Machine learning-based fracture-hit detection algorithm using LFDAS signal
- 1 July 2019
- journal article
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 38 (7), 520-524
- https://doi.org/10.1190/tle38070520.1
Abstract
Low-frequency distributed acoustic sensing (LFDAS) signal has been used to detect fracture hits at offset monitor wells during hydraulic fracturing operations. Typically, fracture hits are manually identified, which can be subjective and inefficient. We implemented machine learning-based models using supervised learning techniques in order to identify fracture zones, which demonstrate a high probability of fracture hits automatically. Several features are designed and calculated from LFDAS data to highlight fracture-hit characterizations. A simple neural network model is trained to fit the manually picked fracture hits. The fracture-hit probability, as predicted by the model, agrees well with the manual picks in training, validation, and test data sets. The algorithm was used in a case study of an unconventional reservoir. The results indicate that smaller cluster spacing design creates denser fractures.Keywords
This publication has 8 references indexed in Scilit:
- Hydraulic-fracture geometry characterization using low-frequency DAS signalGeophysics, 2017
- New Age Fracture Mapping Diagnostic Tools-A STACK Case StudyPublished by Society of Petroleum Engineers (SPE) ,2017
- Perforation Cluster Efficiency of Cemented Plug and Perf Limited Entry Completions; Insights from Fiber Optics DiagnosticsPublished by Society of Petroleum Engineers (SPE) ,2016
- Monitoring Hydraulic Fracturing Operations Using Fiber-Optic Distributed Acoustic SensingPublished by American Association of Petroleum Geologists AAPG/Datapages ,2015
- 3-D Hydraulic Fracturing and Reservoir Flow Modeling—Key to the Successful Implementation of a Geo-Engineered Completion Optimization Program in the Eagle Ford ShalePublished by American Association of Petroleum Geologists AAPG/Datapages ,2015
- Fiber-Optic Monitoring: Stimulation Results From Unconventional ReservoirsPublished by American Association of Petroleum Geologists AAPG/Datapages ,2015
- Flow Monitoring and Production Profiling Using DASPublished by Society of Petroleum Engineers (SPE) ,2014
- A logical calculus of the ideas immanent in nervous activityBulletin of Mathematical Biology, 1943