Skip to content

Repository for our project in Experts in Teamwork (EiT) at NTNU. The web app serves forecasts for water temperatures in Korsvika, Trondheim, based on historical data and forecasts from The Norwegian Meteorological Institute. The predictions are served via a pretrained ML-model in Tensorflow that is deployed to and loaded in firebase function.

Notifications You must be signed in to change notification settings

Magssch/TMA4851-water-temperature-prediction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

87 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

TMA4851-water-temperature-prediction

Repository for our project in Experts in Teamwork (EiT) at NTNU. The web app serves predictions for surface water temperatures at future dates, based on historical data from YR / Norwegian Meteorological Institute. Predictions are served via a pretrained Keras model that is loaded in a firebase function with Tensorflow.js.

The ML model consists of time-series data fed through a single convolutional layer which is then fed into two bidirectional layers of LSTM. This structure is commonly known as the "CNN-LSTM" model.

Live demo

Team members:

  • Anders Hoel
  • Herman Sletmoen
  • Nora Høva Erevik
  • Kaja Sofie Lundgaard
  • Henrik Lia
  • Magnus Schjølberg

About

Repository for our project in Experts in Teamwork (EiT) at NTNU. The web app serves forecasts for water temperatures in Korsvika, Trondheim, based on historical data and forecasts from The Norwegian Meteorological Institute. The predictions are served via a pretrained ML-model in Tensorflow that is deployed to and loaded in firebase function.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published