Picarro, Inc.

Aaron Van Pelt

Sze Meng Tan

David Steele

Chris W Rella

Yonggang He

Sean Patrick MacMullin

Alex Balkanski

Tim Clark

Chris W Relia

In some embodiments, data from multiple vehicle-based natural gas leak detection survey runs are used by computer-implemented machine learning systems to generate a list of natural gas leaks ranked by hazard level. A risk model embodies training data having known hazard levels, and is used to classify newly-discovered leaks. Hazard levels may be expressed by continuous variables, and/or probabilities that a given leak fits within a predefined category of hazard (e.g. Grades 1-3). Each leak is represented by a cluster of leak indications (peaks) originating from a common leak source. Hazard-predictive features may include maximum, minimum, mean, and/or median CH4/amplitude of aggregated leak indications; estimated leak flow rate, determined from an average of leak indications in a cluster; likelihood of leak being natural gas based on other indicator data (e.g. ethane concentration); probability the leak was detected on a given pass; and estimated distance to leak source.

Leak detection event aggregation and ranking systems and methods

In some embodiments, data from multiple vehicle-based natural gas leak detection survey runs are used by computer-implemented machine learning systems to generate a list of natural gas leaks ranked by hazard level. A risk model embodies training data having known hazard levels, and is used to classify newly-discovered leaks. Hazard levels may be expressed by continuous variables, and/or probabilities that a given leak fits within a predefined category of hazard (e.g. Grades 1-3). Each leak is represented by a cluster of leak indications (peaks) originating from a common leak sources. Hazard-predictive features may include maximum, minimum, mean, and/or median CH4/amplitude of aggregated leak indications; estimated leak flow rate, determined from an average of leak indications in a cluster; likelihood of leak being natural gas based on other indicator data (e.g. ethane concentration); probability the leak was detected on a given pass; and estimated distance to leak source.

In some embodiments, a natural gas leak detection system generates display content including indicators of remote and local potential leak source areas situated on a map of an area of a gas concentration measurement survey performed by a vehicle-borne device. The remote area may be shaped as a wedge extending upwind from an associated gas concentration measurement point. The local area graphically represents a potential local leak source area situated around the gas concentration measurement point, and having a boundary within a predetermined distance (e.g. 10 meters) of the gas concentration measurement point. The local area may be represented as a circle, ellipse, or other shape, and may include an area downwind from the measurement point. Size and/or shape parameters of the local area indicator may be determined according to survey vehicle speed and direction data, and/or wind speed and direction data characterizing the measurement point.

Gas detection systems and methods using measurement position uncertainty representations

Growing community of inventors

Hayward, CA, United States of America

Aaron Van Pelt