Inhalable Particle Prediction via Dispersal and Accumulation Event Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting inhalable particles concentration, such as physical and statistical models, face challenges in accuracy due to the difficulty in acquiring precise data and performance in high pollutant scenarios.
Innovation Solution
A computer-implemented method and system that identifies dispersal and accumulation events, generates dispersal and change prediction models based on historical data, and uses these models to predict inhalable particles concentration chronologically, leveraging weather information to improve prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a physical model (e.g., WRF-CHEM, CMAQ) is used for prediction, then the prediction covers full scale and multiple processes, but the prediction accuracy is low due to difficulty in acquiring accurate data
Solution Approach 1:
The patent segments the continuous prediction problem into discrete event types (dispersal events and accumulation events). By identifying and separately modeling these different event types, the system can apply appropriate prediction strategies for each, improving overall accuracy while maintaining comprehensive coverage.
Solution Approach 2:
The patent applies different prediction approaches for different local conditions - using dispersal prediction models for dispersal events and accumulation prediction models for accumulation events. This localized modeling approach allows each model to be optimized for its specific event type, improving prediction accuracy for each scenario.
2Ease of operation
If a statistical model trained using weather information is used, then the model is easier to operate, but the performance is bad in high pollutant prediction
Solution Approach 1:
The patent dynamically selects between different prediction models based on the identified event type. The system transitions between dispersal prediction models and accumulation prediction models depending on whether a dispersal event or accumulation event is detected, allowing the model to adapt its behavior to match the current pollution scenario.
Solution Approach 2:
The patent changes the modeling parameters and approaches based on the event type. For dispersal events, it uses models optimized for particle dispersion; for accumulation events, it uses models optimized for particle accumulation. This parameter adaptation enables accurate prediction across different pollution levels and scenarios.
Data Source
AI summary
In an embodiment of the present disclosure, a method for modeling prediction of inhalable particles concentration is disclosed. In the method, at least one dispersal event is identified, and at least one accumulation event is identified based on the identified at least one dispersal event. Then a dispersal prediction model is generated based on the identified at least one dispersal event. Then at least one accumulation level of inhalable particles concentration is obtained for the at least one accumulation event. A change prediction model for the accumulation level is generated. Then a plurality of accumulation prediction models is generated.