Russian Federation
The aim of this study was to explore the feasibility of using artificial neural networks to model forest inventory parameters for pine and larch stands. These networks are capable of integrating experimental research, providing a sufficiently high modeling accuracy, and possessing reliable predictive power. A drawback of existing information modeling systems for forest growth and productivity dynamics in the Russian Federation is that they are based on regression models, which have insufficient accuracy and predictive power. Published data on forest inventory parameters for pine and larch stands were used for neural network processing. Neural network modeling was implemented using the open-source TensorFlow library in Python, version 3.11.7.
taxation characteristics, pine and larch stands, artificial neural networks
1. Arapov D.V., Kuricyn V.A., Skorobogatov S.A. Avtomatizirovannaya mobil'naya sistema prinyatiya resheniy dlya ispol'zovaniya v special'noy medicine // Modelirovanie sistem i processov. 2024. T.17. № 3. S. 7-16.
2. Bogachev A.V. Lesotaksacionnye issledovaniya. M.: VNIILM, 2007. 344 s.
3. Grachev A.V. Primenenie neyrosetevyh tehnologiy dlya prognozirovaniya sostoyaniya raboty ob'ektov predpriyatiy APK // Tehnika i tehnologiya pischevyh proizvodstv. 2023. T.53. №4. S. 816-823.
4. Dubenok N.N., Lebedev A.V., Kuz'michev V.V. Dinamicheskaya model' izrezhivaniya kul'tur sosny // Izvestiya Sankt-Peterburgskoy lesotehnicheskoy akademii. 2022. Vyp. 239. S. 6–21.
5. Dubenok N.N., Kuz'michev V.V., Lebedev A.V. Nelineynaya model' smeshannyh effektov zavisimosti vysoty ot diametra derev'ev v drevostoyah listvennicy // Trudy Sankt-Peterburgskogo nauchno-issledovatel'skogo instituta lesnogo hozyaystva. 2021. № 4. S. 42-56.
6. Dubenok N. N., Lebedev A.V., Kuz'michev V.V. Ocenka statisticheskih modeley raspredeleniya derev'ev po diametru v kul'turah sosny // Lesohozyaystvennaya informaciya. 2022. № 1. S. 50-61
7. Kireeva K.A., Korobova L.A., Arapov D.V. Razrabotka iskusstvennoy neyronnoy seti dlya klassifikacii EKG // Modelirovanie sistem i processov. 2023. T.16. №3. S. 42 – 54.
8. Lebedev A.V., Kuz'michev V.V. Taksacionnye pokazateli sosnovyh drevostoev po dannym dolgovremennyh nablyudeniy // Sibirskiy lesnoy zhurnal. 2023. № 2. S. 3–16.
9. Mel'nik P.G., Voronin F.N., Merzlenko M.D. Lesokul'turno-lesovodstvennoe znachenie parametrov razmescheniya eli pri posadke v nacional'nom parke «Losinyy ostrov» // Vestnik Altayskogo gosudarstvennogo agrarnogo universiteta. 2014. №1. S. 52–58.
10. Merzlenko M.D. Obosnovanie teorii volnoobraznogo rosta hvoynyh lesnyh kul'tur // Lesnoy vestnik. 2021. T. 25, №2. S. 3–9.
11. Sokolov, A.I., Haritonov V.A., Pekkoev A.N., Krivenko T.I. Sohrannost' i rost kul'tur sosny, sozdannyh posadochnym materialom s zakrytoy kornevoy sistemoy v usloviyah Karelii // Izvestiya vuzov. Lesnoy zhurnal. 2015. №6. S. 46–56.
12. Shvidenko A.Z., Schepaschenko D.G., Nil'sson S, Buluy Yu.I. Tablicy i modeli hoda rosta i produktivnosti nasazhdeniy osnovnyh lesoobrazuyuschih porod Severnoy Evrazii: normativnye spravochnye materialy: 2-e izd. pererab. i dopoln. M.: Rosleshoz. 2008. 886 s.
13. Shvidenko A.Z., Schepaschenko D.G., Nil'sson S, Buluy Yu.I. Sistema modeley rosta i dinamiki produktivnosti lesov Rossii (tablicy i modeli bioproduktivnosti) // Lesnoe hozyaystvo. 2004. № 2. S. 40–44.
14. Shvidenko A.Z., Schepaschenko D.G., Nil'sson S, Buluy Yu.I. Sistema modeley rosta i dinamiki produktivnosti lesov Rossii (tablicy hoda rosta) // Lesnoe hozyaystvo. 2003. № 6. S. 34–38.
15. Shutov I.V., Ivanov A.M., Antonov O.I., Vlasov R.V., Sergienko V.G., Belenec Yu.E., Smirnov E.G., Vyrodova S.A., Stepanenko S.M. Rost sosny v ryadovyh kul'turah pri zadannyh variantah gustoty i raznyh shirine mezhduryadiy i shage posadki // Trudy Sankt-Peterburgskogo NII lesnogo hozyaystva. 2014. № 1. S. 19–29.
16. Arapov D.V., Kuritsyn V.A., Petrov S.M., Podgornova N.M. Simulation of the rate of dissolution of sucrose crystals. Journal of Food Engineering. 2022. 318: 110887. – URL: https://doi.org/10.1016/j.jfoodeng.2021.110887.
17. Elfwing S., Uchibe E., Doya K. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Networks. 2018. – URL: https://doi.org/10.1016/j.neunet.2017.12.012
18. Hinton G.E., Srivastava N., Krizhevsky A., Sutskever I., Salakhutdinov R.R. Improving neural networks by preventing co-adaptation of feature detectors. arXiv:1207.0580v1[cs.NE] 3 Jul 2012. – URL: https://doi.org/10.48550/arXiv.1207.0580.
19. Kuritsyn V.A., Arapov D.V., Goril'chenko R.L. Optimization of circulation water cooling process in forced-draft towers. Chemistry and Technology of Fuels and Oils, 2012, vol. 48, no. 2, pp. 97–108. – URL: https://doi.org/10.1007/s10553-012-0344-1.
