干旱区生态环境知识资源中心(Arid): Leveraging Google Earth Engine (GEE) and machine learning algorithms to incorporate in situ measurement from different times for rangelands monitoring

Arid

DOI	10.1016/j.rse.2019.111521
	Leveraging Google Earth Engine (GEE) and machine learning algorithms to incorporate in situ measurement from different times for rangelands monitoring
	Zhou, Bo; Okin, Gregory S.; Zhang, Junzhe
通讯作者	Zhou, Bo
来源期刊	REMOTE SENSING OF ENVIRONMENT
ISSN	0034-4257
EISSN	1879-0704
出版年	2020
卷号	236
英文摘要	Mapping and monitoring of indicators of soil cover, vegetation structure, and various native and non-native species is a critical aspect of rangeland management. With the advancement in satellite imagery as well as cloud storage and computing, the capability now exists to conduct planetary-scale analysis, including mapping of rangeland indicators. Combined with recent investments in the collection of large amounts of in situ data in the western U.S., new approaches using machine learning can enable prediction of surface conditions at times and places when no in situ data are available. However, little analysis has yet been done on how the temporal relevancy of training data influences model performance. Here, we have leveraged the Google Earth Engine (GEE) platform and a machine learning algorithm (Random Forest, after comparison with other candidates) to identify the potential impact of different sampling times (across months and years) on estimation of rangeland indicators from the Bureau of Land Management's (BLM) Assessment, Inventory, and Monitoring (AIM) and Landscape Monitoring Framework (LMF) programs. Our results indicate that temporally relevant training data improves predictions, though the training data need not be from the exact same month and year for a prediction to be temporally relevant. Moreover, inclusion of training data from the time when predictions are desired leads to lower prediction error but the addition of training data from other times does not contribute to overall model error. Using all of the available training data can lead to biases, toward the mean, for times when indicator values are especially high or low. However, for mapping purposes, limiting training data to just the time when predictions are desired can lead to poor predictions of values outside the spatial range of the training data for that period. We conclude that the best Random Forest prediction maps will use training data from all possible times with the understanding that estimates at the extremes will be biased.
英文关键词	Google earth engine Big data Machine learning Domain adaptation Transfer learning Feature selection Rangeland monitoring
类型	Article
语种	英语
国家	USA
收录类别	SCI-E
WOS记录号	WOS:000502894400026
WOS关键词	LAND-COVER DATABASE ; VEGETATION ; SURFACE ; DESERTIFICATION ; REFLECTANCE ; VARIABILITY ; INDICATORS ; SCIENCE
WOS类目	Environmental Sciences ; Remote Sensing ; Imaging Science & Photographic Technology
WOS研究方向	Environmental Sciences & Ecology ; Remote Sensing ; Imaging Science & Photographic Technology
EI主题词	2020-01-01
来源机构	University of California, Los Angeles
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/312260
作者单位	Univ Calif Los Angeles, Dept Geog, 1255 Bunche Hall, Los Angeles, CA 90095 USA
推荐引用方式 GB/T 7714	Zhou, Bo,Okin, Gregory S.,Zhang, Junzhe. Leveraging Google Earth Engine (GEE) and machine learning algorithms to incorporate in situ measurement from different times for rangelands monitoring[J]. University of California, Los Angeles,2020,236.
APA	Zhou, Bo,Okin, Gregory S.,&Zhang, Junzhe.(2020).Leveraging Google Earth Engine (GEE) and machine learning algorithms to incorporate in situ measurement from different times for rangelands monitoring.REMOTE SENSING OF ENVIRONMENT,236.
MLA	Zhou, Bo,et al."Leveraging Google Earth Engine (GEE) and machine learning algorithms to incorporate in situ measurement from different times for rangelands monitoring".REMOTE SENSING OF ENVIRONMENT 236(2020).