Stratified Spatiotemporal Residual Detection of Weak Active-Fire Anomalies from VIIRS 375 m Time Series

Satellite active-fire products may miss fires that occupy only a small fraction of a pixel and produce limited absolute thermal responses. In this study, weak thermal anomalies are operationally defined as confirmed fire-affected VIIRS pixels with relatively low absolute BT4 and ΔBT responses but positive deviations from their recent temporal and local spatial backgrounds. STAR-FD (Stratified Spatiotemporal Adaptive Residual Fire Detection) was developed to detect such anomalies from VIIRS 375 m observations. The method reconstructs a 14-day recent thermal background and jointly evaluates single-pixel temporal residuals and spatial-contrast temporal residuals. Stable non-fire samples are stratified by day/night condition, season, macroclimate zone, land cover, and view zenith angle, and residual thresholds are estimated within each stratum. Validation was conducted in Heilongjiang, northwestern India, and California using Sentinel-2 MSI, Landsat 8/9 OLI, and available external fire information. STAR-FD detected 927 overpass-level thermal-anomaly events, of which 855 were confirmed as Fire, corresponding to a confirmation rate of 92.23%. VNP14IMG detected 343 events, of which 333 were confirmed as Fire (97.08%). STAR-FD identified 522 more confirmed fire-related thermal-anomaly events than VNP14IMG, corresponding to a 156.76% increase, while retaining 88.05% of VNP14IMG events. In northwestern India and Heilongjiang, STAR-FD-added daytime confirmed fire pixels had median BT4 values 9.49 K and 11.88 K lower, respectively, and median ΔBT values 8.10 K and 10.78 K lower than detections shared by both methods. These results show that STAR-FD provides complementary detection of confirmed fire-related thermal anomalies with weaker absolute thermal signals.