Tags

Type your tag names separated by a space and hit enter

Source Apportionment of Soil Samples by the Combination of Two Neural Networks Based on Computer-Controlled Scanning Electron Microscopy.
J Air Waste Manag Assoc 1999; 49(7):773-783JA

Abstract

The apportionment of ambient aerosol mass to different sources of airborne soil is a difficult problem because of the similarity of the chemical composition of crustal sources. However, additional information can be obtained using individual particle analysis. A novel approach based on the combination of two neural networks, the adaptive resonance theory-based neural network (ART-2a) and the back-propagation (BP) neural network with electron microscopy data, has been developed to apportion the mass contributions of the crustal sources to ambient particle samples. The crustal source samples were analyzed using computer-controlled scanning electron microscopy (CCSEM). CCSEM provides elemental compositions and size parameters for individual particles as well as estimates of the shape and density from which the volume and mass of each particle can be estimated. The ART-2a neural network was first used to partition particles into homogeneous classes based on the elemental composition data. After the different particle type classes were produced by ART-2a, their mass fractions were calculated. In this way, the source profiles for the crustal dust sources can be obtained in terms of the mass fractions for different particle types. Then the BP neural network was applied to build the model between the mass fractions of different particle types and the mass contributions. Using the three physical source samples prepared for this study, artificial ambient samples were generated by randomly mixing particles from the three source samples. These samples were then used to examine the proposed method. Satisfactory predictions for the mass contributions of the three sources to the ambient samples have been obtained, indicating the proposed method is a promising tool for the source apportionment of chemically similar soil samples.

Authors+Show Affiliations

a Department of Chemistry , Clarkson University , Potsdam , New York , USA.a Department of Chemistry , Clarkson University , Potsdam , New York , USA.a Department of Chemistry , Clarkson University , Potsdam , New York , USA.b Crocker Nuclear Laboratory, Air Quality Group , University of California , Davis , California , USA.b Crocker Nuclear Laboratory, Air Quality Group , University of California , Davis , California , USA.c R.J. Lee Group, Inc. , Monroeville , Pennsylvania , USA.c R.J. Lee Group, Inc. , Monroeville , Pennsylvania , USA.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

28060662

Citation

Song, Xin-Hua, et al. "Source Apportionment of Soil Samples By the Combination of Two Neural Networks Based On Computer-Controlled Scanning Electron Microscopy." Journal of the Air & Waste Management Association (1995), vol. 49, no. 7, 1999, pp. 773-783.
Song XH, Hadjiiski L, Hopke PK, et al. Source Apportionment of Soil Samples by the Combination of Two Neural Networks Based on Computer-Controlled Scanning Electron Microscopy. J Air Waste Manag Assoc. 1999;49(7):773-783.
Song, X. H., Hadjiiski, L., Hopke, P. K., Ashbaugh, L. L., Carvacho, O., Casuccio, G. S., & Schlaegle, S. (1999). Source Apportionment of Soil Samples by the Combination of Two Neural Networks Based on Computer-Controlled Scanning Electron Microscopy. Journal of the Air & Waste Management Association (1995), 49(7), pp. 773-783. doi:10.1080/10473289.1999.10463848.
Song XH, et al. Source Apportionment of Soil Samples By the Combination of Two Neural Networks Based On Computer-Controlled Scanning Electron Microscopy. J Air Waste Manag Assoc. 1999;49(7):773-783. PubMed PMID: 28060662.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Source Apportionment of Soil Samples by the Combination of Two Neural Networks Based on Computer-Controlled Scanning Electron Microscopy. AU - Song,Xin-Hua, AU - Hadjiiski,Lubomir, AU - Hopke,Philip K, AU - Ashbaugh,Lowell L, AU - Carvacho,Omar, AU - Casuccio,Gary S, AU - Schlaegle,Steven, PY - 2017/1/7/entrez PY - 1999/7/1/pubmed PY - 1999/7/1/medline SP - 773 EP - 783 JF - Journal of the Air & Waste Management Association (1995) JO - J Air Waste Manag Assoc VL - 49 IS - 7 N2 - The apportionment of ambient aerosol mass to different sources of airborne soil is a difficult problem because of the similarity of the chemical composition of crustal sources. However, additional information can be obtained using individual particle analysis. A novel approach based on the combination of two neural networks, the adaptive resonance theory-based neural network (ART-2a) and the back-propagation (BP) neural network with electron microscopy data, has been developed to apportion the mass contributions of the crustal sources to ambient particle samples. The crustal source samples were analyzed using computer-controlled scanning electron microscopy (CCSEM). CCSEM provides elemental compositions and size parameters for individual particles as well as estimates of the shape and density from which the volume and mass of each particle can be estimated. The ART-2a neural network was first used to partition particles into homogeneous classes based on the elemental composition data. After the different particle type classes were produced by ART-2a, their mass fractions were calculated. In this way, the source profiles for the crustal dust sources can be obtained in terms of the mass fractions for different particle types. Then the BP neural network was applied to build the model between the mass fractions of different particle types and the mass contributions. Using the three physical source samples prepared for this study, artificial ambient samples were generated by randomly mixing particles from the three source samples. These samples were then used to examine the proposed method. Satisfactory predictions for the mass contributions of the three sources to the ambient samples have been obtained, indicating the proposed method is a promising tool for the source apportionment of chemically similar soil samples. SN - 2162-2906 UR - https://www.unboundmedicine.com/medline/citation/28060662/Source_Apportionment_of_Soil_Samples_by_the_Combination_of_Two_Neural_Networks_Based_on_Computer_Controlled_Scanning_Electron_Microscopy_ L2 - http://www.tandfonline.com/doi/full/10.1080/10473289.1999.10463848 DB - PRIME DP - Unbound Medicine ER -