Latest
YesterdayFriuli Venezia Giulia Council Backs Adaptive Streetlight Study After €156.6M Udine Crash Toll YesterdayNYC Department of Transportation Ends Automotus Curb Camera Pilot on the Upper West Side YesterdayAomori Prefecture Installs 12 AI Bear-Detection Cameras In Hakkoda Mountains After Fatal Attack YesterdayAjuntament d’Olot Puts Sewer Cameras and GIS Mapping on 161 Km Network YesterdayCity of São Paulo’s Smart Sampa Contract Allows €10.4M Fine After Data Exposure YesterdayHonolulu Emergency Management Plans $300K Flood Detection Pilot By June 2027 YesterdayPuigcerdà Council Funds €373,000 Water Network Upgrade YesterdayRegione Basilicata Opens €18.8M Public Lighting Call For Comuni And Two Provinces YesterdayARENA Commits A$4M To JET Charge For Up To 130 V2G Fleet Vehicles In The ACT YesterdayInnovate UK And Private Investors Commit £750K To Go Eve’s DockChain Multi-Bay EV Charging
Kurrantly News · Weekly briefingThe week in smart cities and utilities, in one email
Share
Environmental Monitoring · South Africa

South Africa Scales Up Low-Cost AI-Powered Air Quality Monitoring

Kurrant News Desk · ·1 min read

South African scientists have developed a cost-effective air-quality monitoring system called Ai_r produced by The South African Consortium Of Air Quality Monitoring (SACAQM), utilizing IoT and AI technologies. The system consists of small sensor units, each costing about R1,800 (approximately €90) to produce. These units can be easily mounted on buildings, where they collect air quality data, specifically particulate matter 2.5, and send it to a cloud platform in real time for analysis.

The project aims to deploy tens of thousands of these sensors across South Africa to create a dense monitoring network. Initially, around 20 devices have been installed in Soweto and Braamfontein, with an additional 120 units planned for deployment in the coming months. The goal is to scale this network significantly by the end of 2024, making it the largest automated air-quality monitoring system in Africa. The overall investment in this initiative is kept low due to the affordability of the sensors and the use of AI for efficient data processing and prediction, making it a scalable solution for widespread monitoring.