Live Fuel Moisture Content Mapping in the Mediterranean Basin Using Random Forests and Combining MODIS Spectral and Thermal Data
Remotely sensed vegetation indices have been widely used to estimate live fuel moisture content (LFMC). However, marked differences in vegetation structure affect the relationship between field-measured LFMC and reflectance, which limits spatial extrapolation of these indices. To overcome this limit...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/13/3162 |
| _version_ | 1797433992894480384 |
|---|---|
| author | Àngel Cunill Camprubí Pablo González-Moreno Víctor Resco de Dios |
| author_facet | Àngel Cunill Camprubí Pablo González-Moreno Víctor Resco de Dios |
| author_sort | Àngel Cunill Camprubí |
| collection | DOAJ |
| description | Remotely sensed vegetation indices have been widely used to estimate live fuel moisture content (LFMC). However, marked differences in vegetation structure affect the relationship between field-measured LFMC and reflectance, which limits spatial extrapolation of these indices. To overcome this limitation, we explored the potential of random forests (RF) to estimate LFMC at the subcontinental scale in the Mediterranean basin wildland. We built RF models (LFMC<sub>RF</sub>) using a combination of MODIS spectral bands, vegetation indices, surface temperature, and the day of year as predictors. We used the Globe-LFMC and the Catalan LFMC monitoring program databases as ground-truth samples (10,374 samples). LFMC<sub>RF</sub> was calibrated with samples collected between 2000 and 2014 and validated with samples from 2015 to 2019, with overall root mean square errors (RMSE) of 19.9% and 16.4%, respectively, which were lower than current approaches based on radiative transfer models (RMSE ~74–78%). We used our approach to generate a public database with weekly LFMC maps across the Mediterranean basin. |
| first_indexed | 2024-03-09T10:24:54Z |
| format | Article |
| id | doaj.art-0fb1e8bc390548c69feab5cf72ce52b9 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T10:24:54Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-0fb1e8bc390548c69feab5cf72ce52b92023-12-01T21:40:59ZengMDPI AGRemote Sensing2072-42922022-07-011413316210.3390/rs14133162Live Fuel Moisture Content Mapping in the Mediterranean Basin Using Random Forests and Combining MODIS Spectral and Thermal DataÀngel Cunill Camprubí0Pablo González-Moreno1Víctor Resco de Dios2Joint Research Unit CTFC-AGROTECNIO-CERCA Center, 25198 Lleida, SpainDepartment of Forest Engineering, Grupo ERSAF, DendroDat Lab, Campus de Rabanales, Universidad de Córdoba, Crta. IV, km. 396, 14071 Córdoba, SpainJoint Research Unit CTFC-AGROTECNIO-CERCA Center, 25198 Lleida, SpainRemotely sensed vegetation indices have been widely used to estimate live fuel moisture content (LFMC). However, marked differences in vegetation structure affect the relationship between field-measured LFMC and reflectance, which limits spatial extrapolation of these indices. To overcome this limitation, we explored the potential of random forests (RF) to estimate LFMC at the subcontinental scale in the Mediterranean basin wildland. We built RF models (LFMC<sub>RF</sub>) using a combination of MODIS spectral bands, vegetation indices, surface temperature, and the day of year as predictors. We used the Globe-LFMC and the Catalan LFMC monitoring program databases as ground-truth samples (10,374 samples). LFMC<sub>RF</sub> was calibrated with samples collected between 2000 and 2014 and validated with samples from 2015 to 2019, with overall root mean square errors (RMSE) of 19.9% and 16.4%, respectively, which were lower than current approaches based on radiative transfer models (RMSE ~74–78%). We used our approach to generate a public database with weekly LFMC maps across the Mediterranean basin.https://www.mdpi.com/2072-4292/14/13/3162live fuel moisture contentwildfireMODISspectral indicesland surface temperaturerandom forests |
| spellingShingle | Àngel Cunill Camprubí Pablo González-Moreno Víctor Resco de Dios Live Fuel Moisture Content Mapping in the Mediterranean Basin Using Random Forests and Combining MODIS Spectral and Thermal Data Remote Sensing live fuel moisture content wildfire MODIS spectral indices land surface temperature random forests |
| title | Live Fuel Moisture Content Mapping in the Mediterranean Basin Using Random Forests and Combining MODIS Spectral and Thermal Data |
| title_full | Live Fuel Moisture Content Mapping in the Mediterranean Basin Using Random Forests and Combining MODIS Spectral and Thermal Data |
| title_fullStr | Live Fuel Moisture Content Mapping in the Mediterranean Basin Using Random Forests and Combining MODIS Spectral and Thermal Data |
| title_full_unstemmed | Live Fuel Moisture Content Mapping in the Mediterranean Basin Using Random Forests and Combining MODIS Spectral and Thermal Data |
| title_short | Live Fuel Moisture Content Mapping in the Mediterranean Basin Using Random Forests and Combining MODIS Spectral and Thermal Data |
| title_sort | live fuel moisture content mapping in the mediterranean basin using random forests and combining modis spectral and thermal data |
| topic | live fuel moisture content wildfire MODIS spectral indices land surface temperature random forests |
| url | https://www.mdpi.com/2072-4292/14/13/3162 |
| work_keys_str_mv | AT angelcunillcamprubi livefuelmoisturecontentmappinginthemediterraneanbasinusingrandomforestsandcombiningmodisspectralandthermaldata AT pablogonzalezmoreno livefuelmoisturecontentmappinginthemediterraneanbasinusingrandomforestsandcombiningmodisspectralandthermaldata AT victorrescodedios livefuelmoisturecontentmappinginthemediterraneanbasinusingrandomforestsandcombiningmodisspectralandthermaldata |