K-sharp: A segmented regression approach for image sharpening and normalization
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-...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-12-01
|
| Series: | Science of Remote Sensing |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666017223000202 |
| _version_ | 1797401694317838336 |
|---|---|
| author | Bruno Aragon Kerry Cawse-Nicholson Glynn Hulley Rasmus Houborg Joshua B. Fisher |
| author_facet | Bruno Aragon Kerry Cawse-Nicholson Glynn Hulley Rasmus Houborg Joshua B. Fisher |
| author_sort | Bruno Aragon |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T02:13:44Z |
| format | Article |
| id | doaj.art-7560777e68004b46a3c91cbe1546ea3d |
| institution | Directory Open Access Journal |
| issn | 2666-0172 |
| language | English |
| last_indexed | 2024-03-09T02:13:44Z |
| publishDate | 2023-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Science of Remote Sensing |
| spelling | doaj.art-7560777e68004b46a3c91cbe1546ea3d2023-12-07T05:30:17ZengElsevierScience of Remote Sensing2666-01722023-12-018100095K-sharp: A segmented regression approach for image sharpening and normalizationBruno Aragon0Kerry Cawse-Nicholson1Glynn Hulley2Rasmus Houborg3Joshua B. Fisher4Planet, San Francisco, CA, USA; Corresponding author.Jet Propulsion Laboratory, California Institute of Technology, Pasadena, CA, USAJet Propulsion Laboratory, California Institute of Technology, Pasadena, CA, USAPlanet, San Francisco, CA, USASchmid College of Science and Technology, Chapman University, 1 University Drive, Orange, CA, 92866, USAIn 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.http://www.sciencedirect.com/science/article/pii/S2666017223000202Image fusionCubeSatSharpeningNormalizationMachine learning |
| spellingShingle | Bruno Aragon Kerry Cawse-Nicholson Glynn Hulley Rasmus Houborg Joshua B. Fisher K-sharp: A segmented regression approach for image sharpening and normalization Science of Remote Sensing Image fusion CubeSat Sharpening Normalization Machine learning |
| title | K-sharp: A segmented regression approach for image sharpening and normalization |
| title_full | K-sharp: A segmented regression approach for image sharpening and normalization |
| title_fullStr | K-sharp: A segmented regression approach for image sharpening and normalization |
| title_full_unstemmed | K-sharp: A segmented regression approach for image sharpening and normalization |
| title_short | K-sharp: A segmented regression approach for image sharpening and normalization |
| title_sort | k sharp a segmented regression approach for image sharpening and normalization |
| topic | Image fusion CubeSat Sharpening Normalization Machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S2666017223000202 |
| work_keys_str_mv | AT brunoaragon ksharpasegmentedregressionapproachforimagesharpeningandnormalization AT kerrycawsenicholson ksharpasegmentedregressionapproachforimagesharpeningandnormalization AT glynnhulley ksharpasegmentedregressionapproachforimagesharpeningandnormalization AT rasmushouborg ksharpasegmentedregressionapproachforimagesharpeningandnormalization AT joshuabfisher ksharpasegmentedregressionapproachforimagesharpeningandnormalization |