Analysis of different modes of factor analysis as least squares fit problems

Paatero, Pentti; Tapper, Unto

doi:10.1016/0169-7439(93)80055-m

Cited by 420 publications

(188 citation statements)

References 6 publications

Supporting

Mentioning

169

Contrasting

Unclassified

Order By: Relevance

“…Backward trajectory of 72 h accessed via the NOAA (National Oceanic and Atmospheric Administration) Air Resources Laboratory, READY (Real-time Environmental Applications and Display sYstem) website with the HYSPLIT4 (HYbrid Single-Particle Lagrangian Integrated Trajectory) model. 21,22 Positive Matrix Factorization (PMF), a multivariate receptor based model developed by Paatero et al, [23][24][25] was applied to the analytical results of the PM 2.5 samples collected at the receptor site during the winters of 2005 and 2006 to identify sources and their contributions to the receptor site airborne fine particulate matter. Receptor based multivariate source apportionment models use chemical composition of fine particulate matter measured at receptor site(s) to determine correlation among them assuming that highly correlated species come from a common source.…”

Section: Model Based Data Analysismentioning

confidence: 99%

Particulate matter (PM2.5) concentration and source apportionment in lahore

Lodhi¹,

Ghauri²,

Khan³

et al. 2009

J. Braz. Chem. Soc.

View full text Add to dashboard Cite

Neste trabalho foram estudadas as concentrações das PM 2.5 (partículas com diâmetro aerodinâmico de 2,5 µm ou menos) e das fontes de incremento das PM 2.5 , monitoradas numa área urbana residencial de Lahore, Pasquitão. Amostras de PM 2.5 em aerosol foram coletadas 2 dias por semana, num inetravlo de 12 h por dia, nas estações seca e húmida, usando um filtro de papel Zefluor TM contendo um amostrador de ar ambiente termo-elétrico (Thermo-Electron Corporation Reference Ambient Air Sampler, RAAS ) durante o inverno, os quais aumentam a concentração total de PM 2.5 quando, relativamente, menos dispersão aérea existe. As partículas de sulfato também aumentam a formação de neblina/nevoeiro em condições calmaria e humidade, reduzindo a visbilidade e aumentando a incidência de doenças respiratórias na cidade ao longo do ano.The work reported in this paper was carried out to study the trends of PM 2.5 (particles with an aerodynamic diameter of 2.5 µm or less) concentrations and source apportionment of PM 2.5 monitored at an urban residential site in Lahore, Pakistan. PM 2.5 aerosol samples were collected for 2 days in a week at 12 h interval in a day, both in dry and wet seasons, on Zefluor TM filter papers using Thermo-Electron Corporation Reference Ambient Air Sampler (RAAS). Total 310 samples were collected during the period under study, i.e., from November 2005 to December 2007. High PM 2.5 loads were observed in winter, which were approximately 4 times greater than those observed in the summer, spring, fall and monsoon seasons in the yearlong measurements. Source apportionment was performed on short duration analysis results of November 2005 to March 2006 using Positive Matrix Factorization (PMF) model. The results derived from PMF model indicated that the major contributors to PM 2.5 in Lahore are: soil/road dust, industrial emissions, vehicular emissions and secondary aerosols. It is, therefore, concluded that in addition to local vehicular and industrial emissions, the city is also affected from trans-boundary air pollutants particularly due to secondary aerosols (especially SO 4 2-) during winter which increase PM 2.5 concentrations manifold when relatively less mixing height exists. The sulfate particles also facilitate in haze/fog formation during calm highly humid conditions, thus reduce visibility and increase the incidents of respiratory diseases encountered in the city every year.

show abstract

Section: Model Based Data Analysismentioning

confidence: 99%

Particulate matter (PM2.5) concentration and source apportionment in lahore

Lodhi¹,

Ghauri²,

Khan³

et al. 2009

J. Braz. Chem. Soc.

View full text Add to dashboard Cite

show abstract

“…The resulting coefficients of the factors to the overall set of data are called factor loadings. [Paatero, 1996;Paatero and Tapper, 1993;1994]. A systematic study of aerosol at Narragansett has shown that PMF resolves minor factors up to 100 times better than conventional factor analysis [Huang et al, 1999].…”

Section: Factor Analysismentioning

confidence: 99%

Semiannual cycles of pollution at Bermuda

Huang¹,

Rahn²,

Arimoto³

et al. 1999

J. Geophys. Res.

View full text Add to dashboard Cite

Abstract. To identify the sources and determine the transport pathways for aerosol during the Atmosphere/Ocean Chemistry Experiment (AEROCE), we examined the temporal variations of trace elements in daily aerosol samples collected at Bermuda from 1988 to 1994. Crustal (e.g., A1) and marine (e.g., Na) elements showed annual cycles with summer and winter maxima, respectively. In contrast, pollution-derived elements (e.g., Sb) showed unusual semiannual cycles with strong spring maxima and weaker fall maxima, which to the best of our knowledge, have not been previously documented. The seasonality in trace element concentrations was mainly transport-driven: The spring maxima of pollutants were caused by rapid westerly transport from North America, and the fall maxima were caused by North American air slowly transported to Bermuda by large high-pressure systems that stagnated over the lower mid-Atlantic states. Low concentrations of pollution elements in winter resulted from the southwestward extension of the Bermuda-Azores high-pressure system that brought marine air to Bermuda from the east or northeast while hindering transport from North America and Africa. The summer minima in pollutants were associated with air transported from the eastern Atlantic and Africa. The variations of the trace gases 03 and CO and two naturally occurring radionuclides, 2•øpb and 7Be, showed semiannual cycles similar to those of the pollution-derived trace elements.

show abstract

“…The PCA method being a bilinear method, connects the data and the parameter spaces. The properties of this connection in the presence of signal noise has been described in in Paatero and Tapper (1993) and Paatero and Hopke (2003) and it may open up some additional research opportunities.…”

Section: Methodsmentioning

confidence: 94%

COSIMA data analysis using multivariate techniques

Silén

Cottin

Hilchenbach

et al. 2015

Geosci. Instrum. Method. Data Syst.

View full text Add to dashboard Cite

Abstract.We describe how to use multivariate analysis of complex TOF-SIMS (time-of-flight secondary ion mass spectrometry) spectra by introducing the method of random projections. The technique allows us to do full clustering and classification of the measured mass spectra. In this paper we use the tool for classification purposes. The presentation describes calibration experiments of 19 minerals on Ag and Au substrates using positive mode ion spectra. The discrimination between individual minerals gives a cross-validation Cohen κ for classification of typically about 80 %. We intend to use the method as a fast tool to deduce a qualitative similarity of measurements.

show abstract

Analysis of different modes of factor analysis as least squares fit problems

Cited by 420 publications

References 6 publications

Particulate matter (PM2.5) concentration and source apportionment in lahore

Particulate matter (PM2.5) concentration and source apportionment in lahore

Semiannual cycles of pollution at Bermuda

COSIMA data analysis using multivariate techniques

Contact Info

Product

Resources

About