Spatio-Temporal Occlusion Forecasting for Remote Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Optical sensing for remote monitoring is hindered by environmental occlusion factors such as clouds, pollution, and fog, which current technologies fail to effectively forecast, leading to challenges in planning remote sensing operations.
Innovation Solution
A spatio-temporal machine-learning model is used to forecast the location, intensity, and time window of environmental occlusion events by integrating historical and forecasted high-resolution weather data, along with remote sensing images, to generate occlusion probability maps at varying resolutions, enabling better management of remote sensing monitoring plans.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If optical sensing is used for remote monitoring, then monitoring coverage and scalability are improved, but reliability deteriorates due to environmental occlusion events
Solution Approach 1:
The system performs preliminary forecasting of occlusion events using machine learning models trained on historical weather and remote sensing data. By predicting occlusion probability maps before remote sensing operations, the system allows operators to plan around expected occlusions, thereby maintaining high monitoring coverage while avoiding unreliable data collection during predicted occlusion events.
2Ease of operation
If current technologies are used without occlusion forecasting, then operational simplicity is maintained, but planning effectiveness deteriorates
Solution Approach 1:
The system introduces an intermediary occlusion forecasting component that sits between operational planning and actual remote sensing execution. This intermediary provides probability maps and predictions that guide planning decisions without complicating the core remote sensing operation. The machine learning model acts as a mediator, translating complex weather and environmental data into actionable forecasting information that enhances planning effectiveness while maintaining ease of operation through automated predictions.
Data Source
AI summary
In an approach for forecasting environmental occlusion events, a processor receives a spatio-temporal zone of interest. A processor collects data associated with the spatio-temporal zone of interest. A processor builds a machine-learning model using the data. A processor generates an occlusion probability map for the spatio-temporal zone of interest based on the machine-learning model and enriched mathematical operators. A processor outputs the occlusion probability map.