TY - JOUR
T1 - K-sharp: A segmented regression approach for image sharpening and normalization
AU - Aragon Solorio, Bruno Jose Luis
AU - Cawse-Nicholson, Kerry
AU - Hulley, Glynn
AU - Houborg, Rasmus
AU - Fisher, Joshua B.
N1 - KAUST Repository Item: Exported on 2023-07-31
Acknowledgements: This study was supported by the National Aeronautics and Space Administration (NASA), United States, the NASA Postdoctoral Program at the Jet Propulsion Laboratory, California Institute of Technology, administered by Universities Space Research Association under contract with NASA, ECOSTRESS Science and Applications Team: Grant No. 80NSSC20K0167, and King Abdullah University of Science and technology (KAUST). KCN and GH contributed to the research at the Jet Propulsion Laboratory, California Institute of Technology, under a contract with NASA and with support from the ECOSTRESS mission and R&A program. We also acknowledge NASA's Commercial Smallsat Data Acquisition (CSDA) Program, which provided access to the PlanetScope imagery.
This publication acknowledges KAUST support, but has no KAUST affiliated authors.
PY - 2023/7/26
Y1 - 2023/7/26
N2 - In recent decades, Earth Observation (EO) satellite missions have improved in spatial resolution and revisit times. These missions, traditionally government-funded, utilize state-of-the-art technology and rigorous instrument calibration, with each mission costing millions of dollars. Recently, nano-satellites known as CubeSats are presenting a cost-effective option for EO; their capacity of working as a constellation has brought an unprecedented opportunity for EO in terms of achievable spatial and temporal resolutions, albeit at the cost of decreased accuracy and cross-sensor consistency. As such, CubeSat datasets often require post-calibration approaches before using them for scientific applications. K-sharp is a relatively simple, data-agnostic machine learning approach that combines K-means and partial least squares regression to derive relationships between two sets of images for normalization. This study used Planet's four-band CubeSat imagery to sharpen day-coincident Landsat 8 normalized difference vegetation index, albedo, and the first short-wave infrared (SWIR) band from 30 m to 3 m spatial resolution (it should be noted that the four-band CubeSat product does not include the first SWIR band, and that the calculation of albedo is not directly possible from this product). K-sharp was tested over agricultural, savanna, rainforest, and tundra sites with and without atmospheric correction. Our model reproduced surface conditions with an average r2 of 0.88 (rMAE = 11.39%) across all study sites and target variables when compared against the original Landsat 8 data. These results showcase the promising potential of K-sharp in generating precise, CubeSat-derived datasets with high radiometric quality, which can be incorporated into agricultural or ecological applications to enhance their decision-making process at fine spatial scales.
AB - In recent decades, Earth Observation (EO) satellite missions have improved in spatial resolution and revisit times. These missions, traditionally government-funded, utilize state-of-the-art technology and rigorous instrument calibration, with each mission costing millions of dollars. Recently, nano-satellites known as CubeSats are presenting a cost-effective option for EO; their capacity of working as a constellation has brought an unprecedented opportunity for EO in terms of achievable spatial and temporal resolutions, albeit at the cost of decreased accuracy and cross-sensor consistency. As such, CubeSat datasets often require post-calibration approaches before using them for scientific applications. K-sharp is a relatively simple, data-agnostic machine learning approach that combines K-means and partial least squares regression to derive relationships between two sets of images for normalization. This study used Planet's four-band CubeSat imagery to sharpen day-coincident Landsat 8 normalized difference vegetation index, albedo, and the first short-wave infrared (SWIR) band from 30 m to 3 m spatial resolution (it should be noted that the four-band CubeSat product does not include the first SWIR band, and that the calculation of albedo is not directly possible from this product). K-sharp was tested over agricultural, savanna, rainforest, and tundra sites with and without atmospheric correction. Our model reproduced surface conditions with an average r2 of 0.88 (rMAE = 11.39%) across all study sites and target variables when compared against the original Landsat 8 data. These results showcase the promising potential of K-sharp in generating precise, CubeSat-derived datasets with high radiometric quality, which can be incorporated into agricultural or ecological applications to enhance their decision-making process at fine spatial scales.
UR - http://hdl.handle.net/10754/693298
UR - https://linkinghub.elsevier.com/retrieve/pii/S2666017223000202
U2 - 10.1016/j.srs.2023.100095
DO - 10.1016/j.srs.2023.100095
M3 - Article
SN - 2666-0172
SP - 100095
JO - Science of Remote Sensing
JF - Science of Remote Sensing
ER -