The article discusses the use of software algorithms to prepare cartographic data for early stages of exploration and field development planning. It is crucial for one of the major engineering tasks of Gazprom Neft, the creation of an integrated development concept, to have high-quality data at the early stage of conceptual design for facilities to develop hydrocarbon deposits. Lack of high-quality cartographic data during the analysis of license areas and early stages of large projects can lead to insufficient development of technical solutions, which can cause problems during exploration, design, and construction, resulting in increased implementation time and costs. Performing detailed field surveys or aerial photography during the early stages may not always be possible or economically feasible. The use of computational algorithms for object recognition based on the processing of remote sensing data from the Earth allows us to obtain detailed information about the terrain, water bodies, types of swamps, vegetation, and the location of common minerals. This information complements the dataset of the corporate geographic information system. The use of these algorithms in remote sensing analysis improves the quality of data, helps find optimal routes for linear objects, and reduces the cost of preparing areal objects for engineering.
References
1. Ronneberger O., Fischer P., Brox T., U-Net: Convolutional networks for biomedical image segmentation, In: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Lecture Notes in Computer Science, 2015, V. 9351, pp. 234-241, DOI: https://doi.org/10.1007/978-3-319-24574-4_28
2. Gholamalinezhad H., Khosravi H., Pooling methods in deep neural networks, a review, arXiv:2009.07485, 2020.
3. Fazzin P. et al., Sentinel-2 remote sensed image classification with patchwise trained ConvNets for grassland habitat discrimination, Remote Sensing, 2021, V. 13,
DOI: http://doi.org/10.3390/rs13122276
4. Tarasov A.V., Estimation of the accuracy of cloud masking algorithms using Sentinel-2 and PlanetScope data (In Russ.), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2020, V. 17, no. 7, pp. 26–38, DOI: http://doi.org/10.21046/2070-7401-2020-17-7-26-38
5. Lei Ma et al., Deep learning in remote sensing applications: A meta-analysis and review, ISPRS Journal of Photogrammetry and Remote Sensing, 2019, V. 152,
pp. 166-177, DOI: http://doi.org/10.1016/j.isprsjprs.2019.04.015
6. Ramzan F., Khan M.U.G., Rehmat A. et al., A deep learning approach for automated diagnosis and multi-class classification of Alzheimer’s disease stages using resting-state fMRI and residual neural networks, Journal of Medical Systems, 2020, V. 44(2), DOI: https://doi.org/10.1007/s10916-019-1475-2
7. Hatem Magdy Keshk, Xu-Cheng Yin, Satellite super-resolution images depending on deep learning Methods: A comparative study, International Conference on Signal Processing, Communications and Computing (ICSPCC), 2017, DOI: https://doi.org/10.1109/ICSPCC.2017.8242625
8. Ivanov K.E., Novikov S.M., Bolota Zapadnoy Sibiri, ikh stroenie i gidrologicheskiy rezhim (Swamps of Western Siberia, their structure and hydrological regime), Moscow: Gidrometeoizdat Publ., 1976, 447 p.
9. Batuev V.I., Kalyuzhny I.L., Specifics of boglands freezing in the north and northwest of the European part of Russia under climate change (In Russ.), Led I Sneg = Ice and Snow, 2019, V. 59(2), pp. 233–244, DOI: https://doi.org/10.15356/2076-6734-2019-2-390
10. Koronatova N.G., Mironycheva-Tokareva N.P., Solomin Ya.R., Thermal regime of peat deposits of palsas and hollows of peat plateaus in Western Siberia (In Russ.), Kriosfera Zemli, 2018, V. 22, no. 6, pp. 16–25, DOI: https://doi.org/10.21782/KZ1560-7496-2018-6(16-25)
