DeepLog: Identify Tight Gas Reservoir Using Multi-Log Signals by a Fully Convolutional Network
| Autor: | Liang Wang, Zhongwei Sun, Kai Zhu, Yonghui Du, Cong Jiang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
business.industry Deep learning Feature extraction 0211 other engineering and technologies Pattern recognition 02 engineering and technology Geotechnical Engineering and Engineering Geology Convolutional neural network Convolution Point (geometry) Artificial intelligence Electrical and Electronic Engineering Layer (object-oriented design) business Tight gas 021101 geological & geomatics engineering |
| Zdroj: | IEEE Geoscience and Remote Sensing Letters. 17:568-571 |
| ISSN: | 1558-0571 1545-598X |
| DOI: | 10.1109/lgrs.2019.2930587 |
| Popis: | In most cases, reservoir properties at one certain depth in the layer can be explicated by logging signals at just this depth point. In fact, the properties of complex reservoirs are often implicated in logging signals from the whole adjacent region of this certain depth point. So far, there is no effective way to solve this problem completely. For the first time, this letter tried to build a fully convolutional neural network (FCNN) to detect hydrocarbon from logging signals for the tight gas reservoir of Ordos Basin. The FCNN was based on a well-designed VGG-net. The prediction comparison between the empirical approach (EMA) and FCNN was implemented on 48 layers. The accuracy of FCNN was about 87.5%, which was higher than that of the EMA (75.0%). FCNN provided more reliable gas testing recommendations, especially when thin layers led to complex reservoir conditions. Deep learning (DL) has been proven to be an automatic feature extraction and direct hydrocarbon detection approach from logging signals. We are looking forward to its improvement and development in geophysics. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|