Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Developing Gridded Emission Inventory from High-Resolution Satellite Object Detection for Improved Air Quality Forecasts

Shubham Ghosal, Manmeet Singh, Sachin Ghude, Harsh Kamath, Vaisakh SB, Subodh Wasekar, Anoop Mahajan, Hassan Dashtian, Zong-Liang Yang, Michael Young, Dev Niyogi

TL;DR

This research not only enhances WRF Chem simulations but also bridges the gap between AI technologies and atmospheric science methodologies, potentially improving urban air quality management and environmental policymaking.

Abstract

This study presents an innovative approach to creating a dynamic, AI based emission inventory system for use with the Weather Research and Forecasting model coupled with Chemistry (WRF Chem), designed to simulate vehicular and other anthropogenic emissions at satellite detectable resolution. The methodology leverages state of the art deep learning based computer vision models, primarily employing YOLO (You Only Look Once) architectures (v8 to v10) and T Rex, for high precision object detection. Through extensive data collection, model training, and finetuning, the system achieved significant improvements in detection accuracy, with F1 scores increasing from an initial 0.15 at 0.131 confidence to 0.72 at 0.414 confidence. A custom pipeline converts model outputs into netCDF files storing latitude, longitude, and vehicular count data, enabling real time processing and visualization of emission patterns. The resulting system offers unprecedented temporal and spatial resolution in emission estimates, facilitating more accurate short term air quality forecasts and deeper insights into urban emission dynamics. This research not only enhances WRF Chem simulations but also bridges the gap between AI technologies and atmospheric science methodologies, potentially improving urban air quality management and environmental policymaking. Future work will focus on expanding the system's capabilities to non vehicular sources and further improving detection accuracy in challenging environmental conditions.

Developing Gridded Emission Inventory from High-Resolution Satellite Object Detection for Improved Air Quality Forecasts

TL;DR

This research not only enhances WRF Chem simulations but also bridges the gap between AI technologies and atmospheric science methodologies, potentially improving urban air quality management and environmental policymaking.

Abstract

This study presents an innovative approach to creating a dynamic, AI based emission inventory system for use with the Weather Research and Forecasting model coupled with Chemistry (WRF Chem), designed to simulate vehicular and other anthropogenic emissions at satellite detectable resolution. The methodology leverages state of the art deep learning based computer vision models, primarily employing YOLO (You Only Look Once) architectures (v8 to v10) and T Rex, for high precision object detection. Through extensive data collection, model training, and finetuning, the system achieved significant improvements in detection accuracy, with F1 scores increasing from an initial 0.15 at 0.131 confidence to 0.72 at 0.414 confidence. A custom pipeline converts model outputs into netCDF files storing latitude, longitude, and vehicular count data, enabling real time processing and visualization of emission patterns. The resulting system offers unprecedented temporal and spatial resolution in emission estimates, facilitating more accurate short term air quality forecasts and deeper insights into urban emission dynamics. This research not only enhances WRF Chem simulations but also bridges the gap between AI technologies and atmospheric science methodologies, potentially improving urban air quality management and environmental policymaking. Future work will focus on expanding the system's capabilities to non vehicular sources and further improving detection accuracy in challenging environmental conditions.

Paper Structure

This paper contains 17 sections, 7 figures, 1 table.

Table of Contents

  1. Introduction
  2. Aim & Contribution
  3. First-Time Development of Gridded Vehicle Count from High-Resolution Satellite Imagery
  4. Accurate Foundation for Future Emission Inventory Generation
  5. Multiple Classes in Gridded Vehicle Count
  6. Development of Labeled Data from Scratch
  7. Methodology
  8. Data Collection
  9. Data Annotation and Model Training
  10. Vehicle Detection and Calculations
  11. Heatmap Generation
  12. Results
  13. F1 Scores and Model Performance
  14. YOLOv8 and YOLOv10: Key Comparisons
  15. Key Takeaways
  16. ...and 2 more sections

Figures (7)

  • Figure 1: Satellite image of Cannaught place, Delhi with cars, buses, trucks, brick kilns and other visible sources. CNES/Airbus, Maxar Technologies, Copyright Google 2024
  • Figure 2: Methodology Flowchart for Data Collection
  • Figure 3: Data Collection - Satellite Images
  • Figure 4: Annotating Images for Defined Object Classes
  • Figure 5: Flowchart - Annotations and Model Training
  • ...and 2 more figures