气候变化领域集成服务门户(CCPortal): Leveraging Google Earth Engine (GEE) and machine learning algorithms to incorporate in situ measurement from different times for rangelands monitoring

CCPortal

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 B.; Okin G.S.; Zhang J.
发表日期	2020
ISSN	00344257
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. © 2019 Elsevier Inc.
英文关键词	Big data; Domain adaptation; Feature selection; Google earth engine; Machine learning; Rangeland monitoring; Transfer learning
语种	英语
scopus关键词	Big data; Decision trees; Digital storage; Engines; Feature extraction; Forecasting; Learning systems; Machine learning; Mapping; Satellite imagery; Soils; Bureau of land managements; Domain adaptation; Google earths; Monitoring frameworks; Rangeland management; Rangeland monitoring; Transfer learning; Vegetation structure; Learning algorithms; algorithm; in situ measurement; Internet; machine learning; mapping; monitoring; rangeland; satellite imagery
来源期刊	Remote Sensing of Environment
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/179582
作者单位	Department of Geography, University of California, 1255 Bunche Hall, Los Angeles, CA 90095, United States
推荐引用方式 GB/T 7714	Zhou B.,Okin G.S.,Zhang J.. Leveraging Google Earth Engine (GEE) and machine learning algorithms to incorporate in situ measurement from different times for rangelands monitoring[J],2020,236.
APA	Zhou B.,Okin G.S.,&Zhang J..(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 B.,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).