Geospatial Risk Mapping With Hybrid DDM-AHP Vulnerability Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vulnerability assessment techniques for natural hazards, such as earthquakes and floods, are complex, time-consuming, and lack the ability to accurately assess physical risks due to slope instability, while statistical models fail to capture physical processes, and existing methods are inefficient in determining vulnerability scores.
Innovation Solution
A method combining a data-driven model (DDM) with an Analytical Hierarchy Process (AHP) model to assess physical risks, using multispectral and hyperspectral data, historical hazards, and dynamic weights to create a combined class vector, training an off-the-shelf model (OTSM) for improved risk assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If physics-based models based on first principles are used for vulnerability assessment, then measurement precision is improved, but device complexity increases significantly
Solution Approach 1:
The patent combines data-driven models (DDM) that process multispectral and hyperspectral satellite imagery with the Analytical Hierarchy Process (AHP) model that incorporates expert knowledge and multiple influencing factors. This merging allows the system to achieve high measurement precision through DDM's pattern recognition capabilities while managing complexity through AHP's structured framework for evaluating slope stability, drainage patterns, and other vulnerability factors.
2Device complexity
If statistical models are used for vulnerability assessment, then device complexity is reduced, but measurement precision deteriorates due to inability to capture physical processes
Solution Approach 1:
The patent replaces traditional statistical models with a hybrid approach that uses data-driven models (DDM) capable of capturing complex physical processes through machine learning from satellite imagery. The DDM learns patterns from historical hazard data and multispectral/hyperspectral images, substituting simple statistical correlations with sophisticated pattern recognition that preserves physical process information while maintaining computational efficiency.
3Measurement precision
If expert driven Analytical Hierarchy Process (AHP) model is used for vulnerability assessment, then measurement precision is improved, but loss of time increases due to tedious field investigation
Solution Approach 1:
The patent performs preliminary remote sensing analysis using satellite imagery to identify and prioritize vulnerable areas before conducting field investigations. The data-driven model processes multispectral and hyperspectral data to generate preliminary vulnerability maps, allowing field teams to focus only on high-risk areas. This preliminary action significantly reduces the time and resources required for comprehensive field investigation while maintaining assessment accuracy.
Solution Approach 2:
The system enables self-service vulnerability assessment by automating the processing of satellite imagery and the generation of vulnerability maps through the hybrid DDM-AHP model. The automated processing of multispectral and hyperspectral data, combined with the structured AHP framework, allows rapid generation of vulnerability assessments without requiring extensive manual field investigation, thus reducing time loss while maintaining precision.
Data Source
AI summary
This disclosure relates generally to system and method to assess physical risks from geospatial data of geographical region. Geospatial data analysis requires combination of data from multiple sources to assess specific vulnerability assessment challenges. The disclosed method maps various areas which are likely to be more or less susceptible to a particular hazard. The method of the present disclosure is a combinatorial approach of data driven model and analytical hierarchical process model which enables to assess vulnerability occurring in geographical region of interest. Here, a combined class vector for each pixel is determined using the first class vector and the second class vector based on one or more dynamic weights to train off the shelf model (OTSM). Finally, the trained OTSM physical risks and a physical risk map for a set of input images associated with the geographical region.