A machine learning model to detect precipitation
Switch branches/tags
Nothing to show
Clone or download
Type Name Latest commit message Commit time
Failed to load latest commit information.
Codes Delete sample Apr 29, 2018
Data Delete sa Apr 29, 2018
DataDrivenApprocah.pdf Add files via upload May 8, 2018
README.md Update README.md May 8, 2018


A Data-driven Approach to Detect Precipitation from Meteorological Sensor Data

With the spirit of reproducible research, this repository contains all the codes required to produce the results in the manuscript:

S. Manandhar, S. Dev, Y. H. Lee, Y. S. Meng and S. Winkler, " A Data-driven Approach to Detect Precipitation from Meteorological Sensor Data", in Proc. IEEE IGARSS, Valencia, Spian, 2018.

Please cite the above paper if you intend to use whole/part of the code. This code is only for academic and research purposes.

The GPS and Weather station data from singpaore (NTU station) which has been used for the paper are also made available.


The author version of this manuscript is DataDrivenApproach.PDF.

Code Organization

All codes are written in MATLAB.


The dataset used in this manuscript is GPS PWV data derived using GIPSY/OASIS II software using RINEX files for IGS station from Singapore (NTUS). The data files also consist of the weather station data. Weather station is collocated to the GPS station.

Core functionality

  • TimeSeries_Plot.m plots the time series of different weather variables and rain.
  • TrainTestResults.m generates the training and testing at different % of train data size