Method and systems for remote emission detection and rate determination

Patent metadata

Field	Value
Publication number	US-10921245-B2
Application number	US-201816235827-A
Country	US
Kind code	B2
Filing date	Dec 28, 2018
Priority date	Jun 8, 2018
Publication date	Feb 16, 2021
Grant date	Feb 16, 2021

Abstract

Methods and systems for remotely detecting gases and emissions of gases are provided. Data is collected from a scene using a sensor system. The data is initially optionally processed as 1D data to remove noise, and is then assigned a confidence value by processing the 1D data using a neural network. The confidence value is related to a likelihood that an emission has been detected at a particular location. The processed 1D data, including the confidence value, is gridded into 2D space. The 2D data is then processed using a neural network to assign a 2D confidence value. The 2D data can be fused with RGB data to produce a map of emission source locations. The data identifying emissions can also be processed using a neural network to determine and output emission rate data.

First claim

What is claimed is:

1. A method for detecting gas plumes, comprising:
obtaining data for a plurality of points within a scene, wherein the data includes a concentration value for a gas of interest at each of a plurality of different locations within a scene;
processing the data including the concentration value for the gas of interest at each of the plurality of different locations within the scene in a neural network to obtain a confidence value;
gridding the obtained and processed data to obtain 2D data;
processing the 2D data in a neural network to obtain a 2D confidence value;
spatially correlating the 2D data; and
outputting the spatially correlated 2D data as a map of likely emission locations for the gas of interest.

2. The method of claim 1 , removing noise from the data prior to processing the data.

3. The method of claim 1 , wherein the 2D data is associated with concentration data concerning a gas of interest.

4. The method of claim 1 , wherein the 2D data is associated with range data.

5. The method of claim 4 , wherein the 2D data is associated with reflectance data.

6. The method of claim 5 , wherein the 2D data is processed using a long short-term memory process.

7. The method of claim 6 , wherein the 2D data is processed by a neural network to provide the 2D confidence value.

8. The method of claim 7 , wherein the 2D data is spatially correlated.

9. The method of claim 8 , further comprising:
determining from the processing of the data by the neural network that an emission of a gas of interest is present.

10. The method of claim 1 , wherein the map of likely emission locations is overlayed on an image of the scene.

11. The method of claim 10 , wherein the data including the concentration value for the gas of interest at each of the plurality of different locations with the scene is obtained by a first sensor carried by a first platform, and wherein the image of the scene on which the map of likely emission locations is overlayed is obtained by a context camera carried by the first platform.

12. The method of claim 11 , wherein the first sensor includes a light detection and ranging system.

13. The method of claim 1 , wherein outputting a map of likely emission locations includes outputting a depiction of a shape of a plume of the gas of interest.

14. The method of claim 1 , further comprising:
outputting a rate of an emission of the gas of interest.

15. A method for detecting gas plumes, comprising:
obtaining data for a plurality of points within a scene;
processing the data in a neural network to obtain a confidence value;
gridding 1D data sources to obtain 2D data,
processing the 2D data in a neural network to obtain a 2D confidence value, wherein the 2D data is associated with concentration data concerning a gas of interest, wherein 2D data is associated with range data, wherein the 2D data is associated with reflectance data, wherein the 2D data is processed using a long short-term memory process, wherein the 2D data is processed by a neural network to provide the 2D confidence value, and wherein the 2D data is spatially correlated;
determining from the processing of the data by the neural network that an emission of the gas of interest is present;
determining a shape of a plume of the gas of interest; and
determining a rate of the emission of the gas of interest.

16. The method of claim 15 , wherein the data includes a concentration value for a gas of interest.

17. The method of claim 16 , further comprising:
fusing the 2D data with red, green, blue (RGB) image data; and
outputting a map indicating locations of likely emission sources.

18. The method of claim 15 , further comprising:
training the neural network using samples of plume shapes and emission rates.

19. The method of claim 15 , further comprising:
outputting a map depicting the shape of the plume of the gas of interest.

20. The method of claim 19 , wherein the map depicting the shape of the plume of the gas of interest is overlayed on an image of the scene.

Assignees

• Ball Aerospace & Tech Corp

Inventors

• Bennett Mats D
• Monnin Jason
• Bartholomew Jarett Levi
• Wallace Cynthia
• Ruppert Lyle
• Rohrschneider Reuben
• Staple Bevan D
• Tandy William

Classifications

• G01S7/4815

  using multiple transmitters · CPC title

• G01N2021/3513

  Open path with an instrumental source · CPC title

• G01S17/89

  for mapping or imaging · CPC title

• G01V8/10

  Detecting, e.g. by using light barriers (by reflection from the object G01S17/00) · CPC title

• G01N2021/394

  DIAL method · CPC title