20240046143. GENERATING HIGH-RESOLUTION CONCENTRATION MAPS FOR ATMOSPHERIC GASES USING GEOGRAPHY-INFORMED MACHINE LEARNING simplified abstract (Palo Alto Research Center Incorporated)

From WikiPatents
Jump to navigation Jump to search

GENERATING HIGH-RESOLUTION CONCENTRATION MAPS FOR ATMOSPHERIC GASES USING GEOGRAPHY-INFORMED MACHINE LEARNING

Organization Name

Palo Alto Research Center Incorporated

Inventor(s)

Kalaivani Ramea Kubendran of Fremont CA (US)

Md Nurul Huda of Hillsboro OR (US)

David Schwartz of Concord MA (US)

Jeyasri Subramanian of Sunnyvale CA (US)

GENERATING HIGH-RESOLUTION CONCENTRATION MAPS FOR ATMOSPHERIC GASES USING GEOGRAPHY-INFORMED MACHINE LEARNING - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240046143 titled 'GENERATING HIGH-RESOLUTION CONCENTRATION MAPS FOR ATMOSPHERIC GASES USING GEOGRAPHY-INFORMED MACHINE LEARNING

Simplified Explanation

The abstract describes a geography-informed machine learning (GIML) model that is trained on a remote sensing dataset for a specific geographic area. The dataset includes atmospheric gas concentration data, multispectral data, and spatially autocorrelated land use classifications. The GIML model is then used to predict atmospheric gas concentration values for a different geographic area using a second remote sensing dataset.

  • The GIML model is trained on a remote sensing dataset for a specific geographic area.
  • The dataset includes atmospheric gas concentration data, multispectral data, and spatially autocorrelated land use classifications.
  • The GIML model can predict atmospheric gas concentration values for a different geographic area using a second remote sensing dataset.
  • The predicted values have a higher spatial resolution than the original datasets.

Potential applications of this technology:

  • Environmental monitoring: The GIML model can be used to predict atmospheric gas concentrations in different geographic areas, aiding in environmental monitoring and assessment.
  • Climate change research: The model can help researchers analyze and understand changes in atmospheric gas concentrations across different regions.
  • Urban planning: The predicted atmospheric gas concentrations can inform urban planning decisions, such as identifying areas with high pollution levels.

Problems solved by this technology:

  • Limited spatial resolution: The GIML model allows for the generation of atmospheric gas concentration values with a higher spatial resolution than the original datasets, providing more detailed information.
  • Generalization across geographic areas: The model can be trained on one geographic area and then applied to another, allowing for predictions in areas where specific data may be limited.

Benefits of this technology:

  • Improved accuracy: By incorporating spatial autocorrelation and multispectral data, the GIML model can provide more accurate predictions of atmospheric gas concentrations.
  • Cost-effective: The model can utilize existing remote sensing datasets, reducing the need for expensive and time-consuming data collection.
  • Scalability: The GIML model can be applied to different geographic areas, making it scalable for various regions and applications.


Original Abstract Submitted

a geography-informed machine learning (giml) model is trained on a first remote sensing dataset corresponding to a first geographic area and including a first set of atmospheric gas concentration data for at least one atmospheric gas, a first set of multispectral data, and a first set of spatially autocorrelated land use classifications. the giml model receives input including a second remote sensing dataset corresponding to a second geographic area. the second remote sensing dataset includes a second set of atmospheric gas concentration data for the atmospheric gas, a second set of multispectral data, and a second set of spatially autocorrelated land use classifications. the giml model generates, for the second geographic area, a plurality of predicted atmospheric gas concentration values for the atmospheric gas having a spatial resolution that is greater than a spatial resolution of the first and second sets of atmospheric gas concentration data.

Retrieved from "http://wikipatents.org/index.php?title=20240046143._GENERATING_HIGH-RESOLUTION_CONCENTRATION_MAPS_FOR_ATMOSPHERIC_GASES_USING_GEOGRAPHY-INFORMED_MACHINE_LEARNING_simplified_abstract_(Palo_Alto_Research_Center_Incorporated)&oldid=32243"