Predicting the Forest Canopy Height from LiDAR and Multi-Sensor Data Using Machine Learning over India
Forest canopy height estimates, at a regional scale, help understand the forest carbon storage, ecosystem processes, the development of forest management and the restoration policies to mitigate global climate change, etc. The recent availability of the NASA’s Global Ecosystem Dynamics Investigation...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-11-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/14/23/5968 |
_version_ | 1797462229935718400 |
---|---|
author | Sujit M. Ghosh Mukunda D. Behera Subham Kumar Pulakesh Das Ambadipudi J. Prakash Prasad K. Bhaskaran Parth S. Roy Saroj K. Barik Chockalingam Jeganathan Prashant K. Srivastava Soumit K. Behera |
author_facet | Sujit M. Ghosh Mukunda D. Behera Subham Kumar Pulakesh Das Ambadipudi J. Prakash Prasad K. Bhaskaran Parth S. Roy Saroj K. Barik Chockalingam Jeganathan Prashant K. Srivastava Soumit K. Behera |
author_sort | Sujit M. Ghosh |
collection | DOAJ |
description | Forest canopy height estimates, at a regional scale, help understand the forest carbon storage, ecosystem processes, the development of forest management and the restoration policies to mitigate global climate change, etc. The recent availability of the NASA’s Global Ecosystem Dynamics Investigation (GEDI) LiDAR data has opened up new avenues to assess the plant canopy height at a footprint level. Here, we present a novel approach using the random forest (RF) for the wall-to-wall canopy height estimation over India’s forests (i.e., evergreen forest, deciduous forest, mixed forest, plantation, and shrubland) by employing the high-resolution top-of-the-atmosphere (TOA) reflectance and vegetation indices, the synthetic aperture radar (SAR) backscatters, the topography and tree canopy density, as the proxy variables. The variable importance plot indicated that the SAR backscatters, tree canopy density and the topography are the most influential height predictors. 33.15% of India’s forest cover demonstrated the canopy height <10 m, while 44.51% accounted for 10–20 m and 22.34% of forests demonstrated a higher canopy height (>20 m). This study advocates the importance and use of GEDI data for estimating the canopy height, preferably in data-deficit mountainous regions, where most of India’s natural forest vegetation exists. |
first_indexed | 2024-03-09T17:33:32Z |
format | Article |
id | doaj.art-22055cc3a03b4b0386e6c284fcab383b |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-09T17:33:32Z |
publishDate | 2022-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-22055cc3a03b4b0386e6c284fcab383b2023-11-24T12:03:29ZengMDPI AGRemote Sensing2072-42922022-11-011423596810.3390/rs14235968Predicting the Forest Canopy Height from LiDAR and Multi-Sensor Data Using Machine Learning over IndiaSujit M. Ghosh0Mukunda D. Behera1Subham Kumar2Pulakesh Das3Ambadipudi J. Prakash4Prasad K. Bhaskaran5Parth S. Roy6Saroj K. Barik7Chockalingam Jeganathan8Prashant K. Srivastava9Soumit K. Behera10Solid World DAO, Pärnu mnt 15 // Tatari tn 2, 10141 Tallinn, EstoniaCentre for Oceans, Rivers, Atmosphere and Land Sciences, IIT Kharagpur, Kharagpur 721302, IndiaCentre for Oceans, Rivers, Atmosphere and Land Sciences, IIT Kharagpur, Kharagpur 721302, IndiaSustainable Landscapes and Restoration, World Resources Institute India, New Delhi 110016, IndiaCentre for Oceans, Rivers, Atmosphere and Land Sciences, IIT Kharagpur, Kharagpur 721302, IndiaOcean Engineering and Naval Architecture, IIT Kharagpur, Kharagpur 721302, IndiaSustainable Landscapes and Restoration, World Resources Institute India, New Delhi 110016, IndiaCSIR-National Botanical Research Institute, Lucknow 226001, IndiaDepartment of Remote Sensing, Birla Institute of Technology (BIT), Mesra, Ranchi 835215, IndiaInstitute of Environment & Sustainable Development, Banaras Hindu University, Varanasi 221005, IndiaCSIR-National Botanical Research Institute, Lucknow 226001, IndiaForest canopy height estimates, at a regional scale, help understand the forest carbon storage, ecosystem processes, the development of forest management and the restoration policies to mitigate global climate change, etc. The recent availability of the NASA’s Global Ecosystem Dynamics Investigation (GEDI) LiDAR data has opened up new avenues to assess the plant canopy height at a footprint level. Here, we present a novel approach using the random forest (RF) for the wall-to-wall canopy height estimation over India’s forests (i.e., evergreen forest, deciduous forest, mixed forest, plantation, and shrubland) by employing the high-resolution top-of-the-atmosphere (TOA) reflectance and vegetation indices, the synthetic aperture radar (SAR) backscatters, the topography and tree canopy density, as the proxy variables. The variable importance plot indicated that the SAR backscatters, tree canopy density and the topography are the most influential height predictors. 33.15% of India’s forest cover demonstrated the canopy height <10 m, while 44.51% accounted for 10–20 m and 22.34% of forests demonstrated a higher canopy height (>20 m). This study advocates the importance and use of GEDI data for estimating the canopy height, preferably in data-deficit mountainous regions, where most of India’s natural forest vegetation exists.https://www.mdpi.com/2072-4292/14/23/5968GEDIvegetation typeSAR backscatterstopographycanopy height |
spellingShingle | Sujit M. Ghosh Mukunda D. Behera Subham Kumar Pulakesh Das Ambadipudi J. Prakash Prasad K. Bhaskaran Parth S. Roy Saroj K. Barik Chockalingam Jeganathan Prashant K. Srivastava Soumit K. Behera Predicting the Forest Canopy Height from LiDAR and Multi-Sensor Data Using Machine Learning over India Remote Sensing GEDI vegetation type SAR backscatters topography canopy height |
title | Predicting the Forest Canopy Height from LiDAR and Multi-Sensor Data Using Machine Learning over India |
title_full | Predicting the Forest Canopy Height from LiDAR and Multi-Sensor Data Using Machine Learning over India |
title_fullStr | Predicting the Forest Canopy Height from LiDAR and Multi-Sensor Data Using Machine Learning over India |
title_full_unstemmed | Predicting the Forest Canopy Height from LiDAR and Multi-Sensor Data Using Machine Learning over India |
title_short | Predicting the Forest Canopy Height from LiDAR and Multi-Sensor Data Using Machine Learning over India |
title_sort | predicting the forest canopy height from lidar and multi sensor data using machine learning over india |
topic | GEDI vegetation type SAR backscatters topography canopy height |
url | https://www.mdpi.com/2072-4292/14/23/5968 |
work_keys_str_mv | AT sujitmghosh predictingtheforestcanopyheightfromlidarandmultisensordatausingmachinelearningoverindia AT mukundadbehera predictingtheforestcanopyheightfromlidarandmultisensordatausingmachinelearningoverindia AT subhamkumar predictingtheforestcanopyheightfromlidarandmultisensordatausingmachinelearningoverindia AT pulakeshdas predictingtheforestcanopyheightfromlidarandmultisensordatausingmachinelearningoverindia AT ambadipudijprakash predictingtheforestcanopyheightfromlidarandmultisensordatausingmachinelearningoverindia AT prasadkbhaskaran predictingtheforestcanopyheightfromlidarandmultisensordatausingmachinelearningoverindia AT parthsroy predictingtheforestcanopyheightfromlidarandmultisensordatausingmachinelearningoverindia AT sarojkbarik predictingtheforestcanopyheightfromlidarandmultisensordatausingmachinelearningoverindia AT chockalingamjeganathan predictingtheforestcanopyheightfromlidarandmultisensordatausingmachinelearningoverindia AT prashantksrivastava predictingtheforestcanopyheightfromlidarandmultisensordatausingmachinelearningoverindia AT soumitkbehera predictingtheforestcanopyheightfromlidarandmultisensordatausingmachinelearningoverindia |