Optimal Combination of Predictors and Algorithms for Forest Above-Ground Biomass Mapping from Sentinel and SRTM Data
Accurate forest above-ground biomass (AGB) mapping is crucial for sustaining forest management and carbon cycle tracking. The Shuttle Radar Topographic Mission (SRTM) and Sentinel satellite series offer opportunities for forest AGB monitoring. In this study, predictors filtered from 121 variables fr...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/11/4/414 |
| _version_ | 1798024622403223552 |
|---|---|
| author | Lin Chen Yeqiao Wang Chunying Ren Bai Zhang Zongming Wang |
| author_facet | Lin Chen Yeqiao Wang Chunying Ren Bai Zhang Zongming Wang |
| author_sort | Lin Chen |
| collection | DOAJ |
| description | Accurate forest above-ground biomass (AGB) mapping is crucial for sustaining forest management and carbon cycle tracking. The Shuttle Radar Topographic Mission (SRTM) and Sentinel satellite series offer opportunities for forest AGB monitoring. In this study, predictors filtered from 121 variables from Sentinel-1 synthetic aperture radar (SAR), Sentinal-2 multispectral instrument (MSI) and SRTM digital elevation model (DEM) data were composed into four groups and evaluated for their effectiveness in prediction of AGB. Five evaluated algorithms include linear regression such as stepwise regression (SWR) and geographically weighted regression (GWR); machine learning (ML) such as artificial neural network (ANN), support vector machine for regression (SVR), and random forest (RF). The results showed that the RF model used predictors from both the Sentinel series and SRTM DEM performed the best, based on the independent validation set. The RF model achieved accuracy with the mean error, mean absolute error, root mean square error, and correlation coefficient in 1.39, 25.48, 61.11 Mg·ha<sup>−1</sup> and 0.9769, respectively. Texture characteristics, reflectance, vegetation indices, elevation, stream power index, topographic wetness index and surface roughness were recommended predictors for AGB prediction. Predictor variables were more important than algorithms for improving the accuracy of AGB estimates. The study demonstrated encouraging results in the optimal combination of predictors and algorithms for forest AGB mapping, using openly accessible and fine-resolution data based on RF algorithms. |
| first_indexed | 2024-04-11T18:05:34Z |
| format | Article |
| id | doaj.art-adf0303f5b6245dcae2f711b0fe52106 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-11T18:05:34Z |
| publishDate | 2019-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-adf0303f5b6245dcae2f711b0fe521062022-12-22T04:10:21ZengMDPI AGRemote Sensing2072-42922019-02-0111441410.3390/rs11040414rs11040414Optimal Combination of Predictors and Algorithms for Forest Above-Ground Biomass Mapping from Sentinel and SRTM DataLin Chen0Yeqiao Wang1Chunying Ren2Bai Zhang3Zongming Wang4Northeast Institute of Geography and Agroecology, Key Laboratory of Wetland Ecology and Environment, Chinese Academy of Sciences, Changchun 130102, ChinaDepartment of Natural Resources Science, University of Rhode Island, 1 Greenhouse Rd., Kingston, RI 02881, USANortheast Institute of Geography and Agroecology, Key Laboratory of Wetland Ecology and Environment, Chinese Academy of Sciences, Changchun 130102, ChinaNortheast Institute of Geography and Agroecology, Key Laboratory of Wetland Ecology and Environment, Chinese Academy of Sciences, Changchun 130102, ChinaNortheast Institute of Geography and Agroecology, Key Laboratory of Wetland Ecology and Environment, Chinese Academy of Sciences, Changchun 130102, ChinaAccurate forest above-ground biomass (AGB) mapping is crucial for sustaining forest management and carbon cycle tracking. The Shuttle Radar Topographic Mission (SRTM) and Sentinel satellite series offer opportunities for forest AGB monitoring. In this study, predictors filtered from 121 variables from Sentinel-1 synthetic aperture radar (SAR), Sentinal-2 multispectral instrument (MSI) and SRTM digital elevation model (DEM) data were composed into four groups and evaluated for their effectiveness in prediction of AGB. Five evaluated algorithms include linear regression such as stepwise regression (SWR) and geographically weighted regression (GWR); machine learning (ML) such as artificial neural network (ANN), support vector machine for regression (SVR), and random forest (RF). The results showed that the RF model used predictors from both the Sentinel series and SRTM DEM performed the best, based on the independent validation set. The RF model achieved accuracy with the mean error, mean absolute error, root mean square error, and correlation coefficient in 1.39, 25.48, 61.11 Mg·ha<sup>−1</sup> and 0.9769, respectively. Texture characteristics, reflectance, vegetation indices, elevation, stream power index, topographic wetness index and surface roughness were recommended predictors for AGB prediction. Predictor variables were more important than algorithms for improving the accuracy of AGB estimates. The study demonstrated encouraging results in the optimal combination of predictors and algorithms for forest AGB mapping, using openly accessible and fine-resolution data based on RF algorithms.https://www.mdpi.com/2072-4292/11/4/414optimal predictorsalgorithm comparisonSentinel-1 SARSentinel-2 MSISRTM DEMforest AGB mapping |
| spellingShingle | Lin Chen Yeqiao Wang Chunying Ren Bai Zhang Zongming Wang Optimal Combination of Predictors and Algorithms for Forest Above-Ground Biomass Mapping from Sentinel and SRTM Data Remote Sensing optimal predictors algorithm comparison Sentinel-1 SAR Sentinel-2 MSI SRTM DEM forest AGB mapping |
| title | Optimal Combination of Predictors and Algorithms for Forest Above-Ground Biomass Mapping from Sentinel and SRTM Data |
| title_full | Optimal Combination of Predictors and Algorithms for Forest Above-Ground Biomass Mapping from Sentinel and SRTM Data |
| title_fullStr | Optimal Combination of Predictors and Algorithms for Forest Above-Ground Biomass Mapping from Sentinel and SRTM Data |
| title_full_unstemmed | Optimal Combination of Predictors and Algorithms for Forest Above-Ground Biomass Mapping from Sentinel and SRTM Data |
| title_short | Optimal Combination of Predictors and Algorithms for Forest Above-Ground Biomass Mapping from Sentinel and SRTM Data |
| title_sort | optimal combination of predictors and algorithms for forest above ground biomass mapping from sentinel and srtm data |
| topic | optimal predictors algorithm comparison Sentinel-1 SAR Sentinel-2 MSI SRTM DEM forest AGB mapping |
| url | https://www.mdpi.com/2072-4292/11/4/414 |
| work_keys_str_mv | AT linchen optimalcombinationofpredictorsandalgorithmsforforestabovegroundbiomassmappingfromsentinelandsrtmdata AT yeqiaowang optimalcombinationofpredictorsandalgorithmsforforestabovegroundbiomassmappingfromsentinelandsrtmdata AT chunyingren optimalcombinationofpredictorsandalgorithmsforforestabovegroundbiomassmappingfromsentinelandsrtmdata AT baizhang optimalcombinationofpredictorsandalgorithmsforforestabovegroundbiomassmappingfromsentinelandsrtmdata AT zongmingwang optimalcombinationofpredictorsandalgorithmsforforestabovegroundbiomassmappingfromsentinelandsrtmdata |