Deep Interpolation of Remote Sensing Land Surface Temperature Data with Partial Convolutions
Land Surface Temperature (LST) is an important resource for a variety of tasks. The data are mostly free of charge and combine high spatial and temporal resolution with reliable data collection over a historical timeframe. When remote sensing is used to provide LST data, such as the MODA11 product u...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/5/1604 |
| _version_ | 1797263848811528192 |
|---|---|
| author | Florian Huber Stefan Schulz Volker Steinhage |
| author_facet | Florian Huber Stefan Schulz Volker Steinhage |
| author_sort | Florian Huber |
| collection | DOAJ |
| description | Land Surface Temperature (LST) is an important resource for a variety of tasks. The data are mostly free of charge and combine high spatial and temporal resolution with reliable data collection over a historical timeframe. When remote sensing is used to provide LST data, such as the MODA11 product using information from the MODIS sensors attached to NASA satellites, data acquisition can be hindered by clouds or cloud shadows, occluding the sensors’ view on different areas of the world. This makes it difficult to take full advantage of the high resolution of the data. A common solution to interpolating LST data is statistical interpolation methods, such as fitting polynomials or thin plate spine interpolation. These methods have difficulties in incorporating additional knowledge about the research area and learning local dependencies that can help with the interpolation process. We propose a novel approach to interpolating remote sensing LST data in a fixed research area considering local ground-site air temperature measurements. The two-step approach consists of learning the LST from air temperature measurements, where the ground-site weather stations are located, and interpolating the remaining missing values with partial convolutions within a U-Net deep learning architecture. Our approach improves the interpolation of LST for our research area by 44% in terms of RMSE, when compared to state-of-the-art statistical methods. Due to the use of air temperature, we can provide coverage of 100%, even when no valid LST measurements were available. The resulting gapless coverage of high resolution LST data will help unlock the full potential of remote sensing LST data. |
| first_indexed | 2024-04-25T00:19:32Z |
| format | Article |
| id | doaj.art-f310f89cecee423ca7bc57683eb48db0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-25T00:19:32Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f310f89cecee423ca7bc57683eb48db02024-03-12T16:55:22ZengMDPI AGSensors1424-82202024-02-01245160410.3390/s24051604Deep Interpolation of Remote Sensing Land Surface Temperature Data with Partial ConvolutionsFlorian Huber0Stefan Schulz1Volker Steinhage2Department of Computer Science IV, University of Bonn, 53121 Bonn, GermanyDepartment of Computer Science IV, University of Bonn, 53121 Bonn, GermanyDepartment of Computer Science IV, University of Bonn, 53121 Bonn, GermanyLand Surface Temperature (LST) is an important resource for a variety of tasks. The data are mostly free of charge and combine high spatial and temporal resolution with reliable data collection over a historical timeframe. When remote sensing is used to provide LST data, such as the MODA11 product using information from the MODIS sensors attached to NASA satellites, data acquisition can be hindered by clouds or cloud shadows, occluding the sensors’ view on different areas of the world. This makes it difficult to take full advantage of the high resolution of the data. A common solution to interpolating LST data is statistical interpolation methods, such as fitting polynomials or thin plate spine interpolation. These methods have difficulties in incorporating additional knowledge about the research area and learning local dependencies that can help with the interpolation process. We propose a novel approach to interpolating remote sensing LST data in a fixed research area considering local ground-site air temperature measurements. The two-step approach consists of learning the LST from air temperature measurements, where the ground-site weather stations are located, and interpolating the remaining missing values with partial convolutions within a U-Net deep learning architecture. Our approach improves the interpolation of LST for our research area by 44% in terms of RMSE, when compared to state-of-the-art statistical methods. Due to the use of air temperature, we can provide coverage of 100%, even when no valid LST measurements were available. The resulting gapless coverage of high resolution LST data will help unlock the full potential of remote sensing LST data.https://www.mdpi.com/1424-8220/24/5/1604deep interpolationpartial convolutionsland surface temperature (LST)image inpaintinggapless MODIS |
| spellingShingle | Florian Huber Stefan Schulz Volker Steinhage Deep Interpolation of Remote Sensing Land Surface Temperature Data with Partial Convolutions Sensors deep interpolation partial convolutions land surface temperature (LST) image inpainting gapless MODIS |
| title | Deep Interpolation of Remote Sensing Land Surface Temperature Data with Partial Convolutions |
| title_full | Deep Interpolation of Remote Sensing Land Surface Temperature Data with Partial Convolutions |
| title_fullStr | Deep Interpolation of Remote Sensing Land Surface Temperature Data with Partial Convolutions |
| title_full_unstemmed | Deep Interpolation of Remote Sensing Land Surface Temperature Data with Partial Convolutions |
| title_short | Deep Interpolation of Remote Sensing Land Surface Temperature Data with Partial Convolutions |
| title_sort | deep interpolation of remote sensing land surface temperature data with partial convolutions |
| topic | deep interpolation partial convolutions land surface temperature (LST) image inpainting gapless MODIS |
| url | https://www.mdpi.com/1424-8220/24/5/1604 |
| work_keys_str_mv | AT florianhuber deepinterpolationofremotesensinglandsurfacetemperaturedatawithpartialconvolutions AT stefanschulz deepinterpolationofremotesensinglandsurfacetemperaturedatawithpartialconvolutions AT volkersteinhage deepinterpolationofremotesensinglandsurfacetemperaturedatawithpartialconvolutions |