The Scripts are used to calculate and generate rainfall grids, using Geostatistical and Deep Learning based interpolation methods, as the requirement of the thesis work, Comparitive Analysis of Rainfall Surface Generation Using Deterministic, Stochastic and Deep Learning Methods
-
Kriging and Regression file contains the scripts for Universal Kriging and Regression Kriging for spatial interpolation.
-
MoNet_GMMConv has the scripts for Gaussian Mixture Model based Neural Networks, using "GMMConv" module to perform spatial interpolation.
-
Test_Elevation is to add the Elevation values from any Digital Elevation Model (DEM), [SRTM was used here], to add to csv files containing rainfall data, for recorded locations.
-
Data folder contains a few amount of data from the set of all the data, that was used in this thesis.
- @inproceedings{monti2017geometric, title={Geometric deep learning on graphs and manifolds using mixture model cnns}, author={Monti, Federico and Boscaini, Davide and Masci, Jonathan and Rodola, Emanuele and Svoboda, Jan and Bronstein, Michael M}, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, pages={5115--5124}, year={2017} }