Hybrid forest disturbance classification using Sentinel-1 and inventory data: a case-study for Southeastern USA

Abstract. Forest ecosystems are increasingly threatened by disturbances such as fires, droughts, storms, and insect and pathogen outbreaks. Accurate and timely disturbance mapping is essential for understanding their dynamics and informing mitigation strategies to combat widespread forest decline. Traditional inventories, such as the U.S. Forest Service's Insect and Disease Survey (IDS), provide detailed information on biotic and abiotic disturbances; however, they have varying coverage and inherent uncertainties in disturbance location, extent, and timing due to data collection constraints. Other approaches, such as satellite remote sensing, can in principle overcome some of these challenges by providing large-scale coverage and continuous spatio-temporal observations. However, robust classification algorithms need to be developed, which in turn require good-quality labels.

We present a novel approach for refining disturbance classification by combining IDS with Sentinel-1 radar backscatter change detection. The disturbed patches identified by Sentinel-1 are typically within 200–950 meters of IDS locations and generally agree on timing. When statistically examined against manual labels from PlanetScope, we found that S1DM performed better than IDS for wind and bark beetle disturbances, but not for defoliators. We find that Sentinel-1 tends to detect bark beetle disturbances earlier than IDS. We then combine spatial and temporal information about disturbance occurrence from Sentinel-1 change detection with information about the corresponding agent from IDS to produce a new high-quality forest disturbance reference dataset, Sentinel-1 Disturbance Mapping (S1DM), that can be used to develop remote sensing forest classification models.

Our approach highlights the benefits of combining satellite-based remote sensing with traditional aerial survey data, reducing costs associated with aerial surveys while providing a scalable method that can be adapted to various regions.