Systems and methods for identifying subsurface hydrogen accumulation

Patent metadata

Field	Value
Publication number	US-12165404-B2
Application number	US-202318528434-A
Country	US
Kind code	B2
Filing date	Dec 4, 2023
Priority date	Apr 30, 2021
Publication date	Dec 10, 2024
Grant date	Dec 10, 2024

Abstract

Systems, apparatuses, methods, and computer program products are disclosed for training an image analysis engine to identify surface features of the Earth consistent with subsurface hydrogen accumulation. An example method includes receiving, by communications circuitry, a training dataset of labeled images illustrating surface features consistent with subsurface hydrogen accumulation, the surface features consistent with subsurface hydrogen accumulation comprising ovoid surficial depressions. The example method further includes training, by a model generator and using the training dataset, an image classification model of the image analysis engine to identify whether new images contain surface features consistent with subsurface hydrogen accumulation. The example method further includes hosting the image classification model by the image analysis engine.

First claim

What is claimed is:

1. A method for training an image analysis engine to identify surface features of the Earth consistent with subsurface hydrogen accumulation, the method comprising:
receiving, by communications circuitry, a training dataset comprising a labeled set of images illustrating surface features consistent with subsurface hydrogen accumulation, the surface features consistent with subsurface hydrogen accumulation comprising ovoid surficial depressions, wherein the labeled set of images comprises panchromatic, multispectral, or hyperspectral images or digital elevation models;
training, by a model generator and using the training dataset, an image classification model of the image analysis engine to identify whether images contain surface features consistent with subsurface hydrogen accumulation, wherein the surface features comprise changes on the order of millimeters to centimeters per year; and
hosting the trained image classification model by the image analysis engine.

2. The method of claim 1 , further comprising:
receiving, by the communications circuitry, a target image; and
identifying, by the image analysis engine and using the image classification model, whether the target image contains any surface features consistent with subsurface hydrogen accumulation.

3. The method of claim 1 ,
wherein the image classification model comprises an object detection model, and
wherein training the image classification model further includes training the image classification model to identify regions within images containing surface features consistent with subsurface hydrogen accumulation.

4. The method of claim 3 , wherein the training dataset includes a set of bounding boxes for each image in the labeled set of images, each bounding box for a particular image surrounding a corresponding segment of the particular image that contains a surface feature consistent with subsurface hydrogen accumulation.

5. The method of claim 1 , wherein the surface features include dynamic surface deformations in the ovoid surficial depressions over time.

6. The method of claim 5 , wherein the dynamic surface deformations comprise swelling or contracting of the ovoid surficial depressions.

7. An apparatus for training an image analysis engine to identify surface features of the Earth consistent with subsurface hydrogen accumulation, the apparatus comprising:
communications circuitry configured to receive a training dataset comprising a labeled set of images illustrating surface features consistent with subsurface hydrogen accumulation, the surface features consistent with subsurface hydrogen accumulation comprising ovoid surficial depressions, wherein the labeled set of images comprises panchromatic, multispectral, or hyperspectral images or digital elevation models; and
a model generator configured to train, using the training dataset, an image classification model of the image analysis engine to identify whether images contain surface features consistent with subsurface hydrogen accumulation, wherein the surface features comprise changes on the order of millimeters to centimeters per year;
wherein the image analysis engine is configured to host the trained image classification model.

8. The apparatus of claim 7 ,
wherein the communications circuitry is further configured to receive a target image, and
wherein the image analysis engine is further configured to identify, using the image classification model, whether the target image contains any surface features consistent with subsurface hydrogen accumulation.

9. The apparatus of claim 7 ,
wherein the image classification model comprises an object detection model, and
wherein the model generator is configured to train the image classification model to identify regions within images containing surface features consistent with subsurface hydrogen accumulation.

10. The apparatus of claim 9 , wherein the training dataset includes a set of bounding boxes for each image in the labeled set of images, each bounding box for a particular image surrounding a corresponding segment of the particular image that contains a surface feature consistent with subsurface hydrogen accumulation.

11. The apparatus of claim 7 , wherein the surface features include dynamic surface deformations in the ovoid surficial depressions over time.

12. The apparatus of claim 11 , wherein the dynamic surface deformations comprise swelling or contracting of the ovoid surficial depressions.

13. A computer program product for training an image analysis engine to identify surface features of the Earth consistent with subsurface hydrogen accumulation, the computer program product comprising at least one non-transitory computer-readable storage medium storing software instructions that, when executed, cause an apparatus to:
receive a training dataset comprising a labeled set of images illustrating surface features consistent with subsurface hydrogen accumulation, the surface features consistent with subsurface hydrogen accumulation comprising ovoid surficial depressions, wherein the labeled set of images comprises panchromatic, multispectral, or hyperspectral images or digital elevation models; and
train, using the training dataset, an image classification model of the image analysis engine to identify whether images contain surface features consistent with subsurface hydrogen accumulation, wherein the surface features comprise changes on the order of millimeters to centimeters per year;
wherein the trained image classification model is hosted by the image analysis engine.

14. The computer program product of claim 13 , wherein the software instructions, when executed, further cause the apparatus to:
receive a target image; and
identify, using the image classification model, whether the target image contains any surface features consistent with subsurface hydrogen accumulation.

15. The computer program product of claim 13 ,
wherein the image classification model comprises an object detection model, and
wherein the software instructions, when executed, further cause the apparatus to train the image classification model to identify regions within images containing surface features consistent with subsurface hydrogen accumulation.

16. The computer program product of claim 15 , wherein the training dataset includes a set of bounding boxes for each image in the labeled set of images, each bounding box for a particular image surrounding a corresponding segment of the particular image that contains a surface feature consistent with subsurface hydrogen accumulation.

17. The computer program product of claim 13 , wherein the surface features include dynamic surface deformations in the ovoid surficial depressions over time.

18. The computer program product of claim 17 , wherein the dynamic surface deformations comprise swelling or contracting of the ovoid surficial depressions.

Assignees

• Ohio State Innovation Foundation

Inventors

• Darrah Thomas
• Howat Ian
• Moortgat Joachim
• Whyte Colin

Classifications

• G01V8/02

  Prospecting · CPC title

• G06V20/13 Primary

  Satellite images · CPC title

• G06V10/26

  Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V10/40

  Extraction of image or video features · CPC title