Publishing House SB RAS:

Publishing House SB RAS:

Address of the Publishing House SB RAS:
Morskoy pr. 2, 630090 Novosibirsk, Russia



Advanced Search

Geography and Natural Resources

2023 year, number 1

Ntroduction of digital technologies in forest monitoring in the Baikal natural territory

I.V. BYCHKOV1, I.N. VLADIMIROV2, G.M. RUZHNIKOV1, A.P. SOFRONOV2, R.K. FEDOROV1, A.K. POPOVA1, Yu.V. AVRAMENKO1, S.L. KRAVTSOV3, E.V. CHURILO4
1V.M. Matrosov Institute for System Dynamics and Control Theory, Siberian Branch, Russian Academy of Sciences, Irkutsk, Russia
2V.B. Sochava Institute of Geography, Siberian Branch, Russian Academy of Sciences, Irkutsk, Russia
3United Institute of Informatics Problems, National Academy of Sciences of Belarus, Minsk, Republic of Belarus
4Forest Institute, National Academy of Sciences of Belarus, Gomel, Republic of Belarus
Keywords: forest, forest resource monitoring, Earth remote sensing, Sentinel-2, satellite images, machine learning

Abstract

The characteristic features are analyzed and the problems of the forest monitoring of the Baikal natural territory (BNT) are highlighted. An approach is proposed for digital transformation of forest resource monitoring using a service-oriented paradigm, an infrastructure approach, declarative specifications as well as end-to-end and Web technologies for collecting and processing large amounts of spatio-temporal data. A scheme of a digital forest monitoring platform based on an information-analytical geoportal environment is described, including a system for processing and storing spatio-temporal data, a catalog of basic and thematic services for assessing the consequences of natural and anthropogenic impacts on forests of the BNT. The experience of using deep learning methods based on neural networks to monitor changes in the state of forests is presented. Automated determination of the land cover types is carried out on the basis of Sentinel-2 images. The composition of classes of the training data set created for the BNT is described. The result of the satellite image classification with identified land cover classes is given. The digital platform thus created can be used to assess and predict the state of forest resources of the BNT, and to make managerial decisions on effective forest management.