TRU-NET: A Deep Learning Approach to High Resolution Prediction of
Rainfall
- URL: http://arxiv.org/abs/2008.09090v2
- Date: Fri, 12 Feb 2021 18:30:08 GMT
- Title: TRU-NET: A Deep Learning Approach to High Resolution Prediction of
Rainfall
- Authors: Rilwan Adewoyin, Peter Dueben, Peter Watson, Yulan He, Ritabrata Dutta
- Abstract summary: We present TRU-NET, an encoder-decoder model featuring a novel 2D cross attention mechanism between contiguous convolutional-recurrent layers.
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.
- Score: 21.399707529966474
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded
Modelling [93.65319031345197]
We propose CasCast, a cascaded framework composed of a deterministic and a probabilistic part to decouple predictions for mesoscale precipitation distributions and small-scale patterns.
CasCast significantly surpasses the baseline (up to +91.8%) for regional extreme-precipitation nowcasting.
arXiv Detail & Related papers (2024-02-06T08:30:47Z) - Precipitation Downscaling with Spatiotemporal Video Diffusion [19.004369237435437]
This work extends recent video diffusion models to precipitation super-resolution.
We use a deterministic downscaler followed by a temporally-conditioned diffusion model to capture noise characteristics and high-frequency patterns.
Our analysis, capturing CRPS, MSE, precipitation distributions, and qualitative aspects using California and the Himalayas, establishes our method as a new standard for data-driven precipitation downscaling.
arXiv Detail & Related papers (2023-12-11T02:38:07Z) - Learning Robust Precipitation Forecaster by Temporal Frame Interpolation [65.5045412005064]
We develop a robust precipitation forecasting model that demonstrates resilience against spatial-temporal discrepancies.
Our approach has led to significant improvements in forecasting precision, culminating in our model securing textit1st place in the transfer learning leaderboard of the textitWeather4cast'23 competition.
arXiv Detail & Related papers (2023-11-30T08:22:08Z) - Residual Diffusion Modeling for Km-scale Atmospheric Downscaling [51.061954281398116]
A cost-effective downscaling model is trained from a high-resolution 2-km weather model over Taiwan.
textitCorrDiff exhibits skillful RMSE and CRPS and faithfully recovers spectra and distributions even for extremes.
Downscaling global forecasts successfully retains many of these benefits, foreshadowing the potential of end-to-end, global-to-km-scales machine learning weather predictions.
arXiv Detail & Related papers (2023-09-24T19:57:22Z) - Towards replacing precipitation ensemble predictions systems using
machine learning [0.0]
We propose a new approach to generating ensemble weather predictions for high-resolution precipitation.
The method uses generative adversarial networks to learn the complex patterns of precipitation.
We demonstrate the feasibility of generating realistic precipitation ensemble members on unseen higher resolutions.
arXiv Detail & Related papers (2023-04-20T12:20:35Z) - An evaluation of deep learning models for predicting water depth
evolution in urban floods [59.31940764426359]
We compare different deep learning models for prediction of water depth at high spatial resolution.
Deep learning models are trained to reproduce the data simulated by the CADDIES cellular-automata flood model.
Our results show that the deep learning models present in general lower errors compared to the other methods.
arXiv Detail & Related papers (2023-02-20T16:08:54Z) - Machine learning emulation of a local-scale UK climate model [22.374171443798037]
We show for the first time a machine learning model that is able to produce realistic samples of high-resolution rainfall.
By adding self-learnt, location-specific information to low resolution relative vorticity, quantiles and time-mean of the samples match well their counterparts from the high-resolution simulation.
arXiv Detail & Related papers (2022-11-29T11:44:35Z) - A Generative Deep Learning Approach to Stochastic Downscaling of
Precipitation Forecasts [0.5906031288935515]
Generative adversarial networks (GANs) have been demonstrated by the computer vision community to be successful at super-resolution problems.
We show that GANs and VAE-GANs can match the statistical properties of state-of-the-art pointwise post-processing methods whilst creating high-resolution, spatially coherent precipitation maps.
arXiv Detail & Related papers (2022-04-05T07:19:42Z) - Semi-Supervised Video Deraining with Dynamic Rain Generator [59.71640025072209]
This paper proposes a new semi-supervised video deraining method, in which a dynamic rain generator is employed to fit the rain layer.
Specifically, such dynamic generator consists of one emission model and one transition model to simultaneously encode the spatially physical structure and temporally continuous changes of rain streaks.
Various prior formats are designed for the labeled synthetic and unlabeled real data, so as to fully exploit the common knowledge underlying them.
arXiv Detail & Related papers (2021-03-14T14:28:57Z) - From Rain Generation to Rain Removal [67.71728610434698]
We build a full Bayesian generative model for rainy image where the rain layer is parameterized as a generator.
We employ the variational inference framework to approximate the expected statistical distribution of rainy image.
Comprehensive experiments substantiate that the proposed model can faithfully extract the complex rain distribution.
arXiv Detail & Related papers (2020-08-08T18:56:51Z) - Improving data-driven global weather prediction using deep convolutional
neural networks on a cubed sphere [7.918783985810551]
We present a significantly-improved data-driven global weather forecasting framework using a deep convolutional neural network (CNN)
New developments in this framework include an offline volume-conservative mapping to a cubed-sphere grid.
Our model is able to learn to forecast complex surface temperature patterns from few input atmospheric state variables.
arXiv Detail & Related papers (2020-03-15T19:57:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.