The use of machine learning methods to estimate aboveground biomass of grasslands: A review
The study of grasslands using machine learning (ML) methods combined with proximal/remote sensing data (RS) has been steadily increasing in the last decades. Available algorithms range from a primarily academic use to more widespread practical applications intended at helping farm management. Here,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-11-01
|
| Series: | Ecological Indicators |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1470160X21007469 |
| _version_ | 1818401835344461824 |
|---|---|
| author | Tiago G. Morais Ricardo F.M. Teixeira Mario Figueiredo Tiago Domingos |
| author_facet | Tiago G. Morais Ricardo F.M. Teixeira Mario Figueiredo Tiago Domingos |
| author_sort | Tiago G. Morais |
| collection | DOAJ |
| description | The study of grasslands using machine learning (ML) methods combined with proximal/remote sensing data (RS) has been steadily increasing in the last decades. Available algorithms range from a primarily academic use to more widespread practical applications intended at helping farm management. Here, we review the use of ML methods applied to aboveground biomass (AGB) estimation in grassland systems. Based on 26 recent papers, we perform a literature review of the topic to identify common practices, namely the relation between estimation performance and the ML method used, data sources, and scale (local/regional). In order to identify the relation between the characteristics of the studies and the estimation accuracy, we use descriptive and correlation analysis. In spite of a surge in the number of papers and application examples, there is no evidence that the estimation performance of the algorithms has been improving over time. In all approaches used by the authors of the papers herein considered, the number of field samples, RS data source, and species composition of the grassland systems are the most relevant variables to explain the estimation accuracy. This accuracy increases with the number of field samples until it plateaus, hinting at the existence of an optimum level for monitoring efforts. Accuracy also increases with the proximity of the sensor to the field, i.e., on average accuracy is higher using field spectroscopy than using satellite data. There is no evidence that any particular ML method is more suited to this problem. The literature also displays significant limitations in terms of its applications of the ML algorithms. For example, a limited number of papers validated the models, casting doubt on the potential of the models for generalized application. Despite those limitations, and considering the advancements verified, we expect that, in the near future, ML methods combined with RS/proximal data will continue to improve and be helpful for farm management. |
| first_indexed | 2024-12-14T07:58:47Z |
| format | Article |
| id | doaj.art-9a1af780b7e84abdad18462459b2bec5 |
| institution | Directory Open Access Journal |
| issn | 1470-160X |
| language | English |
| last_indexed | 2024-12-14T07:58:47Z |
| publishDate | 2021-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Indicators |
| spelling | doaj.art-9a1af780b7e84abdad18462459b2bec52022-12-21T23:10:30ZengElsevierEcological Indicators1470-160X2021-11-01130108081The use of machine learning methods to estimate aboveground biomass of grasslands: A reviewTiago G. Morais0Ricardo F.M. Teixeira1Mario Figueiredo2Tiago Domingos3MARETEC − Marine, Environment and Technology Centre, LARSyS, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001 Lisbon, Portugal; Corresponding author.MARETEC − Marine, Environment and Technology Centre, LARSyS, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001 Lisbon, PortugalInstituto de Telecomunicações, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001 Lisbon, PortugalMARETEC − Marine, Environment and Technology Centre, LARSyS, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001 Lisbon, PortugalThe study of grasslands using machine learning (ML) methods combined with proximal/remote sensing data (RS) has been steadily increasing in the last decades. Available algorithms range from a primarily academic use to more widespread practical applications intended at helping farm management. Here, we review the use of ML methods applied to aboveground biomass (AGB) estimation in grassland systems. Based on 26 recent papers, we perform a literature review of the topic to identify common practices, namely the relation between estimation performance and the ML method used, data sources, and scale (local/regional). In order to identify the relation between the characteristics of the studies and the estimation accuracy, we use descriptive and correlation analysis. In spite of a surge in the number of papers and application examples, there is no evidence that the estimation performance of the algorithms has been improving over time. In all approaches used by the authors of the papers herein considered, the number of field samples, RS data source, and species composition of the grassland systems are the most relevant variables to explain the estimation accuracy. This accuracy increases with the number of field samples until it plateaus, hinting at the existence of an optimum level for monitoring efforts. Accuracy also increases with the proximity of the sensor to the field, i.e., on average accuracy is higher using field spectroscopy than using satellite data. There is no evidence that any particular ML method is more suited to this problem. The literature also displays significant limitations in terms of its applications of the ML algorithms. For example, a limited number of papers validated the models, casting doubt on the potential of the models for generalized application. Despite those limitations, and considering the advancements verified, we expect that, in the near future, ML methods combined with RS/proximal data will continue to improve and be helpful for farm management.http://www.sciencedirect.com/science/article/pii/S1470160X21007469Remote sensingSpectroscopySatelliteUnmanned Aerial VehiclesPartial least squares regressionRandom forests |
| spellingShingle | Tiago G. Morais Ricardo F.M. Teixeira Mario Figueiredo Tiago Domingos The use of machine learning methods to estimate aboveground biomass of grasslands: A review Ecological Indicators Remote sensing Spectroscopy Satellite Unmanned Aerial Vehicles Partial least squares regression Random forests |
| title | The use of machine learning methods to estimate aboveground biomass of grasslands: A review |
| title_full | The use of machine learning methods to estimate aboveground biomass of grasslands: A review |
| title_fullStr | The use of machine learning methods to estimate aboveground biomass of grasslands: A review |
| title_full_unstemmed | The use of machine learning methods to estimate aboveground biomass of grasslands: A review |
| title_short | The use of machine learning methods to estimate aboveground biomass of grasslands: A review |
| title_sort | use of machine learning methods to estimate aboveground biomass of grasslands a review |
| topic | Remote sensing Spectroscopy Satellite Unmanned Aerial Vehicles Partial least squares regression Random forests |
| url | http://www.sciencedirect.com/science/article/pii/S1470160X21007469 |
| work_keys_str_mv | AT tiagogmorais theuseofmachinelearningmethodstoestimateabovegroundbiomassofgrasslandsareview AT ricardofmteixeira theuseofmachinelearningmethodstoestimateabovegroundbiomassofgrasslandsareview AT mariofigueiredo theuseofmachinelearningmethodstoestimateabovegroundbiomassofgrasslandsareview AT tiagodomingos theuseofmachinelearningmethodstoestimateabovegroundbiomassofgrasslandsareview AT tiagogmorais useofmachinelearningmethodstoestimateabovegroundbiomassofgrasslandsareview AT ricardofmteixeira useofmachinelearningmethodstoestimateabovegroundbiomassofgrasslandsareview AT mariofigueiredo useofmachinelearningmethodstoestimateabovegroundbiomassofgrasslandsareview AT tiagodomingos useofmachinelearningmethodstoestimateabovegroundbiomassofgrasslandsareview |