Estimating Forest Volume and Biomass and Their Changes Using Random Forests and Remotely Sensed Data
Despite the popularity of random forests (RF) as a prediction algorithm, methods for constructing confidence intervals for population means using this technique are still only sparsely reported. For two regional study areas (Spain and Norway) RF was used to predict forest volume or aboveground bioma...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/11/16/1944 |
| _version_ | 1798025786884620288 |
|---|---|
| author | Jessica Esteban Ronald E. McRoberts Alfredo Fernández-Landa José Luis Tomé Erik Nӕsset |
| author_facet | Jessica Esteban Ronald E. McRoberts Alfredo Fernández-Landa José Luis Tomé Erik Nӕsset |
| author_sort | Jessica Esteban |
| collection | DOAJ |
| description | Despite the popularity of random forests (RF) as a prediction algorithm, methods for constructing confidence intervals for population means using this technique are still only sparsely reported. For two regional study areas (Spain and Norway) RF was used to predict forest volume or aboveground biomass using remotely sensed auxiliary data obtained from multiple sensors. Additionally, the changes per unit area of these forest attributes were estimated using indirect and direct methods. Multiple inferential frameworks have attracted increased recent attention for estimating the variances required for confidence intervals. For this study, three different statistical frameworks, design-based expansion, model-assisted and model-based estimators, were used for estimating population parameters and their variances. Pairs and wild bootstrapping approaches at different levels were compared for estimating the variances of the model-based estimates of the population means, as well as for mapping the uncertainty of the change predictions. The RF models accurately represented the relationship between the response and remotely sensed predictor variables, resulting in increased precision for estimates of the population means relative to design-based expansion estimates. Standard errors based on pairs bootstrapping within or internal to RF were considerably larger than standard errors based on both pairs and wild external bootstrapping of the entire RF algorithm. Pairs and wild external bootstrapping produced similar standard errors, but wild bootstrapping better mimicked the original structure of the sample data and better preserved the ranges of the predictor variables. |
| first_indexed | 2024-04-11T18:24:25Z |
| format | Article |
| id | doaj.art-a5d7e86bee8e404da0461e71b5df5834 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-11T18:24:25Z |
| publishDate | 2019-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-a5d7e86bee8e404da0461e71b5df58342022-12-22T04:09:41ZengMDPI AGRemote Sensing2072-42922019-08-011116194410.3390/rs11161944rs11161944Estimating Forest Volume and Biomass and Their Changes Using Random Forests and Remotely Sensed DataJessica Esteban0Ronald E. McRoberts1Alfredo Fernández-Landa2José Luis Tomé3Erik Nӕsset4Departamento de Topografía y Geomática, Universidad Politécnica de Madrid, 28040 Madrid, SpainNorthern Research Station, U.S. Forest Service, St. Paul, MN 55108, USAAgresta Soc. Coop., 28012 Madrid, SpainAgresta Soc. Coop., 28012 Madrid, SpainFaculty of Environmental Sciences and Natural Resource Management, Norwegian University of Life Sciences, P.O. Box 5003, NO-1432 Ås, NorwayDespite the popularity of random forests (RF) as a prediction algorithm, methods for constructing confidence intervals for population means using this technique are still only sparsely reported. For two regional study areas (Spain and Norway) RF was used to predict forest volume or aboveground biomass using remotely sensed auxiliary data obtained from multiple sensors. Additionally, the changes per unit area of these forest attributes were estimated using indirect and direct methods. Multiple inferential frameworks have attracted increased recent attention for estimating the variances required for confidence intervals. For this study, three different statistical frameworks, design-based expansion, model-assisted and model-based estimators, were used for estimating population parameters and their variances. Pairs and wild bootstrapping approaches at different levels were compared for estimating the variances of the model-based estimates of the population means, as well as for mapping the uncertainty of the change predictions. The RF models accurately represented the relationship between the response and remotely sensed predictor variables, resulting in increased precision for estimates of the population means relative to design-based expansion estimates. Standard errors based on pairs bootstrapping within or internal to RF were considerably larger than standard errors based on both pairs and wild external bootstrapping of the entire RF algorithm. Pairs and wild external bootstrapping produced similar standard errors, but wild bootstrapping better mimicked the original structure of the sample data and better preserved the ranges of the predictor variables.https://www.mdpi.com/2072-4292/11/16/1944bootstrappingmodel-assistedmodel-basedpopulation parameters |
| spellingShingle | Jessica Esteban Ronald E. McRoberts Alfredo Fernández-Landa José Luis Tomé Erik Nӕsset Estimating Forest Volume and Biomass and Their Changes Using Random Forests and Remotely Sensed Data Remote Sensing bootstrapping model-assisted model-based population parameters |
| title | Estimating Forest Volume and Biomass and Their Changes Using Random Forests and Remotely Sensed Data |
| title_full | Estimating Forest Volume and Biomass and Their Changes Using Random Forests and Remotely Sensed Data |
| title_fullStr | Estimating Forest Volume and Biomass and Their Changes Using Random Forests and Remotely Sensed Data |
| title_full_unstemmed | Estimating Forest Volume and Biomass and Their Changes Using Random Forests and Remotely Sensed Data |
| title_short | Estimating Forest Volume and Biomass and Their Changes Using Random Forests and Remotely Sensed Data |
| title_sort | estimating forest volume and biomass and their changes using random forests and remotely sensed data |
| topic | bootstrapping model-assisted model-based population parameters |
| url | https://www.mdpi.com/2072-4292/11/16/1944 |
| work_keys_str_mv | AT jessicaesteban estimatingforestvolumeandbiomassandtheirchangesusingrandomforestsandremotelysenseddata AT ronaldemcroberts estimatingforestvolumeandbiomassandtheirchangesusingrandomforestsandremotelysenseddata AT alfredofernandezlanda estimatingforestvolumeandbiomassandtheirchangesusingrandomforestsandremotelysenseddata AT joseluistome estimatingforestvolumeandbiomassandtheirchangesusingrandomforestsandremotelysenseddata AT eriknæsset estimatingforestvolumeandbiomassandtheirchangesusingrandomforestsandremotelysenseddata |