- Популярные видео
- Авто
- Видео-блоги
- ДТП, аварии
- Для маленьких
- Еда, напитки
- Животные
- Закон и право
- Знаменитости
- Игры
- Искусство
- Комедии
- Красота, мода
- Кулинария, рецепты
- Люди
- Мото
- Музыка
- Мультфильмы
- Наука, технологии
- Новости
- Образование
- Политика
- Праздники
- Приколы
- Природа
- Происшествия
- Путешествия
- Развлечения
- Ржач
- Семья
- Сериалы
- Спорт
- Стиль жизни
- ТВ передачи
- Танцы
- Технологии
- Товары
- Ужасы
- Фильмы
- Шоу-бизнес
- Юмор
MIT808 2026 GR21:Will Air Quality Have an Exceedance Today?24-Hour Ozone Forecasting on the Highveld
MIT808 2026 — Masters in IT: Big Data Science Capstone Exhibition
University of Pretoria, Department of Computer Science
Lecturers: Dr Olaperi Okuboyejo and Dr Abiodun Modupe
Project: Will Air Quality Have an Exceedance Today? 24-Hour Ozone Forecasting on the Highveld
Team: n-ary
Students: Kamogelo Moukangwe and Rivoningo Mageza
Partner: Geography, Geoinformatics and Meteorology Department, University of Pretoria
A machine learning system predicts hourly ozone concentrations up to 24 hours ahead using data from 36 SAAQIS stations and Open-Meteo weather data. Random Forest (R²=0.781, RMSE=5.94 ppb) and XGBoost (R²=0.776, trained 20× faster) provide the best results. An interactive Streamlit app delivers 24-hour forecasts with visual alerts when ozone exceeds 61 ppb and optional daily subscriptions.
🔗 MIT808 2026 Exhibition: https://up-mitc-ds.github.io/808exhibition
📋 Poster page: https://up-mitc-ds.github.io/808exhibition/poster_2026-21.html
📚 MIT808 course: https://www.dsfsi.co.za/mit808/
Видео MIT808 2026 GR21:Will Air Quality Have an Exceedance Today?24-Hour Ozone Forecasting on the Highveld канала Data Science for Social Impact (DSFSI)
University of Pretoria, Department of Computer Science
Lecturers: Dr Olaperi Okuboyejo and Dr Abiodun Modupe
Project: Will Air Quality Have an Exceedance Today? 24-Hour Ozone Forecasting on the Highveld
Team: n-ary
Students: Kamogelo Moukangwe and Rivoningo Mageza
Partner: Geography, Geoinformatics and Meteorology Department, University of Pretoria
A machine learning system predicts hourly ozone concentrations up to 24 hours ahead using data from 36 SAAQIS stations and Open-Meteo weather data. Random Forest (R²=0.781, RMSE=5.94 ppb) and XGBoost (R²=0.776, trained 20× faster) provide the best results. An interactive Streamlit app delivers 24-hour forecasts with visual alerts when ozone exceeds 61 ppb and optional daily subscriptions.
🔗 MIT808 2026 Exhibition: https://up-mitc-ds.github.io/808exhibition
📋 Poster page: https://up-mitc-ds.github.io/808exhibition/poster_2026-21.html
📚 MIT808 course: https://www.dsfsi.co.za/mit808/
Видео MIT808 2026 GR21:Will Air Quality Have an Exceedance Today?24-Hour Ozone Forecasting on the Highveld канала Data Science for Social Impact (DSFSI)
Комментарии отсутствуют
Информация о видео
27 мая 2026 г. 0:03:53
00:08:31
Другие видео канала





















