Skip to content

A Spark application for weather forecasting using ensemble of tree-based models, trained on long-term historical data.

License

Notifications You must be signed in to change notification settings

mtalebizadeh/weather-forecasting

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Application of tree-based models for weather forecasting

This application enables creation of a structured dataset from a number of text files containing historical weather variables across the Netherlands that are provided by Koninklijk Nederlands Meteorologisch Instituut (KNMI). The tree-based models include a single decision tree model as well as two types of tree ensemble models including the Random Forest and Gradient-boosted models. The forecast variable is a discrete variable representing the severity of precipitation.

Build and dependency management

SBT 1.1.X and Java 8+ are needed to build. For a list of dependencies and Scala version, please see build.sbt.

Data source

The daily weather data are maintained by the Royal Netherlands Meteorological Institute and available for download at: http://projects.knmi.nl/klimatologie/daggegevens/selectie.cgi.

License

This project is licensed under the MIT License - see the LICENSE.md file for details.

About

A Spark application for weather forecasting using ensemble of tree-based models, trained on long-term historical data.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages