Vol. 30, issue 07, article # 7

Abstract:

Application of bionic methods, such as neural networks and genetic algorithms, to solution of the inverse problem of CO₂ relative concentration determination from stratospheric airship signals is considered. The backscattered and reflected from the surface signals at wavelengths near 1572 nm are used for the measurements. The errors of the standard DIAL approach and DIAL-IDPA technology are compared. For the lidar with specification described, the mean error of algorithms developed is lower than 1 ppm. The genetic algorithm used is based on the minimization of the difference between the model signal and the signal received. Application of neural networks is based on their training on the examples of the simulated signals (reflected and scattered) and the altitude distribution of the gas concentration.

Keywords:

atmosphere, lidar, carbon dioxide, greenhouse gas, bionic method, neural net, genetic algorithm

References:

1. Dufour E. and Bréon F.-M. Spaceborne Estimate of Atmospheric CO₂ Column by Use of the Differential Absorption Method: Error Analysis // Appl. Opt. 2003. V. 42, N 18. P. 3595–3609.
2. Ehret G., Kiemle C., Wirth M., Amediek A. Space-borne remote sensing of CO₂, CH₄, and N₂O by integrated path absorption lidar: А sensitivity analysis // Appl. Phys. B. 2008. V. 90. P. 593–608.
3. Бабченко С.В., Матвиенко Г.Г., Суханов А.Я. Оценки возможностей зондирования парниковых газов CH₄ и CO₂ над подстилающей поверхностью IPDA лидаром космического базирования // Оптика атмосф. и океана. 2015. Т. 28, № 1. С. 37–45; Babchenko S.V., Matvienko G.G., Sukhanov A.Ya. Assessing the possibilities of sensing CH₄ and CO₂ greenhouse gases above the underlying surface with satellite-based IDPA lidar // Atmos. Ocean. Opt. 2015. V. 28, N 3. P. 245–253.
4. Miller S.H., Fesen R., Hillenbrand L., Rhodes J., Baird G., Blake G., Booth J., Carlile D.E., Duren R., Edworthy F.G., Freeze B., Friedl R.R., Goldsmith P.F., Hall J.L., Hoffman S.E., Hovarter S.E., Jensen-Clem R.M., Jones R.M., Kauffmann J., Kiessling A., King O.G., Konidaris N., Lachenmeier T.L., Lord S.D., Neu J., Quetin G.R., Ram A., Sander S., Simard M., Smith M., Smith S., Smoot S., Susca S., Swann A., Young E.F., Zambrano T. Airships: A new horizon for science. Keck Institute for Space Studies, California Institute of Technology, Jet Propulsion Laboratory. 2014. 56 p.
5. Prus Ju.V., Bituev B.Zh., Shapovalov V.M. Nekotorye aspekty ispol'zovanija stratosfernyh dirizhablej v interesah obespechenija bezopasnosti territorii // Internet-zhurnal «Tehnologii tehnosfernoj bezopasnosti» Issue 1 (29). 2010. 10 p. (http://ipb.mos.ru/ttb)
6. Problemnye voprosy sozdanija vysotnyh ajerostaticheskih platform kak perspektivnogo sredstva teleradiokommunikacionnogo i monitoringovogo obespechenija / Pod red. S.L. Chernysheva // Tr. CAGI. 2009. Issue 2682. 58 p.
7. Menzies R.T., Tratt D.M. Differential laser absorption spectrometry for global profiling of tropospheric carbon dioxide: Selection of optimum sounding frequencies for high precision measurements // Appl. Opt. 2003. V. 42, iss. 33. P. 6569–6577.
8. Spiers G.D., Menzies R.T., Phillips M., Geier S., Poberezhskiy I., Meras P. Recent results and progress on the development of a Laser Absorption Spectrometer for CO₂ sink and source detection // Proc. 14th Coherent Laser Radar Conf. Snowmass, Colorado, 2007. P. 118–121.
9. Dobbs M.E., Dobler J., Braun M., McGrefor D., Over-beck J., Moore III B., Browell E.V., Zaccheo T.S. A Modulated CW Fiber Laser-Lidar Suite for the ASCENDS Mission // Proc. 24th Int. Laser Radar Conf. Boulder, 2008. P. 24–29.
10. Dobbs M.E., Sharp W., Browell E.V., Zaccheo T.S., Moore III B. A Sinusoidal Modulated CW Integrated Path Differential Absorption Lidar for Mapping Sources and Sinks of Carbon Dioxide from Space // Proc. 14th Coherent Laser Radar Conf. Snowmass, Colorado, 2007. P. 124–127.
11. Dobler J.T., Harrison F.W., Browell E.V., Lin B., McGre-gor D., Kooi S., Choi Y., Ismail S. Atmospheric CO₂ column measurements with an airborne intensity-modulated continuous wave 1.57 μm fiber laser lidar // Appl. Opt. 2013. V. 52, N 12. P. 2874–2892. DOI: 10.1364/AO.52.002874.
12. Dobler J., Dobbs M., Erxleben W., McGregor D., Moore III B., Harrison W., Zaccheo T.S., Hager S. Pressure Retrieval using CW Laser Absorption Spectroscopy of an O₂ Line near 1271 nm with a Spectrally Broad Laser Source // Proc. 24th International Laser Radar Conf. Boulder, 2008. P. 49–52.
13. Arshinov M.Ju., Belan B.D., Davydov D.K., Krekov G.M., Fofonov A.V., Babchenko S.V., Inoue G., Machida T., Maksutov Sh., Sasakawa M., Shimoyama K. Dinamika vertikal'nogo raspredelenie parnikovyh gazov v atmosfere // Optika atmosf. i okeana. 2012. V. 25, N 12. P. 1051–1061.
14. Labitzke K., Barnett J.J., Edwards B. (eds.). Handbook MAP 16. SCOSTEP. 1985. 320 p.
15. Hedin A.E. Extension of the MSIS Thermospheric Model into the Middle and Lower Atmosphere // J. Geophys. Res. 1991. V. 96, iss. A2. P. 1159–1172.
16. Komarov V.S. Statisticheskie modeli temperatury i gazovyh komponent atmosfery. L.: Gidrometeoizdat, 1986. 264 p.
17. Krekov G.M., Krekova M.M., Suhanov A.Ja. Ocenka jeffektivnosti ispol'zovanija perspektivnyh lidarov belogo sveta dlja zondirovanija mikrofizicheskih parametrov sloistoj oblachnosti. 3. Reshenie obratnoj zadachi // Optika atmosf. i okeana. 2009. V. 22, N 9. P. 862–872.
18. Krekov G.M., Suhanov A.Ja. Uluchshennyj geneticheskij algoritm mnogovolnovogo lidarnogo zondirovanija atmosfernogo ajerozolja // Optika atmosf. i okeana. 2011. V. 24, N 9. P. 754–758; Krekov G.M., Sukhanov A.Ya. Improved genetic algorithm for multiwave lidar sensing of atmospheric aerosol // Atmos. Ocean. Opt. 2012. V. 25, N 2. P. 130–134.
19. Holland J.H. Adaptation in natural and artificial systems. University of Michigan Press, Ann Arbor, 1975.  183 p.
20. Banah V.A., Belov V.V., Zemljanov A.A., Krekov G.M., Lukin V.P., Matvienko G.G., Nosov V.V., Suhanov A.Ja., Falic A.V. Rasprostranenie opticheskih voln v neodnorodnyh, sluchajnyh, nelinejnyh sredah. Tomsk: Izd-vo IOA SO RAN, 2012. 402 p.
21. Bobrovnikov S.M., Matvienko G.G., Romanovskij O.A., Serikov I.B., Suhanov A.Ja. Lidarnyj spektroskopicheskij gazoanaliz atmosfery. Tomsk: Izd-vo IOA SO RAN, 2014. 510 p.
22. Apeksimov D.V., Bagaev S.N., Gejnc Ju.Je., Zemljanov A.A., Kabanov A.M., Kirpichnikov A.V., Kistenev Ju.V., Krekov G.M., Krekova M.M., Matvienko G.G., Oshlakov V.K., Panina E.K., Petrov V.V., Pestrjakov E.V., Ponomarev Ju.N., Suhanov A.Ja., Tihomirov B.A., Trunov V.I., Uogintas S.R., Frolov S.A., Hudorozhkov D.G. Femtosekundnaja atmosfernaja optika / Pod obshh. red. S.N. Bagaeva, G.G. Matvienko. Novosibirsk: Izd-vo SO RAN, 2010. 240 p.
23. Balin Ju.S., Borovoj A.G., Burlakov V.D., Dolgij S.I., Klemasheva M.G., Konoshonkin A.V., Kohanenko G.P., Kustova N.V., Marichev V.N., Matvienko G.G., Nevzorov A.A., Nevzorov A.V., Penner I.Je., Romanovskij O.A., Samojlova S.V., Suhanov A.Ja., Harchenko O.V., Shishko V.A. Lidarnyj monitoring oblachnyh i ajerozol'nyh polej, malyh gazovyh sostavljajushhih i meteoparametrov atmosfery / Pod red. G.G. Matvienko. Tomsk: Izd-vo IOA SO RAN, 2015. 450 p.
24. Suhanov A.Ja., Krekov G.M. Raspoznavanie spektrov fluorescencii bakterij i poliaromaticheskih uglevodorodov // MMRO-15. Petrozavodsk, Respublika Karelija, 11–17 september 2011. 4 p.
25. Suhanov A.Ja. Algoritmy, metody i kompleksy programm dlja reshenija zadach lidarnogo zondirovanija atmosfery: Disc. … kand. tehn. nauk. Tomsk, 2006. 151 p.
26. Rumelhart D.E., Hinton G.E., Williams R.J. Learning representations by back-propagating errors // Nature. (Gr. Brit.). 1986. V. 323. P. 533–536.
27. Rumelhart D.E., Hinton G.E., Williams R.J. Learning internal representations by error propagation / D.E. Rumelhart, J.L. McClelland, (eds.) Parallel Distributed Processing: Explorations in the Microstructure of Cognition. V. 1. Foundations MIT Press, Cambridge, MA, 1986. P. 318–362.
28. Suhanov A.Ja., Petrov I.V. Sravnenie algoritmov obuchenija nejronnoj seti dlja reshenija zadachi identifikacii bioajerozolej // Ajerozoli Sibiri. XXIII Rabochaja gruppa: 29 november – 2 december 2016 year Tomsk: Izd-vo IOA SO RAN. Тез. докл. P. 84. http:// symp.iao.ru/files/symp/sa/23/ru/abstr_8506.pdf
29. Glorot X., Bengio Y. Understanding the difficulty of training deep feedforward neural networks // Proc. Mach. Learn. Res. 2010. V. 9. P. 249–256.
30. Pascanu R., Mikolov T., Bengio Y. On the difficulty of training Recurrent Neural Networks // arXiv preprint arXiv:1211.5063 [http://arxiv.org/abs/1211.5063v2]. 2012. 11 p.