TRACER | Ship Traffic and the Impact on Air Quality

Awards & Nominations

TRACER has received the following awards and nominations. Way to go!

Global Winner
Open Science

The solution that best demonstrates the use of open science principles, which include transparency, inclusion, accessibility, and reproducibility.

Global Finalist

Ship Traffic and the Impact on Air Quality

The COVID-19 pandemic strongly affected global logistics and supply chains, and hence shipping activity. This challenge asks you to target the characterization of dynamic shipping activities as seen from space.

TRACER (Tracer of Ship Traffic and Nitrogen Dioxide)

Summary

Ship traffic is a strong emitter of air pollutants, such as nitrogen dioxide (NO2) and sulfur dioxide (SO2). However, it is still the important transport mode between countries.To investigate the dynamic shipping activities and pollution, we combine the TROPOMI NO2 product, U.S. AIS dataset, weather information as a interactive tool to help scientists and policies understand the relationship among them. Machine learning is also aplied to predict the ship NO2 pollution.

How I Addressed This Challenge

TRACER is an integrated satellite data portal that aims to track ship activities and measure NO2 pollution in regions near shipping lanes. Below is the general process for analyzing and forecasting ship pollution:


  • U.S. AIS ship data is downloaded from MarineCadastre.gov and satellite/weather data are accessed from the Euro Data Cube Public Collections.
  • Ship data is resampled into hourly ship density and converted into NetCDF files as the input of visualization and machine learning.
  • An interactive tool is developed to show ship activities and NO2 pollution by combining all available data together.
  • The analysis generated by the interactive tool can help us understand how COVID-19 and weather affect the patterns between shipping dynamics and observed air quality parameters.
  • The pandemic and machine learning provide the unique opportunity of identifying shipping routes and exploring the effects of ship pollution over heavily populated areas.
How I Developed This Project

Team TRACER wanted a multifaceted approach that can help scientists and policies to better understand the effects of ship pollution. Our interactive tool is developed using Python to read multi-sources data and generate figures automatically. We used U.S. AIS ship data, TROPOMI NO2 data then interspersed it with wind/cloud and COVID-19 status. Finally, we fixed the model and visualization bugs in the last two days to provide the preliminary report of the complicated relationship among them.

How I Used Space Agency Data in This Project

Most data used in our project are accessed from the the Earth Observing Dashboard, such as TROPOMI NO2/cloud and weekly NO2 data. Since the Earth Observing Dashboard doesn't provide the hourly wind data, we download the ERA5 hourly 10 m U, V, and uvb from the Climate Change Service (CDS). Besides, the open/free ship AIS data is accessed from MarineCadastre.gov.

Project Demo
Earth Observing Dashboard Integration

The visualization tool is written in Jupyter Notebook. Therefore, the overlayed variables can be converted into indicators to be shown in the Dashboard.

Data & Resources
Tags

#ship, #NO2, #air quality, #TROPOMI, #machine learning, #visualization

Judging

This project has been submitted for consideration during the Judging process.