An Algorithm of Association Rule Mining for Microbial Energy Prospection.

Area of Science:

• Geomicrobiology
• Data Mining
• Biogeochemistry

Background:

• Hydrocarbon presence alters soil and sediment microbiology.
• Current detection methods are costly, time-consuming, and specialized.
• Microbial anomalies serve as indicators for subsurface hydrocarbon exploration.

Purpose of the Study:

• To develop a novel, efficient algorithm for hydrocarbon exploration.
• To apply context-based association rule mining to microbial data.
• To correlate microbial attributes with hydrocarbon presence using non-spatial data.

Main Methods:

• Modified context-based association rule mining algorithm for non-spatial data.
• Utilized a curated database of microbial indicators and soil manifestations.
• Generated direct and indirect associations among microbial attributes.

Main Results:

• The algorithm successfully mined associations between microbial indicators and hydrocarbon reserves.
• Demonstrated higher accuracy in rule generation for non-spatial data.
• Provided reliable and robust rules for predicting hydrocarbon presence.

Conclusions:

• The proposed algorithm offers an accurate and efficient approach for hydrocarbon exploration.
• Context-based association rule mining is effective for analyzing microbial data in this context.
• This method reduces the cost and time associated with traditional detection techniques.