Geospatial Analysis Device for Ground Height Displacement Factors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques can determine the presence or absence of ground surface variations but fail to identify the factors contributing to these variations in height.
Innovation Solution
An analysis device that extracts geospatial information from multiple types of data representing ground surface states and beneath the surface, training a determination model to predict or determine the factors contributing to height displacements using heterogeneous mixed learning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning is used to determine ground surface variations, then the presence or absence of variations can be determined, but the factors contributing to height variations cannot be identified
Solution Approach 1:
The patent segments the geospatial information into multiple types (e.g., terrain data, land use data, vegetation data, soil data) and analyzes each type separately to identify specific factors contributing to height variations. This segmentation allows the system to not only detect variations but also attribute them to specific causal factors.
Solution Approach 2:
The patent transitions from binary classification (presence/absence of variation) to multi-dimensional analysis by incorporating multiple types of geospatial information dimensions. This enables the system to identify both the presence of variations and the underlying factors by analyzing data across multiple informational dimensions simultaneously.
2Loss of information
If multiple types of geospatial information are extracted and analyzed, then factors contributing to height variations can be identified, but the complexity of the analysis system increases
Solution Approach 1:
The patent employs a unified machine learning framework that can process multiple types of geospatial information (terrain, land use, vegetation, soil) through a single determination model. This multi-functional approach allows the system to identify various contributing factors without requiring separate specialized systems for each data type, thereby managing complexity while achieving comprehensive factor analysis.
3Loss of information
If geospatial information is extracted from multiple data sources, then comprehensive factor analysis is enabled, but the processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary extraction and preprocessing of geospatial information from multiple data sources before feeding it into the machine learning model. By preparing and organizing the data in advance, the system reduces computational burden during the actual analysis phase, thereby decreasing overall processing time while maintaining comprehensive factor analysis capability.
Data Source
AI summary
An analysis device according to an aspect of the present disclosure includes: at least one memory configured to store instructions; and at least one processor configured to execute the instructions to: extract values of geospatial information at a plurality of points on a ground surface from a plurality of types of geospatial information, the plurality of types of geospatial information each representing at least a state of the ground surface or a state beneath the ground surface; and train a determination model based on height displacements at the plurality of points and the extracted values of the geospatial information in such a way that the determination model determines a set of the geospatial information contributing to the height displacement based on at least a part of the values of the geospatial information.