Leveraging remote sensing to distinguish closely related beech species in assisted gene flow scenarios

European beech ( Fagus sylvatica L. ) forests are suffering under increasingly severe and frequent drought. Closely related beech species from Bulgaria, Asia Minor, the Caucasus, and Iran offer genetic resources for adaptive forest management strategies such as assisted migration (AM) and assisted gene flow (AGF) to enhance climate adaptation. However, due to similar morphology and leaf color, as well as hybridization in some cases, it is challenging to track the fate of introduced beech genotypes from these related species. Traditional identification methods relying on detailed morphological assessments and genetic testing are labor-intensive and costly, making them impractical for large-scale applications. This study evaluates the potential of high-resolution remote sensing to classify and monitor hybridizing beech species. Using multispectral data from PlanetScope SuperDove, we developed a remote sensing classification approach that captures phenological differences between the European beech F. sylvatica and co-planted Caucasian beech (Fagus hohenackeriana Palibin), two species capable of hybridization. Our method optimizes classification performance by focusing on key temporal windows and spectral features. We evaluated various machine learning algorithms with stratified spatial and temporal cross-validation on data from over 200 genetically classified individuals in two well-studied sites in France and Switzerland, where Caucasian beech was introduced over a century ago. The approach was further tested on three different study areas in Germany, where Caucasian beech was also planted in a known region but without individual tree coordinates. Key results show that our approach reveals distinct temporal and spectral differences during spring and autumn, corresponding with budbreak and senescence. Most algorithms achieved classification accuracies above 90 %. The algorithms effectively identified candidate zones for Caucasian beech within or near areas indicated by local foresters. This study demonstrates the potential of high-resolution multispectral satellite imagery and machine learning for classifying two closely related beech species in multiple locations where Caucasian beech was introduced to European beech forests. This classification is most accurate at the beginning or end of the growing season, likely due to phenological differences. By leveraging remote sensing, we provide a proof of concept for large-scale tracking of tree species introduction in AGF and AM scenarios, offering a valuable tool for adaptive forest management using Earth observation data. • Remote sensing of unique phenological differences between closely related beech species. • Models with optimized classification parameters differentiated highly similar, introduced trees. • Real-world application to assisted gene flow sites yielded high performance and testable predictions.