Comparison of Machine Learning Methods to Up-Scale Gross Primary Production
Eddy covariance observation is an applicable way to obtain accurate and continuous carbon flux at flux tower sites, while remote sensing technology could estimate carbon exchange and carbon storage at regional and global scales effectively. However, it is still challenging to up-scale the field-obse...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-06-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/13/2448 |
id |
doaj-c39cf23bf043414f843b9dcfc83b8c58 |
---|---|
record_format |
Article |
spelling |
doaj-c39cf23bf043414f843b9dcfc83b8c582021-07-15T15:44:06ZengMDPI AGRemote Sensing2072-42922021-06-01132448244810.3390/rs13132448Comparison of Machine Learning Methods to Up-Scale Gross Primary ProductionTao Yu0Qiang Zhang1Rui Sun2Research Institute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, ChinaState Key Laboratory of Remote Sensing Science, Jointly Sponsored by Beijing Normal University and Institute of Remote Sensing and Digital Earth of Chinese Academy of Sciences, Beijing 100875, ChinaState Key Laboratory of Remote Sensing Science, Jointly Sponsored by Beijing Normal University and Institute of Remote Sensing and Digital Earth of Chinese Academy of Sciences, Beijing 100875, ChinaEddy covariance observation is an applicable way to obtain accurate and continuous carbon flux at flux tower sites, while remote sensing technology could estimate carbon exchange and carbon storage at regional and global scales effectively. However, it is still challenging to up-scale the field-observed carbon flux to a regional scale, due to the heterogeneity and the unstable air conditions at the land surface. In this paper, gross primary production (GPP) from ground eddy covariance systems were up-scaled to a regional scale by using five machine learning methods (Cubist regression tree, random forest, support vector machine, artificial neural network, and deep belief network). Then, the up-scaled GPP were validated using GPP at flux tower sites, weighted GPP in the footprint, and MODIS GPP products. At last, the sensitivity of the input data (normalized difference vegetation index, fractional vegetation cover, shortwave radiation, relative humidity and air temperature) to the precision of up-scaled GPP was analyzed, and the uncertainty of the machine learning methods was discussed. The results of this paper indicated that machine learning methods had a great potential in up-scaling GPP at flux tower sites. The validation of up-scaled GPP, using five machine learning methods, demonstrated that up-scaled GPP using random forest obtained the highest accuracy.https://www.mdpi.com/2072-4292/13/13/2448GPPup-scalingmachine learningvalidation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Tao Yu Qiang Zhang Rui Sun |
spellingShingle |
Tao Yu Qiang Zhang Rui Sun Comparison of Machine Learning Methods to Up-Scale Gross Primary Production Remote Sensing GPP up-scaling machine learning validation |
author_facet |
Tao Yu Qiang Zhang Rui Sun |
author_sort |
Tao Yu |
title |
Comparison of Machine Learning Methods to Up-Scale Gross Primary Production |
title_short |
Comparison of Machine Learning Methods to Up-Scale Gross Primary Production |
title_full |
Comparison of Machine Learning Methods to Up-Scale Gross Primary Production |
title_fullStr |
Comparison of Machine Learning Methods to Up-Scale Gross Primary Production |
title_full_unstemmed |
Comparison of Machine Learning Methods to Up-Scale Gross Primary Production |
title_sort |
comparison of machine learning methods to up-scale gross primary production |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2021-06-01 |
description |
Eddy covariance observation is an applicable way to obtain accurate and continuous carbon flux at flux tower sites, while remote sensing technology could estimate carbon exchange and carbon storage at regional and global scales effectively. However, it is still challenging to up-scale the field-observed carbon flux to a regional scale, due to the heterogeneity and the unstable air conditions at the land surface. In this paper, gross primary production (GPP) from ground eddy covariance systems were up-scaled to a regional scale by using five machine learning methods (Cubist regression tree, random forest, support vector machine, artificial neural network, and deep belief network). Then, the up-scaled GPP were validated using GPP at flux tower sites, weighted GPP in the footprint, and MODIS GPP products. At last, the sensitivity of the input data (normalized difference vegetation index, fractional vegetation cover, shortwave radiation, relative humidity and air temperature) to the precision of up-scaled GPP was analyzed, and the uncertainty of the machine learning methods was discussed. The results of this paper indicated that machine learning methods had a great potential in up-scaling GPP at flux tower sites. The validation of up-scaled GPP, using five machine learning methods, demonstrated that up-scaled GPP using random forest obtained the highest accuracy. |
topic |
GPP up-scaling machine learning validation |
url |
https://www.mdpi.com/2072-4292/13/13/2448 |
work_keys_str_mv |
AT taoyu comparisonofmachinelearningmethodstoupscalegrossprimaryproduction AT qiangzhang comparisonofmachinelearningmethodstoupscalegrossprimaryproduction AT ruisun comparisonofmachinelearningmethodstoupscalegrossprimaryproduction |
_version_ |
1721298681879068672 |