Seismic Fault Detection Using Convolutional Neural Networks Trained on Synthetic Poststacked Amplitude Maps

Pochet Axelle; Diniz Pedro H. B.; Lopes Halo; Gattass Marcelo

国产bbaaaaa片,成年美女黄网站色视频免费,成年黄大片,а天堂中文最新一区二区三区,成人精品视频一区二区三区尤物

首頁> 外文期刊>IEEE Geoscience and Remote Sensing Letters >Seismic Fault Detection Using Convolutional Neural Networks Trained on Synthetic Poststacked Amplitude Maps

【24h】

Seismic Fault Detection Using Convolutional Neural Networks Trained on Synthetic Poststacked Amplitude Maps

機(jī)譯：使用在合成后疊加振幅圖上訓(xùn)練的卷積神經(jīng)網(wǎng)絡(luò)進(jìn)行地震故障檢測(cè)

獲取原文

獲取原文并翻譯 | 示例

開具論文收錄證明 >>

頁面導(dǎo)航

摘要
著錄項(xiàng)
引文網(wǎng)絡(luò)
相似文獻(xiàn)
相關(guān)主題

摘要

Fault detection is a crucial step in reservoir characterization. Despite the many tools developed in the past decades, automation of this task remains a challenge. We investigate the application of convolutional neural networks (CNNs) to seismic fault detection. CNN is a deep learning method growing in interest in the computer vision community, due to its high performances in a great variety of object detection tasks. One of the constraints of this method is the need to provide a massive number of interpreted data, a requirement particularly difficult to attend in the seismic area. To this end, we built a synthetic data set with simple fault geometries. The input of our network is the seismic amplitude only; the method does not require computing any seismic attribute. We apply a strategy of patch classification along the images, which requires a simple postprocess to extract the exact fault location. Our network shows good results on synthetic data and encouraging results when tested on regions of a real section of The Netherland offshore F3 block in the North Sea.

機(jī)譯：故障檢測(cè)是儲(chǔ)層表征中的關(guān)鍵步驟。盡管在過去的幾十年中開發(fā)了許多工具，但這項(xiàng)任務(wù)的自動(dòng)化仍然是一個(gè)挑戰(zhàn)。我們研究了卷積神經(jīng)網(wǎng)絡(luò)（CNN）在地震故障檢測(cè)中的應(yīng)用。 CNN是一種深度學(xué)習(xí)方法，由于其在各種對(duì)象檢測(cè)任務(wù)中的高性能而在計(jì)算機(jī)視覺界引起了越來越多的興趣。該方法的限制之一是需要提供大量的解釋數(shù)據(jù)，這一要求在地震地區(qū)尤為困難。為此，我們建立了具有簡單故障幾何形狀的綜合數(shù)據(jù)集。我們網(wǎng)絡(luò)的輸入僅是地震振幅。該方法不需要計(jì)算任何地震屬性。我們對(duì)圖像應(yīng)用補(bǔ)丁分類策略，這需要簡單的后處理來提取確切的故障位置。當(dāng)在北海的荷蘭海上F3區(qū)塊的實(shí)際部分區(qū)域進(jìn)行測(cè)試時(shí)，我們的網(wǎng)絡(luò)在綜合數(shù)據(jù)上顯示出良好的結(jié)果，并獲得令人鼓舞的結(jié)果。

著錄項(xiàng)

來源
《IEEE Geoscience and Remote Sensing Letters》 |2019年第3期|352-356|共5頁
作者
Pochet Axelle; Diniz Pedro H. B.; Lopes Halo; Gattass Marcelo;
展開▼
作者單位

Pontifical Catholic Univ Rio de Janeiro, Dept Informat, BR-22451900 Rio De Janeiro, Brazil;

Pontificia Univ Catolica Rio de Janeiro, Dept Informat, BR-22451900 Rio De Janeiro, Brazil;

Pontifical Catholic Univ Rio de Janeiro, Dept Informat, BR-22451900 Rio De Janeiro, Brazil;

Pontificia Univ Catolica Rio de Janeiro, Dept Informat, BR-22451900 Rio De Janeiro, Brazil;

展開▼
收錄信息
原文格式 PDF
正文語種 eng
中圖分類
關(guān)鍵詞
Convolutional neural networks (CNNs); Hough transform; seismic fault;

機(jī)譯：卷積神經(jīng)網(wǎng)絡(luò);霍夫變換;地震斷層;

相似文獻(xiàn)

外文文獻(xiàn)
中文文獻(xiàn)
專利

1. Seismic Fault Detection Using Convolutional Neural Networks Trained on Synthetic Poststacked Amplitude Maps [J] . Pochet Axelle, Diniz Pedro H. B., Lopes Halo, Annals of the American Thoracic Society . 2019,第3期

機(jī)譯：使用卷積神經(jīng)網(wǎng)絡(luò)培訓(xùn)的抗震故障檢測(cè)綜合性后袋幅度圖
2. Seismic fault detection in real data using transfer learning from a convolutional neural network pre-trained with synthetic seismic data [J] . Computers & geosciences . 2020,第Feba期

機(jī)譯：使用從經(jīng)過合成地震數(shù)據(jù)預(yù)訓(xùn)練的卷積神經(jīng)網(wǎng)絡(luò)的轉(zhuǎn)移學(xué)習(xí)中獲取實(shí)際數(shù)據(jù)中的地震故障
3. FaultSeg3D: Using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation [J] . Wu Xinming, Liang Luming, Shi Yunzhi, Geophysics: Journal of the Society of Exploration Geophysicists . 2019,第3期

機(jī)譯：FAULTSEG3D：使用合成數(shù)據(jù)集培訓(xùn)用于3D地震故障分割的端到端卷積神經(jīng)網(wǎng)絡(luò)
4. Object Detection and Pose Estimation Based on Convolutional Neural Networks Trained with Synthetic Data [C] . Josip Josifovski, Matthias Kerzel, Christoph Pregizer, IEEE/RSJ International Conference on Intelligent Robots and Systems . 2018

機(jī)譯：綜合數(shù)據(jù)訓(xùn)練的卷積神經(jīng)網(wǎng)絡(luò)目標(biāo)檢測(cè)與姿態(tài)估計(jì)
5. Spam Review Detection Using Self-Organizing Maps and Convolutional Neural Networks [D] . Neisari, Ashraf. 2020

機(jī)譯：使用自組織地圖和卷積神經(jīng)網(wǎng)絡(luò)的垃圾郵件審查檢測(cè)
6. Breast cancer detection using synthetic mammograms from generative adversarial networks in convolutional neural networks [O] . Shuyue Guan, Murray Loew 2019

機(jī)譯：在卷積神經(jīng)網(wǎng)絡(luò)中使用生成對(duì)抗網(wǎng)絡(luò)的合成乳房X線照片檢測(cè)乳腺癌
7. Improving Regional and Teleseismic Detection for Single-Trace Waveforms Using a Deep Temporal Convolutional Neural Network Trained with an Array-Beam Catalog [O] . Joshua Dickey, Brett Borghetti, William Junek 2019

機(jī)譯：使用具有陣列束目錄訓(xùn)練的深顳卷積神經(jīng)網(wǎng)絡(luò)，從而改善單跡波形的區(qū)域和情感檢測(cè)

獲取原文

客服郵箱：kefu@zhangqiaokeyan.com

京公網(wǎng)安備：11010802029741號(hào) ICP備案號(hào)：京ICP備15016152號(hào)-6 六維聯(lián)合信息科技 (北京) 有限公司?版權(quán)所有

客服微信
服務(wù)號(hào)

国产bbaaaaa片,成年美女黄网站色视频免费,成年黄大片,а天堂中文最新一区二区三区,成人精品视频一区二区三区尤物

Seismic Fault Detection Using Convolutional Neural Networks Trained on Synthetic Poststacked Amplitude Maps

摘要

著錄項(xiàng)

引文網(wǎng)絡(luò)

相似文獻(xiàn)

相關(guān)主題

期刊訂閱