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
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
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