Michael Turmon

Biographical Sketch

Michael's research interests include pattern recognition, clustering, object tracking, and maximum-likelihood estimation, with applications to object time series, solar image analysis, and robotic navigation. His method and software for identifying and tracking solar active regions is part for several space weather data products for Solar Dynamics Observatory, and methods he developed for terrain classification were used in field tests during DARPA Learning Applied to Ground Robotics program.

Michael graduated in 1987 from Washington University in St. Louis, receiving bachelor's degrees in Computer Science and in Electrical Engineering. He went on to get a Ph.D. in Electrical Engineering from Cornell University in 1995, with an emphasis on probabilistic theories of learning in neural networks. He came to JPL thereafter, joining the Machine Learning group and later the Science Data Understanding group. He received the NASA Exceptional Achievement Medal and the Presidential Early Career Award for Scientists and Engineers (PECASE) in 2000.

Projects

• Solar feature identification
• Learning for robotic navigation

Selected Publications

Hoeksema, J. T., Liu, Y., Hayashi, K., Sun, X., Schou, J., Couvidat, S., Norton, A., Bobra, M., Centeno, R., Leka, K. D., Barnes, G., and Turmon, M. (2014). “The HMI Vector Magnetic Field Pipeline: Overview and Performance,” Solar Physics, 289, pp. 3483-3530. Cross-posted to ArXiv. Download.

Turmon, M., Hoeksema, J. T., and Bobra, M. (2014). “Tracked Active Region Patches for MDI and HMI,” American Astronomical Society Meeting Abstracts #224, vol. 224, pp. #123.52.

Bobra, M. G., Sun, X., Hoeksema, J. T., Turmon, M., Liu, Y., Hayashi, K., Barnes, G., and Leka, K. D. (2014). “The HMI Vector Magnetic Field Pipeline: SHARPs - Space-Weather HMI Active Region Patches,” Solar Physics, 289, pp. 3549-3578. Cross-posted to ArXiv. Download.

Djorgovski, S. G., Mahabal, A. A., Donalek, C., Graham, M. J., Drake, A. J., Moghaddam, B., and Turmon, M. (2012). “Flashes in a Star Stream: Automated Classification of Astronomical Transient Events,” IEEE 8th International Conference on e-Science. Cross-posted to ArXiv. Download.

M. Turmon, H. P. Jones, O. Malanushenko, and J. Pap (2010). “Statistical Feature Recognition for Multidimensional Solar Imagery,” Solar Physics, 262(2), pp. 277–298. Download (CL 10-0771).

Rankin, A., Bajracharya, M., Huertas, A., Howard, A., Moghaddam, B., Brennan, S., Ansar, A., Tang, B., Turmon, M., and Matthies, L. (2010). “Stereo-vision-based perception capabilities developed during the Robotics Collaborative Technology Alliances program,” SPIE Conference Series, vol. 7692, pp. 76920C-76920C-15. Download.

M. Bajracharya, A. Howard and L. Matthies, B. Tang, and M. Turmon (2009). “Autonomous off-road navigation with end-to-end learning for the LAGR program,” Journal of Field Robotics, 26(1), pp. 3–25.

R. Granat, K. L. Wagstaff, B. Bornstein, B. Tang, and M. Turmon (2009). “Simulating and Detecting Radiation-Induced Errors for Onboard Machine Learning,” Proc. Third IEEE International Conference on Space Mission Challenges for Information Technology (SMC-IT), July 2009, pp. 125-131. Download (CL #09-1474).

M. Sarrel and M. Turmon (2008). “Improved Estimates of Spitzer Space Telescope Data Volumes with Error Bars,” AIAA SPACE 2008. Download (CL 08-0637).

H. P. Jones, G. A. Chapman, K. L. Harvey, J. M. Pap, D. G. Preminger, M. J. Turmon, and S. R. Walton (2008). “A Comparison of feature classification methods for modeling solar irradiance variation,” Solar Physics, 248(2), pp. 323-337.

A. Mahabal, S. G. Djorgovski, M. Turmon, J. Jewell and R. Williams, A. Drake, M. G. Graham, C. Donalek, and E. Glikmanand and the PalomarQUEST team (2008). “Automated probabilistic classification of transients and variables,” Astron. Notes, 329(3), pp. 288-291.

T. M. Chin, M. Turmon, J. Jewell, and M. Ghil (2007). “An Ensemble-Based Smoother with Retrospectively Updated Weights for Highly Nonlinear Systems,” Monthly Weather Review, 135(1), pp. 186-202. Download.

A. Howard, M. Turmon, L. Matthies, B. Tang, A. Angelova, and E. Mjolsness (2006). “Towards Learned Traversability for Robot Navigation: From Underfoot to the Far Field,” Journal of Field Robotics, 23(11/12), pp. 1005-1017.

J. Pap, I. Ermolli, F. Gyorgi, and M. Turmon (2004). “Study of Solar Magnetic Feature Properties and Irradiance Variations,” 35th COSPAR Scientific Assembly.

T. M. Chin, J. B. Jewell, and M. Turmon (2004). “Phase Changes and State Estimation for Non-linear Systems,” Eos Trans. AGU, 85(47), Fall Meet. Suppl.. Abstract NG31B-0877.

M. Turmon (2004). “Symmetric Normal Mixtures,” Compstat 2004-Proceedings in Computational Statistics, pp. 1909-16, Physica-Verlag. Download (CL 04-1276).

M. Turmon, R. Granat, D. Katz, and J. Z. Lou (2003). “Tests and tolerances for High-Performance Software-Implemented Fault Detection,” IEEE Trans. Computers, pp. 579–591. Download (CL 02-0735).

H.P. Jones, K.L. Harvey, J.M. Pap and D.G. Preminger, M. Turmon, and S.R. Walton (2002). “A comparison of feature classification methods for modeling solar irradiance variation,” 34th COSPAR Scientific Assembly.

J. Pap, H. Jones, M. Turmon, and L. Floyd (2002). “Study of the SOHO/VIRGO Irradiance Variations Using MDI and Kitt Peak Images,” Proc. SOHO-11 Workshop. ESA SP-508.

J. M. Pap, M. Turmon, L. Floyd, C. Frolich , and Ch. Wehrli (2002). “Total solar and spectral irradiance variations in solar cycles 21 to 23,” Adv. Space Res., 29, pp. 1923-1932.

M. Turmon, J. Pap, and S. Mukhtar (2002). “Statistical Pattern Recognition for Labeling Solar Active Regions: Application to SoHO/MDI Imagery,” Astrophysical Journal, 568(1), pp. 396-407. Download (CL 01-2847).

E. Mjolsness, W. Fink, M. Turmon (2001). “Stochastic Parameterized Grammars for Bayesian Model Composition,” Interface-2001, Costa Mesa, CA.

M. Turmon (2001). “Mixture models for labeling scientific imagery,” Mixtures 2001: Recent Developments in Mixture Modeling, Hamburg.

M. Turmon, R. Granat, and D. S. Katz (2000). “Software-Implemented Fault Detection for High-Performance Space Applications,” Proc. Intl. Conf. Dependable Systems and Networks, pp. 107–116. Download (CL 99-2014).

M. Turmon and R. Granat (2000). “Algorithm-Based Fault Tolerance for Spaceborne Computing: Basis and Implementations,” Proc. IEEE Aerospace Conference, pp. 411-420. Download (CL 00-0901).

M. Turmon, E. Mjolsness, V. Gluzman, and L. Ramsey (1999). “A Language for Probabilistic Modeling of Scientific Data,” Proc. Second Conf. Highly Structured Stochastic Systems, pp. 298–300, Pavia, Italy. Download (CL 99-1413, 00-1004).

M. Turmon and S. Mukhtar (1998). “Representing Solar Active Regions with Triangulations,” Proc. Compstat-98, pp. 473-478, Bristol, UK. Download (CL 98-0761).

M. Turmon (1998). “Book review of <it>Machine Learning and Statistics</it>,” Jour. American Statistical Association, 93(442), pp. 833-834.

M. Turmon, J. M. Pap, and S. Mukhtar (1998). “Automatically finding solar active regions using SoHO/MDI photograms and magnetograms,” Proc. SoHO 6/GONG '98 Workshop on Structure and Dynamics of the Sun, pp. 979-984.

M. Turmon (1997). “Identification of Solar Features via Markov Random Fields,” Proc. Second Conf. International Assoc. for Statistical Computing, pp. 194–200.

M. Turmon and J. Pap (1997). “Segmenting Chromospheric Images with Markov Random Fields,” Statistical Challenges in Modern Astronomy II, ed. G. Babu and E. Feigelson, pp. 408–411, Springer.

M. Turmon, S. Mukhtar, and J. Pap (1997). “Bayesian Inference for Identifying Solar Active Regions,” Proc. Third Conf. on Knowledge Discovery and Data Mining, ed. D. Heckerman, H. Mannila, D. Pregibon, and R. Uthurusamy, pp. 267-270, MIT Press. Download (CL 97-0755).

M. Turmon and S. Mukhtar (1997). “Recognizing Chromospheric Objects via Markov Chain Monte Carlo,” Proc. IEEE Intl. Conf. Image Processing, vol. III, pp. 320–323. Download (CL 97-1147).

J. Pap, M. Turmon, S. Mukhtar, R. Bogart , R. Ulrich, C. Frolich, and Ch. Wehrli (1997). “Automated Recognition and Characterization of Solar Active Regions based on the SOHO/MDI Images,” Proc. 31st ESLAB Symposium, pp. 477-482, Nordwijk, Netherlands.

M. Turmon (1995). Assessing Generalization of Feedforward Neural Networks, PhD thesis, Cornell.

M. Turmon and T. L. Fine (1995). “Empirically Estimating Generalization Ability of Feedforward Neural Networks,” World Conference on Neural Networks, pp. 600-605. Invited paper.

M. Turmon and T. L. Fine (1995). “Sample Size Requirements for Feedforward Neural Networks,” Neural Information Processing Systems 7, ed. G. , pp. 327-334, Morgan-Kauffman.

M. Turmon and T. L. Fine (1995). “Assessing Generalization of Feedforward Neural Networks,” IEEE 1995 International Symposium on Information Theory, p. 168. Long paper.

M. J. Turmon and M. I. Miller (1994). “Maximum-Likelihood estimation of constrained means and Toeplitz covariances with application to direction-finding,” IEEE Trans. on Signal Processing, 42(5), pp. 1074–1086.

M. Turmon and T. L. Fine (1993). “Sample Size Requirements of Feedforward Neural Network Classifiers,” IEEE 1993 International Symposium on Information Theory, p. 432.

M. J. Turmon (1990). “Maximum-likelihood estimation of constrained means and Toeplitz covariances with application to direction-finding,” M.S. thesis, Washington University, St. Louis.

M. J. Turmon, M. I. Miller, D. L. Snyder, and J. A. O'Sullivan (1988). “Performance Evaluation of Maximum-Likelihood Toeplitz Covariance Estimates Generated Using the Expectation Maximization Algorithm,” Proc. Fourth ASSP Workshop on Spectrum Estimation and Modeling, pp. 182-185.

M. J. Turmon and M. I. Miller (1987). “Simulation results for maximum-likelihood estimation of Toeplitz constrained covariances,” Proc. Twenty-first Annual Conference on Information Sciences and Systems.

M. I. Miller, D. L. Snyder, and M. J. Turmon (1986). “Iterative maximum-likelihood estimation of Toeplitz-constrained covariances,” Proc. Twenty-fourth Annual Allerton Conference on Communication, Control and Computing, pp. 111-112.

M. I. Miller, D. L. Snyder, and M. J. Turmon (1986). “The application of maximum-entropy and maximum-likelihood for spectral estimation,” IEEE 1986 International Symposium on Information Theory.