Artificial Intelligence in Forest Plantation Management: A Systematic Literature Review of Operational Applications and Practical Implications

Abstract

Artificial intelligence (AI) is increasingly being applied in forest plantation management, yet the literature remains fragmented across technical domains and has rarely been synthesized from an operational management perspective. This study aimed to systematically review how AI has been used in forest plantation management, with particular emphasis on operational applications and practical implications. A systematic literature review approach was adopted using the Dimensions database. The initial search retrieved 627 records from journal articles and conference proceedings published between 2010 and 2026. After removing duplicates, non-English records, and review or conceptual papers, 592 records remained for title–abstract screening. Following the PRISMA-based screening process, 113 full-text reports were assessed for eligibility, and 73 eligible studies were selected for detailed analysis. The reviewed studies were classified into six major themes: growth, yield, and productivity prediction; forest health and protection; plantation establishment, maintenance, and quality monitoring; remote sensing and plantation mapping; plantation inventory and mensuration; and harvesting and operational efficiency. The results show that AI has been most widely used to improve prediction, detection, monitoring, mapping, measurement, and operational control. Across the reviewed studies, the most common practical uses included yield forecasting, biomass estimation, pest and disease detection, fire-related monitoring, planting success assessment, plantation mapping, tree measurement, harvester productivity prediction, and post-harvest timber quantification. The review also indicates that AI is evolving from a technical innovation into a practical support tool for plantation management. However, much of the current literature remains site-specific and weakly connected to routine management workflows. For Indonesia, the findings are especially relevant for peatland plantations dominated by Acacia crassicarpa and dryland plantations dominated by Eucalyptus, where AI has strong potential to support water monitoring, forest health surveillance, growth forecasting, inventory, and harvesting efficiency