Speaker
Description
Forest operations with forwarders frequently cause soil deformation and wheel rut formation, negatively affecting soil bearing capacity, hydrological processes, and longterm forest productivity. Existing studies primarily focus on post-operational rut assessment using UAV photogrammetry, LiDAR-derived digital terrain models, and machine learning-based image segmentation, as well as predictive modelling based on soil moisture, traffic intensity, and machine load. However, these approaches are predominantly retrospective and do not support real-time operational decision-making during timber extraction.
This study proposes the development and validation of an integrated real-time wheel rut monitoring system embedded in a forwarder. The system combines distance sensors, GNSS positioning, and LiDAR technology to continuously detect and quantify rut depth and spatial distribution during machine operation. The collected data enable dynamic assessment of soil impact and provide immediate feedback to operators, supporting adaptive driving strategies and optimized extraction routing.
The expected outcomes include a functional prototype of the monitoring system, methodological evaluation of measurement accuracy and reliability, and practical recommendations for its implementation in forest operations. By enabling objective, data-driven soil impact assessment in real time, the proposed solution contributes to sustainable forest management and advances the integration of smart technologies within the bioeconomy sector.
| Keywords | Wheel rutting; Real-time monitoring |
|---|
