Geospatial and Machine Learning Approaches for Site Suitability, Risk Assessment, and Resource Management in Apiculture

Beekeeping and the broader pollinator-dependent landscape increasingly depend on accurate spatial information to identify suitable areas, anticipate risks, and support sustainable planning. Apiary site selection, honey production potential, and pollinator habitat conservation are shaped by a complex set of environmental, climatic, and anthropogenic factors — including land use change, exposure to natural hazards such as wildfire and landslide, and the accelerating expansion of renewable energy infrastructure (solar, wind, geothermal), which increasingly competes with or complements pollinator habitat and agricultural land. Geographic Information Systems (GIS), remote sensing, and multi-criteria decision analysis (MCDA) methods such as AHP, TOPSIS, and VIKOR have long supported these evaluations. More recently, machine learning and maximum entropy modeling have offered greater predictive accuracy and the ability to process large, heterogeneous spatial datasets, opening new opportunities for integrated, data-driven decision support for apiculture and the wider natural resource landscape it depends on.This Research Topic aims to bring together studies that apply geospatial technologies and machine learning to solve site suitability, risk assessment, and resource management problems centered on apiculture and pollinator habitat, while extending to the broader natural resource decisions that shape the landscapes bees depend on. Despite growing interest in spatial decision-making tools, there remains a need for research that rigorously compares methodologies, validates model performance across diverse regions, and translates findings into actionable guidance for beekeepers, land managers, and policymakers. Recent advances in machine learning algorithms, remote sensing image analysis, and criteria-weighting techniques have improved the accuracy and transferability of suitability and risk models, yet gaps remain in standardization, ground-truthing, and the integration of climate change, land-use change, and renewable-energy expansion scenarios into pollinator-relevant decision-making. This collection seeks to address these gaps by showcasing methodological innovations, comparative analyses, and applied case studies that advance evidence-based spatial planning for apiculture and the natural resource sectors it intersects with.We welcome contributions addressing (but not limited to):1. GIS- and remote sensing-based apiary and pollinator habitat suitability modeling.2. Multi-criteria decision analysis (AHP, TOPSIS, VIKOR, PROMETHEE) evaluating trade-offs and synergies between renewable energy siting (solar, wind, geothermal) and pollinator habitat or agricultural pollination services.3. Machine learning and maximum entropy models for predicting natural hazard risks — such as wildfire and landslide — affecting apiaries and pollinator-dependent agricultural areas.4. Land use and land cover change impacts on beekeeping and pollinator ecosystem services, including CA-Markov and similar predictive models.5. Remote sensing applications for vegetation, crop, and flowering monitoring relevant to honey production scheduling.We invite Original Research, Review, Mini Review, and Methods articles that present novel methodologies, comparative assessments, or applied case studies from any geographic region. Topic editors: Fatih SARI, Lekhnath Kafle Source: https://www.frontiersin.org/research-topics/84542/geospatial-and-machine-learning-approaches-for-site-suitability-risk-assessment-and-resource-management-in-apiculture