Method for classifying AVO data using an interpreter-trained neural network

US6662112B2 · kind B2 · utility

Assignee

• EXXONMOBIL UPSTREAM RESEARCH COMPANY · US

Inventors

• John Eastwood · Bellaire, US
• Brian P. West · Houston, US
• Michael Gross · Salem, DE
• Dwight C. Dawson · Spring, US
• David H. Johnston · Redondo Beach, US

Key dates

• Filing date: Aug 29, 2002
• Grant date: Dec 9, 2003
• Expiry date: Aug 29, 2022

Classification

• Technology area (CPC G): Physics
• CPC primary: G01V1/34
• WIPO field: Measurement
• WIPO sector: Instruments

Abstract

AVO anomalies are classified in near-offset and far-offset seismic data volumes, by first calculating a plurality of initial AVO seismic attributes representative of the offset seismic data volumes. A probabilistic neural network is constructed from the calculated initial AVO seismic attributes. AVO anomaly classifications are calculated in a portion of the offset seismic data volumes. The preceding steps are repeated until the calculated AVO anomaly classifications in the portion of the offset seismic data volumes are satisfactory. AVO anomaly classifications are calculated throughout the offset seismic data volumes using the constructed probabilistic neural network.