干旱区生态环境知识资源中心(Arid): High-resolution paleovalley classification from airborne electromagnetic imaging and deep neural network training using digital elevation model data

Arid

DOI	10.5194/hess-23-2561-2019
	High-resolution paleovalley classification from airborne electromagnetic imaging and deep neural network training using digital elevation model data
	Jiang, Zhenjiao 1,2; Mallants, Dirk 2; Peeters, Luk 3; Gao, Lei 2; Soerensen, Camilla 3; Mariethoz, Gregoire 4
通讯作者	Jiang, Zhenjiao
来源期刊	HYDROLOGY AND EARTH SYSTEM SCIENCES
ISSN	1027-5606
EISSN	1607-7938
出版年	2019
卷号	23 期号:6 页码:2561-2580
英文摘要	Paleovalleys are buried ancient river valleys that often form productive aquifers, especially in the semiarid and arid areas of Australia. Delineating their extent and hydrostratigraphy is however a challenging task in groundwater system characterization. This study developed a methodology based on the deep learning super-resolution convolutional neural network (SRCNN) approach, to convert electrical conductivity (EC) estimates from an airborne electromagnetic (AEM) survey in South Australia to a high-resolution binary paleovalley map. The SRCNN was trained and tested with a synthetic training dataset, where valleys were generated from readily available digital elevation model (DEM) data from the AEM survey area. Electrical conductivities typical of valley sediments were generated by Archie's law, and subsequently blurred by down-sampling and bicubic interpolation to represent noise from the AEM survey, inversion and interpolation. After a model training step, the SRCNN successfully removed such noise, and reclassified the low-resolution, converted unimodal but skewed EC values into a high-resolution paleovalley index following a bimodal distribution. The latter allows us to distinguish valley from non-valley pixels. Furthermore, a realistic spatial connectivity structure of the paleovalley was predicted when compared with borehole lithology logs and a valley bottom flatness indicator. Overall the methodology permitted us to better constrain the three-dimensional paleovalley geometry from AEM images that are becoming more widely available for groundwater prospecting.
类型	Article
语种	英语
国家	Peoples R China ; Australia ; Switzerland
开放获取类型	Green Submitted, gold
收录类别	SCI-E
WOS记录号	WOS:000471598700001
WOS关键词	SUPER-RESOLUTION ; PALEOCHANNELS ; CONDUCTIVITY ; INVERSION ; AQUIFER
WOS类目	Geosciences, Multidisciplinary ; Water Resources
WOS研究方向	Geology ; Water Resources
来源机构	Commonwealth Scientific and Industrial Research Organisation
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/216211
作者单位	1.Jilin Univ, Coll Environm & Resources, Minist Educ, Key Lab Groundwater Resources & Environm, Changchun 130021, Jilin, Peoples R China; 2.CSIRO, Land & Water, Locked Bag 2, Glen Osmond, SA 5064, Australia; 3.CSIRO, Mineral Resources, Locked Bag 2, Glen Osmond, SA 5064, Australia; 4.Univ Lausanne, Fac Geosci & Environm, Inst Earth Surface Dynam, Lausanne, Switzerland
推荐引用方式 GB/T 7714	Jiang, Zhenjiao,Mallants, Dirk,Peeters, Luk,et al. High-resolution paleovalley classification from airborne electromagnetic imaging and deep neural network training using digital elevation model data[J]. Commonwealth Scientific and Industrial Research Organisation,2019,23(6):2561-2580.
APA	Jiang, Zhenjiao,Mallants, Dirk,Peeters, Luk,Gao, Lei,Soerensen, Camilla,&Mariethoz, Gregoire.(2019).High-resolution paleovalley classification from airborne electromagnetic imaging and deep neural network training using digital elevation model data.HYDROLOGY AND EARTH SYSTEM SCIENCES,23(6),2561-2580.
MLA	Jiang, Zhenjiao,et al."High-resolution paleovalley classification from airborne electromagnetic imaging and deep neural network training using digital elevation model data".HYDROLOGY AND EARTH SYSTEM SCIENCES 23.6(2019):2561-2580.