Barkov, Viacheslav

Advanced Machine Learning Regression Methods for Natural System Parameter Estimation from Remote and Proximal Sensing Data

As the volume and complexity of natural system sensor data grow, an increasing need emerges for advanced predictive modeling, knowledge discovery, and explainable decision-making in environmental monitoring contexts. This research develops advanced machine learning approaches to estimate environmental parameters from increasingly complex sensor data. By focusing on precision, interpretability, and robustness, the project spans multiple sensing modalities from proximal soil sensors to remote laser scanning of forests. In pedometrics and soil science, the work advances tabular regression and deep learning models for digital soil mapping. For forestry applications, the research develops deep learning methods for processing laser scanning point cloud data to estimate forest plantation biometrics. Across both domains, the research emphasizes predictive precision, robust uncertainty quantification, and interpretability of results. This integrated approach contributes to improved environmental parameter estimation, supporting more reliable agricultural and environmental decision-making.

Project team: Viacheslav Barkov (Ph.D. Student), Prof. Dr. Martin Atzmüller (UOS), Dr. agr. Robin Gebbers (ATB)

Publications

2025

• J. Schmidinger, S. Vogel, V. Barkov, A. D. Pham, R. Gebbers, H. Tavakoli, J. Correa, T. R. Tavares, P. Filippi, E. J. Jones, V. Lukas, E. Boenecke, J. Ruehlmann, I. Schroeter, E. Kramer, S. Paetzold, M. Kodaira, A. M. J. C. Wadoux, L. Bragazza, K. Metzger, J. Huang, D. S. M. Valente, J. L. Safanelli, E. L. Bottega, R. S. D. Dalmolin, C. Farkas, A. Steiger, T. Z. Horst, L. Ramirez-Lopez, T. Scholten, F. Stumpf, P. Rosso, M. M. Costa, R. S. Zandonadi, J. Wetterlind, and M. Atzmueller, “ Limesoda: A dataset collection for benchmarking of machine learning regressors in digital soil mapping,” 2025. dx.doi.org/10.48550/arXiv.2502.20139

2024

• V. Barkov, J. Schmidinger, R. Gebbers, and M. Atzmueller, “ An efficient model-agnostic approach for uncertainty estimation in data-restricted pedometric applications,” in 2024 International Conference on Machine Learning and Applications (ICMLA), pp. 198–205, 2024. dx.doi.org/10.1109/ICMLA61862.2024.00033
• J. Schmidinger, V. Barkov, H. Tavakoli, J. Correa, M. Ostermann, M. Atzmueller, R. Gebbers, and S. Vogel, “ Which and how many soil sensors are ideal to predict key soil properties: A case study with seven sensors,” Geoderma, vol. 450, p. 117017, 2024. doi.org/10.1016/j.geoderma.2024.117017
• M. Lucas, V. Barkov, R. Pecenka, M. Atzmueller, and B. Waske, “ Mapping trees outside forests using semantic segmentation,” in IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, pp. 4435–4438, 2024. doi.org/10.1109/IGARSS53475.2024.10641035