气候变化领域集成服务门户(CCPortal): From calibration to parameter learning: Harnessing the scaling effects of big data in geoscientific modeling

CCPortal

DOI	10.1038/s41467-021-26107-z
	From calibration to parameter learning: Harnessing the scaling effects of big data in geoscientific modeling
	Tsai W.-P.; Feng D.; Pan M.; Beck H.; Lawson K.; Yang Y.; Liu J.; Shen C.
发表日期	2021
ISSN	2041-1723
卷号	12 期号:1
英文摘要	The behaviors and skills of models in many geosciences (e.g., hydrology and ecosystem sciences) strongly depend on spatially-varying parameters that need calibration. A well-calibrated model can reasonably propagate information from observations to unobserved variables via model physics, but traditional calibration is highly inefficient and results in non-unique solutions. Here we propose a novel differentiable parameter learning (dPL) framework that efficiently learns a global mapping between inputs (and optionally responses) and parameters. Crucially, dPL exhibits beneficial scaling curves not previously demonstrated to geoscientists: as training data increases, dPL achieves better performance, more physical coherence, and better generalizability (across space and uncalibrated variables), all with orders-of-magnitude lower computational cost. We demonstrate examples that learned from soil moisture and streamflow, where dPL drastically outperformed existing evolutionary and regionalization methods, or required only ~12.5% of the training data to achieve similar performance. The generic scheme promotes the integration of deep learning and process-based models, without mandating reimplementation. © 2021, The Author(s).
语种	英语
scopus关键词	calibration; computer simulation; mapping; parameterization; performance assessment; soil moisture; spatial variation; streamflow; training; article; big data; calibration; deep learning; regionalization; soil moisture
来源期刊	Nature Communications
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/251337
作者单位	Civil and Environmental Engineering, Pennsylvania State University, University Park, PA, United States; Center for Western Weather and Water Extremes, Scripps Institution of Oceanography, University of California San Diego, La Jolla, CA, United States; Civil and Environmental Engineering, Princeton University, Princeton, NJ, United States; GloH2O, Almere, Netherlands; HydroSapient, Inc, State College, PA, United States; Department of Hydraulic Engineering, Tsinghua University, Beijing, China; Institute of Science and Technology, China Three Gorges Corporation, Beijing, China
推荐引用方式 GB/T 7714	Tsai W.-P.,Feng D.,Pan M.,et al. From calibration to parameter learning: Harnessing the scaling effects of big data in geoscientific modeling[J],2021,12(1).
APA	Tsai W.-P..,Feng D..,Pan M..,Beck H..,Lawson K..,...&Shen C..(2021).From calibration to parameter learning: Harnessing the scaling effects of big data in geoscientific modeling.Nature Communications,12(1).
MLA	Tsai W.-P.,et al."From calibration to parameter learning: Harnessing the scaling effects of big data in geoscientific modeling".Nature Communications 12.1(2021).