2026-10-06T06:41:40Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34010712 2026-09-28T07:50:52Z category_1311 portal_316 item_type_3 month_year_09_2026

Table 1_AI-driven assessment of forest dynamics and ecosystem services in response to land use change: current progress and future perspectives.pdf Lili Zhao (442802) Xuncheng Fan (21188846) Shihong Xiao (19669681) Forestry Management and Environment artificial intelligence deep learning ecosystem services forest dynamics geospatial analysis land use change remote sensing sustainable forest management <p>Forests cover approximately 31% of the global land surface and provide critical ecosystem services including carbon sequestration, hydrological regulation, and biodiversity support, yet ongoing deforestation and fragmentation are progressively eroding these services. The convergence of artificial intelligence (AI), multi-source remote sensing, and cloud computing offers unprecedented opportunities to monitor forest dynamics and quantify ecosystem service responses to land use change, but the literature remains fragmented, with no synthesis tracing the causal chain from land use drivers through forest responses to ecosystem service outcomes. This review addresses that gap through an original four-tier framework encompassing monitoring, assessment, prediction, and optimization, clarifying how AI and geospatial technologies perform at each stage and how outputs of one tier feed into the next. We searched Web of Science, Scopus, and Google Scholar for studies published between 2016 and 2026; screening against explicit eligibility criteria and a formal quality appraisal confirmed 27 core studies directly reporting a quantified AI/ML performance metric, supplemented by 70 contextual references. At the monitoring tier, deep learning architectures such as U-Net achieve F1-scores of 0.75–0.77 for forest change detection, with an advantage over conventional classifiers that is conditional rather than absolute, varying with label quality, spectral availability, and geographic transfer. At the assessment tier, AI has advanced carbon stock estimation through multi-source fusion, species distribution modeling in which convolutional neural networks substantially outperform Maximum Entropy models, an advantage that persists and even widens under stricter spatial cross-validation even as both methods' absolute accuracy declines, and hydrological service quantification coupled with process-based models. At the prediction tier, machine learning-enhanced land use simulation has reached accuracies exceeding 0.93, while reinforcement learning shows potential to jointly optimize ecosystem service and economic objectives, though only at proof-of-concept stage. Persistent challenges include limited explainability, near-absent uncertainty quantification, weak cross-domain transferability, and largely sequential AI-process model integration, with direct consequences for policy applications: AI-derived carbon stock maps and ecosystem service assessments intended to inform emissions trading, conservation planning, or land use policy currently lack the quantified uncertainty and cross-region validation such applications require. We propose a phased research agenda spanning near-term methodological consolidation, medium-term foundation model adaptation, and long-term integrated forest digital twins with equitable global coverage, offering a roadmap for translating AI and geospatial technologies into evidence-based forest ecosystem stewardship.</p> 2026-09-28T07:50:52Z Dataset Dataset 10.3389/ffgc.2026.1933500.s001 https://figshare.com/articles/dataset/Table_1_AI-driven_assessment_of_forest_dynamics_and_ecosystem_services_in_response_to_land_use_change_current_progress_and_future_perspectives_pdf/34010712 CC BY 4.0