Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

oluwamayowaa/Air-Quality-Prediction-zindi-challenge

Domaine:

environment and energygeospatial

Type de record:

project
Créateur:
olu
Hôte:
This challenge tackles predicting air quality (PM2.5) in Kampala, Uganda, using satellite data (Sentinel-5P) from areas lacking sensor coverage. The goal is to build a model that leverages satellite data to predict PM2.5 readings where ground-based sensors are absent. ## Context AirQo’s air quality sensing network has more than 120 low-cost devices deployed across Uganda, which regulalry sense and report on air quality using the PM2.5 measure. In this challenge we explore using satellite radar data from Sentinel 5P to predict air quality in regions in Kampala. The use of satellite data could expand air quality predictions to areas without air quality sensor devices. The objective of this challenge is to predict air quality readings from AirQo’s sensors using Sentinel 5P data. ## Evaluation The evaluation metric for this challenge is Mean Absolute Error.

Visit

github.com

Tags

jupyter-notebookxgboost