Abstract
Linear mixing models of compositional data have been developed in various branches of the earth sciences (e.g., geochemistry, petrology, mineralogy, sedimentology) for the purpose of summarizing variation among a series of observations in terms of proportional contributions of (theoretical) end members. Methods of parameter estimation range from relatively straightforward normative partitioning by (nonnegative) least squares, to more sophisticated bilinear inversion techniques. Solving the bilinear mixing problem involves the estimation of both mixing proportions and end-member compositions from the data. Normative partitioning, also known as linear unmixing, thus can be regarded as a special situation of bilinear unmixing with (supposedly) known end members. Previous attempts to model linear mixing processes are reviewed briefly, and a new iterative strategy for solving the bilinear problem is developed. This end-member modeling algorithm is more robust and has better convergence properties than previously proposed numerical schemes. The bilinear unmixing solution is intrinsically nonunique, unless additional constraints on the model parameters are introduced. In situations where no a priori knowledge is available, the concept of an “ optimal ” solution may be used. This concept is based on the trade-off between mathematical and geological feasibility, two seemingly contradictory but equally desirable requirements of the unmixing solution.
Similar content being viewed by others
References
Aitchison, J., 1986, The statistical analysis of compositional data: Chapman & Hall, London, 416 P.
Aitchison, J., and Shen, S. M., 1984, Measurement error in compositional data: Math. Geology, v. 16, no. 6, p. 637–650.
Albaréde, F., and Provost, A., 1977, Petrological and geochemical mass-balance equations: an algorithm for least-squares fitting and general error analysis: Computers & Geosciences, v. 3, no. 3, p. 309–326.
Banks, R., 1979, The use of linear programming in the analysis of petrological mixing problems: Contributions to Mineralogy and Petrology, v. 70, no. 3, p. 237–244.
Bezdek, J. C., Ehrlich, R., and Full, W. E., 1984, FCM: the fuzzy c-means clustering algorithm: Computers & Geosciences, v. 10, no. 2-3, p. 191–203 (+ Erratum, v. 11, no. 5, p. 660).
Blatt, H., 1967, Provenance determinations and recycling of sediments: Jour. Sedimentary Petrology, v. 37, no. 4, p. 1031–1044.
Bryan, W. B., Finger, L. W., and Chayes, F., 1969, Estimating proportions in petrographie mixing equations by least squares approximation: Science, v. 163, no. 3870, p. 926–927.
Burt, C. L., 1937, Correlations between persons: British Jour. Psychology, v. 28, p. 56–96.
Butler, J. C., 1979, Effects of closure on the measures of similarity between samples: Math. Geology, v. 11, no. 4, p. 431–440.
Chatterjee, A., Sarkar, S. S., Nandy, S., and Saha, A. K., 1989, A quadratic programming approach for solving petrological mixing models: Indian Jour. Earth Sciences, v. 16, no. 2, p. 104–118.
Chayes, F., 1968, A least squares approximation for estimating the amounts of petrographic partition products: Mineralogica et Petrographica Acta, v. 14, p. 111–114.
Clarke, T. L., 1978, An oblique factor analysis solution for the analysis of mixtures: Math. Geology, v. 10, no. 2, p. 225–241.
Cohen, D., and Ward, C. R., 1991, SEDNORM-A program to calculate a normative mineralogy for sedimentary rocks based on chemical analyses: Computers & Geosciences, v. 17, no. 9, p. 1235–1253.
Cross, W., Iddings, J. P., Pirrson, L. V., and Washington, H. S., 1902, A quantitative chemicomineralogical classification and nomenclature of igneous rocks: Jour. Geology, v. 10, no. 6, p. 555–690.
Davis, J. C., 1986, Statistics and data analysis in geology (2nd ed.): John Wiley & Sons, New York, 646 p.
De Leeuw, J., and Van der Heijden, P. G. M., 1988, The analysis of time budgets with a latent time-budget model,in Diday, E., and others, eds., Data analysis and informatics 5: North Holland Publishers, Amsterdam, p. 159–166.
De Leeuw, J., Van der Heijden, P. G. M., and Verboon, P., 1990, A latent time-budget model: Statistica Neerlandica, v. 44, no. 1, p. 1–22.
Dymond, J., 1981, Geochemistry of Nazca Plate surface sediments: an evaluation of hydrothermal, biogenic, detrital, and hydrogenous sources,in Kulm, L. D., and others, eds., Nazca Plate: Crustal formation and Andean convergence: Geol. Soc. America Mem. 154, p. 133–174.
Dymond, J., Lyle, M., Finney, B., Piper, D. Z., Murphy, K., Conrad, R., and Pisias, N., 1984, Ferromanganese nodules from MANOP sites H, S, and R-Control of mineralogica] and chem- ical composition by multiple accretionary processes: Geochimica et Cosmochimica Acta, v. 48, no. 5, p. 931–949.
Ehrlich, R., and Full, W. E., 1987, Sorting out geology-Unmixing mixtures,in Size, W. B., ed., Use and abuse of statistical methods in the earth sciences: Intern. Assoc. Math. Geology, Studies in Math. Geology no. 1, Oxford Univ. Press, New York and Oxford, p. 33–46.
Full, W. E., and Ehrlich, R., 1986, Comment on “ An objective technique for determining end- member compositions and for partitioning sediments according to their sources ”: Geochimica et Cosmochimica Acta, v. 50, no. 6, p. 1303.
Full, W. E., Ehrlich, R., and Klovan, J. E., 1981, EXTENDED QMODEL-Objective definition of external endmembers in the analysis of mixtures: Math. Geology, v. 13, no. 4, p. 331–344.
Full, W. E., Ehrlich, R., and Bezdek, J. C., 1982, FUZZY QMODEL-A new approach for linear unmixing: Math. Geology, v. 14, no. 3, p. 259–270.
Garrels, R. M., and Mackenzie, F. T., 1971, Evolution of sedimentary rocks: W. W. Norton. New York, 397 p.
Gray N. H., 1973, Estimation of parameters in petrologic materials balance equations: Math. Geology, v. 5, no. 3, p. 225–236.
Hadley, G., 1961, Linear algebra: Addison-Wesley Publ. Co., Reading, Massachusetts, 290 p.
Hamann, I. M., and Herzfeld, U. C., 1991, On the effects of pre-analysis standardization: Jour. Geology, v. 99, no. 4, p. 621–631.
Harvey, P. K., and Lovell, M. A., 1992, Downhole mineralogy logs: mineral inversion methods and the problem of compositional colinearity,in Hurst, A., and others, eds., Geological ap- plications of wireline logs II: Geol. Soc. Spec. Publ. 65, p. 361–368.
Heath, G. R., and Dymond, J., 1977, Genesis and transformation of metalliferous sediments from the East Pacific Rise, Bauer Deep, and Central Basin, northwest Nazca plate: Geol. Soc. America Bull., v. 88, no. 5, p. 723–733.
Herron, M. M., 1986, Mineralogy from geochemical well logging: Clays & Clay Minerals, v. 34, no. 2, p. 204–213.
Hodgson, M., and Dudeney, A. W. L., 1984, Estimation of clay proportions in mixtures by X-ray diffraction and computerized chemical mass balance: Clays & Clay Minerals, v. 32, no. 1, p. 19–28.
Imbrie, J., 1963, Factor and vector analysis programs for analyzing geologic data: Tech. Rept. 6, ONR Task No. 389–135, Office of Naval Research, Geography Branch, 83 p.
Imbrie, J., and Poldervaart, A., 1959, Mineral compositions calculated from chemical analyses of sedimentary rocks: Jour. Sedimentary Petrology, v. 29, no. 4, p. 588–595.
Imbrie, J., and Purdy, E. G., 1962, Classification of modem Bahamian carbonate sediments,in Ham, W. E., ed., Classification of carbonate rocks-A symposium: Am. Assoc. Petroleum Geol. Mem. 1, p. 253–272.
Imbrie, J., and Van Andel, T. H., 1964, Vector analysis of heavy mineral-data: Geol. Soc. Am. Bull., v. 75, no. 11, p. 1131–1156.
Johnsson, M. J., Stallard, R. F., and Meade, R. H., 1988, First-cycle quartz arenites in the Orinoco River basin, Venezuela and Colombia: Jour. Geology, v. 96, no. 3, p. 263–277.
Jöreskog, K. G., Klovan, J. E., and Reyment, R. A., 1976, Geological factor analysis: Methods in Geomathematics no. 1, Elsevier Science Publ., Amsterdam, 178 p.
Kelsey, C. H., 1965, Calculation of the CIPW norm: Mineralogical Magazine, v. 34, p. 276–282.
Klovan, J. E., and Imbrie, J., 1971, An algorithm and FORTRAN-IV program for large-scale Q-mode factor analysis and calculation of factor scores: Math. Geology, v. 3, no. 1, p. 61–77.
Klovan, J. E., and Miesch, A. T., 1976, Extended CABFAC and QMODEL computer programs for Q-mode factor analysis of compositional data: Computers & Geosciences, v. 1, no. 3, p. 161–178.
Laube, N., Hergarten, S., and Neugebauer, H. J., 1996, MODUSCALC-A computer program to calculate a mode from a geochemical analysis: Computers & Geosciences, v. 22, no. 6, p. 631–637.
Lawson, C. L. and Hanson, R. J., 1974, Solving least squares problems: Prentice-Hall, Englewood Cliffs, New Jersey, 340 p.
Leinen, M., and Pisias, N., 1984, An objective technique for determining end-member compositions and for partitioning sediments according to their sources: Geochimica et Cosmochimica Acta, v. 48, no. 1, p. 47–62.
Leinen, M., and Pisias, N., 1986, Reply to critical comment on “ An objective technique for determining end-member compositions and for partitioning sediments according to their sources ”: Geochimica et Cosmochimica Acta, v. 50, no. 6, p. 1305–1306.
LeMaitre, R. W., 1979, A new generalised petrological mixing model: Contributions to Mineralogy and Petrology, v. 71, no. 2, p. 133–137.
LeMaitre, R. W., 1981, GENMIX-A generalized petrological mixing model program: Computers & Geosciences, v. 7, no. 3, p. 229–247.
Manson, V., and Imbrie, J., 1964, FORTRAN program for factor and vector analysis of geologic data using an IBM 7090 or 7094/1401 computer system: Kansas Geol. Survey Spec. Distrib. Publ. 13, 46 p.
Menke, W., 1984, Geophysical data analysis: discrete inverse theory: Academic Press, Orlando, 260 p.
Merodio, J. C., Spalletti, L. A., and Bertone, L. M., 1992, A FORTRAN program for the cal- culation of normative composition of clay minerals and pelitic rocks: Computers & Geosci- ences, v. 18, no. 1, p. 47–61.
Miesch, A. T., 1962, Computing mineral compositions of sedimentary rocks from chemical anal- yses: Jour. Sedimentary Petrology, v. 32, no. 2, p. 217–225.
Miesch, A. T., 1976a, Q-mode factor analysis of geochemical and petrologic data matrices with constant row sums: U.S. Geol. Survey Prof. Paper 574-G, 47 p.
Miesch, A. T., 1976b, Q-mode factor analysis of compositional data: Computers & Geosciences, v. 1, no. 3, p. 147–159.
Miesch, A. T., 1976c, Interactive computer programs for petrologic modeling with extended Q- mode factor analysis: Computers & Geosciences, v. 2, no. 4, p. 439–492.
Miesch, A. T., 1980, Scaling variables and interpretation of eigenvalues in principal component analysis of geologic data: Math. Geology, v. 12, no. 6, p. 523–538.
Miesch, A. T., 1981, Computer methods for geochemical and petrologic mixing problems,in Merriam, D. F., ed., Computer applications in the earth sciences-an update of the 70’s: Plenum Press, New York, p. 243–265.
Nicholls, G. D., 1962, A scheme for recalculating the chemical analysis of argillaceous rocks for comparative purposes: American Mineralogist, v. 47, no. 1-2, p. 34–46.
Owen, R. M., 1987, Geostatistical problems in marine placer exploration,in Teleki, P. G., and others, eds., Marine minerals: D. Reidel Publ. Co., Dordrecht, The Netherlands, p. 533–540.
Pearson, M. J., 1978, Quantitative clay mineralogical analyses from the bulk chemistry of sedi- mentary rocks: Clays & Clay Minerals, v. 26, no. 6, p. 423–433.
Perry, K. Jr., 1967, An application of linear algebra to petrologic problems: Part I. Mineral clas- sification: Geochimica et Cosmochimica Acta, v. 31, no. 6, p. 1043–1078.
Philip, G. M., and Watson, D. F., 1988, Angles measure compositional differences: Geology, v. 16, no. 11, p. 976–979.
Preisendorfer, R. W., 1988, Principal component analysis in meterology and oceanography: De- velopments in atmospheric science 17: Elsevier Science Publ., Amsterdam, 425 p.
Press, W. H., Flannery, B. P., Teukolsky, S. A., and Vetterling, W. T., 1989, Numerical recipes- The art of scientific computing (FORTRAN version): Cambridge Univ. Press, Cambridge, 702 P.
Provost, A., and Allégre, C. J., 1979, Process identification and search for optimal differentiation parameters from major element data: General presentation with emphasis on the fractional crystallisation process: Geochimica et Cosmochimica Acta, v. 43, no. 4, p. 487–501.
Reid, M. J., Gancarz, A. J., and Albee, A. L., 1973, Constrained least-squares analysis of petrologic problems with an application to lunar sample 12040: Earth and Planetary Science Letters, v. 17, no. 2, p. 433–445.
Renner, R. M., 1988, On the resolution of compositional datasets into convex combinations of extreme vectors: Tech. Rept. No. 88/02, Inst. Statistics and Operations Research, Victoria Univ. Wellington, New Zealand, 49 p.
Renner, R. M., 1991, An examination of the use of the logratio transformation for the testing of endmember hypotheses: Math. Geology, v. 23, no. 4, p. 549–563.
Renner, R. M., 1993a, The resolution of a compositional dataset into mixtures of fixed source compositions: Appl. Statist., Jour. Roy. Stat. Soc, Ser. C, v. 42, no. 4, p. 615–631.
Renner, R. M., 1993b, A constrained least-squares subroutine for adjusting negative estimated element concentrations to zero: Computers & Geosciences, v. 19, no. 9, p. 1351–1360.
Renner, R. M., 1995, The construction of extreme compositions. Math. Geology, v. 27, no. 4, p. 485–497.
Renner, R. M., 1996, An algorithm for constructing extreme compositions. Computers & Geo- sciences, v. 22, no. 1, p. 15–25.
Renner, R. M., Glasby, G. P., Manheim, F. T., and Lane-Bostwick, C. M., 1989, A partitioning process for geochemical datasets,in Agterberg, F. P., and Bonham-Carter, G. F., eds., Sta- tistical applications in the earth sciences: Geol. Survey Canada Paper 89–9, p. 319–328.
Ripley, B. D., 1990, Unmixing finite mixtures: unpubl. rept. BP Research, Sunbury, 16 p.
Rock, N. M. S., 1987, ROBUST: an interactive FORTRAN 77 package for exploratory data analysis via robust estimates of location and scale, tests for normality and outlier assessment: Computers & Geosciences, v. 13, no. 5, p. 463–494.
Rock, N. M. S., 1988, Numerical geology: a source guide, glossary and selective bibliography to geological uses of computers and statistics: Lecture notes in earth sciences 18, Springer-Verlag, Berlin, 427 p.
Russell, J. K., 1986, A FORTRAN 77 computer program for the least squares analysis of chemical data in Pearce variation diagrams: Computers & Geosciences, v. 12, no. 3, p. 327–338.
Stornier, J. C., and Nicholls, J., 1978, XLFRAC-A program for the interactive testing of magmatic differentiation models: Computers & Geosciences, v. 4, no. 2, p. 143–159.
Trochimczyk, J., and Chayes, F., 1977, Sampling variation of principal components: Math. Ge- ology, v. 9, no. 5, p. 497–506.
Van der Heijden, P. G. M., 1994, End-member analysis and latent budget analysis (letter to the editor): Appl. Statist., Jour. Roy. Stat. Soc, Ser. C., v. 43, no. 3, p. 527–528.
Van der Heijden, P. G. M., Mooijaart, A., and De Leeuw, J., 1992, Constrained latent budget analysis,in Clogg, C. C., ed., Sociological methodology 1992, vol. 22, Basil Blackwell, Cambridge, p. 279–320.
Weltje, G. J., 1994, Provenance and dispersal of sand-sized sediments: reconstruction of dispersal patterns and sources of sand-sized sediments by means of inverse modelling techniques: unpubl. doctoral dissertation, Faculty of Earth Sciences, Utrecht University, Geologica Ultraiectina 121, 208 p.
Weltje, G. J., 1995, Unravelling mixed provenance of coastal sands: the Po delta and adjacent beaches of the northern Adriatic Sea as a test case,in Oti, M. N., and Postma, G., eds., Geology of deltas: Balkema, Rotterdam, p. 181–202.
Weltje, G. J., Van Ansenwoude, S. O. K. J., and De Boer, P. L., 1996, High-frequency detrital signals in Eocene fan-delta sandstones of mixed parentage (south-central Pyrenees, Spain): a reconstruction of chemical weathering in transit: Jour. Sedimentary Research, v. 66, no. 1, p. 119–131.
Williams, D. F., Lerche, I., and Full, W. E., 1988, Isotope chronostratigraphy-theory and meth- ods: Academic Press Geology series, Academic Press, San Diego, 345 p.
Woronow, A., 1991a, Endmember unmixing of compositional data: Geochimica et Cosmochimica Acta, v. 55, no. 8, p. 2351–2353.
Woronow, A., 1991b, Analysis of mixtures: unpubl. manuscript, 32 p.
Wright, T. L., and Doherty, P. C., 1970, A linear programming and least squares computer method for solving petrologic mixing problems: Geol. Soc. America Bull., v. 81, no. 7, p. 1995–2008.
Zhou, D., 1987, Robust statistics and geochemical data analysis: Math. Geology, v. 19, no. 3, p. 207–218.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Weltje, G.J. End-member modeling of compositional data: Numerical-statistical algorithms for solving the explicit mixing problem. Math Geol 29, 503–549 (1997). https://doi.org/10.1007/BF02775085
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02775085