Extraction of bamboo forests based on GEE and remote sensing different feature datasets: a case study of Wuxing District, China

Dejin Dong; Yuichiro Fujioka; Daohong Gong

doi:10.1117/12.3007479

30 August 2023 Extraction of bamboo forests based on GEE and remote sensing different feature datasets: a case study of Wuxing District, China

Dejin Dong, Yuichiro Fujioka, Daohong Gong

Author Affiliations +

Proceedings Volume 12797, Second International Conference on Geographic Information and Remote Sensing Technology (GIRST 2023); 127972U (2023) https://doi.org/10.1117/12.3007479
Event: 2nd International Conference on Geographic Information and Remote Sensing Technology (GIRST 2023), 2023, Qingdao, China

Abstract

Bamboo forests, especially Moso bamboo forests, are vital forestry resources due to their rapid growth rate and significant capacity for carbon sequestration. Accurate assessment of the quantity and spatial distribution of bamboo forest resources is essential for the development of the bamboo industry and the assessment of its ecosystem services. However, remote sensing techniques face limitations in detecting Moso bamboo forests due to spectral similarity with other vegetation and the presence of cloud cover. In this study, we used random forests through the Google Earth Engine (GEE) platform in combination with spectral indices, texture and topographic features to classify the study area in Wuxing District, China. The results show that: it is not that the more features the higher the classification accuracy, after the selection of features, the number of features was reduced from 40 to 28, and the classification accuracy (overall accuracy 92.69%, Kappa coefficient 0.91) was slightly improved compared with that before the optimization (overall accuracy 92.17%, Kappa coefficient 0.90). In addition, Topographic features play an important role in land cover classification. This study provides a reference for extracting spatial features using open source remote sensing data.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Dejin Dong, Yuichiro Fujioka, and Daohong Gong "Extraction of bamboo forests based on GEE and remote sensing different feature datasets: a case study of Wuxing District, China", Proc. SPIE 12797, Second International Conference on Geographic Information and Remote Sensing Technology (GIRST 2023), 127972U (30 August 2023); https://doi.org/10.1117/12.3007479

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available