Location Agnostic Adaptive Rain Precipitation Prediction using Deep Learning

TL;DR

This paper introduces an adaptive deep learning framework for rain precipitation prediction that generalizes across locations and adapts over time, addressing distribution shifts and changing weather patterns.

Contribution

The paper presents a novel adaptive deep learning approach that improves precipitation prediction accuracy across different locations and temporal changes, outperforming non-adaptive models.

Findings

43.51% improvement for Paris

5.09% improvement for Los Angeles

38.62% improvement for Tokyo

Abstract

Rain precipitation prediction is a challenging task as it depends on weather and meteorological features which vary from location to location. As a result, a prediction model that performs well at one location does not perform well at other locations due to the distribution shifts. In addition, due to global warming, the weather patterns are changing very rapidly year by year which creates the possibility of ineffectiveness of those models even at the same location as time passes. In our work, we have proposed an adaptive deep learning-based framework in order to provide a solution to the aforementioned challenges. Our method can generalize the model for the prediction of precipitation for any location where the methods without adaptation fail. Our method has shown 43.51%, 5.09%, and 38.62% improvement after adaptation using a deep neural network for predicting the precipitation of Paris, Los Angeles, and Tokyo, respectively.