F.C. de Meneses, E.H. Shiguemori, P. Muralikrishna and B.R. Clemesha
ABSTRACT The inverse problem to retrieve useful airglow volume emission rate profiles from rocket-borne photometer measurements has been solved by adopting the well-characterized spectral photometric methods. An alternative recovery method based on artificial neural network (ANN) is presented. A multilayer perceptron neural network was trained with available experimental and synthetic data. Integrated emissions profiles measured by a rocket experiment were taken as the input data. From the results obtained in this work, it may be concluded that the ANN technique is a convenient tool to recover volume emission rate profiles.
applied computing in space and environmental sciences, neural networks, inverse problem, airglow, rocket.
 HARGREAVES JK. 1992. The Solar-Terrestrial environment, Cambridge University Press.
 GOMBOSI TI. 2004. Physics of the space environment, Cambridge University Press.
 CHAMBERLAIN JW. 1961. Physics of the Aurora and Airglow, Academic Press.
 HAIDER SA, KIM J, NAGY AF, KELLER CN, VERIGIN MI, GRINGAUZ KI, SHUTTE NM, SZEGO K & KIRALY P. 1992. Calculated ionization rates, ion densities, and airglow emission rates due to precipitating electrons in the nightside ionosphere of Mars. Journal of Geophysical Research, 97: 10637-10641.
 SLANGER TG, COSBY PC, HUESTIS DL & BIDA TA. 2001. Discovery of the Atomic Oxygen Green Line in the Venus Night Airglow. Science 291, 5503: 463-465.
 KRASNOPOLSKY VA. 1986. Oxygen emissions in the night airglow of the Earth, Venus and Mars. Planetary and Space Science, 34(6): 511-518.
 BURITI RA, TAKAHASHI H & GOBBI D. 2001. First results from mesospheric airglow observations at 7.5?S. Revista Brasileira de Geofísica, 19(2): 169-176.
 RAJESH PK, LIU JY, SINHA HSS, BANERJEE SB, MISRA RN, DUTT N & DADHANIA MB. 2007. Observations of plasma depletions in 557.7-nm images over Kavalur. Journal of Geophysical Research, 112: A07307.
 GOBBI D, TAKAHASHI H, CLEMESHA BR & BATISTA PP. 1992. Equatorial atomic oxygen profiles derived from rocket observations of OI 557.7 nm airglow emission. Planetary and Space Science, 40: 775-781.
 MELO STELLA ML, TAKAHASHI H, CLEMESHA BR, BATISTA PP & SIMONICH DM. 1996. Atomic oxygen concentrations from rocket airglow observations in the equatorial region. Journal of Atmospheric and Terrestrial Physics, 58(16): 1935-1942.
 GAO H, XU J & YUAN W. 2005. A Method of Inversing the Peak Density of Atomic Oxygen Vertical Distribution in the MLT Region From the OI (557.7nm) Night Airglow Intensity. Chinese Journal of Space Science, 25: 5.
 SHEPHERD G. 2002. Spectral imaging of the atmosphere, Academic Press.
 TAKAHASHI H, CLEMESHA BR, SIMONICH DM, MELO STELLA ML, ERAS A, STEGMAN J & WITT G. 1996. Equatorial airglow rocket measurement: MULTIFOT 92 data base. Journal of Atmospheric and Terrestrial Physics, 58(16): 1943-1961.
 MURTAGH DP, GREER RGH, McDADE IC, LLEWELLYN EJ & BANTLE M. 1984. Representative volume emission profiles from rocket photometer data. Annales Geophysicae, 2: 467-474.
 SISKIND DE & SHARP WE. 1991. A comparison of measurements of the oxygen nightglow and atomic oxygen in the lower thermosphere. Planetary and Space Science, 39(4): 627-639.
 CLEMESHA BR & TAKAHASHI H. 1996. Rocket-borne measurements of horizontal structure in the OH(8,3) and Na D airglow emissions. Advances in Space Research, 17(11): 81-84.
 ALTINAY O, TULUNAY E, TULUNAY Y. 1997. Forecasting of ionospheric frequency using neural networks. Geophysical Research Letters, 24: 1467-1470.
 WINTOFT P & CANDER LJR. 1999. Short-term prediction of fof2 using time-delay neural network. Physics and Chemistry of the Earth, Part C: Solar, Terrestrial & Planetary Science, 24(4): 343- 347.
 McKINNELL LA & POOLE WV. 2000. The development of a neural network based short term foF2 forecast program. Physics and Chemistry of the Earth, Part C: Solar, Terrestrial & Planetary Science, 25(4): 287-290.
 ZENG Z, HU X & ZHANG X. 2002. Applying artificial neural network to the short-term prediction of electron density structure using GPS occultation data. Geophysical Research Letters, 29(9): 35-1.
 NAKAMURA MI, MARUYAMA T & SHIDAMA Y. 2007. Using a neural network to make operational forecasts of ionospheric variations and storms at Kokubunji, Japan. Earth, Planets and Space, 59: 1231-1239.
 McKINNELL LA. 2002. A neural network based ionospheric model for the bottomside electron density profile over Grahamstown, South Africa, PhD. Thesis, Rhodes University, Grahamstown.
 McKINNELL LA & FRIEDRICH M. 2007. A neural network-based ionospheric model for the auroral zone. Journal of Atmospheric and Solar-Terrestrial Physics, 69(12): 1459-1470.
 VANDEGRIFF J, WAGSTAFF K, HO G & PLAUGER J. 2005. Forecasting space weather: Predicting interplanetary shocks using neural networks. Advances in Space Research, 36: 2323-2327.
 JANKOVIČOVÁ, D.; DOLINSKÝ, P.; VALACH, F.; VÖRÖS, Z. 2002. Neural network-based nonlinear prediction of magnetic storms. Journal of Atmospheric and Solar-Terrestrial Physics, 64(5-6): 651-656.
 OZC ELIK R, DIAMANTOPOULOU MJ, BROOKS JR & WIANT HV Jr. 2010. Estimating tree bole volume using artificial neural network models for four species in Turkey. Journal of environmental management, 91(3): 742-53.
 YANG Y, TAI NL & YU WY. 2005. ART artificial neural networks based adaptive phase selector. Electric Power Systems Research, 76: 115-120.
 ZHANG GP. 2010. Avoiding pitfalls in neural network research. IEEE Transaction on Systems, Man, and Cybernetics-Part C: Applications and Reviews, 37 i1. 3-16.
 SHIGUEMORI EH, CHIWIACOWSKY LD, DE CAMPOS VELHO HF & DA SILVA JDS. 2005. An inverse vibration problem solved by an artificial neural network. TEMA: Tendências em Matemática Aplicada e Computacional, 6(1): 163-175.
 HAYKIN, S. 1999. Neural Networks: A Comprehensive Foundation. Prentice Hall.
 JIMENEZ C, ERIKSSON P, MURTAGH D. 2003. First inversions of observed submillimeter limb sounding radiances by neural networks. Journal of Geophysical Research, 108(D24): 4791.