Improving ICESat‐2‐based boreal forest height estimation by a multivariate sample quality control approach
Abstract Boreal forest heights are associated with global carbon stocks and energy budgets. The launch of the Advanced Topographic Laser Altimeter System (ATLAS) onboard the NASA's Ice, Cloud and Land Elevation Satellite (ICESat‐2) enables canopy vertical structure measurement at a global scale...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-07-01
|
| Series: | Methods in Ecology and Evolution |
| Subjects: | |
| Online Access: | https://doi.org/10.1111/2041-210X.14112 |
| _version_ | 1797766999156195328 |
|---|---|
| author | Tianqi Zhang Desheng Liu |
| author_facet | Tianqi Zhang Desheng Liu |
| author_sort | Tianqi Zhang |
| collection | DOAJ |
| description | Abstract Boreal forest heights are associated with global carbon stocks and energy budgets. The launch of the Advanced Topographic Laser Altimeter System (ATLAS) onboard the NASA's Ice, Cloud and Land Elevation Satellite (ICESat‐2) enables canopy vertical structure measurement at a global scale. However, with a photon‐counting laser system, ICESat‐2 contains high uncertainties in the estimated canopy heights, requiring appropriate quality control before being applied to canopy height modelling. We adopted a multivariate quality control approach (i.e. the Cook's distance) to improve the quality of ICESat‐2 samples. The controlled ICESat‐2 data were then input as the response variable for predicting boreal forest heights based on spatially continuous satellite data and machine learning (ML) regression models. The examined ML regressors include artificial neural networks (ANN), gradient boosting machine (GBM), random forest (RF) and support vector regression (SVR). The proposed quality control effectively removes low‐quality ICESat‐2 samples and enhances the correlations between ICESat‐2 and airborne laser scanning (ALS) observations. Moreover, the controlled ICESat‐2 samples help achieve a trade‐off between sample quality and quantity for all ML regressors, generating close canopy heights to ALS‐derived counterparts. Overall, RF and GBM make better canopy height predictions than ANN and SVR. Of all explanatory variables, the normalized difference vegetation index calculated based on the first red edge band of Sentinel‐2 (NDVIredEdge1) is considered the most important. The proposed quality control on ICESat‐2 sample selection and canopy height model (CHM) development workflow will greatly benefit forest structure investigations in the Arctic community. |
| first_indexed | 2024-03-12T20:32:24Z |
| format | Article |
| id | doaj.art-880eb30d40db4369a1b6135e6710e7cb |
| institution | Directory Open Access Journal |
| issn | 2041-210X |
| language | English |
| last_indexed | 2024-03-12T20:32:24Z |
| publishDate | 2023-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | Methods in Ecology and Evolution |
| spelling | doaj.art-880eb30d40db4369a1b6135e6710e7cb2023-08-01T18:55:57ZengWileyMethods in Ecology and Evolution2041-210X2023-07-011471623163810.1111/2041-210X.14112Improving ICESat‐2‐based boreal forest height estimation by a multivariate sample quality control approachTianqi Zhang0Desheng Liu1Department of Geography The Ohio State University Columbus Ohio USADepartment of Geography The Ohio State University Columbus Ohio USAAbstract Boreal forest heights are associated with global carbon stocks and energy budgets. The launch of the Advanced Topographic Laser Altimeter System (ATLAS) onboard the NASA's Ice, Cloud and Land Elevation Satellite (ICESat‐2) enables canopy vertical structure measurement at a global scale. However, with a photon‐counting laser system, ICESat‐2 contains high uncertainties in the estimated canopy heights, requiring appropriate quality control before being applied to canopy height modelling. We adopted a multivariate quality control approach (i.e. the Cook's distance) to improve the quality of ICESat‐2 samples. The controlled ICESat‐2 data were then input as the response variable for predicting boreal forest heights based on spatially continuous satellite data and machine learning (ML) regression models. The examined ML regressors include artificial neural networks (ANN), gradient boosting machine (GBM), random forest (RF) and support vector regression (SVR). The proposed quality control effectively removes low‐quality ICESat‐2 samples and enhances the correlations between ICESat‐2 and airborne laser scanning (ALS) observations. Moreover, the controlled ICESat‐2 samples help achieve a trade‐off between sample quality and quantity for all ML regressors, generating close canopy heights to ALS‐derived counterparts. Overall, RF and GBM make better canopy height predictions than ANN and SVR. Of all explanatory variables, the normalized difference vegetation index calculated based on the first red edge band of Sentinel‐2 (NDVIredEdge1) is considered the most important. The proposed quality control on ICESat‐2 sample selection and canopy height model (CHM) development workflow will greatly benefit forest structure investigations in the Arctic community.https://doi.org/10.1111/2041-210X.14112artificial neural networksboreal forestscanopy height modelgradient boosting machineICESat‐2multivariate quality control |
| spellingShingle | Tianqi Zhang Desheng Liu Improving ICESat‐2‐based boreal forest height estimation by a multivariate sample quality control approach Methods in Ecology and Evolution artificial neural networks boreal forests canopy height model gradient boosting machine ICESat‐2 multivariate quality control |
| title | Improving ICESat‐2‐based boreal forest height estimation by a multivariate sample quality control approach |
| title_full | Improving ICESat‐2‐based boreal forest height estimation by a multivariate sample quality control approach |
| title_fullStr | Improving ICESat‐2‐based boreal forest height estimation by a multivariate sample quality control approach |
| title_full_unstemmed | Improving ICESat‐2‐based boreal forest height estimation by a multivariate sample quality control approach |
| title_short | Improving ICESat‐2‐based boreal forest height estimation by a multivariate sample quality control approach |
| title_sort | improving icesat 2 based boreal forest height estimation by a multivariate sample quality control approach |
| topic | artificial neural networks boreal forests canopy height model gradient boosting machine ICESat‐2 multivariate quality control |
| url | https://doi.org/10.1111/2041-210X.14112 |
| work_keys_str_mv | AT tianqizhang improvingicesat2basedborealforestheightestimationbyamultivariatesamplequalitycontrolapproach AT deshengliu improvingicesat2basedborealforestheightestimationbyamultivariatesamplequalitycontrolapproach |