Parcel Growth Prediction With Graph Models for Micro-Level Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to accurately predict real estate parcel growth at a micro level due to the lack of detailed parcel information in aerial imagery, leading to imprecise infrastructure planning and capacity issues.
Innovation Solution
A parcel growth prediction system using parcel data, population data, and artificial intelligence to generate a graph model by merging parcels with similar characteristics, training a parcel growth AI model, and predicting future development probabilities based on historical data and centroid connections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If aerial imagery is used to predict parcel growth, then the prediction process is simple and fast, but the prediction precision is low due to lack of detailed parcel information
Solution Approach 1:
The patent combines multiple data sources including aerial imagery, parcel data with detailed attributes (legal descriptions, land use codes, subdivision names), and population data to create a comprehensive prediction system. This merging of data sources resolves the contradiction by maintaining the visual overview capability of aerial imagery while adding the detailed information needed for precise predictions at the micro level
Solution Approach 2:
The patent introduces graph models as an intermediary structure that connects parcels with similar characteristics. These graph models serve as mediators between the coarse aerial imagery data and the fine-grained parcel-level predictions, enabling detailed predictions without processing every individual parcel directly from aerial imagery
2Measurement precision
If detailed parcel data processing is implemented to improve prediction accuracy, then prediction precision increases, but system complexity increases
Solution Approach 1:
The patent segments the prediction system into distinct modules: aerial imagery processing, parcel data processing, graph model construction, and prediction generation. Each module handles specific data types and tasks independently, reducing overall system complexity while enabling precise predictions through coordinated module interactions
Solution Approach 2:
Graph models serve as intermediaries that organize and simplify complex parcel relationships. By grouping parcels with similar characteristics into graph structures, the system manages complexity while maintaining detailed analysis capability for precision predictions
3Reliability
If infrastructure is increased uniformly across geographic area to support population growth, then infrastructure capacity is sufficient, but infrastructure placement efficiency decreases due to non-uniform population growth distribution
Solution Approach 1:
The patent applies local quality by predicting parcel growth probabilities at the micro level for specific individual parcels rather than uniformly across the entire geographic area. This enables infrastructure to be placed precisely where population growth is most likely to occur, matching infrastructure capacity increases to local needs while maintaining overall reliability
Solution Approach 2:
The system performs preliminary prediction of which parcels are most likely to experience growth before infrastructure placement decisions are made. This advance identification allows infrastructure to be proactively placed in high-growth areas, improving placement efficiency while ensuring capacity matches future population needs
Data Source
AI summary
An improved parcel growth prediction system that uses parcel data, population data, and artificial intelligence to predict the growth of a geographic area at a micro level (e.g., a real estate parcel level) is described herein. For example, the improved parcel growth prediction system may generate a graph model and apply the graph model as an input to an artificial intelligence model to predict the likelihood that a particular parcel may be developed some time in the future. Ultimately, implementing the improved parcel growth prediction system described herein may lead to more precise placements of infrastructure projects and/or to infrastructure projects that more precisely support the needs of the population of a geographic area as time passes.