Key points are not available for this paper at this time.
Abstract Purpose of Review This systematic review aims to map the current landscape of Artificial Intelligence (AI) applications within forest operations engineering research. It seeks to identify dominant AI techniques, common data sources, key problem domains, demonstrated strengths, persistent challenges, and future research trajectories by analyzing a curated dataset of 173 scholarly papers, providing a comprehensive overview of AI’s transformative role in this specific scientific topic. Recent Findings Current research demonstrates a significant surge in AI adoption in forest operations engineering, particularly since 2017. Machine learning (ML), especially deep learning methods like Convolutional Neural Networks (CNNs), frequently combined with remote sensing data from satellites, drones, and LiDAR, is pivotal. These tools are applied to optimize wood supply chains, assess ergonomic risks, and manage forest infrastructure by accurately extracting and updating road and skid trail networks. Furthermore, tasks such as tree species classification and 3D forest reconstruction are increasingly utilized in operational contexts, specifically to plan extraction trails in single-tree selection harvesting and to feed Decision Support Systems (DSS) for optimal harvesting system selection. Summary AI enables more accurate and efficient solutions to complex forest engineering challenges. However, practical implementation remains constrained by the "black box" nature of AI, poor model generalizability across diverse ecosystems, and heavy computational demands and large datasets required—which are often incompatible with a typical forest manager's workflows and budget. Future advancements must focus on explainable AI, external validation, benchmarking, and user-friendly, edge-computing systems to transition AI from theoretical research to practical, operational forestry tools. These will further enhance sustainable forest management and engineering practices, guiding impactful future research and application.
Forkuo et al. (Tue,) studied this question.