Sand accumulation elevation system and a method for elevating sand accumulation

The geospatial elevation system uses CNNs with U-Net architecture and pre-trained ResNet34 weights to predict sand accumulation from satellite images, addressing the challenge of estimating dynamic geographical structures with high accuracy and real-time data.

WO2025219748A1PCT designated stage Publication Date: 2025-10-23ABU DHABI GAS DEVELOPMENT CO LTD +1
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
PCT/IB2024/053834
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2024-04-19
Publication Date
2025-10-23

Smart Images

  • Figure IB2024053834_23102025_PF_FP_ABST
    Figure IB2024053834_23102025_PF_FP_ABST
Patent Text Reader

Abstract

Method for predicting sand accumulation, comprising the steps of receiving an electro-optical, EO, imagery for a geographic area with sand accumulation; estimating evaluation values within the EO imagery for a geographic area with sand accumulation based upon an artificial intelligence, Al, model; generating a monocular depth estimation map for the geographic area with sand accumulation from the estimated evaluation values; and outputting the monocular depth estimation map on a display (20).
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • CNN (Convolutional Neural Network) and Transform improved lightweight monocular depth estimation method

    CN117710429A

  • Systems and methods for weakly supervised training of a model for monocular depth estimation

    US11386567B2

  • Predicting depth from image data using a statistical model

    US20190213481A1

  • Artificial intelligence (AI) system and methods for generating estimated height maps from electro-optic imagery

    US20220092812A1

  • Method and system for monocular depth estimation

    WO2022058243A1