0000000001168735
AUTHOR
Laura Martínez-ferrer
Quantifying uncertainty in high resolution biophysical variable retrieval with machine learning
The estimation of biophysical variables is at the core of remote sensing science, allowing a close monitoring of crops and forests. Deriving temporally resolved and spatially explicit maps of parameters of interest has been the subject of intense research. However, deriving products from optical sensors is typically hampered by cloud contamination and the trade-off between spatial and temporal resolutions. In this work we rely on the HIghly Scalable Temporal Adaptive Reflectance Fusion Model (HISTARFM) algorithm to generate long gap-free time series of Landsat surface reflectance data by fusing MODIS and Landsat reflectances. An artificial neural network is trained on PROSAIL inversion to p…
Remote sensing data for crop yield in CONUS
I) SUMMARY This database contains harmonized time series for the study of crop yields using remote sensing data and meteorological data. We collected information on soybean, corn, and wheat yields (t/ha) over the CONUS (continuous US) from USDA-NASS for years 2015–2018 at a county level, and collocated time series for the following variables: Enhanced Vegetation Index (EVI) from MODIS satellite (MOD13C1 v6 product) Soil Moisture (SM) from SMAP satellite through MT-DCA algorithm Vegetation Optical Depth (VOD) from SMAP satellite through MT-DCA algorithm Maximum temperature (TMAX) from Daymet v3 Precipitation (PRCP) from Daymet v3 II) CONTACT For questions, please email Laura Mart&iacut…