TRU-NET: A Deep Learning Approach to High Resolution Prediction of Rainfall
Climate models (CM) are used to evaluate the impact of climate change on the risk of floods and strong precipitation events. However, these numerical simulators have difficulties representing precipitation events accurately, mainly due to limited spatial resolution when simulating multi-scale dynami...
Saved in:
Main Authors | , , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
20.08.2020
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Climate models (CM) are used to evaluate the impact of climate change on the
risk of floods and strong precipitation events. However, these numerical
simulators have difficulties representing precipitation events accurately,
mainly due to limited spatial resolution when simulating multi-scale dynamics
in the atmosphere. To improve the prediction of high resolution precipitation
we apply a Deep Learning (DL) approach using an input of CM simulations of the
model fields (weather variables) that are more predictable than local
precipitation. To this end, we present TRU-NET (Temporal Recurrent U-Net), an
encoder-decoder model featuring a novel 2D cross attention mechanism between
contiguous convolutional-recurrent layers to effectively model multi-scale
spatio-temporal weather processes. We use a conditional-continuous loss
function to capture the zero-skewed %extreme event patterns of rainfall.
Experiments show that our model consistently attains lower RMSE and MAE scores
than a DL model prevalent in short term precipitation prediction and improves
upon the rainfall predictions of a state-of-the-art dynamical weather model.
Moreover, by evaluating the performance of our model under various, training
and testing, data formulation strategies, we show that there is enough data for
our deep learning approach to output robust, high-quality results across
seasons and varying regions. |
---|---|
DOI: | 10.48550/arxiv.2008.09090 |