Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 5, 2025Environmental Data ScienceOpen Access

Air quality prediction from images in Indonesia: enhancing model explainability through visual explanation with AQI-net and grad-CAM

View Full Paper
Ask AI
Bookmark
Share

Authors

MAMohammed AlauddinNYNovanto YudistiraMRMuhammad Arif Rahman

Discussion

Loading...

Member takes

Overview

Research employs deep learning to classify air quality using images, highlighting insights from grad-CAM and CNNs.

Key Points

  • The study achieved an impressive accuracy of 99.81% for air quality classification.
  • Images were categorized into four air quality classes: good, moderate, unhealthy for sensitive groups, and unhealthy.
  • A dataset of 11,000 images from three Indonesian regions was collected for analysis.
  • Grad-CAM was used to enhance model explainability in classifying air quality conditions.

Cite This Study

Alauddin et al. (2025) studied this question.

synapsesocial.com/papers/68bb420d2b87ece8dc958023https://doi.org/10.1017/eds.2025.10011
View Full Paper
Ask AI
Bookmark
Share