气候变化领域集成服务门户(CCPortal): Deep Learning as a Tool to Forecast Hydrologic Response for Landslide-Prone Hillslopes

CCPortal

DOI	10.1029/2020GL088731
	Deep Learning as a Tool to Forecast Hydrologic Response for Landslide-Prone Hillslopes
	Orland E.; Roering J.J.; Thomas M.A.; Mirus B.B.
发表日期	2020
ISSN	0094-8276
卷号	47 期号:16
英文摘要	Empirical thresholds for landslide warning systems have benefitted from the incorporation of soil-hydrologic monitoring data, but the mechanistic basis for their predictive capabilities is limited. Although physically based hydrologic models can accurately simulate changes in soil moisture and pore pressure that promote landslides, their utility is restricted by high computational costs and nonunique parameterization issues. We construct a deep learning model using soil moisture, pore pressure, and rainfall monitoring data acquired from landslide-prone hillslopes in Oregon, USA, to predict the timing and magnitude of hydrologic response at multiple soil depths for 36-hr intervals. We find that observation records as short as 6 months are sufficient for accurate predictions, and our model captures hydrologic response for high-intensity rainfall events even when those storm types are excluded from model training. We conclude that machine learning can provide an accurate and computationally efficient alternative to empirical methods or physical modeling for landslide hazard warning. ©2020. American Geophysical Union. All Rights Reserved.
英文关键词	Forecasting; Landslides; Learning systems; Monitoring; Pore pressure; Rain; Soil moisture; Accurate prediction; Computational costs; Computationally efficient; High intensity rainfall; Hydrologic monitoring; Hydrologic response; Physically-based hydrologic models; Predictive capabilities; Deep learning; early warning system; hazard assessment; hillslope; hydrological regime; landslide; machine learning; parameterization; pore pressure; precipitation intensity; soil moisture; storm surge; Oregon; United States
语种	英语
来源期刊	Geophysical Research Letters
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/169941
作者单位	Department of Earth Sciences, University of Oregon, Eugene, OR, United States; U.S. Geological Survey Geologic Hazards Science Center, Golden, CO, United States
推荐引用方式 GB/T 7714	Orland E.,Roering J.J.,Thomas M.A.,et al. Deep Learning as a Tool to Forecast Hydrologic Response for Landslide-Prone Hillslopes[J],2020,47(16).
APA	Orland E.,Roering J.J.,Thomas M.A.,&Mirus B.B..(2020).Deep Learning as a Tool to Forecast Hydrologic Response for Landslide-Prone Hillslopes.Geophysical Research Letters,47(16).
MLA	Orland E.,et al."Deep Learning as a Tool to Forecast Hydrologic Response for Landslide-Prone Hillslopes".Geophysical Research Letters 47.16(2020).