AQI Based Research and Initial/Early Findings

AirLive is a free web service that tracks air quality for 284 places in ten countries and runs entirely on a free-tier edge platform. An hourly pipeline blends ground-station readings (inverse-distance weighting, k = 3, 25 km) with CAMS model values, learns a per-place station-to-model ratio, and publicly scores the bias-corrected forecast against stations (seven-day half-life). The engine expresses one reading in six national index scales and derives personal verdict limits, inhaled dose, mask and indoor-air estimates whose arithmetic is shown to the user. Personal health guidance is computed in the browser from a structured profile that never leaves the device; saved profiles are AES-256-GCM encrypted under a user-chosen passphrase. In the first live scoring window (21 h), bias correction reduced +6 h mean absolute error from 70.0 to 51.4 AQI points and improved 16 of 22 cities. This project documents the design, formulas, constants, resource budget, privacy verification and limitations.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-12
DOI
https://doi.org/10.5281/zenodo.24166151
Primary Topic
Air Quality Monitoring and Forecasting
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

AQI Based Research and Initial/Early Findings

DHANANJAY LOCHAVE
Zenodo (CERN European Organization for Nuclear Research)
Air Quality Monitoring and Forecasting
article

AQI Based Research and Initial/Early Findings

DHANANJAY LOCHAVE
article en

Abstract

AirLive is a free web service that tracks air quality for 284 places in ten countries and runs entirely on a free-tier edge platform. An hourly pipeline blends ground-station readings (inverse-distance weighting, k = 3, 25 km) with CAMS model values, learns a per-place station-to-model ratio, and publicly scores the bias-corrected forecast against stations (seven-day half-life). The engine expresses one reading in six national index scales and derives personal verdict limits, inhaled dose, mask and indoor-air estimates whose arithmetic is shown to the user. Personal health guidance is computed in the browser from a structured profile that never leaves the device; saved profiles are AES-256-GCM encrypted under a user-chosen passphrase. In the first live scoring window (21 h), bias correction reduced +6 h mean absolute error from 70.0 to 51.4 AQI points and improved 16 of 22 cities. This project documents the design, formulas, constants, resource budget, privacy verification and limitations.

Zenodo (CERN European Organization for Nuclear Research)
Sustainable cities and communities
Air Quality Monitoring and Forecasting
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon