A deep learning network for estimation of seismic local slopes
- PDF / 8,506,146 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 77 Downloads / 203 Views
ORIGINAL ARTICLE
A deep learning network for estimation of seismic local slopes Wei‑Lin Huang1 · Fei Gao1 · Jian‑Ping Liao2,3 · Xiao‑Yu Chuai4 Received: 18 June 2020 / Accepted: 14 September 2020 © The Author(s) 2020
Abstract The local slopes contain rich information of the reflection geometry, which can be used to facilitate many subsequent procedures such as seismic velocities picking, normal move out correction, time-domain imaging and structural interpretation. Generally the slope estimation is achieved by manually picking or scanning the seismic profile along various slopes. We present here a deep learning-based technique to automatically estimate the local slope map from the seismic data. In the presented technique, three convolution layers are used to extract structural features in a local window and three fully connected layers serve as a classifier to predict the slope of the central point of the local window based on the extracted features. The deep learning network is trained using only synthetic seismic data, it can however accurately estimate local slopes within real seismic data. We examine its feasibility using simulated and real-seismic data. The estimated local slope maps demonstrate the successful performance of the synthetically-trained network. Keywords Deep learning · Neural network · Seismic data · Local slopes
1 Introduction As one of the geometric attributes of seismic signal, the local slopes contain complete information of the reflection geometry, which is of great significance to the analysis of seismic data. An accurate estimation of the slope information can benefit many subsequent procedures such as horizons interpretation (Fomel 2010; Wu and Hale 2015), structure enhancement (Hale 2009; Liu et al. 2010), incoherent/ Edited by Jie Hao and Xiu-Qiu Peng * Wei‑Lin Huang [email protected] * Xiao‑Yu Chuai [email protected] 1
State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum-Beijing, Beijing 102249, China
2
State Key Laboratory of Coal Resources and Safe Mining, China University of Mining and Technology-Beijing, Beijing 100083, China
3
Hunan Provincial Key Laboratory of Shale Gas Resource Utilization, Hunan University of Science and Technology, Xiangtan 411201, China
4
Hebei Coal Research Institute Co., Ltd, Jizhong Energy Group, Xingtai 054000, China
coherent noise attenuation (Liu et al. 2015; Huang et al. 2017), deblending (Huang et al. 2018), seismic interpolation/reconstruction (Gan et al. 2016; Huang and Liu 2020), inversion (Yao et al. 2020; Liu et al. 2020a) and imaging (Fomel 2007; Zhang et al. 2019b). The introduction of local slopes into seismic data processing can be traced back to the work of Rieber (1936), in this basic, a method of controlled direction reception is developed, which can achieve excellent results in seismic processing and interpretation (Riabinkin 1957). After then, a number of researchers have used several techniques to estimate the local slopes. Ottolini (1983) proposed a picking method of local
Data Loading...
