Remote Sensing-Based Mapping of Senescent Leaf C:N Ratio in the Sundarbans Reserved Forest Using Machine Learning Techniques
Carbon to nitrogen ratio (C:N) of senescent leaf is a crucial functional trait and indicator of litter quality that affects belowground carbon and nitrogen cycles, especially soil decomposition. Although mapping the C:N ratio of fresh mature canopies has been attempted, few studies have attempted to...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-04-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/9/1375 |
id |
doaj-36a07497748645ba8aa35866cb9f800c |
---|---|
record_format |
Article |
spelling |
doaj-36a07497748645ba8aa35866cb9f800c2020-11-25T02:36:28ZengMDPI AGRemote Sensing2072-42922020-04-01121375137510.3390/rs12091375Remote Sensing-Based Mapping of Senescent Leaf C:N Ratio in the Sundarbans Reserved Forest Using Machine Learning TechniquesMd Mizanur Rahman0Xunhe Zhang1Imran Ahmed2Zaheer Iqbal3Mojtaba Zeraatpisheh4Mamoru Kanzaki5Ming Xu6Key Laboratory of Geospatial Technology for the Middle and Lower Yellow River Regions, College of Environment and Planning, Henan University, Kaifeng 475004, ChinaKey Laboratory of Geospatial Technology for the Middle and Lower Yellow River Regions, College of Environment and Planning, Henan University, Kaifeng 475004, ChinaBangladesh Forest Department, Bon Bhaban, Plot No E8, B2, Agargaon, ShereBangla Nagar, Dhaka 1207, BangladeshBangladesh Forest Department, Bon Bhaban, Plot No E8, B2, Agargaon, ShereBangla Nagar, Dhaka 1207, BangladeshKey Laboratory of Geospatial Technology for the Middle and Lower Yellow River Regions, College of Environment and Planning, Henan University, Kaifeng 475004, ChinaGraduate School of Agriculture, Kyoto University, Kitashirakawa Oiwake, Sakyo, Kyoto 6068502, JapanKey Laboratory of Geospatial Technology for the Middle and Lower Yellow River Regions, College of Environment and Planning, Henan University, Kaifeng 475004, ChinaCarbon to nitrogen ratio (C:N) of senescent leaf is a crucial functional trait and indicator of litter quality that affects belowground carbon and nitrogen cycles, especially soil decomposition. Although mapping the C:N ratio of fresh mature canopies has been attempted, few studies have attempted to map the C:N ratio of senescent leaves, particularly in mangroves. In this study, four machine learning models (Stochastic Gradient Boosting, SGB; Random Forest, RF; Support Vector Machine, SVM; and Partial Least Square Regression, PLSR) were compared for testing the predictability of using the Landsat TM 5 (LTM5) and Landsat 8 to map spatial and temporal distribution of C:N ratio of senescent leaves in Sundarbans Reserved Forest (SRF), Bangladesh. Surface reflectance of bands, texture metrics of bands and vegetation indices of LTM5 and Landsat 8 yearly composite images were extracted using Google Earth Engine for 2009–2010 and 2019. We found SGB, RF and SVM were significant different from PLSR based on MAE, RMSE, and R<sup>2</sup> (<i>p</i> < 0.05). Our results indicate that remote sensing data, such as Landsat TM data, can be used to map the C:N ratio of senescent leaves in mangroves with reasonable accuracy. We also found that the mangroves had a high spatial variation of C:N ratio and the C:N ratio map developed in the current study can be used for improving the biogeochemical and ecosystem models in the mangroves.https://www.mdpi.com/2072-4292/12/9/1375functional traitlitter qualitymachine learningspatial modelingremote sensingmangrove |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Md Mizanur Rahman Xunhe Zhang Imran Ahmed Zaheer Iqbal Mojtaba Zeraatpisheh Mamoru Kanzaki Ming Xu |
spellingShingle |
Md Mizanur Rahman Xunhe Zhang Imran Ahmed Zaheer Iqbal Mojtaba Zeraatpisheh Mamoru Kanzaki Ming Xu Remote Sensing-Based Mapping of Senescent Leaf C:N Ratio in the Sundarbans Reserved Forest Using Machine Learning Techniques Remote Sensing functional trait litter quality machine learning spatial modeling remote sensing mangrove |
author_facet |
Md Mizanur Rahman Xunhe Zhang Imran Ahmed Zaheer Iqbal Mojtaba Zeraatpisheh Mamoru Kanzaki Ming Xu |
author_sort |
Md Mizanur Rahman |
title |
Remote Sensing-Based Mapping of Senescent Leaf C:N Ratio in the Sundarbans Reserved Forest Using Machine Learning Techniques |
title_short |
Remote Sensing-Based Mapping of Senescent Leaf C:N Ratio in the Sundarbans Reserved Forest Using Machine Learning Techniques |
title_full |
Remote Sensing-Based Mapping of Senescent Leaf C:N Ratio in the Sundarbans Reserved Forest Using Machine Learning Techniques |
title_fullStr |
Remote Sensing-Based Mapping of Senescent Leaf C:N Ratio in the Sundarbans Reserved Forest Using Machine Learning Techniques |
title_full_unstemmed |
Remote Sensing-Based Mapping of Senescent Leaf C:N Ratio in the Sundarbans Reserved Forest Using Machine Learning Techniques |
title_sort |
remote sensing-based mapping of senescent leaf c:n ratio in the sundarbans reserved forest using machine learning techniques |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2020-04-01 |
description |
Carbon to nitrogen ratio (C:N) of senescent leaf is a crucial functional trait and indicator of litter quality that affects belowground carbon and nitrogen cycles, especially soil decomposition. Although mapping the C:N ratio of fresh mature canopies has been attempted, few studies have attempted to map the C:N ratio of senescent leaves, particularly in mangroves. In this study, four machine learning models (Stochastic Gradient Boosting, SGB; Random Forest, RF; Support Vector Machine, SVM; and Partial Least Square Regression, PLSR) were compared for testing the predictability of using the Landsat TM 5 (LTM5) and Landsat 8 to map spatial and temporal distribution of C:N ratio of senescent leaves in Sundarbans Reserved Forest (SRF), Bangladesh. Surface reflectance of bands, texture metrics of bands and vegetation indices of LTM5 and Landsat 8 yearly composite images were extracted using Google Earth Engine for 2009–2010 and 2019. We found SGB, RF and SVM were significant different from PLSR based on MAE, RMSE, and R<sup>2</sup> (<i>p</i> < 0.05). Our results indicate that remote sensing data, such as Landsat TM data, can be used to map the C:N ratio of senescent leaves in mangroves with reasonable accuracy. We also found that the mangroves had a high spatial variation of C:N ratio and the C:N ratio map developed in the current study can be used for improving the biogeochemical and ecosystem models in the mangroves. |
topic |
functional trait litter quality machine learning spatial modeling remote sensing mangrove |
url |
https://www.mdpi.com/2072-4292/12/9/1375 |
work_keys_str_mv |
AT mdmizanurrahman remotesensingbasedmappingofsenescentleafcnratiointhesundarbansreservedforestusingmachinelearningtechniques AT xunhezhang remotesensingbasedmappingofsenescentleafcnratiointhesundarbansreservedforestusingmachinelearningtechniques AT imranahmed remotesensingbasedmappingofsenescentleafcnratiointhesundarbansreservedforestusingmachinelearningtechniques AT zaheeriqbal remotesensingbasedmappingofsenescentleafcnratiointhesundarbansreservedforestusingmachinelearningtechniques AT mojtabazeraatpisheh remotesensingbasedmappingofsenescentleafcnratiointhesundarbansreservedforestusingmachinelearningtechniques AT mamorukanzaki remotesensingbasedmappingofsenescentleafcnratiointhesundarbansreservedforestusingmachinelearningtechniques AT mingxu remotesensingbasedmappingofsenescentleafcnratiointhesundarbansreservedforestusingmachinelearningtechniques |
_version_ |
1724799966270980096 |