target area. At the same time, data characterization is also more convenient for subsequent archaeological site prediction. Preprocessing can eliminate data interference caused by noise, errors, outliers, resolution mismatch and other factors.

[0026] Finally, the target feature vector can be used as the input of the archaeological site prediction model. The distribution probability of archaeological sites in the target area can be predicted based on the output of the archaeological site prediction model. By combining multi-factor characteristics to predict the distribution probability of archaeological sites in the target area, the accuracy of the prediction can be effectively improved.

[0027] The archaeological site prediction model can be trained based on the locations of real archaeological relics carrying feature labels, thereby fully reflecting the relationship between spatial features and archaeological relics.

[0028] Compared with the prior art, the archaeological site prediction method coupled with multi-factor features provided in this embodiment determines the target feature vector, that is, the input feature of the archaeological site prediction model, through the geographic feature data and remote sensing image data of the target area, thereby realizing the multi-factor feature extraction of the target area, and then predicts the distribution probability of archaeological sites in the target area based on the target feature vector and the archaeological site prediction model trained according to the real archaeological site locations carrying feature labels. Taking into account multi-factor features, the accuracy of archaeological site prediction can be effectively improved. The present invention improves the accuracy and flexibility of archaeological site prediction by coupling multi-factor features to perform archaeological site prediction.

[0029] Exemplarily, determining the target feature vector based on the preprocessed geographic element data and remote sensing image data includes: Determine the geographic element characteristics, remote sensing image data characteristics and time series characteristics of the target area based on the preprocessed geographic element data and remote sensing image data; Determining the target feature vector based on the geographic element features, remote sensing image data features and time series features of the target area; The geographical element characteristics of the target area include the topographic characteristics and hydrological characteristics of the target area, the remote sensing image data characteristics of the target area include the normalized vegetation index and the normalized water body index, and the time series characteristics of the target area include the vegetation change rate and the surface temperature change rate.

[0030] Specifically, the geographic element features, remote sensing image data features and time series features of the target area can be determined based on the pre-processed geographic element data and remote sensing image data of the target area, and then the target feature vector can be determined based on the geographic element features, remote sensing image data features and time series features of the target area, so as to characterize the data and make the data more intuitively applicable to archaeological site prediction. The time series features are extracted because the acquired remote sensing image data may come from different time periods, and the time series features can be used to identify the changing trends such as vegetation changes and surface temperature changes in the target area, and then used to infer the activity history of the site.

[0031] The geographical element characteristics of the target area may include the topographic characteristics and hydrological characteristics of the target area, the remote sensing image data characteristics of the target area may include the normalized vegetation index and the normalized water body index, and the time series characteristics of the target area may include the vegetation change rate and the surface temperature change rate. The above characteristics have a greater impact on the site selection of ancient cities. Providing these characteristics can effectively predict archaeological sites.

[0032] Exemplarily, the topographic features of the target area include the elevation, slope and slope aspect of each preset location in the target area, and the hydrological features of the target area include the distance to the water source of each preset location in the target area and the water system density of the target area.

[0033] Specifically, the topographic features of the target area may include the elevation, slope and slope aspect of each preset position in the target area, and the hydrological features of the target area may include the distance to the water source of each preset position in the target area, and the water system density of the target area. The preset positions in the target area can be determined by dividing the target area into regions, and further refining the features can further improve the accuracy of the archaeological site prediction.

[0034] Exemplarily, the preprocessing of the geographic element data and remote sensing images of the target area includes: Performing outlier elimination and denoising processing on the geographic element data and remote sensing image data of the target area to obtain a first data set; Performing data format conversion on the first data set so that the spatial resolution and spatial coordinate system of all data in the first data set are the same, thereby obtaining a second data set; The remote sensing image data in the second data set is corrected to obtain pre-processed geographic element data and remote sensing image data of the target area.

[0035] Specifically, when preprocessing the geographic element data and remote sensing image data of the target area, the geographic element data and remote sensing image data of the target area can first be subjected to outlier removal and denoising to avoid the influence of outliers and noise on subsequent predictions, thereby obtaining a first data set.

[0036] Next, the format of the first data set may be converted to keep the spatial resolution and spatial coordinate system of all data in the first data set the same, so as to facilitate subsequent feature extraction and feature fusion to obtain the second data set.

[0037] Finally, the remote sensing image data in the second data set is corrected to reduce the error in the remote sensing image data, and the pre-processed geographic element data and remote sensing image data of the target area are obtained.

[0038] Exemplarily, the correcting the remote sensing image data in the second data set includes: The remote sensing image data in the second data set is subjected to geometric correction, radiation correction and atmospheric correction.

[0039] Specifically, when correcting the remote sensing image data in the second data set, geometric correction, radiation correction and atmospheric correction may be performed on the remote sensing image data in the second data set according to the characteristics of the remote sensing image data.

[0040] Exemplarily, determining the target feature vector based on the geographic element features, remote sensing image data features and time series features of the target area includes: The target feature vector is obtained by performing feature dimensionality reduction on the geographic feature, remote sensing image data and time series features of the target area, and performing feature fusion on the geographic feature, remote sensing image data and time series features of the target area after feature dimensionality reduction.

[0041] Specifically, when determining the target feature vector based on the geographic element characteristics, remote sensing image data characteristics and time series characteristics of the target area, we can first perform feature dimensionality reduction on the geographic element characteristics, remote sensing image data characteristics and time series characteristics of the target area. For example, feature selection and dimensionality reduction can be performed through algorithms such as PCA and Lasso regression to remove redundant or irrelevant features and retain only features that contribute more to the prediction of archaeological sites, so as to improve prediction efficiency.

[0042] Then, the geographic element features, remote sensing image data features and time series features of the target area after dimensionality reduction are fused, for example, by weighted averaging, feature splicing, etc., to obtain a unified multimodal feature vector (i.e., the target feature vector).

[0043] Exemplarily, the archaeological site prediction model is obtained by training a random forest model with real archaeological site locations as positive samples, real non-archaeological site locations as negative samples, and the geographic element features, remote sensing image data features and time series features of the positive and negative samples as labels.

[0044] Specifically, the archaeological site prediction model used in the present invention is obtained by training a random forest model with real archaeological site locations as positive samples, real non-archaeological site locations as negative samples, and the geographical element characteristics, remote sensing image data characteristics and time series characteristics of the positive and negative samples as labels. Through the above training, the archaeological site prediction model can fully learn the relationship between multi-factor characteristics and the location of archaeological sites, thereby improving the prediction accuracy.

[0045] The technical solution of the present invention is better described below with reference to a specific embodiment: The present invention provides an archaeological site prediction method coupling multi-factor features. Firstly, the relationship between ancient city sites and geographical elements is analyzed spatially, and various geographical elements are loaded into the GEE platform to further extract the geographical element features of the ancient city sites. Secondly, based on the GEE platform, time series Sentinel-2 satellite images are obtained, and time series remote sensing images of the ancient city site area are analyzed. Through the time series changes of image bands and spectral indices, the spectral characteristics of the ancient city site area are discovered. Finally, multi-factor features are coupled to establish a machine learning model to realize the spatial distribution prediction and visualization of the potential distribution area of ​​the ancient city sites.

[0046] Combination Figure 2 Come and see, Figure 2 This is a flow chart of an embodiment of the archaeological site prediction process provided by the present invention. The specific steps of the process are as follows: 1. Collection of geographical elements and image data of the site.

[0047] (1) Topographic data collection: Obtain topographic data related to the archaeological site from public or proprietary geographic information system (GIS) databases, including elevation, slope, surface morphology, etc.

[0048] (2) Hydrological data: Extract hydrological elements in the region, such as rivers, lakes, groundwater flows, etc.

[0049] (3) Land use type data: Land use type data of the acquisition area.

[0050] (4) Image data acquisition: Based on the GEE platform, obtain Sentinel-2 multispectral imagery and Sentinel-1 image data.

[0051] 2. Processing of site geographical elements and image data.

[0052] (1) Resample the DEM-derived data such as elevation, slope, and aspect to a resolution of 10 m.

[0053] (2) Calculate the distance of the site from the water and identify the spatial distribution of hydrological characteristics.

[0054] (3) Resample the land use type data to a resolution of 10 m.

[0055] (4) Crop, align and upload the acquired geographic feature data to the GEE platform.

[0056] (5) Using the GEE platform, preprocess the Sentinel-2 multispectral images and Sentinel-1 images, such as radiation correction, atmospheric correction, geometric correction, and cropping, to improve the image data quality.

[0057] 3. Identification and extraction of multi-factor features of the site.

[0058] (1) Constructing site sample points and non-site sample points: Site sample points are generated according to the site location, while non-site sample points are generated randomly.

[0059] (2) Identification of geographical features: From a spatial analysis perspective, analyze the relationship between the site location and geographical features, and identify the characteristics of geographical features.

[0060] (3) Time series image analysis: By analyzing remote sensing images of different time periods, the changing trends in the region (such as vegetation changes, shrinking water areas, etc.) are identified, and features are generated for multispectral images, including the calculation of common indices such as the Normalized Difference Vegetation Index (NDVI) and the Normalized Difference Water Index (NDWI), to extract possible indirect indicator features of archaeological sites (such as vegetation anomalies, proximity to water bodies, etc.).

[0061] (4) Spatial resolution alignment: Spatial resolution alignment of geographic elements and remote sensing image features from different sources is performed to ensure that all data are processed at the same geographic scale and to reduce errors caused by scale mismatch.

[0062] (5) Feature standardization and normalization: All extracted geographic element features and image features are standardized to eliminate the dimensional differences between different feature dimensions and ensure the equality of features in the model.

[0063] (6) Feature dimensionality reduction and selection: Use algorithms such as PCA and Lasso regression to perform feature selection and dimensionality reduction, remove redundant or irrelevant features, and retain only features that contribute more to the prediction of archaeological sites, thereby improving model efficiency.

[0064] (7) Multi-factor feature fusion: The features of geographic elements and remote sensing images are combined through fusion algorithms (such as weighted averaging, feature splicing, etc.) to form a unified multimodal feature vector, which provides input for subsequent machine learning model training.

[0065] 4. Establish a machine learning prediction model for the site.

[0066] (1) Division of training set and test set: Based on the spatial distribution of known archaeological sites, a site sample dataset is constructed and divided into a training set and a test set for training and verification of machine learning models.

[0067] (2) Model selection and training: The random forest algorithm was selected and the model was trained by inputting feature vectors to enable it to learn the relationship between geographic elements and image features and the location of archaeological sites.

[0068] (3) Hyperparameter tuning: The number of decision trees and learning rate parameters of the model are adjusted through grid search or random search to optimize model performance and ensure the accuracy and generalization ability of the model in predicting heritage sites.

[0069] (4) Model verification and evaluation: Use the test set to evaluate the trained model, use multiple evaluation indicators such as precision, recall rate, F1-score, etc. to measure the performance of the model, and use cross-validation to reduce the risk of overfitting of the model.

[0070] 5. Site prediction and visualization.

[0071] (1) Prediction of unlabeled areas: Apply the trained model to the target area, predict the location of sites in areas that have not yet been explored by archaeology, and output a probability distribution map of the sites.

[0072] (2) Spatial analysis of prediction results: Spatial analysis of the predicted potential sites is conducted, combined with topography, hydrology, soil and other geographic information to further verify the rationality of the prediction results and provide clues for archaeologists.

[0073] (3) Visualization of prediction results: Use GIS tools to visualize the predicted site locations. By overlaying different geographic element features and image features on the map, you can intuitively understand the possible site locations.

[0074] (4) Archaeological verification and feedback optimization: The prediction results are verified by examining the probability distribution of the latest suspected site locations, determining the accuracy of the model, and further optimizing and iterating the performance of the prediction model.

[0075] The present invention combines the characteristics of geographic elements and remote sensing images, and overcomes the problem of insufficient information from a single data source through multimodal feature fusion. It can capture the environmental characteristics related to archaeological sites more comprehensively and accurately, thereby improving the accuracy of archaeological site prediction.

[0076] The discovery of traditional archaeological sites often relies on a lot of manpower for field exploration, which is time-consuming and laborious. The machine learning model proposed in the present invention can automatically predict large areas, greatly reducing the manpower and time costs in the archaeological exploration process and improving the efficiency of archaeological work.

[0077] The present invention visualizes the prediction results through the GIS system, so that archaeologists can intuitively view the predicted site distribution and related feature information, helping decision makers to better plan archaeological exploration work. Through accurate site prediction, unnecessary excavation and interference with the surrounding environment can be reduced, thereby better protecting the cultural heritage that has not yet been discovered.

[0078] The embodiment of the present invention also provides an archaeological site prediction device that couples multiple factor features. Figure 3 Come and see, Figure 3 The schematic diagram of the structure of an embodiment of an archaeological site prediction device coupled with multiple elements provided by the present invention is as follows. The archaeological site prediction device coupled with multiple elements 300 comprises: An acquisition module 301 is used to acquire geographic element data and remote sensing image data of a target area, wherein the geographic element data includes DEM, land use type and river system data; A determination module 302 is used to determine a target feature vector based on the pre-processed geographic element data and remote sensing image data; The prediction module 303 is used to use the target feature vector as the input of the archaeological site prediction model, and predict the distribution probability of the archaeological sites in the target area based on the output of the archaeological site prediction model. The archaeological site prediction model is trained based on the location of real archaeological relics carrying feature labels.

[0079] The specific implementation methods of each module of the archaeological site prediction device coupling multi-factor features can be found in the description of the above-mentioned archaeological site prediction method coupling multi-factor features, and have similar beneficial effects, so they will not be repeated here.

[0080] The embodiment of the present invention further provides an electronic device, Figure 4 Come and see, Figure 4 This is a structural diagram of an embodiment of an electronic device provided by the present invention. The electronic device 400 includes a processor 401, a memory 402, and a computer program stored in the memory 402 and executable on the processor 401. When the processor 401 executes the program, the archaeological site prediction method coupling multiple factor features as described above is implemented.

[0081] As a preferred embodiment, the electronic device 400 further includes a display 403 for displaying that the processor 401 executes the archaeological site prediction method coupling multiple factor features as described above.

[0082] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the memory 402, and are executed by the processor 401 to complete the present invention. One or more modules / units may be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device 400. For example, the computer program may be divided into the acquisition module 301, the determination module 302, and the prediction module 303 in the above embodiment, and the specific functions of each module are as described above, and are not described one by one here.

[0083] The electronic device 400 may be a desktop computer, a notebook, a PDA or a smart phone with an adjustable camera module.

[0084] Among them, the processor 401 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor 401 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0085] The memory 402 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electric erasable programmable read-only memory (EEPROM), etc. The memory 402 is used to store programs, and the processor 401 executes the program after receiving the execution instruction. The process definition method disclosed in any of the embodiments of the present invention may be applied to the processor 401 or implemented by the processor 401.

[0086] The display 403 may be an LCD display screen or an LED display screen, for example, a display screen on a mobile phone.

[0087] Understandably, Figure 4 The structure shown is only a schematic diagram of the structure of the electronic device 400. The electronic device 400 may also include Figure 4 More or fewer components as shown. Figure 4 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0088] The electronic device provided according to the above-mentioned embodiment of the present invention can be implemented with reference to the specific description of the archaeological site prediction method of coupling multi-factor features as described above according to the present invention, and has similar beneficial effects as the archaeological site prediction method of coupling multi-factor features as described above, which will not be repeated here.

[0089] An embodiment of the present invention also provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the archaeological site prediction method coupling multiple factor features as described above is implemented.

[0090] Generally speaking, the computer instructions for implementing the method of the present invention can be carried by any combination of one or more computer-readable storage media. Non-transitory computer-readable storage media can include any computer-readable media except for the signal itself that is temporarily propagating.

[0091] Computer-readable storage media may be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0092] Computer program codes for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages, in particular, Python suitable for neural network computing and platform frameworks based on TensorFlow, PyTorch, etc. may be used. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0093] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0094] The present invention discloses an archaeological site prediction method and device coupling multi-factor features, which determines a target feature vector, i.e., an input feature of an archaeological site prediction model, through geographic feature data and remote sensing image data of a target area, thereby realizing multi-factor feature extraction of the target area, and then performs distribution probability prediction of archaeological sites in the target area based on the target feature vector and an archaeological site prediction model trained according to the position of real archaeological relics carrying feature labels. In consideration of multi-factor features, the accuracy of archaeological site prediction can be effectively improved. The present invention improves the accuracy and flexibility of archaeological site prediction by coupling multi-factor features to perform archaeological site prediction.

[0095] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for predicting archaeological sites by coupling multiple factor features, characterized in that: include: Acquire geographic element data and remote sensing image data of the target area, wherein the geographic element data includes DEM, land use type and river system data; Determine the target feature vector based on the preprocessed geographic element data and remote sensing image data; The target feature vector is used as the input of an archaeological site prediction model, and the distribution probability of archaeological sites in the target area is predicted based on the output of the archaeological site prediction model, wherein the archaeological site prediction model is trained based on the locations of real archaeological relics carrying feature labels.

2. The method for predicting archaeological sites by coupling multiple factor features according to claim 1, characterized in that: The step of determining the target feature vector based on the pre-processed geographic element data and remote sensing image data includes: Determine the geographic element characteristics, remote sensing image data characteristics and time series characteristics of the target area based on the preprocessed geographic element data and remote sensing image data; Determining the target feature vector based on the geographic element features, remote sensing image data features and time series features of the target area; The geographical element characteristics of the target area include the topographic characteristics and hydrological characteristics of the target area, the remote sensing image data characteristics of the target area include the normalized vegetation index and the normalized water body index, and the time series characteristics of the target area include the vegetation change rate and the surface temperature change rate.

3. The method for predicting archaeological sites by coupling multiple factor features according to claim 2, characterized in that: The topographic features of the target area include the elevation, slope and slope direction of each preset position in the target area, and the hydrological features of the target area include the distance to the water source of each preset position in the target area and the water system density of the target area.

4. The method for predicting archaeological sites by coupling multiple factor features according to claim 1, characterized in that: The preprocessing of the geographic element data and remote sensing image data of the target area includes: Performing outlier elimination and denoising processing on the geographic element data and remote sensing image data of the target area to obtain a first data set; Performing data format conversion on the first data set so that the spatial resolution and spatial coordinate system of all data in the first data set are the same, thereby obtaining a second data set; The remote sensing image data in the second data set is corrected to obtain pre-processed geographic element data and remote sensing image data of the target area.

5. The method for predicting archaeological sites by coupling multiple factor features according to claim 4, characterized in that: The correcting the remote sensing image data in the second data set includes: The remote sensing image data in the second data set is subjected to geometric correction, radiation correction and atmospheric correction.

6. The method for predicting archaeological sites by coupling multiple factor features according to claim 2, characterized in that: The determining of the target feature vector based on the geographic element features, remote sensing image data features and time series features of the target area includes: The target feature vector is obtained by performing feature dimensionality reduction on the geographic element features, remote sensing image data features and time series features of the target area, and performing feature fusion on the geographic element features, remote sensing image data features and time series features of the target area after feature dimensionality reduction.

7. The method for predicting archaeological sites by coupling multiple factor features according to any one of claims 1 to 5, characterized in that: The archaeological site prediction model is obtained by training a random forest model using real archaeological site locations as positive samples, real non-archaeological site locations as negative samples, and geographic element features, remote sensing image data features, and time series features of the positive and negative samples as labels.

8. An archaeological site prediction device coupled with multiple factor features, characterized in that: include: An acquisition module is used to acquire geographic element data and remote sensing image data of a target area, wherein the geographic element data includes DEM, land use type and river system data; A determination module, used for determining a target feature vector based on preprocessed geographic element data and remote sensing image data; A prediction module is used to use the target feature vector as the input of an archaeological site prediction model, and to predict the distribution probability of archaeological sites in the target area based on the output of the archaeological site prediction model, wherein the archaeological site prediction model is trained based on the location of real archaeological relics carrying feature labels.

9. An electronic device, characterized in that: It includes a memory and a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the archaeological site prediction method coupling multi-factor features according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method for predicting archaeological sites by coupling multiple factor features as described in any one of claims 1 to 7 is implemented.

Images