The European spruce bark beetle ( Ips typographus L.) is a biotic disturbance that devastates forest environmental services, and its activities are exacerbated due to climate change. Accordingly, researchers seek workflows using remote sensing imagery for bark beetle detection in the early stage of the attack, enabling proactive management. Most previous studies attempted to detect attacks with pixel-based approaches. This study explores the applicability of pixels’ spatial information, using kernels, for early bark beetle detection in south Sweden. Four vegetation indices, Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), Normalized Distance Red and SWIR (NDRS), and Chlorophyll Carotenoid Index (CCI), were derived from Sentinel-2 images and time-series of the coefficient of variation (CV) were calculated, followed by interpolation and smoothing to eliminate gaps and reduce noise. The CV time series were fed to a change detection algorithm called Detecting Breakpoints and Estimating Segments in Trend (DBEST). Detection accuracies ranged from 83.80% to 87.89%, with the highest related to NDVI, followed by NDRS. Detection dates mainly fell in June and July, 6–7 weeks after the bark beetle swarming. NDRS performed slightly better in detecting the attacks earlier, with an average detection date of 29th June. NDVI obtained higher detection accuracies for pine, spruce, and mixed conifer forests in nonwetland areas, dominating the study area. In general, the detection accuracies increased as the number of attacked trees and pixels increased in kernels. Results demonstrated the applicability of kernel-based early bark beetle attack detection, which can elucidate a new paradigm for bark beetle studies.

The European spruce bark beetle is a major disturbance agent in Norway spruce forests in Europe, and with a changing climate it is predicted that damage will increase. To prevent the bark beetle population buildup, and to limit further spread during outbreaks, it is crucial to detect attacked trees early. In this study, we utilize Sentinel-2 data in combination with a risk map, created from geodata and forestry data, to detect trees predisposed to and attacked by the European spruce bark beetle. Random forest models were trained over two tiles (90 × 90 km) in southern Sweden for all dates with a sufficient number of cloud-free Sentinel-2 pixels during the period May–September in 2017 and 2018. The pixels were classified into attacked and healthy to study how detection accuracy changed with time after bark beetle swarming and to find which Sentinel-2 bands are more important for detecting bark beetle attacked trees. Random forest models were trained with (1) single-date data, (2) temporal features (1-year difference), (3) single-date and temporal features combined, and (4) Sentinel-2 data and a risk map combined. We also included a spatial variability metric. The results show that detection accuracy was high already before the trees were attacked in May 2018, indicating that the Sentinel-2 data detect predisposed trees and that the early signs of attack are low for trees at high risk of being attacked. For single-date models, the accuracy ranged from 63 to 79% and 84 to 94% for the two tiles. For temporal features, accuracy ranged from 65 to 81% and 81 to 92%. When the single-date and temporal features were combined, the accuracy ranged from 70 to 84% and 90 to 96% for the two tiles, and with the risk map included, the accuracy ranged from 83 to 91% and 92 to 97%, showing that remote sensing data and geodata can be combined to increase detection accuracy. The differences in accuracy between the two tiles indicate that local differences can influence accuracy, suggesting that geographically weighted methods should be applied. For the single-date models, the SWIR, red-edge, and blue bands were generally more important, and the SWIR bands were more important after the attack, suggesting that they are most suitable for detecting the early signs of a bark beetle attack. For the temporal features, the SWIR and blue bands were more important, and for the variability metric, the green band was generally more important.