Method and device for zircon age prediction, electronic equipment and storage medium

Abstract

The invention provides a zircon age prediction method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring and sorting a cathode luminescence CL image of the zircon, wherein zircon feature information in the CL image at least comprises growth annulus features of the zircon; performing prediction processing on the zircon CL image by adopting a preset target zircon age prediction model, and obtaining an age prediction result of the zircon; the target zircon age prediction model comprises an annulus extraction module, a multi-scale feature fusion module and an age prediction module, the annulus extraction module is used for extracting growth annulus features in CL image information, and the multi-scale feature fusion module is used for performing multi-scale feature extraction and fusion on the growth annulus features to obtain an age prediction result; and the age prediction module is used for obtaining a final zircon age prediction result based on the multi-scale spatial information.

Description

Technical Field

[0001] The present invention belongs to the technical field of artificial intelligence and geoscience big data, and specifically relates to a method, device, electronic equipment and storage medium for zircon age prediction. Background Art

[0002] Image age prediction is an important task in the field of computer vision. In today's era of continuous progress in sedimentary geology, more and more computer vision methods are being introduced into the field of geology to solve the efficiency and accuracy problems of traditional research methods. In geological research, a large amount of data information, especially the microscopic image data of minerals, provides scientists with rich information for studying the formation, evolution and environmental conditions of minerals. In zircon research, the age, formation environment and evolution characteristics of zircon are important clues for geologists to study sedimentary history and tectonic movements. Rapid and accurate age prediction of zircon is a core research direction that geologists have long focused on.

[0003] Among them, traditional zircon age analysis methods rely on microscopic observation and element ratio analysis, such as U-Pb determination. These methods are not only time-consuming and labor-intensive, but also require complex experimental equipment and professional background support. At the same time, they are easily affected by factors such as sample preservation status and analysis conditions, resulting in inaccurate age analysis. Zircon CL (cathodoluminescence) images are correlated with age prediction. The width, number and texture characteristics of the growth rings formed by zircon in different geological history stages are closely related to the age of zircon; however, the existing related technologies lack methods that can accurately predict the age of zircon through zircon CL images.

[0004] Therefore, the present application contemplates a method for zircon age prediction based on zoning extraction technology. Summary of the invention

[0005] In view of the problems existing in the prior art, the present invention provides a method, device, electronic device and storage medium for zircon age prediction, which can efficiently and accurately predict the zircon age.

[0006] In a first aspect, an embodiment of the present invention provides a method for zircon age prediction, comprising:

[0007] Collecting and collating cathode luminescence (CL) images of zircon, wherein the characteristic information of zircon in the CL images at least includes growth zoning characteristics of zircon;

[0008] The preset target zircon age prediction model is used to predict the zircon CL image and obtain the zircon age prediction result;

[0009] The target zircon age prediction model includes a ring zone extraction module, a multi-scale feature fusion module and an age prediction module. The ring zone extraction module is used to extract the growth ring zone features in the CL image information, the multi-scale feature fusion module is used to perform multi-scale feature extraction and fusion on the growth ring zone features to obtain multi-scale spatial information, and the age prediction module is used to obtain the final zircon age prediction result based on the multi-scale spatial information.

[0010] Furthermore, before the target zircon age prediction model predicts the age of zircon, it also includes training and obtaining the target zircon age model, and the training and obtaining the target zircon age model includes:

[0011] Collecting and collating CL images of zircons to be tested and age labels of zircons to be tested, wherein the characteristic information of zircons in the CL images at least includes growth zoning characteristics of zircons;

[0012] Using the CL images of the zircon to be tested and the age labels to create a training data set, a verification data set and a test data set;

[0013] Construct an initial zircon age prediction model;

[0014] Based on the training data set and the validation data set, the initial zircon age prediction model is optimized using a stochastic gradient descent method to obtain an optimized zircon age prediction model;

[0015] The optimized zircon age prediction model is used to predict the zircon CL images in the test data set to obtain the predicted age results;

[0016] Based on the comparative analysis of the predicted age results and the corresponding real age labels in the test data set, a target zircon age prediction model is obtained.

[0017] Further, obtaining the optimized zircon age prediction model includes:

[0018] Using a stochastic gradient descent optimizer to train the initial zircon age prediction model; and

[0019] A data enhancement strategy is used to optimize the initial zircon age prediction model.

[0020] Further, the CL image is input into a target zircon age prediction model according to a preset size;

[0021] In the zircon zoning extraction module, a CL image of zircon is input, the image is cropped and normalized according to a preset size to obtain a segmented image patch, the image patch is input into the structure of the ViT model, processed layer by layer, the feature relationship is calculated through the self-attention mechanism, the output features of the ViT model are mixed and calculated through convolution and multi-layer perceptron modules to obtain the growth zoning features;

[0022] In the multi-scale feature fusion module, the growth ring features are extracted layer by layer through the transformer block, the correlation between local and global features is calculated through the self-attention mechanism, the feature map is nonlinearly transformed through the feedforward neural network, image patches of different scales are integrated through patch merging, and multi-scale spatial information is integrated by splicing and fusing the output features of different layers;

[0023] In the age prediction module, the time series information of the multi-scale spatial information is captured through a long short-term memory network, and a multi-layer perceptron is used to perform dimensionality reduction and nonlinear mapping to generate an initial age prediction result. The prediction value is optimized using a dual sorting loss, and the relative time order between samples is sorted to output the final zircon age prediction result.

[0024] Furthermore, the growth ring characteristics are obtained, including:

[0025]

[0026] F out =MLP(Conv(F Attention ,W conv ));

[0027] In the formula, Q, K, and V represent the query vector, key vector, and value vector respectively, and d k is the dimension of the key, F Attention is the output feature of the self-attention mechanism, W conv are the convolution weights.

[0028] Furthermore, obtaining the multi-scale spatial information includes:

[0029] F concat =[F trans1 ,F trans2 ,F trans3 ,F trans4 ];

[0030] F unified =MLP(F concat );

[0031] F up =Upsample(F unified );

[0032] In the formula, F concat It is through F trans1 ,F trans2 ,F trans3 ,F trans4 The feature map obtained by feature concatenation, F unified is the multi-scale feature fusion feature, F up It is a high-resolution feature map after upsampling.

[0033] Furthermore, the final zircon age prediction results are obtained, including:

[0034] F time =LSTM(F up );

[0035] Age pred =MLP(F time );

[0036]

[0037] In the formula, F up It is the feature map after multi-scale feature fusion, F time is the time series feature generated by LSTM, Age pred is the age prediction value, and the prediction value is optimized using Pairwise RankingLoss.

[0038] In a second aspect, an embodiment of the present disclosure provides a device for zircon age prediction, the device comprising:

[0039] A collection unit is configured to collect and organize cathode luminescence (CL) images of zircon, wherein the characteristic information of zircon in the CL images at least includes growth zoning characteristics of zircon;

[0040] The zircon age prediction unit is configured to use a preset target zircon age prediction model to perform prediction processing on the zircon CL image and obtain the zircon age prediction result; wherein the target zircon age prediction model includes a ring zone extraction module, a multi-scale feature fusion module and an age prediction module, the ring zone extraction module is used to extract the growth ring zone features in the CL image information, the multi-scale feature fusion module is used to perform multi-scale feature extraction and fusion on the growth ring zone features to obtain multi-scale spatial information, and the age prediction module is used to obtain the final zircon age prediction result based on the multi-scale spatial information.

[0041] In a third aspect, an embodiment of the present disclosure provides an electronic device, the electronic device comprising:

[0042] at least one processor; and,

[0043] a memory communicatively connected to the at least one processor; wherein,

[0044] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the above-mentioned method for zircon age prediction.

[0045] In a fourth aspect, an embodiment of the present disclosure provides a non-transitory computer-readable storage medium, which stores computer instructions for causing the computer to execute the above-mentioned method for zircon age prediction.

[0046] Other optional features and technical effects of the embodiments of the present invention are partially described below, and partially can be understood by reading this document.

[0047] Compared with the prior art, the present invention has the following beneficial technical effects:

[0048] The present invention provides a method for zircon age prediction, comprising: collecting and arranging cathode luminescence CL images of zircon, wherein the zircon feature information in the CL images at least includes the growth zoning features of the zircon; using a preset target zircon age prediction model to predict and process the zircon CL images, and obtain the age prediction results of the zircon; the target zircon age prediction model comprises a zoning extraction module, a multi-scale feature fusion module and an age prediction module, wherein the zoning extraction module is used to extract the growth zoning features in the CL image information, the multi-scale feature fusion module is used to perform multi-scale feature extraction and fusion on the growth zoning features to obtain multi-scale spatial information, and the age prediction module is used to obtain the final zircon age prediction results based on the multi-scale spatial information. The method can automatically identify the zircon age by sending the zircon CL image into the target zircon age prediction model, and has efficient and accurate prediction capabilities. Compared with the prediction results in other prediction models, the present application only needs to perform simple resolution adaptation to predict the age of zircon, and therefore, the present application has a wide range of applications in geological image age prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A schematic flow chart of a method for zircon age prediction according to an embodiment of the present disclosure is shown;

[0050] Figure 2 A schematic diagram of a zircon age prediction model according to an embodiment of the present disclosure is shown;

[0051] Figure 3 The partial results of zircon age prediction according to the present disclosure are shown;

[0052] Figure 4A diagram of a device for zircon age prediction according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0053] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0054] The following describes the embodiments of the present disclosure through specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0055] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0056] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present disclosure. The drawings only show components related to the present disclosure rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0057] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects described may be practiced without these specific details.

[0058] In the first aspect, Figure 1 A method 100 for zircon age prediction provided by an embodiment of the present invention is shown, comprising the following steps:

[0059] In step S101, cathode luminescence (CL) images of zircon are collected and sorted, wherein characteristic information of zircon in the CL images at least includes growth zoning characteristics of zircon.

[0060] Specifically, the growth zoning of zircon is formed when it crystallizes in magma, usually appearing as a series of light and dark bands. The existence and characteristics of these zoning can reflect important information such as the composition changes of magma, the crystallization process, and the multi-stage nature of magma activity.

[0061] Next, go to step S102.

[0062] At step S102, a preset target zircon age prediction model is used to perform prediction processing on the zircon CL image, and an age prediction result of the zircon is obtained; wherein the target zircon age prediction model includes a ring zone extraction module, a multi-scale feature fusion module and an age prediction module, the ring zone extraction module is used to extract the growth ring zone features in the CL image information, the multi-scale feature fusion module is used to perform multi-scale feature extraction and fusion on the growth ring zone features to obtain multi-scale spatial information, and the age prediction module is used to obtain the final zircon age prediction result based on the multi-scale spatial information.

[0063] In some embodiments, before the target zircon age prediction model performs age prediction on zircon, the method further includes training and obtaining the target zircon age model, wherein the training and obtaining the target zircon age model includes:

[0064] Collecting and collating CL images of zircons to be tested and age labels of zircons to be tested, wherein the characteristic information of zircons in the CL images at least includes growth zoning characteristics of zircons;

[0065] Using the CL images of the zircon to be tested and the age labels to create a training data set, a verification data set and a test data set;

[0066] Construct an initial zircon age prediction model;

[0067] Based on the training data set and the validation data set, the initial zircon age prediction model is optimized using a stochastic gradient descent method to obtain an optimized zircon age prediction model;

[0068] The optimized zircon age prediction model is used to predict the zircon CL images in the test data set to obtain the predicted age results;

[0069] Based on the comparative analysis of the predicted age results and the corresponding real age labels in the test data set, a target zircon age prediction model is obtained.

[0070] It should be noted that in the disclosed embodiment, the age label and the annual zero error are used in the training optimization and evaluation index stage of the model. The age label is the real zircon age, which is used as the target value in supervised learning. When using PairwiseRanking Loss to optimize the predicted value of the model, the age label is used to evaluate whether the ranking relationship of the model is reasonable. The age error is used to evaluate the accuracy of the model.

[0071] Specifically, Table 1 shows the zircon CL image dataset of an embodiment of the present disclosure, including a training dataset (TrainDataset), a validation dataset (Valid Dataset), a test dataset (Test Dataset) and the total number of images (Image), wherein the training dataset is 1324 groups, the validation dataset is 166 groups, the test dataset is 166 groups, and the total number of images is 1656 groups.

[0072] Table 1. Zircon CL image dataset

[0073]

[0074] Further, in some embodiments, obtaining the optimized zircon age prediction model includes:

[0075] Using a stochastic gradient descent optimizer to train the initial zircon age prediction model; and

[0076] A data enhancement strategy is used to optimize the initial zircon age prediction model.

[0077] Specifically, by performing data augmentation (Augment) after inputting the image (Image). In some embodiments, the data augmentation strategy includes random cropping, resizing, horizontal flipping, random rotation, color adjustment, and automatic augmentation strategy (AutoAugment).

[0078] The stochastic gradient descent optimizer (SGD) is an iterative method for optimizing model parameters, which speeds up training and helps to escape local optimal solutions by using only a small portion of training samples to update parameters in each iteration. During training, enhanced training samples are generated by applying data enhancement strategies in real time, and these samples are fed to the SGD optimizer for parameter updates. This helps the model learn more robust feature representations on a wider data distribution.

[0079] In some embodiments, the CL image is input into a target zircon age prediction model according to a preset size.

[0080] In the zircon ring zone extraction module, the CL image of the zircon is input, the image is cropped and normalized according to a preset size to obtain segmented image patches, the image patches are input into the structure of the ViT model, processed layer by layer, the feature relationship is calculated through the self-attention mechanism, and the output features of the ViT model are mixed and calculated through convolution and multi-layer perceptron modules to obtain the growth ring features.

[0081] In the multi-scale feature fusion module, the growth ring features are extracted layer by layer through the transformer block, the correlation between local and global features is calculated through the self-attention mechanism, the feature map is nonlinearly transformed through the feedforward neural network, image patches of different scales are integrated through patch merging, and multi-scale spatial information is obtained by splicing and fusing the output features of different layers.

[0082] In the age prediction module, the time series information of the multi-scale spatial information is captured through a long short-term memory network, and a multi-layer perceptron is used to perform dimensionality reduction and nonlinear mapping to generate an initial age prediction result. The prediction value is optimized using a dual sorting loss, and the relative time order between samples is sorted to output the final zircon age prediction result.

[0083] Specifically, the growth ring characteristics are obtained, including:

[0084]

[0085] F out =MLP(Conv(F Attention ,W conv ));

[0086] In the formula, Q, K, and V represent the query vector, key vector, and value vector respectively, and d k is the dimension of the key, F Attention is the output feature of the self-attention mechanism, W conv are the convolution weights.

[0087] Specifically, obtaining the multi-scale spatial information includes:

[0088] F concat =[F trans1 ,F trans2 ,F trans3 ,F trans4 ];

[0089] F unified =MLP(F concat );

[0090] F up =Upsample(F unified );

[0091] In the formula, F concat It is through F trans1 ,F trans2 ,F trans3 ,F trans4 The feature map obtained by feature concatenation, F unified is the multi-scale feature fusion feature, F up It is a high-resolution feature map after upsampling.

[0092] Specifically, the final zircon age prediction results include:

[0093] F time =LSTM(F up );

[0094] Age pred =MLP(F time );

[0095]

[0096] In the formula, F up It is the feature map after multi-scale feature fusion, F time is the time series feature generated by LSTM, Age pred is the age prediction value, and the prediction value is optimized using Pairwise RankingLoss.

[0097] Furthermore, Figure 2 A schematic diagram of a target zircon age prediction model in an embodiment of the present disclosure is shown. Figure 2 As shown, in an embodiment of the present disclosure, the zircon CL image (Image) is input into the target zircon age prediction model according to a preset size, that is, according to an input image of a given H×W size.

[0098] In the zircon zone extraction module (Zones Extract Model), the CL image of zircon is input, the image is cropped and normalized according to the given size of 224×224, and the segmented patch is input into the Vision Transformer (ViT) structure, which is a deep learning model that applies the Transformer architecture to visual recognition tasks; the feature relationship is calculated through the self-attention mechanism, and the output features are mixed through 3×3 convolution and MLP multi-layer perceptron module (MLP) to extract the growth zone features.

[0099] In the multi-scale feature fusion module, the segmented patches are first converted into vector form by overlapping patch embeddings, and then features are extracted layer by layer by TransformerBlock transformer blocks. Specifically, there are multiple Transformer Block transformer blocks, and the Transformer Block transformer blocks include Transformer Block1 transformer block, TransformerBlock2 transformer block, Transformer Block3 transformer block and Transformer Block4 transformer block. The Transformer Block transformer blocks all include efficient self-attention mechanism ESA (Efficient Self-Attention), feed-forward neural network FFN (Feed-Forward Network) and patch merging. The efficient self-attention mechanism ESA (Efficient Self-Attention) calculates the correlation between local and global features, and the feed-forward neural network FFN (Feed-Forward The Patch Merging process integrates patches of different scales, and finally, the output features of different layers are concatenated and fused to integrate multi-scale spatial information.

[0100] In the age prediction module (Age Prediction Module), the time series information of the multi-scale characteristics of the zircon ring is captured by the long short-term memory network LSTM (Long Short-Term Memory), and the multi-layer perceptron MLP (Multi-Layer Perceptron) is used for dimensionality reduction and nonlinear mapping to generate age prediction results. The pairwise ranking loss is used to optimize the prediction value to meet the relative time order between samples, and the final age prediction value of the zircon is output.

[0101] For example, Table 2 shows the results of predicting zircon age based on zircon CL images using the target zircon age prediction model provided by this embodiment, and compares it with other models to analyze the improvement of accuracy ACC@0, ACC@1, ACC@5, and ACC@10. Among them, other models include model Resnet50, coral, and model MiVOLO.

[0102] Table 2. Comparison of zircon age prediction results

[0103]

[0104] It should be noted that Predict age (%), that is, age error, is an indicator of the accuracy of age prediction, which is usually used to evaluate the performance of age prediction models. It indicates the percentage of the model-predicted age that is consistent with the actual age. ResNet50 is a deep convolutional neural network model. MiVOLO is a multi-input transformer for age and gender estimation. The Coral framework (CorrelationAlignment) is an unsupervised transfer learning algorithm. The ACC@0 is the proportion of model predictions that are completely correct, and ACC@1 indicates the proportion of the category with the highest model prediction probability that is consistent with the actual category. ACC@5 indicates the proportion of true labels within the 5 categories with the highest model prediction probability. ACC@10 indicates the proportion of true labels within the 10 categories with the highest model prediction probability.

[0105] For example, Figure 3 A diagram of the zircon age prediction result of the embodiment of the present disclosure is shown, which shows a zircon image (image), a zircon CL image (zircon extract image), an age label (age label), an age error (sigma) and an age prediction result (predict age). It can be seen from the diagram that the target zircon age prediction model provided in this embodiment can more accurately predict the age of the zircon.

[0106] The second embodiment of the present invention further provides a device for zircon age prediction, the device comprising:

[0107] A collection unit is configured to collect and organize cathode luminescence (CL) images of zircon, wherein the characteristic information of zircon in the CL images at least includes growth zoning characteristics of zircon;

[0108] The zircon age prediction unit is configured to use a preset target zircon age prediction model to perform prediction processing on the zircon CL image and obtain the zircon age prediction result; wherein the target zircon age prediction model includes a ring zone extraction module, a multi-scale feature fusion module and an age prediction module, the ring zone extraction module is used to extract the growth ring zone features in the CL image information, the multi-scale feature fusion module is used to perform multi-scale feature extraction and fusion on the growth ring zone features to obtain multi-scale spatial information, and the age prediction module is used to obtain the final zircon age prediction result based on the multi-scale spatial information.

[0109] A third embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0110] at least one processor; and,

[0111] a memory communicatively connected to the at least one processor; wherein,

[0112] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method for zircon age prediction of any of the aforementioned embodiments.

[0113] The fourth embodiment of the present invention further provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method for zircon age prediction described in any of the aforementioned embodiments.

[0114] The fifth embodiment of the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the method for zircon age prediction of any of the aforementioned embodiments.

[0115] Figure 4 A schematic diagram of a method or device 1000 that can implement an embodiment of the present invention is shown, which may include more or fewer devices than shown in the figure in some embodiments. In some embodiments, it can be implemented using a single or multiple devices. In some embodiments, it can be implemented using cloud or distributed devices.

[0116] like Figure 4 As shown, the device 1000 includes a processor 1001, which can perform various appropriate operations and processes according to the program and / or data stored in the read-only memory (ROM) 1002 or the program and / or data loaded from the storage part 1008 to the random access memory (RAM) 1003. Processor 1001 can be a multi-core processor or can include multiple processors. In some embodiments, processor 1001 can include a general main processor and one or more special coprocessors, such as a central processing unit (CPU), a graphics processing unit (GPU), a neural network processor (NPU), a digital signal processor (DSP), etc. In RAM 1003, various programs and data required for the operation of device 1000 are also stored. Processor 1001, ROM 1002 and RAM 1003 are connected to each other via bus 1004. Input / output (I / O) interface 1005 is also connected to bus 1004.

[0117] The processor and the memory are used together to execute the program stored in the memory. When the program is executed by the computer, the methods, steps or functions described in the above embodiments can be implemented.

[0118] The following components are connected to the I / O interface 1005: an input section 1006 including a keyboard, a mouse, a touch screen, etc.; an output section 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, a modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed, so that a computer program read therefrom is installed into the storage section 1008 as needed. Figure 4 Only some components are schematically shown in the figure, which does not mean that the device 1000 only includes Figure 4 Components shown.

[0119] The systems, devices, modules or units described in the above embodiments may be implemented by a computer or its associated components. The computer may be, for example, a mobile terminal, a smart phone, a personal computer, a laptop computer, a vehicle-mounted human-computer interaction device, a personal digital assistant, a media player, a navigation device, a game console, a tablet computer, a wearable device, a smart TV, an Internet of Things system, a smart home, an industrial computer, a server or a combination thereof.

[0120] Although not shown, in an embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program / instruction is stored, and when the computer program / instruction is executed by a processor, the method for zircon age prediction described in the embodiment is implemented.

[0121] Storage media in embodiments of the present invention include permanent and non-permanent, removable and non-removable items that can be used to store information by any method or technology. Examples of storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0122] Although not shown, an embodiment of the present invention further provides a computer program product, including: a computer program / instruction, which, when executed by a processor, implements the method for zircon age prediction described in the embodiment.

[0123] The methods, programs, systems, devices, etc. of the embodiments of the present invention may be executed or implemented in a single or multiple networked computers, or may be practiced in a distributed computing environment. In the embodiments of this specification, in these distributed computing environments, tasks may be performed by remote processing devices connected via a communication network.

[0124] Those skilled in the art should understand that the embodiments of the present specification may be provided as methods, systems or computer program products. Therefore, those skilled in the art may imagine that the functional modules / units or controllers and related method steps described in the above embodiments may be implemented in software, hardware or a combination of software / hardware.

[0125] Unless explicitly stated, the actions or steps of the methods, programs, and embodiments of the present invention do not have to be performed in a specific order and can still achieve the desired results. In some implementations, multitasking and parallel processing are also possible or may be advantageous.

[0126] In this article, multiple embodiments of the present invention are described, but for the sake of brevity, the description of each embodiment is not exhaustive, and the same or similar features or parts between the embodiments may be omitted. In this article, "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" are meant to be applicable to at least one embodiment or example according to the present invention, but not all embodiments. The above terms do not necessarily mean to refer to the same embodiment or example. In the absence of contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples.

[0127] The exemplary systems and methods of the present invention have been specifically shown and described with reference to the above embodiments, which are merely examples of the best modes for implementing the present systems and methods. It will be appreciated by those skilled in the art that various changes may be made to the embodiments of the systems and methods described herein when implementing the present systems and / or methods without departing from the spirit and scope of the present invention as defined in the appended claims.

[0128] In addition, the method, system, device, and medium for zircon age prediction according to the present invention can also be implemented in the following manner:

[0129] (1) A method for zircon age prediction, comprising:

[0130] Collecting and collating cathode luminescence (CL) images of zircon, wherein the characteristic information of zircon in the CL images at least includes growth zoning characteristics of zircon;

[0131] The preset target zircon age prediction model is used to predict the zircon CL image and obtain the zircon age prediction result;

[0132] The target zircon age prediction model includes a ring zone extraction module, a multi-scale feature fusion module and an age prediction module. The ring zone extraction module is used to extract the growth ring zone features in the CL image information, the multi-scale feature fusion module is used to perform multi-scale feature extraction and fusion on the growth ring zone features to obtain multi-scale spatial information, and the age prediction module is used to obtain the final zircon age prediction result based on the multi-scale spatial information.

[0133] (2) The method according to (1) is characterized in that before the target zircon age prediction model predicts the age of zircon, it also includes training and obtaining the target zircon age model, and the training and obtaining the target zircon age model includes:

[0134] Collecting and collating CL images of zircons to be tested, as well as age labels and error labels of zircons to be tested, wherein the zircon characteristic information in the CL images at least includes growth zoning characteristics of the zircons;

[0135] The CL image of the zircon to be tested, the age label and the error label are used to create a training data set, a verification data set and a test data set;

[0136] Construct an initial zircon age prediction model;

[0137] Based on the training data set and the validation data set, the initial zircon age prediction model is optimized using a stochastic gradient descent method to obtain an optimized zircon age prediction model;

[0138] The optimized zircon age prediction model is used to predict the zircon CL images in the test data set to obtain the predicted age results;

[0139] Based on the comparison and analysis between the predicted age results and the corresponding true age labels and error labels in the test data set, a target zircon age prediction model is obtained.

[0140] (3) The method according to (1) is characterized in that obtaining the optimized zircon age prediction model comprises:

[0141] Using a stochastic gradient descent optimizer to train the initial zircon age prediction model; and

[0142] A data enhancement strategy is used to optimize the initial zircon age prediction model.

[0143] (4) The method according to (1), characterized in that the CL image is input into the target zircon age prediction model according to a preset size;

[0144] In the zircon zoning extraction module, a CL image of zircon is input, the image is cropped and normalized according to a preset size to obtain a segmented image patch, the image patch is input into the structure of the ViT model, processed layer by layer, the feature relationship is calculated through the self-attention mechanism, the output features of the ViT model are mixed and calculated through convolution and multi-layer perceptron modules to obtain the growth zoning features;

[0145] In the multi-scale feature fusion module, the growth ring features are extracted layer by layer through the transformer block, the correlation between local and global features is calculated through the self-attention mechanism, the feature map is nonlinearly transformed through the feedforward neural network, image patches of different scales are integrated through patch merging, and multi-scale spatial information is integrated by splicing and fusing the output features of different layers;

[0146] In the age prediction module, the time series information of the multi-scale spatial information is captured through a long short-term memory network, and a multi-layer perceptron is used to perform dimensionality reduction and nonlinear mapping to generate an initial age prediction result. The prediction value is optimized using a dual sorting loss, and the relative time order between samples is sorted to output the final zircon age prediction result.

[0147] (5) The method according to (4), characterized in that obtaining the growth ring characteristics comprises:

[0148]

[0149] F out =MLP(Conv(F Attention ,W conv ));

[0150] In the formula, Q, K, and V represent the query vector, key vector, and value vector respectively, and d k is the dimension of the key, F Attention is the output feature of the self-attention mechanism, W conv are the convolution weights.

[0151] (6) The method according to (4), characterized in that obtaining the multi-scale spatial information includes:

[0152] F concat =[F trans1 ,F trans2 ,F trans3 ,F trans4 ];

[0153] F unified =MLP(F concat );

[0154] F up =Upsample(F unified );

[0155] In the formula, F concat It is through F trans1 ,F trans2 ,F trans3 ,F trans4 The feature map obtained by feature concatenation, F unified is the multi-scale feature fusion feature, F up It is a high-resolution feature map after upsampling.

[0156] (7) The method according to (4), characterized in that obtaining the final zircon age prediction result comprises:

[0157] F time =LSTM(F up );

[0158] Age pred =MLP(F time );

[0159]

[0160] In the formula, F up It is the feature map after multi-scale feature fusion, F time is the time series feature generated by LSTM, Age pred is the age prediction value, and the prediction value is optimized using Pairwise RankingLoss.

[0161] (8) A device for zircon age prediction, characterized in that the method for zircon age prediction according to any one of (1) to (14) comprises:

[0162] A collection unit is configured to collect and organize cathode luminescence (CL) images of zircon, wherein the characteristic information of zircon in the CL images at least includes growth zoning characteristics of zircon;

[0163] The zircon age prediction unit is configured to use a preset target zircon age prediction model to perform prediction processing on the zircon CL image and obtain the zircon age prediction result; wherein the target zircon age prediction model includes a ring zone extraction module, a multi-scale feature fusion module and an age prediction module, the ring zone extraction module is used to extract the growth ring zone features in the CL image information, the multi-scale feature fusion module is used to perform multi-scale feature extraction and fusion on the growth ring zone features to obtain multi-scale spatial information, and the age prediction module is used to obtain the final zircon age prediction result based on the multi-scale spatial information.

[0164] (9) The device according to (8), characterized in that the zircon age prediction unit is configured to, before the target zircon age prediction model predicts the age of zircon, further include training and obtaining the target zircon age model, wherein the training and obtaining the target zircon age model includes:

[0165] Collecting and collating CL images of zircons to be tested, as well as age labels and error labels of zircons to be tested, wherein the zircon characteristic information in the CL images at least includes growth zoning characteristics of the zircons;

[0166] The CL image of the zircon to be tested, the age label and the error label are used to create a training data set, a verification data set and a test data set;

[0167] Construct an initial zircon age prediction model;

[0168] Based on the training data set and the validation data set, the initial zircon age prediction model is optimized using a stochastic gradient descent method to obtain an optimized zircon age prediction model;

[0169] The optimized zircon age prediction model is used to predict the zircon CL images in the test data set to obtain the predicted age results;

[0170] Based on the comparison and analysis between the predicted age results and the corresponding true age labels and error labels in the test data set, a target zircon age prediction model is obtained.

[0171] (10) The device according to (8), characterized in that the zircon age prediction unit is configured to obtain the optimized zircon age prediction model, including:

[0172] Using a stochastic gradient descent optimizer to train the initial zircon age prediction model; and

[0173] A data enhancement strategy is used to optimize the initial zircon age prediction model.

[0174] (11) The device according to (8), characterized in that the zircon age prediction unit is configured to input the CL image into a target zircon age prediction model according to a preset size;

[0175] In the zircon zoning extraction module, a CL image of zircon is input, the image is cropped and normalized according to a preset size to obtain a segmented image patch, the image patch is input into the structure of the ViT model, processed layer by layer, the feature relationship is calculated through the self-attention mechanism, the output features of the ViT model are mixed and calculated through convolution and multi-layer perceptron modules to obtain the growth zoning features;

[0176] In the multi-scale feature fusion module, the growth ring features are extracted layer by layer through the transformer block, the correlation between local and global features is calculated through the self-attention mechanism, the feature map is nonlinearly transformed through the feedforward neural network, image patches of different scales are integrated through patch merging, and multi-scale spatial information is integrated by splicing and fusing the output features of different layers;

[0177] In the age prediction module, the time series information of the multi-scale spatial information is captured through a long short-term memory network, and a multi-layer perceptron is used to perform dimensionality reduction and nonlinear mapping to generate an initial age prediction result. The prediction value is optimized using a dual sorting loss, and the relative time order between samples is sorted to output the final zircon age prediction result.

[0178] (12) The device according to (8), characterized in that the zircon age prediction unit is configured to obtain the growth ring characteristics, including:

[0179]

[0180] F out =MLP(Conv(F Attention ,W conv ));

[0181] In the formula, Q, K, and V represent the query vector, key vector, and value vector respectively, and d k is the dimension of the key, F Attention is the output feature of the self-attention mechanism, W conv are the convolution weights.

[0182] (13) The device according to (8), characterized in that the zircon age prediction unit is configured to obtain the multi-scale spatial information, including:

[0183] F concat =[F trans1 ,F trans2 ,F trans3,F trans4 ];

[0184] F unified =MLP(F concat );

[0185] F up =Upsample(F unified );

[0186] In the formula, F concat It is through F trans1 ,F trans2 ,F trans3 ,F trans4 The feature map obtained by feature concatenation, F unified is the multi-scale feature fusion feature, F up It is a high-resolution feature map after upsampling.

[0187] (14) The device according to (8), characterized in that the zircon age prediction unit is configured to obtain a final zircon age prediction result, including:

[0188] F time =LSTM(F up );

[0189] Age pred =MLP(F time );

[0190]

[0191] In the formula, F up It is the feature map after multi-scale feature fusion, F time is the time series feature generated by LSTM, Age pred is the age prediction value, and the prediction value is optimized using Pairwise RankingLoss.

[0192] (15) An electronic device, characterized in that the electronic device comprises:

[0193] at least one processor; and,

[0194] a memory communicatively connected to the at least one processor; wherein,

[0195] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for zircon age prediction described in any one of (1) to (14).

[0196] (16) A non-transitory computer-readable storage medium, characterized in that the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method for zircon age prediction described in any one of (1) to (14).

[0197] (17) A computer program product, comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, which, when executed by a computer, cause the computer to execute the method for zircon age prediction described in any one of (1) to (14).

Claims

1. A method for zircon age prediction, characterized in that: include: Collecting and collating cathode luminescence (CL) images of zircon, wherein the characteristic information of zircon in the CL images at least includes growth zoning characteristics of zircon; The preset target zircon age prediction model is used to predict the CL image of zircon to obtain the age prediction result of zircon; The target zircon age prediction model includes a ring zone extraction module, a multi-scale feature fusion module and an age prediction module. The ring zone extraction module is used to extract the growth ring zone features in the CL image information, the multi-scale feature fusion module is used to perform multi-scale feature extraction and fusion on the growth ring zone features to obtain multi-scale spatial information, and the age prediction module is used to obtain the age prediction result of the zircon based on the multi-scale spatial information.

2. The method according to claim 1, characterized in that Before using the target zircon age prediction model to predict the age of zircon, the method further includes training and obtaining the target zircon age model, wherein the training and obtaining the target zircon age model includes: Collecting and collating CL images of zircons to be tested and age labels of zircons to be tested, wherein the characteristic information of zircons in the CL images at least includes growth zoning characteristics of zircons; Using the CL images of the zircon to be tested and the age labels to create a training data set, a verification data set and a test data set; Construct an initial zircon age prediction model; Based on the training data set and the validation data set, the initial zircon age prediction model is optimized using a stochastic gradient descent method to obtain an optimized zircon age prediction model; The optimized zircon age prediction model is used to predict the zircon CL images in the test data set to obtain the predicted age results; Based on the comparative analysis of the predicted age results and the corresponding real age labels in the test data set, a target zircon age prediction model is obtained.

3. The method according to claim 2, characterized in that Obtaining the optimized zircon age prediction model includes: Using a stochastic gradient descent optimizer to train the initial zircon age prediction model; and A data enhancement strategy is used to optimize the initial zircon age prediction model.

4. The method according to claim 1, characterized in that: Inputting the CL image into a target zircon age prediction model according to a preset size; In the zircon zoning extraction module, a CL image of zircon is input, the image is cropped and normalized according to a preset size to obtain a segmented image patch, the image patch is input into the structure of the ViT model, processed layer by layer, the feature relationship is calculated through the self-attention mechanism, the output features of the ViT model are mixed and calculated through convolution and multi-layer perceptron modules to obtain the growth zoning features; In the multi-scale feature fusion module, the growth ring features are extracted layer by layer through the transformer block, the correlation between local and global features is calculated through the self-attention mechanism, the feature map is nonlinearly transformed through the feedforward neural network, image patches of different scales are integrated through patch merging, and multi-scale spatial information is integrated by splicing and fusing the output features of different layers; In the age prediction module, the time series information of the multi-scale spatial information is captured through a long short-term memory network, and a multi-layer perceptron is used to perform dimensionality reduction and nonlinear mapping to generate an initial age prediction result. The prediction value is optimized using a dual sorting loss, and the relative time order between samples is sorted to output the final zircon age prediction result.

5. The method according to claim 4, characterized in that Obtaining the growth ring characteristics includes: F out =MLP(Conv(F Attention ,W conv )); In the formula, Q, K, and V represent the query vector, key vector, and value vector respectively, and d k is the dimension of the key, F Attention is the output feature of the self-attention mechanism, W conv are the convolution weights.

6. The method according to claim 4, characterized in that The multi-scale spatial information is obtained, including: F concat =[F trans1 ,F trans2 ,F trans3 ,F trans4 ]; F unified =MLP(F concat ); F up =Upsample(F unified ); In the formula, F concat It is through F trans1 ,F trans2 ,F trans3 ,F trans4 The feature map obtained by feature concatenation, F unified is the multi-scale feature fusion feature, F up It is a high-resolution feature map after upsampling.

7. The method according to claim 4, characterized in that The final zircon age prediction results are obtained, including: F time =LSTM(F up ); Age pred =MLP(F time ); In the formula, F up It is the feature map after multi-scale feature fusion, F time is the time series feature generated by LSTM, Age pred is the age prediction value, and the prediction value is optimized using Pairwise RankingLoss.

8. A device for predicting zircon age, characterized in that: Based on the method for zircon age prediction according to any one of claims 1 to 7, the device comprises: A collection unit is configured to collect and organize cathode luminescence (CL) images of zircon, wherein the characteristic information of zircon in the CL images at least includes growth zoning characteristics of zircon; The zircon age prediction unit is configured to use a preset target zircon age prediction model to perform prediction processing on the zircon CL image and obtain the zircon age prediction result; wherein the target zircon age prediction model includes a ring zone extraction module, a multi-scale feature fusion module and an age prediction module, the ring zone extraction module is used to extract the growth ring zone features in the CL image information, the multi-scale feature fusion module is used to perform multi-scale feature extraction and fusion on the growth ring zone features to obtain multi-scale spatial information, and the age prediction module is used to obtain the final zircon age prediction result based on the multi-scale spatial information.

9. An electronic device, characterized in that: The electronic device includes: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for zircon age prediction as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, which are used to cause the computer to execute the method for zircon age prediction as described in any one of claims 1 to 7.

Images