U-shaped deep-learning models for island ecosystem type classification, a case study in Con Dao Island of Vietnam

IF 1.8 Q3 ECOLOGY One Ecosystem Pub Date : 2022-02-14 DOI:10.3897/oneeco.7.e79160
Kinh Bac Dang, T. Nguyen, H. Nguyen, Q. Truong, Thi Phuong Vu, Hanh Nguyen Pham, T. Duong, Van Trong Giang, Duc Minh Nguyen, Thu Huong Bui, Benjamin Burkhard
{"title":"U-shaped deep-learning models for island ecosystem type classification, a case study in Con Dao Island of Vietnam","authors":"Kinh Bac Dang, T. Nguyen, H. Nguyen, Q. Truong, Thi Phuong Vu, Hanh Nguyen Pham, T. Duong, Van Trong Giang, Duc Minh Nguyen, Thu Huong Bui, Benjamin Burkhard","doi":"10.3897/oneeco.7.e79160","DOIUrl":null,"url":null,"abstract":"The monitoring of ecosystem dynamics utilises time and resources from scientists and land-use managers, especially in wetland ecosystems in islands that have been affected significantly by both the current state of oceans and human-made activities. Deep-learning models for natural and anthropogenic ecosystem type classification, based on remote sensing data, have become a tool to potentially replace manual image interpretation. This study proposes a U-Net model to develop a deep learning model for classifying 10 island ecosystems with cloud- and shadow-based data using Sentinel-2, ALOS and NOAA remote sensing data. We tested and compared different optimiser methods with two benchmark methods, including support vector machines and random forests. In total, 48 U-Net models were trained and compared. The U-Net model with the Adadelta optimiser and 64 filters showed the best result, because it could classify all island ecosystems with 93 percent accuracy and a loss function value of 0.17. The model was used to classify and successfully manage ecosystems on a particular island in Vietnam. Compared to island ecosystems, it is not easy to detect coral reefs due to seasonal ocean currents. However, the trained deep-learning models proved to have high performances compared to the two traditional methods. The best U-Net model, which needs about two minutes to create a new classification, could become a suitable tool for island research and management in the future.","PeriodicalId":36908,"journal":{"name":"One Ecosystem","volume":" ","pages":""},"PeriodicalIF":1.8000,"publicationDate":"2022-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"One Ecosystem","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3897/oneeco.7.e79160","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ECOLOGY","Score":null,"Total":0}
引用次数: 5

Abstract

The monitoring of ecosystem dynamics utilises time and resources from scientists and land-use managers, especially in wetland ecosystems in islands that have been affected significantly by both the current state of oceans and human-made activities. Deep-learning models for natural and anthropogenic ecosystem type classification, based on remote sensing data, have become a tool to potentially replace manual image interpretation. This study proposes a U-Net model to develop a deep learning model for classifying 10 island ecosystems with cloud- and shadow-based data using Sentinel-2, ALOS and NOAA remote sensing data. We tested and compared different optimiser methods with two benchmark methods, including support vector machines and random forests. In total, 48 U-Net models were trained and compared. The U-Net model with the Adadelta optimiser and 64 filters showed the best result, because it could classify all island ecosystems with 93 percent accuracy and a loss function value of 0.17. The model was used to classify and successfully manage ecosystems on a particular island in Vietnam. Compared to island ecosystems, it is not easy to detect coral reefs due to seasonal ocean currents. However, the trained deep-learning models proved to have high performances compared to the two traditional methods. The best U-Net model, which needs about two minutes to create a new classification, could become a suitable tool for island research and management in the future.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
岛屿生态系统类型分类的U型深度学习模型——以越南康岛岛为例
生态系统动态监测利用了科学家和土地利用管理者的时间和资源,特别是在受到当前海洋状况和人类活动严重影响的岛屿湿地生态系统中。基于遥感数据的自然和人为生态系统类型分类的深度学习模型已成为一种可能取代手动图像解释的工具。本研究提出了一个U-Net模型,以开发一个深度学习模型,利用Sentinel-2、ALOS和NOAA遥感数据,利用基于云和阴影的数据对10个岛屿生态系统进行分类。我们测试并比较了不同的优化器方法与两种基准方法,包括支持向量机和随机森林。总共训练和比较了48个U-Net模型。使用阿达德尔塔优化器和64个滤波器的U-Net模型显示出最好的结果,因为它可以以93%的准确率和0.17的损失函数值对所有岛屿生态系统进行分类。该模型被用于对越南某个特定岛屿的生态系统进行分类并成功管理。与岛屿生态系统相比,由于季节性洋流的影响,检测珊瑚礁并不容易。然而,与两种传统方法相比,训练的深度学习模型被证明具有较高的性能。最好的U-Net模型需要大约两分钟的时间来创建一个新的分类,它可能成为未来岛屿研究和管理的合适工具。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
One Ecosystem
One Ecosystem Environmental Science-Nature and Landscape Conservation
CiteScore
4.60
自引率
0.00%
发文量
26
审稿时长
12 weeks
期刊最新文献
CH4 and N2O emissions and their potential control by rice biomass biochar: The case of continuously flooded paddy fields in Indonesia - A review The influence of naturalness of the landscape structure on children’s connectedness to Nature in north-eastern Italy Historical reconstruction of the invasions of four non-native tree species at local scale: a detective work on Ailanthus altissima, Celtis occidentalis, Prunus serotina and Acer negundo As green infrastructure, linear semi-natural habitats boost regulating ecosystem services supply in agriculturally-dominated landscapes Practical framework for cultural ecosystem service in urban landscape design
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1