Granted Patent B2

US 12,608,930 · App. 18/357,667 · Granted Apr 21, 2026

Inventors: Sarbajit K. Rakshit (Kolkata, IN); Subha Basu (Howrah, IN); Sourav Banerjee (Konnagar, IN); Shaik Mohammed Gouse Basha (Lansdale, PA)

Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION

G06V20/13A62C3/0278G01W1/10G06T11/26G06V10/22H04N23/69H04N23/815

Abstract

Claims (64)

1 . A computer-based method of predicting and mitigating forest fires based on low earth orbit (LEO) satellites, the method comprising:

receiving historical LEO satellite images of a forested region;

identifying a geographical area and a boundary of the geographical area based on the historical LEO satellite images;

identifying a time range of a fire season in the geographical area;

determining whether at least one LEO satellite is positioned within the boundary of the geographical area during the time range;

in response to determining the at least one LEO satellite is not positioned within the boundary of the geographical area during the time range, adapting a location of the at least one LEO satellite to be within the boundary during the time range;

capturing live LEO satellite images of inflammable material in the geographical area; and

identifying a range of changes in the inflammable material by comparing the live LEO satellite images and the historical LEO satellite images, wherein identifying the range of changes in the inflammable material includes the at least one LEO satellite performing edge computation on the historical LEO satellite images and the live LEO satellite images to evaluate a rate at which a density of leaves on trees decreases from one time period to another.

2 . The computer-based method of claim 1 , wherein adapting the location of the at least one LEO satellite to be within the boundary during the time range further comprises:

adapting a configuration of the at least one LEO satellite including a zoom level and a resolution of a camera of the at least one LEO satellite.

3 . The computer-based method of claim 1 , further comprising:

predicting an amount of the inflammable material that has accumulated in the geographical area based on the comparison of the live LEO satellite images and the historical LEO satellite images;

predicting a fire propagation capability based on identified weather patterns in the geographical area during the time range;

creating a heat map of the accumulated inflammable material; and

executing one or more mitigation actions to prevent fire propagation.

4 . The computer-based method of claim 3 , wherein predicting the fire propagation capability based on the identified weather patterns in the geographical area during the time range further comprises:

estimating a wind speed and direction in the geographical area during the time range; and

predicting a direction of fire propagation based on the estimated wind speed and direction.

5 . The computer-based method of claim 3 , wherein the executed one or more mitigation actions include deploying a robotic device to remove the accumulated inflammable material.

6 . The computer-based method of claim 5 , wherein the robotic device is deployed to remove the accumulated inflammable material in descending order from a portion of the geographical area having greatest accumulation to a portion of the geographical area having least accumulation based on the heat map.

7 . The computer-based method of claim 3 , wherein the executed one or more mitigation actions include identifying an aerial location within the boundary of the geographical area where cloud seeding is to be performed based on the heat map.

8 . A computer system, the computer system comprising:

one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more computer-readable tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, wherein the computer system is capable of performing a method comprising:

receiving historical LEO satellite images of a forested region;

identifying a geographical area and a boundary of the geographical area based on the historical LEO satellite images;

identifying a time range of a fire season in the geographical area;

determining whether at least one LEO satellite is positioned within the boundary of the geographical area during the time range;

in response to determining the at least one LEO satellite is not positioned within the boundary of the geographical area during the time range, adapting a location of the at least one LEO satellite to be within the boundary during the time range;

capturing live LEO satellite images of inflammable material in the geographical area; and

identifying a range of changes in the inflammable material by comparing the live LEO satellite images and the historical LEO satellite images, wherein identifying the range of changes in the inflammable material includes the at least one LEO satellite performing edge computation on the historical LEO satellite images and the live LEO satellite images to evaluate a rate at which a density of leaves on trees decreases from one time period to another.

9 . The computer system of claim 8 , wherein adapting the location of the at least one LEO satellite to be within the boundary during the time range further comprises:

adapting a configuration of the at least one LEO satellite including a zoom level and a resolution of a camera of the at least one LEO satellite.

10 . The computer system of claim 8 , the method further comprising:

predicting an amount of the inflammable material that has accumulated in the geographical area based on the comparison of the live LEO satellite images and the historical LEO satellite images;

predicting a fire propagation capability based on identified weather patterns in the geographical area during the time range;

creating a heat map of the accumulated inflammable material; and

executing one or more mitigation actions to prevent fire propagation.

11 . The computer system of claim 10 , wherein predicting the fire propagation capability based on the identified weather patterns in the geographical area during the time range further comprises:

estimating a wind speed and direction in the geographical area during the time range; and

predicting a direction of fire propagation based on the estimated wind speed and direction.

12 . The computer system of claim 10 , wherein the executed one or more mitigation actions include deploying a robotic device to remove the accumulated inflammable material.

13 . The computer system of claim 12 , wherein the robotic device is deployed to remove the accumulated inflammable material in descending order from a portion of the geographical area having greatest accumulation to a portion of the geographical area having least accumulation based on the heat map.

14 . The computer system of claim 10 , wherein the executed one or more mitigation actions include identifying an aerial location within the boundary of the geographical area where cloud seeding is to be performed based on the heat map.

15 . A computer program product, the computer program product comprising:

one or more computer-readable tangible storage medium and program instructions stored on at least one of the one or more computer-readable tangible storage medium, the program instructions executable by a processor capable of performing a method, the method comprising:

receiving historical LEO satellite images of a forested region;

identifying a geographical area and a boundary of the geographical area based on the historical LEO satellite images;

identifying a time range of a fire season in the geographical area;

determining whether at least one LEO satellite is positioned within the boundary of the geographical area during the time range;

in response to determining the at least one LEO satellite is not positioned within the boundary of the geographical area during the time range, adapting a location of the at least one LEO satellite to be within the boundary during the time range;

capturing live LEO satellite images of inflammable material in the geographical area; and

identifying a range of changes in the inflammable material by comparing the live LEO satellite images and the historical LEO satellite images, wherein identifying the range of changes in the inflammable material includes the at least one LEO satellite performing edge computation on the historical LEO satellite images and the live LEO satellite images to evaluate a rate at which a density of leaves on trees decreases from one time period to another.

16 . The computer program product of claim 15 , wherein adapting the location of the at least one LEO satellite to be within the boundary during the time range further comprises:

adapting a configuration of the at least one LEO satellite including a zoom level and a resolution of a camera of the at least one LEO satellite.

17 . The computer program product of claim 15 , the method further comprising:

predicting an amount of the inflammable material that has accumulated in the geographical area based on the comparison of the live LEO satellite images and the historical LEO satellite images;

predicting a fire propagation capability based on identified weather patterns in the geographical area during the time range;

creating a heat map of the accumulated inflammable material; and

executing one or more mitigation actions to prevent fire propagation.

18 . The computer program product of claim 17 , wherein predicting the fire propagation capability based on the identified weather patterns in the geographical area during the time range further comprises:

estimating a wind speed and direction in the geographical area during the time range; and

predicting a direction of fire propagation based on the estimated wind speed and direction.

19 . The computer program product of claim 17 , wherein the executed one or more mitigation actions include deploying a robotic device to remove the accumulated inflammable material.

20 . The computer program product of claim 19 , wherein the robotic device is deployed to remove the accumulated inflammable material in descending order from a portion of the geographical area having greatest accumulation to a portion of the geographical area having least accumulation based on the heat map.

Assignments (1)

Continuity (1)

References Cited (20)