AGTML: A novel approach to land cover classification by integrating automatic generation of training samples and machine learning algorithms on Google Earth Engine
文献类型: 外文期刊
作者: Cui, Yanglin 1 ; Yang, Gaoxiang 2 ; Zhou, Yanbing 1 ; Zhao, Chunjiang 1 ; Pan, Yuchun 1 ; Sun, Qian 1 ; Gu, Xiaohe 1 ;
作者机构: 1.Beijing Acad Agr & Forestry Sci, Informat Technol Res Ctr, Beijing 100097, Peoples R China
2.Nanjing Agr Univ, Natl Engn & Technol Ctr Informat Agr, Nanjing 210095, Jiangsu, Peoples R China
3.China Agr Univ, Coll Informat & Elect Engn, Beijing 100083, Peoples R China
关键词: Land cover mapping; Landsat 8; Machine learning; Optimal focal radii; Training sample generation
期刊名称:ECOLOGICAL INDICATORS ( 影响因子:6.9; 五年影响因子:6.6 )
ISSN: 1470-160X
年卷期: 2023 年 154 卷
页码:
收录情况: SCI
摘要: The timely, accurate, and automatic acquisition of land cover (LC) information is a prerequisite for detecting LC dynamics and performing ecological analyses. Cloud computing platforms, such as the Google Earth Engine, have substantially improved the efficiency and scale of LC classification. However, the lack of sufficient and representative training samples hinders automatic and accurate LC classification. In this study, we propose a new approach that integrates the automatic generation of training samples and machine learning algorithms (AGTML) for LC classification in Heilongjiang Province, China. After optimal focal radii were determined for different LC types using Landsat 8 based on focal statistics and unique phenology. Then target training samples were automatically generated based on the improved distance measure SED (a composite of Spectral angle distance (SAD) and Euclidean distance (ED)). Furthermore, LC classification was performed using four feature combinations and three machine learning algorithms. According to independent validation data, the automatically generated training samples demonstrated good representativeness and stability among all three classifiers, with an overall accuracy (OA) of classification higher than 86%, and showed high consistency in the landscape pattern of classification. RF yielded the highest classification accuracy (92.99% OA). AGTML outperformed GLCFCS30 in identifying large fragmentation and small patch regions in the landscape types. The AGTML approach was subsequently applied to the Guanzhong Plain using different satellite imagery. Results were consistent and accurate (>96.50% OA), demonstrating that the AGTML approach can be applied to various regions and sensors, and has immense potential for automated LC classification across regional and global scales.
- 相关文献
作者其他论文 更多>>
-
Deceptive evidence detection in information fusion of belief functions based on reinforcement learning
作者:Kang, Bingyi;Zhao, Chunjiang;Kang, Bingyi;Zhao, Chunjiang;Zhao, Chunjiang;Kang, Bingyi
关键词:Deceptive evidence detection; Information fusion; Reinforcement learning; Dempster-Shafer evidence theory; Belief entropy; Conflict management
-
Hybrid Uncalibrated Visual Servoing Control of Harvesting Robots With RGB-D Cameras
作者:Li, Tao;Zhao, Chunjiang;Yu, Jinpeng;Yu, Jinpeng;Qiu, Quan
关键词:Depth camera; object detection; robotics; tracking control; uncalibrated system; visual servoing (VS)
-
Improvement of the growth performance, intestinal health, and water quality in juvenile crucian carp (Carassius auratus gibelio) biofortified system with the bacteria-microalgae association br
作者:Wang, Chu;Xu, Shengjun;Jiang, Cancan;Sun, Qian;Zhuang, Xuliang;Wang, Chu;Peng, Xiawei;Xie, Xiangming;Zhou, Xiaodong;Zhu, Lifei
关键词:Biofortified system; Bioremediation; Bacteria-microalgae association; Juvenile crucian; Intestinal microbiota
-
LettuceGDB: The community database for lettuce genetics and omics
作者:Guo, Zhonglong;Li, Bo;Du, Jianjun;Shen, Fei;Zhao, Yongxin;Deng, Yang;Kuang, Zheng;Lu, Xianju;Wang, Ying;Wei, Jianhua;Guo, Xinyu;Zhao, Chunjiang;Yang, Xiaozeng;Guo, Zhonglong;Tao, Yihan;Wan, Miaomiao;Wang, Ying;Li, Lei;Guo, Zhonglong;Tao, Yihan;Wan, Miaomiao;Wang, Ying;Li, Lei;Guo, Zhonglong;Li, Bo;Shen, Fei;Zhao, Yongxin;Deng, Yang;Kuang, Zheng;Wang, Ying;Yang, Xiaozeng;Guo, Zhonglong;Du, Jianjun;Lu, Xianju;Guo, Xinyu;Zhao, Chunjiang;Wang, Dong;Han, Yingyan
关键词:lettuce; genome; multi-omics; germplasms; breeding; community
-
Differential analysis and genome-wide association analysis of stomata density of maize inbred lines leaves at ear position
作者:Jin, Yu;Wang, Jinglu;Guo, Xinyu;Zhao, Chunjiang;Wang, Jinglu;Zhang, Ying;Lu, Xianju;Wen, Weiliang;Liu, Xiang;Guo, Xinyu;Zhao, Chunjiang;Wang, Jinglu;Zhang, Ying;Lu, Xianju;Wen, Weiliang;Liu, Xiang;Guo, Xinyu;Zhao, Chunjiang;Zhao, Yanxin
关键词:maize; ear leaf; stomata density; genome-wide association analysis; haplotype
-
Towards resilience effectiveness: Assessing its patterns and determinants to identify optimal geographic zones
作者:Cheng, Tong;Zhao, Yonghua;Gao, Peng;Zhang, Mengna;Zhao, Chunjiang;Cheng, Tong;Zhao, Yonghua;Song, Yongze;Zhang, Zehua;Ma, Le;Luo, Peng;Zhao, Chunjiang;Zhao, Yonghua;Zhao, Chunjiang
关键词:COVID-19; Resilience effectiveness; Economic resilience; Patterns; Determinants; Optimal geographic zones
-
Energy-Saving Control Method for Factory Mushroom Room Air Conditioning Based on MPC
作者:Wang, Mingfei;Zhao, Chunjiang;Chen, Yang;Chen, Chunling;Wang, Mingfei;Zheng, Wengang;Zhao, Chunjiang;Zhang, Xin
关键词:mushroom room; energy conservation; neural network; MPC