pytorch implemention of trajGRU.

PyTorch-Code for the Paper "SmaAt-UNet: Precipitation Nowcasting using a Small, Attentive UNet-Architecture"

A list of Precipitation Nowcasting papers and related resources.

The repository for paper AA-TransUNet: Attention Augmented TransUNet For Nowcasting Tasks.

An implementation of Deep Generative Model of Radars from DeepMind in PyTorch

This is a Pytorch implementation of PFST-LSTM, a recurrent model for precipitation nowcasting (radar echo extrapolation) as described in the following paper: PFST-LSTM: a SpatioTemporal LSTM Model with Pseudo-flow Prediction for Precipitation Nowcasting

Code for improving precipitation nowcasting models using weighted average ensemble methods.

Source code for the manuscript "DEUCE v1.0: A neural network for probabilistic precipitation nowcasting with aleatoric and epistemic uncertainties" by Harnist et al. (2024)

Repository For My BigData and Artificial Intelligence Course in KNU

Implemented state-of-the-art ConvLSTM and TrajGRU models for precipitation nowcasting, leveraging satellite data with higher spatial (4 km x 4 km) and temporal resolution (15 min) . Created datasets of 1,560 and 779 sequences to train and test. Achieved RMSE of 3.69 mm/hr with 2-hour lead time and RMSE of 8.06 mm/hr with 4-hour lead-time

A ConvLSTM3D model for nowcasting of precipitation using C-Band DWR TERLS.

The M.Sc. Thesis of Bent Harnist (2022) at Aalto University, "Probabilistic Precipitation Nowcasting Using Bayesian Convolutional Neural Networks"

Analyzes 140 years of Central Park percipitation using methods like SARIMAX, Marked Point Processes, and LSTM networks. gaussian processes Includes frequency analysis, predictive modeling, and uncertainty quantification to explore precipitation trends and improve forecasting accuracy.

In this project we worked on developing an understanding of RNN and LSTM machine learning paradigms and their application in precipitation nowcasting