Pollutant Sensor Placement Using Plume Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies for detecting atmospheric leaks of pollutants like methane lack efficient methods for optimally placing sensors to effectively cover large areas and detect emissions from point sources, leading to incomplete coverage and high costs.
Innovation Solution
A method and system for pollutant sensor placement that involves receiving environmental data, transforming it into common spatial and temporal discretization, predicting emission plumes, and greedily selecting sensor locations based on detectable plumes, allowing for efficient coverage and cost-effective detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If ground sensors are deployed to cover large areas, then detection coverage is improved, but deployment cost increases
Solution Approach 1:
The system performs preliminary actions by using satellite data and atmospheric models to predict emission plume locations and trajectories before deploying sensors. This allows sensor placement to be targeted at high-probability detection zones rather than uniformly distributing sensors across the entire area, reducing the number of sensors needed while maintaining coverage.
Solution Approach 2:
The system applies local quality by concentrating sensor deployment in specific high-value locations identified through plume prediction, rather than uniform distribution. Sensors are placed where predicted emissions are most likely to occur based on atmospheric conditions and source characteristics, optimizing detection efficiency per sensor.
2Reliability
If more sensors are deployed, then detection reliability is improved, but system complexity increases
Solution Approach 1:
The system applies partial action by deploying only the minimum number of sensors needed to achieve reliable detection of predicted plumes, rather than over-deploying. The greedy selection algorithm adds sensors only until detection reliability requirements are met, avoiding unnecessary complexity from excess sensors.
3Measurement precision
If sensors are placed to maximize plume detection, then detection precision is improved, but placement complexity increases
Solution Approach 1:
The system performs preliminary plume prediction using atmospheric dispersion models and satellite observations before sensor placement. This pre-computation of expected plume locations and characteristics simplifies the subsequent sensor placement decision, as sensors can be positioned to target specific predicted plume trajectories rather than optimizing for all possible scenarios.
Solution Approach 2:
The system uses the predicted plume data to automatically determine optimal sensor locations through a greedy selection algorithm that evaluates detectability metrics. The placement process is self-directed by the prediction model's output, reducing the need for complex manual optimization or iterative adjustments.
Data Source
AI summary
A method for pollutant sensor placement for pollutants from point sources is described. Data about environmental characteristics for a geographic region are received from a plurality of environmental sensors. The geographic region includes pollutant sources that emit a pollutant. The received data from one or more of the plurality of environmental sensors are transformed into common data having a common spatial and temporal discretization across the geographic region. Predicted emission plumes are generated for the pollutant sources within the geographic region that identify pollutant detection regions for the pollutant when the pollutant is emitted by the pollutant sources using the common data. Sensor locations for a plurality of pollutant sensors are greedily selected across the common spatial and temporal discretization according to a number of predicted emission plumes that are detectable by the plurality of pollutant sensors.