Atmospheric single particle source identification method and device based on morphology, particle size and composition

By combining scanning electron microscopy and machine learning models, the source of single particles in the atmospheric environment is identified, which solves the problem of the lack of identification methods for morphology, particle size and composition information in existing technologies, and realizes accurate identification and quantitative analysis of atmospheric particulate matter sources.

CN119290940BActive Publication Date: 2025-11-18BEIJING INTERSON TECH CO LTD +1
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411327259.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-23
Publication Date
2025-11-18
Estimated Expiration
2044-09-23

AI Technical Summary

Technical Problem

Existing technologies lack methods for identifying the sources of single particles in the atmospheric environment based on information on single particle morphology, size, and composition, making it difficult to accurately identify particulate matter from different pollution sources.

Method used

The morphology, particle size and composition of particulate matter were analyzed using computer-controlled scanning electron microscopy. A source analysis model based on residual network and extreme gradient boosting model was constructed. Through iterative training and validation, the sources of particulate matter were identified.

Benefits of technology

It enables accurate identification and quantitative analysis of atmospheric particulate matter sources, supports research on the physicochemical properties of atmospheric particulate matter and source apportionment, and improves the ability to identify pollution source contributions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119290940B_ABST
    Figure CN119290940B_ABST
Patent Text Reader

Abstract

The application discloses a method and device for identifying the source of atmospheric single particles based on topography, particle size and composition, and the method comprises the following steps: acquiring the image, composition data and particle size parameters of single particles by analyzing the sample of a set pollution source through a computer-controlled scanning electron microscope, constructing a single particle data set, and randomly dividing the single particle data set into a first data set and a second data set; constructing a source analysis model according to a residual network model and an extreme gradient boosting model; training the source analysis model through the first data set and the second data set; and obtaining the probability value of a target single particle belonging to the set pollution source through the trained source analysis model, and determining the source of the target single particle. The application can fully excavate the topography, particle size and composition characteristics of particulate matters, identify the source of the particulate matters, and be helpful to further study the physical and chemical properties of atmospheric particulate matters and the source analysis of the atmospheric particulate matters.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of atmospheric particulate matter source analysis technology, specifically to a method and apparatus for identifying the source of a single atmospheric particle based on morphology, particle size, and composition. Background Technology

[0002] Particulate matter pollution has a significant impact on climate, ecosystems, and human health, and has received widespread attention from all sectors of society in recent years. Source apportionment of particulate matter is an important tool for formulating particulate matter pollution reduction policies.

[0003] Atmospheric particulate matter has complex sources, including both natural and anthropogenic sources. Accurately identifying the sources of atmospheric particulate matter can provide important technical support for formulating emission reduction strategies for atmospheric particulate matter pollution and protecting human health. Scanning electron microscopy-energy dispersive spectroscopy (SEM-EDS) can obtain information on the morphology, particle size, and composition of atmospheric particulate matter and has been widely used in research on the physicochemical properties of atmospheric particles.

[0004] Currently, direct observation studies of particulate matter emitted from pollution sources have revealed certain differences in morphology, particle size, and composition among particulate matter emitted from different pollution sources. However, there is currently no method that can identify the source of a single particulate matter in the atmospheric environment based on information about the morphology, particle size, and composition of individual particles.

[0005] Therefore, how to invent a source apportionment method that can identify the source of single particles in the atmosphere based on their morphology, size, and composition information has become an urgent problem to be solved. Summary of the Invention

[0006] Therefore, this invention provides a method and apparatus for identifying the source of atmospheric single particles based on morphology, particle size, and composition. This method can fully utilize the morphological, particle size, and compositional characteristics of particulate matter to identify its source. Simultaneously, it facilitates further research on the physicochemical properties of atmospheric particulate matter and source apportionment studies.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a method for identifying the source of atmospheric single particles based on morphology, particle size, and composition, comprising:

[0008] By using a computer-controlled scanning electron microscope to analyze the collected samples of a designated pollution source, images, composition data and particle size parameters of individual particles in the sample of the designated pollution source are obtained, and a single particle dataset of the pollution source sample is constructed.

[0009] The single-particle dataset is randomly divided into a first dataset and a second dataset according to a set ratio; the first dataset is used for training the source analysis model; the second dataset is used for validating the source analysis model.

[0010] Based on the residual network model and the extreme gradient boosting model, a source analysis model is constructed;

[0011] The source analysis model is iteratively trained using the first dataset; the prediction results of the source analysis model are verified using the second dataset to obtain the trained source analysis model.

[0012] The composition data and particle size parameters of the target single particle are input into the trained source analysis model for processing to obtain the probability value of the target single particle belonging to the set pollution source, thereby determining the source of the target single particle.

[0013] As a preferred method for identifying atmospheric single-particle sources based on morphology, particle size, and composition, the selected pollution sources include: soil dust, road dust, construction dust, coal dust, biomass combustion dust, and iron and steel smelting dust, when the samples collected are analyzed by using a computer-controlled scanning electron microscope.

[0014] As a preferred embodiment of the atmospheric single-particle source identification method based on morphology, particle size, and composition, the image of the single particle includes: a high-resolution micrograph of the single particle;

[0015] The composition data of the single particles include: carbon, oxygen, sodium, magnesium, aluminum, silicon, phosphorus, sulfur, chlorine, potassium, calcium, zinc, barium, vanadium, chromium, cobalt, selenium, tin, titanium, manganese, nickel, copper and lead;

[0016] The particle size parameters of the single particle include: maximum diameter, minimum diameter, average diameter, vertical diameter, and equivalent circle diameter.

[0017] As a preferred embodiment of the atmospheric single-particle source identification method based on morphology, particle size, and composition, in the process of inputting the image, composition data, and particle size parameters of the target single particle into the trained source analysis model for processing to obtain the probability value of the target single particle belonging to the set pollution source, the image features of the target single particle are extracted through the residual network model, and the source of the target single particle is initially predicted based on the image features of the target single particle to obtain the preliminary probability value of the target single particle belonging to the set pollution source.

[0018] As a preferred embodiment of the atmospheric single-particle source identification method based on morphology, particle size, and composition, in the process of inputting the image, composition data, and particle size parameters of the target single particle into the trained source analysis model for processing to obtain the probability value of the target single particle belonging to the set pollution source, the preliminary probability value of the target single particle belonging to the set pollution source is merged with the particle size parameters and composition data of the target single particle, and input into the extreme gradient enhancement model. The probability value of the target single particle belonging to the set pollution source is obtained through prediction by the extreme gradient enhancement model.

[0019] This invention also provides an atmospheric single-particle source identification device based on morphology, particle size, and composition, employing the above-described atmospheric single-particle source identification method based on morphology, particle size, and composition, including:

[0020] The single-particle dataset acquisition module is used to analyze the collected samples of a designated pollution source using a computer-controlled scanning electron microscope, and to acquire images, composition data and particle size parameters of single particles in the samples of the designated pollution source, thereby constructing a single-particle dataset of the pollution source samples.

[0021] The single-particle dataset partitioning module is used to randomly divide the single-particle dataset into a first dataset and a second dataset according to a set ratio; the first dataset is used for training the source analysis model; and the second dataset is used for validating the source analysis model.

[0022] The source analysis model building module is used to build a source analysis model based on the residual network model and the extreme gradient boosting model.

[0023] The source analysis model training module is used to iteratively train the source analysis model using the first dataset; and to verify the prediction results of the source analysis model using the second dataset to obtain the trained source analysis model.

[0024] The single-particle source determination module is used to input the image, composition data and particle size parameters of the target single particle into the trained source analysis model for processing, to obtain the probability value of the target single particle belonging to the set pollution source, and to determine the source of the target single particle.

[0025] As a preferred embodiment of an atmospheric single-particle source identification device based on morphology, particle size, and composition, the single-particle dataset acquisition module includes the following pollution sources: soil dust, road dust, construction dust, coal dust, biomass combustion dust, and iron and steel smelting dust, during the analysis of the collected samples of the designated pollution sources using a computer-controlled scanning electron microscope: soil dust, road dust, construction dust, coal smoke dust, biomass combustion dust, and iron and steel smelting dust.

[0026] As a preferred embodiment of an atmospheric single-particle source identification device based on morphology, particle size, and composition, the single-particle dataset acquisition module includes images of single particles including: high-resolution micrographs of single particles.

[0027] The composition data of the single particles include: carbon, oxygen, sodium, magnesium, aluminum, silicon, phosphorus, sulfur, chlorine, potassium, calcium, zinc, barium, vanadium, chromium, cobalt, selenium, tin, titanium, manganese, nickel, copper and lead;

[0028] The particle size parameters of the single particle include: maximum diameter, minimum diameter, average diameter, vertical diameter, and equivalent circle diameter.

[0029] As a preferred embodiment of an atmospheric single-particle source identification device based on morphology, particle size, and composition, the single-particle source determination module, in the process of inputting the image, composition data, and particle size parameters of the target single particle into the trained source analysis model for processing to obtain the probability value of the target single particle belonging to the set pollution source, extracts the image features of the target single particle through the residual network model, and preliminarily predicts the source of the target single particle based on the image features of the target single particle, thereby obtaining the preliminary probability value of the target single particle belonging to the set pollution source.

[0030] As a preferred embodiment of an atmospheric single-particle source identification device based on morphology, particle size, and composition, in the single-particle source determination module, during the process of inputting the image, composition data, and particle size parameters of the target single particle into the trained source analysis model for processing to obtain the probability value of the target single particle belonging to the set pollution source, the preliminary probability value of the target single particle belonging to the set pollution source is merged with the particle size parameters and composition data of the target single particle, and input into the extreme gradient enhancement model. The probability value of the target single particle belonging to the set pollution source is obtained through prediction by the extreme gradient enhancement model.

[0031] This invention has the following advantages: It analyzes collected samples from designated pollution sources using a computer-controlled scanning electron microscope to obtain images, compositional data, and particle size parameters of individual particles in the samples, constructing a single-particle dataset of the pollution source samples. This dataset is then randomly divided into a first dataset and a second dataset according to a predetermined ratio. The first dataset is used to train the source analysis model; the second dataset is used to validate the model. A source analysis model is constructed based on a residual network model and an extreme gradient boosting model. The model is iteratively trained using the first dataset. The prediction results of the model are validated using the second dataset to obtain a well-trained model. The image, compositional data, and particle size parameters of the target single particle are input into the trained model for processing to obtain the probability value of the target single particle belonging to the designated pollution source, thus determining the source of the target single particle. This invention can fully explore the morphology, particle size, and compositional characteristics of particulate matter, identify particulate matter sources, and quantify the contributions of different pollution sources. Simultaneously, it contributes to further research on the physicochemical properties of atmospheric particulate matter and source apportionment studies of atmospheric particulate matter. Attached Figure Description

[0032] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0033] The structures, proportions, sizes, etc. illustrated in this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed herein, and are not intended to limit the conditions under which the present invention can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportions, or adjustments to the size, without affecting the effects and objectives that the present invention can produce, should still fall within the scope of the technical content disclosed in the present invention.

[0034] Figure 1 This is a schematic flowchart of the atmospheric single-particle source identification method based on morphology, particle size, and composition provided in Embodiment 1 of the present invention.

[0035] Figure 2 This is a schematic diagram illustrating the specific implementation steps of the atmospheric single-particle source identification method based on morphology, particle size, and composition provided in Embodiment 1 of the present invention.

[0036] Figure 3 This is a schematic diagram illustrating the accuracy of the source apportionment model in predicting different pollution sources in the atmospheric single-particle source identification method based on morphology, particle size, and composition provided in Embodiment 1 of the present invention.

[0037] Figure 4 This diagram illustrates the accuracy of source apportionment model predictions for different types of particulate matter sources in the atmospheric single-particle source identification method based on morphology, particle size, and composition provided in Embodiment 1 of the present invention.

[0038] Figure 5 This is a schematic diagram of the confusion matrix of different types of particulate matter predicted by the source apportionment model in the atmospheric single-particle source identification method based on morphology, particle size, and composition provided in Embodiment 1 of the present invention.

[0039] Figure 6 This is a schematic diagram of the architecture of the atmospheric single-particle source identification device based on morphology, particle size, and composition provided in Embodiment 2 of the present invention. Detailed Implementation

[0040] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] Example 1

[0042] See Figure 1 and Figure 2 Embodiment 1 of the present invention provides a method for identifying the source of atmospheric single particles based on morphology, particle size, and composition, including:

[0043] S1. The collected samples of the designated pollution source are analyzed by using a computer-controlled scanning electron microscope to obtain images, composition data and particle size parameters of single particles in the samples of the designated pollution source, and to construct a single particle dataset of the pollution source samples.

[0044] S2. The single-particle dataset is randomly divided into a first dataset and a second dataset according to a set ratio; the first dataset is used for training the source analysis model; the second dataset is used for validating the source analysis model.

[0045] S3. Construct a source analysis model based on the residual network model and the extreme gradient boosting model;

[0046] S4. Iteratively train the source analysis model using the first dataset; validate the prediction results of the source analysis model using the second dataset to obtain the trained source analysis model.

[0047] S5. Input the image, composition data and particle size parameters of the target single particle into the trained source analysis model for processing, obtain the probability value of the target single particle belonging to the set pollution source, and determine the source of the target single particle.

[0048] In this embodiment, in step S1, during the analysis of the collected samples of the designated pollution sources using a computer-controlled scanning electron microscope, the designated pollution sources include: soil dust, road dust, construction dust, coal smoke dust, biomass combustion dust, and iron and steel smelting dust.

[0049] Specifically, in this embodiment, samples from six types of pollution sources were collected: soil dust, road dust, construction dust, coal smoke dust, biomass combustion dust, and iron and steel smelting dust. Scanning electron microscopy-energy dispersive spectroscopy (SEM-EDS) was used to analyze the pollution source samples, constructing a database of single particles from typical pollution sources. Computer-controlled scanning electron microscopy-energy dispersive spectroscopy (CCSEM-EDS) was used to analyze at least 10,000 particles from each source sample, with at least 2,000 particles analyzed from each sample.

[0050] In this embodiment, during step S1, when acquiring the image, composition data, and particle size parameters of a single particle in the sample of the set pollution source, the image, composition data, and particle size parameters of the single particle are...

[0051] Specifically, the data collected by CCSEM-EDS includes a microscopic image of the particle, particle size parameters (such as maximum diameter, minimum diameter, average diameter, vertical diameter, and equivalent circle diameter), and elemental data (including carbon (C), oxygen (O), sodium (Na), magnesium (Mg), aluminum (Al), silicon (Si), phosphorus (P), sulfur (S), chlorine (Cl), potassium (K), calcium (Ca), zinc (Zn), barium (Ba), vanadium (V), chromium (Cr), cobalt (Co), selenium (Se), tin (Sn), titanium (Ti), manganese (Mn), nickel (Ni), copper (Cu), and lead (Pb). The maximum, minimum, and average diameters refer to the particle's maximum, minimum, and average diameters calculated through multiple rotation measurements. The vertical diameter refers to the diameter of the particle perpendicular to its maximum diameter, and the equivalent circle diameter refers to the diameter of a circle with the same area as the particle. In this embodiment, in step S2, the single-particle dataset is randomly divided into a first dataset and a second dataset according to a set ratio; the first dataset is used for training the source analysis model; the second dataset is used for validating the source analysis model.

[0052] Specifically, the single-particle datasets obtained from the source samples are divided into two sets. 80% of the single-particle data from each pollution source is randomly selected as the first dataset, which is mainly used for training the source apportionment model. The remaining 20% ​​of the single-particle data from each pollution source is used as the second dataset, which is used to verify the accuracy of the source apportionment results.

[0053] In this embodiment, in step S3, a source analysis model is constructed based on the residual network model and the extreme gradient boosting model;

[0054] Specifically, the residual network model is combined with the extreme gradient boosting model to form a source analysis model. The residual network model is used to obtain the preliminary probability value of a single particle belonging to a set pollution source. The preliminary probability value of a single particle belonging to a set pollution source, along with its corresponding particle size parameters and composition data, are simultaneously input into the extreme gradient boosting model to predict the probability value of a single particle belonging to the set pollution source.

[0055] In this embodiment, in step S4, the source analysis model is iteratively trained using the first dataset;

[0056] Specifically, the single-particle data from the first dataset are input into the source analysis model in batches. The source analysis model is used to predict the pollution source of each single particle. The predicted results are compared with the actual pollution sources to continuously optimize the source analysis model.

[0057] The prediction results of the source analysis model are validated using the second dataset to obtain the trained source analysis model.

[0058] Specifically, the trained source analysis model is used to predict the pollution sources of single particles in the second dataset. The accuracy of predictions for different pollution sources is as follows: Figure 3 As shown.

[0059] By weighting and summing the probability values ​​of the obtained single particles belonging to the designated pollution source based on their mass or quantity, the mass or quantity proportion of atmospheric particulate matter emitted by the designated pollution source is obtained. Figure 3 The values ​​along the top left-bottom right diagonal represent the prediction accuracy for various pollution sources, with the values ​​in parentheses indicating the sample size. The prediction accuracy for the six pollution sources ranged from 91.53% to 99.09%, with an average accuracy of 95.22%. Considering that the same pollution source may contain different types of particulate matter (different in morphology and chemical composition), and different pollution sources may contain similar types of particulate matter (e.g., road dust may contain metal particles and aluminosilicates, while aluminosilicates are also present in soil dust), to further explore the accuracy of this invention in identifying different types of particulate pollution sources, the particulate matter is now classified. The particulate matter classification steps are as follows:

[0060] T1. Variable Selection: Considering the different inherent meanings of shape parameters, particle size, and elemental concentration variables, it may be difficult to interpret them through cluster analysis. Therefore, chemical element variables (including C, O, Na, Mg, Al, Si, P, S, Cl, K, Ca, Zn, Ba, V, Cr, Co, Se, Sn, Ti, Mn, Ni, Cu, and Pb) are first selected from all variables for cluster analysis.

[0061] T2. Data noise handling: If any X-ray count of a particle is less than twice the square root of the total X-ray count, it is set to zero.

[0062] T3. Data Transformation: The data was logarithmically transformed to compress the distribution, and then the X-ray spectra of each particle data were normalized to ensure that all chemical element variables had equal weight in the classification.

[0063] T4. Cluster Analysis: All sample data are integrated, and cluster analysis is performed using the k-means method. The optimal k value is determined using the elbow method, which involves selecting different k values ​​and observing the changes in the sum of squared errors (SSE). k This represents the error in clustering samples into k classes, specifically the sum of squared distances from each point within a cluster to the cluster center.

[0064]

[0065] In the formula, X i It is the i-th cluster; j is X i Sample points in; m i It is X i The center of mass, i.e., X i The mean of all samples in the sample.

[0066] As the number of clusters k increases, the sample partitioning becomes increasingly refined, and SSE... k Gradually decrease. When k is greater than a certain number, SSE... k The value of k tends to level off as the value of k continues to increase. The k=K value corresponding to the elbow is taken as the number of clusters in this embodiment. To make the particle classification more detailed, the value of k is set to 100 here.

[0067] T5. Manual Classification: After clustering, based on the similarity between the EDS spectra and the EDS spectra of different types of particles in related studies, and combined with the morphological characteristics of individual particles, the 100 clusters were divided into 33 categories, namely Si-Al, Si-rich, Si-Al-Ca, Si-Al-Fe, Si-Al-K-Mg, Si-Al-Mg, Si-Al-Na, Si-Al-Ca-Mg-Fe, Si-Al-Ca-Mg, Si-Ca, Al-rich, Al-Ca, Ca-Mg, Ca-Mg-Cl, P-containing, K-containing, Fly ash, C-rich, Fe-rich, Ca-rich, S-Ca, Ti-rich, Fe-Ca-S, Fe-K-Cl, Mn-rich, K-Cl, Pb-Cl, Pb-Fe-Cl, Pb-Cl-K, S-Al-Ca-Mg, S-Ca-Pb, S-Ca-K-Cl, and Other.

[0068] The accuracy and model confusion matrix of prediction results for different types of particulate matter sources are as follows: Figure 4 and Figure 5 As shown in the figure. The results demonstrate that the source apportionment model in this invention can accurately identify different types of particulate matter to their corresponding pollution sources, further proving the model's excellent performance.

[0069] In this embodiment, in step S5, during the process of inputting the image, composition data, and particle size parameters of the target single particle into the trained source analysis model for processing to obtain the probability value of the target single particle belonging to the set pollution source, the image features of the target single particle are extracted through the residual network model, and the source of the target single particle is initially predicted based on the image features of the target single particle to obtain the preliminary probability value of the target single particle belonging to the set pollution source.

[0070] Specifically, data augmentation techniques are applied to enhance the diversity of the dataset. Random rotation, flipping, and scaling of single-particle micrographs are used to mitigate the impact of particle position and size variability on prediction results. Simultaneously, image brightness, contrast, saturation, and hue are randomly adjusted to reduce the differences in micrograph images between different samples caused by variations in CCSEM analysis conditions. For image feature extraction, a Residual Network (ResNet) is used to extract image features and identify particle sources based on these features. Compared to traditional Convolutional Neural Networks (CNNs), ResNet uses skip connections in its residual blocks, mitigating the gradient vanishing problem that occurs with increasing neural network depth. Traditional CNN architectures require a large amount of training data to achieve high prediction accuracy; this invention employs a transfer learning strategy, using parameters trained on a large ImageNet dataset for the initial parameters of the ResNet model. To adapt the pre-trained features to the single-particle image dataset, the last residual block is fine-tuned while maintaining the pre-trained weights of other blocks. After feature extraction using the ResNet model, a fully connected layer is added for particle source prediction. During training, the Adam optimizer was used with a learning rate of 1e-2, a step size of 7, and a decay rate of 0.1. The negative log-likelihood loss function was employed to calculate the loss and optimize model performance. Finally, the initial probability values ​​of each particle originating from different sources were recorded.

[0071] In this embodiment, step S5 further includes processing the image, composition data, and particle size parameters of the target single particle into the trained source analysis model to obtain the probability value of the target single particle belonging to the set pollution source. In this process, the preliminary probability value of the target single particle belonging to the set pollution source is merged with the particle size parameters and composition data of the target single particle and input into the extreme gradient boosting model. The probability value of the target single particle belonging to the set pollution source is obtained by prediction through the extreme gradient boosting model.

[0072] Specifically, the preliminary probability value of a single particle belonging to the designated pollution source, predicted by the residual network model, is combined with the particle size parameters and composition data of the single particle and used as input to the Extreme Gradient Boosting (XGBoost) model. The particle source label is the dependent variable. This completes the training of the XGBoost model, and the output is the probability calculated by the XGBoost model that each particle belongs to a different pollution source. During the optimization process of the XGBoost model, grid search is used to select the most suitable hyperparameters, and five-fold cross-validation is used to evaluate the performance of the XGBoost model.

[0073] In summary, this invention analyzes samples collected from designated pollution sources using a computer-controlled scanning electron microscope to obtain images, compositional data, and particle size parameters of individual particles in the samples, constructing a single-particle dataset of the pollution source samples. This dataset is then randomly divided into a first dataset and a second dataset according to a predetermined ratio. The first dataset is used for training the source analysis model, while the second dataset is used for validation. A source analysis model is constructed based on a residual network model and an extreme gradient boosting model. The model is iteratively trained using the first dataset, and its prediction results are validated using the second dataset to obtain a trained model. The image, compositional data, and particle size parameters of the target single particle are input into the trained model for processing to obtain the probability value of the target single particle belonging to the designated pollution source, thus determining the source of the target single particle. This invention can fully exploit the morphology, particle size, and compositional characteristics of particulate matter, identify particulate matter sources, and quantify the contributions of different pollution sources. Simultaneously, it contributes to further research on the physicochemical properties of atmospheric particulate matter and source apportionment studies of atmospheric particulate matter.

[0074] It should be noted that the method of this disclosure embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this disclosure embodiment, and the multiple devices will interact with each other to complete the method described.

[0075] It should be noted that the above description describes some embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0076] Example 2

[0077] See Figure 6 Embodiment 2 of the present invention provides an atmospheric single-particle source identification device based on morphology, particle size, and composition, comprising:

[0078] The single-particle dataset acquisition module 001 is used to analyze the collected samples of the designated pollution source using a computer-controlled scanning electron microscope, and to acquire images, composition data and particle size parameters of single particles in the sample of the designated pollution source, and to construct a single-particle dataset of the pollution source sample.

[0079] The single-particle dataset partitioning module 002 is used to randomly partition the single-particle dataset into a first dataset and a second dataset according to a set ratio; the first dataset is used for training the source analysis model; and the second dataset is used for validating the source analysis model.

[0080] Source analysis model construction module 003 is used to construct the source analysis model based on the residual network model and the extreme gradient boosting model;

[0081] The source analysis model training module 004 is used to iteratively train the source analysis model using the first dataset and to verify the prediction results of the source analysis model using the second dataset to obtain the trained source analysis model.

[0082] The single particle source determination module 005 is used to input the image, composition data and particle size parameters of the target single particle into the trained source analysis model for processing, to obtain the probability value of the target single particle belonging to the set pollution source, and to determine the source of the target single particle.

[0083] In this embodiment, in the single-particle dataset acquisition module 001, during the analysis of the collected samples of the designated pollution sources using a computer-controlled scanning electron microscope, the designated pollution sources include: soil dust, road dust, construction dust, coal smoke dust, biomass combustion dust, and iron and steel smelting dust.

[0084] In this embodiment, the image of the single particle in the single particle data acquisition module 001 includes: a high-resolution photomicrograph of the single particle;

[0085] The composition data of the single particles include: carbon, oxygen, sodium, magnesium, aluminum, silicon, phosphorus, sulfur, chlorine, potassium, calcium, zinc, barium, vanadium, chromium, cobalt, selenium, tin, titanium, manganese, nickel, copper and lead;

[0086] The particle size parameters of the single particle include: maximum diameter, minimum diameter, average diameter, vertical diameter, and equivalent circle diameter.

[0087] In this embodiment, in the single particle source determination module 005, during the process of inputting the image, composition data, and particle size parameters of the target single particle into the trained source analysis model for processing to obtain the probability value of the target single particle belonging to the set pollution source, the image features of the target single particle are extracted through the residual network model, and the source of the target single particle is initially predicted based on the image features of the target single particle to obtain the preliminary probability value of the target single particle belonging to the set pollution source.

[0088] In this embodiment, in the single particle source determination module 005, during the process of inputting the image, composition data, and particle size parameters of the target single particle into the trained source analysis model for processing to obtain the probability value of the target single particle belonging to the set pollution source, the preliminary probability value of the target single particle belonging to the set pollution source is merged with the particle size parameters and composition data of the target single particle, and input into the extreme gradient enhancement model. The probability value of the target single particle belonging to the set pollution source is obtained through prediction by the extreme gradient enhancement model.

[0089] It should be noted that the information interaction and execution process between the modules / units of the above system are based on the same concept as the method embodiment in Embodiment 1 of this application, and the resulting technical effects are the same as those in the method embodiment of this application. For details, please refer to the description in the method embodiment shown above in this application, and it will not be repeated here.

[0090] Example 3

[0091] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium storing program code for an atmospheric single-particle source identification method based on morphology, particle size, and composition. The program code includes instructions for executing the atmospheric single-particle source identification method based on morphology, particle size, and composition according to Embodiment 1 or any possible implementation thereof.

[0092] Computer-readable storage media can be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives, SSDs).

[0093] Example 4

[0094] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;

[0095] The processor and the memory communicate with each other via a bus; the memory stores program instructions that can be executed by the processor, and the processor can call the program instructions to execute the atmospheric single particle source identification method based on morphology, particle size and composition according to Embodiment 1 or any possible implementation thereof.

[0096] Specifically, a processor can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, an integrated circuit, etc. When implemented in software, the processor can be a general-purpose processor that reads software code stored in memory. This memory can be integrated into the processor or located outside the processor and exist independently.

[0097] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0098] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0099] Although the present invention has been described in detail above with general descriptions and specific embodiments, modifications or improvements can be made to it, which will be obvious to those skilled in the art. Therefore, all such modifications or improvements made without departing from the spirit of the present invention fall within the scope of protection claimed by the present invention.

Claims

1. A method for identifying the source of a single atmospheric particle based on morphology, particle size, and composition, characterized in that, include: By using a computer-controlled scanning electron microscope to analyze the collected samples of a designated pollution source, images, composition data and particle size parameters of individual particles in the sample of the designated pollution source are obtained, and a single particle dataset of the pollution source sample is constructed. The single-particle dataset is randomly divided into a first dataset and a second dataset according to a set ratio; the first dataset is used for training the source analysis model; the second dataset is used for validating the source analysis model. Based on the residual network model and the extreme gradient boosting model, a source analysis model is constructed; The source analysis model is iteratively trained using the first dataset; The prediction results of the source analysis model are validated using the second dataset to obtain the trained source analysis model. The image, composition data, and particle size parameters of the target single particle are input into the trained source analysis model for processing to obtain the probability value of the target single particle belonging to the set pollution source, thereby determining the source of the target single particle.

2. The method for identifying the source of atmospheric single particles based on morphology, particle size, and composition according to claim 1, characterized in that, During the analysis of samples collected from the designated pollution sources using a computer-controlled scanning electron microscope, the designated pollution sources include: soil dust, road dust, construction dust, coal smoke dust, biomass combustion dust, and iron and steel smelting dust.

3. The method for identifying the source of atmospheric single particles based on morphology, particle size, and composition according to claim 2, characterized in that, The images of the single particle include: high-resolution photomicrographs of the single particle; The composition data of the single particles include: carbon, oxygen, sodium, magnesium, aluminum, silicon, phosphorus, sulfur, chlorine, potassium, calcium, zinc, barium, vanadium, chromium, cobalt, selenium, tin, titanium, manganese, nickel, copper and lead; The particle size parameters of the single particle include: maximum diameter, minimum diameter, average diameter, vertical diameter, and equivalent circle diameter.

4. The method for identifying the source of atmospheric single particles based on morphology, particle size, and composition according to claim 3, characterized in that, In the process of inputting the image, composition data, and particle size parameters of the target single particle into the trained source analysis model for processing, and obtaining the probability value of the target single particle belonging to the set pollution source, the image features of the target single particle are extracted through the residual network model, and the source of the target single particle is initially predicted based on the image features of the target single particle, thereby obtaining the preliminary probability value of the target single particle belonging to the set pollution source.

5. The method for identifying the source of atmospheric single particles based on morphology, particle size, and composition according to claim 4, characterized in that, In the process of inputting the image, composition data, and particle size parameters of the target single particle into the trained source analysis model for processing, and obtaining the probability value of the target single particle belonging to the set pollution source, the preliminary probability value of the target single particle belonging to the set pollution source is merged with the particle size parameters and composition data of the target single particle, and input into the extreme gradient boosting model. The probability value of the target single particle belonging to the set pollution source is obtained through prediction by the extreme gradient boosting model.

6. An atmospheric single-particle source identification device based on morphology, particle size, and composition, employing the atmospheric single-particle source identification method based on morphology, particle size, and composition as described in claims 1-5, characterized in that... include: The single-particle dataset acquisition module is used to analyze the collected samples of a designated pollution source using a computer-controlled scanning electron microscope, and to acquire images, composition data and particle size parameters of single particles in the samples of the designated pollution source, thereby constructing a single-particle dataset of the pollution source samples. The single-particle dataset partitioning module is used to randomly divide the single-particle dataset into a first dataset and a second dataset according to a set ratio; the first dataset is used for training the source analysis model; and the second dataset is used for validating the source analysis model. The source analysis model building module is used to build a source analysis model based on the residual network model and the extreme gradient boosting model. The source analysis model training module is used to iteratively train the source analysis model using the first dataset; The prediction results of the source analysis model are validated using the second dataset to obtain the trained source analysis model. The single-particle source determination module is used to input the image, composition data and particle size parameters of the target single particle into the trained source analysis model for processing, to obtain the probability value of the target single particle belonging to the set pollution source, and to determine the source of the target single particle.

7. The atmospheric single-particle source identification device based on morphology, particle size, and composition according to claim 6, characterized in that, In the single-particle dataset acquisition module, during the analysis of the collected samples from the designated pollution sources using a computer-controlled scanning electron microscope, the designated pollution sources include: soil dust, road dust, construction dust, coal smoke dust, biomass combustion dust, and iron and steel smelting dust.

8. The atmospheric single-particle source identification device based on morphology, particle size, and composition according to claim 7, characterized in that, The images of the single particle include: high-resolution photomicrographs of the single particle; In the single-particle data acquisition module, the composition data of the single particle includes: carbon, oxygen, sodium, magnesium, aluminum, silicon, phosphorus, sulfur, chlorine, potassium, calcium, zinc, barium, vanadium, chromium, cobalt, selenium, tin, titanium, manganese, nickel, copper, and lead. The particle size parameters of the single particle include: maximum diameter, minimum diameter, average diameter, vertical diameter, and equivalent circle diameter.

9. The atmospheric single-particle source identification device based on morphology, particle size, and composition according to claim 8, characterized in that, In the single-particle source determination module, during the process of inputting the image, composition data, and particle size parameters of the target single particle into the trained source analysis model for processing to obtain the probability value of the target single particle belonging to the set pollution source, the image features of the target single particle are extracted through the residual network model, and the source of the target single particle is initially predicted based on the image features of the target single particle to obtain the preliminary probability value of the target single particle belonging to the set pollution source.

10. The atmospheric single-particle source identification device based on morphology, particle size, and composition according to claim 9, characterized in that, In the single-particle source determination module, during the process of inputting the image, composition data, and particle size parameters of the target single particle into the trained source analysis model for processing to obtain the probability value of the target single particle belonging to the set pollution source, the preliminary probability value of the target single particle belonging to the set pollution source is merged with the particle size parameters and composition data of the target single particle, and input into the extreme gradient enhancement model. The probability value of the target single particle belonging to the set pollution source is obtained through prediction by the extreme gradient enhancement model.

Citation Information

Patent Citations

  • Atmospheric particulate real-time source analytic method based on single-particle mass spectrums

    CN103674789A

  • Method for analyzing particulate matter sources by using single-particle aerosol mass spectrometer

    CN110243738A