TY - JOUR
T1 - Downscaling MODIS NDSI to Sentinel-2 fractional snow cover by random forest regression
AU - Kollert, Andreas
AU - Mayr, Andreas
AU - Dullinger, Stefan
AU - Hülber, Karl
AU - Moser, Dietmar
AU - Lhermitte, Stef
AU - Gascoin, Simon
AU - Rutzinger, Martin
PY - 2024
Y1 - 2024
N2 - Imagery acquired by the Moderate-resolution Imaging Spectroradiometer (MODIS) provides a global archive of dailyNormalized Difference Snow Index (NDSI) at 500 m nominal resolution since the year 2000. While Sentinel-2 (S2) NDSI provides an increased spatial resolution of 20 m since the year 2015, the temporal resolution amounts to only 5 days and thus lacks the high temporal resolution of MODIS. Efforts to combine NDSI datasets for an increased temporal and spatial resolution have so far focused on the deriving binary snow cover maps or combining data from other sensors. In contrast, we produce fine scale (20 m) fractional snow cover (FSC) by downscaling MODIS NDSI to S2 resolution. Random forest regression predicts S2 NDSI based on dynamic features (MODIS NDSI, day-of-year) and static, topographic features for an alpine study site. Subsequently, FSC is derived from S2 NDSI. Cross-validation results in R2 of 0.795 and RMSE of 0.155 for FSC and outperforms common resampling methods. Multi-annual S2 NDSI metrics are able to slightly improve model accuracy. Our results suggest that combining topographical data and low-resolution NDSI allows to produce daily, high-resolution S2 NDSI and FSC and improve fine scale characterization of snow cover dynamics in mountain landscapes.
AB - Imagery acquired by the Moderate-resolution Imaging Spectroradiometer (MODIS) provides a global archive of dailyNormalized Difference Snow Index (NDSI) at 500 m nominal resolution since the year 2000. While Sentinel-2 (S2) NDSI provides an increased spatial resolution of 20 m since the year 2015, the temporal resolution amounts to only 5 days and thus lacks the high temporal resolution of MODIS. Efforts to combine NDSI datasets for an increased temporal and spatial resolution have so far focused on the deriving binary snow cover maps or combining data from other sensors. In contrast, we produce fine scale (20 m) fractional snow cover (FSC) by downscaling MODIS NDSI to S2 resolution. Random forest regression predicts S2 NDSI based on dynamic features (MODIS NDSI, day-of-year) and static, topographic features for an alpine study site. Subsequently, FSC is derived from S2 NDSI. Cross-validation results in R2 of 0.795 and RMSE of 0.155 for FSC and outperforms common resampling methods. Multi-annual S2 NDSI metrics are able to slightly improve model accuracy. Our results suggest that combining topographical data and low-resolution NDSI allows to produce daily, high-resolution S2 NDSI and FSC and improve fine scale characterization of snow cover dynamics in mountain landscapes.
KW - downscaling
KW - Fractional Snow Cover (FSC)
KW - machine learning
KW - MODIS
KW - Normalized Difference Snow Index (NDSI)
KW - Sentinel-2 (S2)
UR - http://www.scopus.com/inward/record.url?scp=85187891867&partnerID=8YFLogxK
U2 - 10.1080/2150704X.2024.2327084
DO - 10.1080/2150704X.2024.2327084
M3 - Article
AN - SCOPUS:85187891867
SN - 2150-704X
VL - 15
SP - 363
EP - 372
JO - Remote Sensing Letters
JF - Remote Sensing Letters
IS - 4
ER -