Forage Biomass Estimation Using Sentinel-2 Imagery at High Latitudes
Forages are the most important kind of crops at high latitudes and are the main feeding source for ruminant-based dairy industries. Maximizing the economic and ecological performances of farms and, to some extent, of the meat and dairy sectors require adequate and timely supportive field-specific in...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/9/2350 |
| _version_ | 1797601771118395392 |
|---|---|
| author | Junxiang Peng Niklas Zeiner David Parsons Jean-Baptiste Féret Mats Söderström Julien Morel |
| author_facet | Junxiang Peng Niklas Zeiner David Parsons Jean-Baptiste Féret Mats Söderström Julien Morel |
| author_sort | Junxiang Peng |
| collection | DOAJ |
| description | Forages are the most important kind of crops at high latitudes and are the main feeding source for ruminant-based dairy industries. Maximizing the economic and ecological performances of farms and, to some extent, of the meat and dairy sectors require adequate and timely supportive field-specific information such as available biomass. Sentinel-2 satellites provide open access imagery that can monitor vegetation frequently. These spectral data were used to estimate the dry matter yield (<i>DMY</i>) of harvested forage fields in northern Sweden. Field measurements were conducted over two years at four sites with contrasting soil and climate conditions. Univariate regression and multivariate regression, including partial least square, support vector machine and random forest, were tested for their capability to accurately and robustly estimate in-season <i>DMY</i> using reflectance values and vegetation indices obtained from Sentinel-2 spectral bands. Models were built using an iterative (300 times) calibration and validation approach (75% and 25% for calibration and validation, respectively), and their performances were formally evaluated using an independent dataset. Among these algorithms, random forest regression (RFR) produced the most stable and robust results, with Nash–Sutcliffe model efficiency (<i>NSE</i>) values (average ± standard deviation) for the calibration, validation and evaluation of 0.92 ± 0.01, 0.55 ± 0.22 and 0.86 ± 0.04, respectively. Although relatively promising, these results call for larger and more comprehensive datasets as performances vary largely between calibration, validation and evaluation datasets. Moreover, RFR, as any machine learning algorithm regression, requires a very large dataset to become stable in terms of performance. |
| first_indexed | 2024-03-11T04:08:30Z |
| format | Article |
| id | doaj.art-dcdea20e42a3473f9f99f61d2a8eebb9 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T04:08:30Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-dcdea20e42a3473f9f99f61d2a8eebb92023-11-17T23:38:59ZengMDPI AGRemote Sensing2072-42922023-04-01159235010.3390/rs15092350Forage Biomass Estimation Using Sentinel-2 Imagery at High LatitudesJunxiang Peng0Niklas Zeiner1David Parsons2Jean-Baptiste Féret3Mats Söderström4Julien Morel5Department of Crop Production Ecology, Swedish University of Agricultural Sciences, 90183 Umeå, SwedenDepartment of Crop Production Ecology, Swedish University of Agricultural Sciences, 90183 Umeå, SwedenDepartment of Crop Production Ecology, Swedish University of Agricultural Sciences, 90183 Umeå, SwedenTETIS, INRAE, AgroParisTech, CIRAD, CNRS, Université Montpellier, 34093 Montpellier, FranceDepartment of Soil and Environment, Swedish University of Agricultural Sciences, 53223 Skara, SwedenDepartment of Crop Production Ecology, Swedish University of Agricultural Sciences, 90183 Umeå, SwedenForages are the most important kind of crops at high latitudes and are the main feeding source for ruminant-based dairy industries. Maximizing the economic and ecological performances of farms and, to some extent, of the meat and dairy sectors require adequate and timely supportive field-specific information such as available biomass. Sentinel-2 satellites provide open access imagery that can monitor vegetation frequently. These spectral data were used to estimate the dry matter yield (<i>DMY</i>) of harvested forage fields in northern Sweden. Field measurements were conducted over two years at four sites with contrasting soil and climate conditions. Univariate regression and multivariate regression, including partial least square, support vector machine and random forest, were tested for their capability to accurately and robustly estimate in-season <i>DMY</i> using reflectance values and vegetation indices obtained from Sentinel-2 spectral bands. Models were built using an iterative (300 times) calibration and validation approach (75% and 25% for calibration and validation, respectively), and their performances were formally evaluated using an independent dataset. Among these algorithms, random forest regression (RFR) produced the most stable and robust results, with Nash–Sutcliffe model efficiency (<i>NSE</i>) values (average ± standard deviation) for the calibration, validation and evaluation of 0.92 ± 0.01, 0.55 ± 0.22 and 0.86 ± 0.04, respectively. Although relatively promising, these results call for larger and more comprehensive datasets as performances vary largely between calibration, validation and evaluation datasets. Moreover, RFR, as any machine learning algorithm regression, requires a very large dataset to become stable in terms of performance.https://www.mdpi.com/2072-4292/15/9/2350foragedry matter yieldmachine learning regressionSentinel-2high latitudes |
| spellingShingle | Junxiang Peng Niklas Zeiner David Parsons Jean-Baptiste Féret Mats Söderström Julien Morel Forage Biomass Estimation Using Sentinel-2 Imagery at High Latitudes Remote Sensing forage dry matter yield machine learning regression Sentinel-2 high latitudes |
| title | Forage Biomass Estimation Using Sentinel-2 Imagery at High Latitudes |
| title_full | Forage Biomass Estimation Using Sentinel-2 Imagery at High Latitudes |
| title_fullStr | Forage Biomass Estimation Using Sentinel-2 Imagery at High Latitudes |
| title_full_unstemmed | Forage Biomass Estimation Using Sentinel-2 Imagery at High Latitudes |
| title_short | Forage Biomass Estimation Using Sentinel-2 Imagery at High Latitudes |
| title_sort | forage biomass estimation using sentinel 2 imagery at high latitudes |
| topic | forage dry matter yield machine learning regression Sentinel-2 high latitudes |
| url | https://www.mdpi.com/2072-4292/15/9/2350 |
| work_keys_str_mv | AT junxiangpeng foragebiomassestimationusingsentinel2imageryathighlatitudes AT niklaszeiner foragebiomassestimationusingsentinel2imageryathighlatitudes AT davidparsons foragebiomassestimationusingsentinel2imageryathighlatitudes AT jeanbaptisteferet foragebiomassestimationusingsentinel2imageryathighlatitudes AT matssoderstrom foragebiomassestimationusingsentinel2imageryathighlatitudes AT julienmorel foragebiomassestimationusingsentinel2imageryathighlatitudes |