Self-Supervised Pre-Training for Precipitation Post-Processor
- URL: http://arxiv.org/abs/2310.20187v3
- Date: Tue, 20 Feb 2024 01:45:22 GMT
- Title: Self-Supervised Pre-Training for Precipitation Post-Processor
- Authors: Sojung An, Junha Lee, Jiyeon Jang, Inchae Na, Wooyeon Park, Sujeong
You
- Abstract summary: We propose a deep learning-based precipitation post-processor for numerical weather prediction (NWP) models.
Our experiments on precipitation correction for regional NWP datasets show that the proposed method outperforms other approaches.
- Score: 1.5553847214012175
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Obtaining a sufficient forecast lead time for local precipitation is
essential in preventing hazardous weather events. Global warming-induced
climate change increases the challenge of accurately predicting severe
precipitation events, such as heavy rainfall. In this paper, we propose a deep
learning-based precipitation post-processor for numerical weather prediction
(NWP) models. The precipitation post-processor consists of (i) employing
self-supervised pre-training, where the parameters of the encoder are
pre-trained on the reconstruction of the masked variables of the atmospheric
physics domain; and (ii) conducting transfer learning on precipitation
segmentation tasks (the target domain) from the pre-trained encoder. In
addition, we introduced a heuristic labeling approach to effectively train
class-imbalanced datasets. Our experiments on precipitation correction for
regional NWP show that the proposed method outperforms other approaches.
Related papers
- Extreme Precipitation Nowcasting using Transformer-based Generative
Models [9.497627628556875]
This paper presents an innovative approach to extreme precipitation nowcasting by employing Transformer-based generative models, namely NowcastingGPT with Extreme Value Loss (EVL) regularization.
We introduce a novel method for computing EVL without assuming fixed extreme representations, addressing the limitations of current models in capturing extreme weather events.
We present both qualitative and quantitative analyses, demonstrating the superior performance of the proposed NowcastingGPT-EVL in generating accurate precipitation forecasts.
arXiv Detail & Related papers (2024-03-06T18:39:41Z) - 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) - Observation-Guided Meteorological Field Downscaling at Station Scale: A
Benchmark and a New Method [66.80344502790231]
We extend meteorological downscaling to arbitrary scattered station scales and establish a new benchmark and dataset.
Inspired by data assimilation techniques, we integrate observational data into the downscaling process, providing multi-scale observational priors.
Our proposed method outperforms other specially designed baseline models on multiple surface variables.
arXiv Detail & Related papers (2024-01-22T14:02:56Z) - Scaling transformer neural networks for skillful and reliable
medium-range weather forecasting [24.02355555479722]
We introduce Stormer, a state-of-the-art performance on weather forecasting with minimal changes to the standard transformer backbone.
At the core of Stormer is a randomized forecasting objective that trains the model to forecast the weather dynamics over varying time intervals.
On WeatherBench 2, Stormer performs competitively at short to medium-range forecasts and outperforms current methods beyond 7 days.
arXiv Detail & Related papers (2023-12-06T19:46:06Z) - 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) - PostRainBench: A comprehensive benchmark and a new model for
precipitation forecasting [15.937786723800883]
Coupling AI-based post-processing techniques with traditional Numerical Weather Prediction (NWP) methods offers a more effective solution for improving forecasting accuracy.
We propose CAMT, a simple yet effective Channel Attention Enhanced Multi-task Learning framework with a specially designed weighted loss function.
Our model is the first deep learning-based method to outperform traditional NWP approaches in extreme precipitation conditions.
arXiv Detail & Related papers (2023-10-04T09:27:39Z) - 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) - Tipping Point Forecasting in Non-Stationary Dynamics on Function Spaces [78.08947381962658]
Tipping points are abrupt, drastic, and often irreversible changes in the evolution of non-stationary dynamical systems.
We learn the evolution of such non-stationary systems using a novel recurrent neural operator (RNO), which learns mappings between function spaces.
We propose a conformal prediction framework to forecast tipping points by monitoring deviations from physics constraints.
arXiv Detail & Related papers (2023-08-17T05:42:27Z) - Generative Modeling of High-resolution Global Precipitation Forecasts [2.1485350418225244]
We present improvements to the architecture and training process of a current state-of-the art deep learning precipitation model (FourCastNet) using a novel generative adversarial network (GAN)
Our improvements achieve superior performance in capturing the extreme percentiles of global precipitation, while comparable to state-of-the-art NWP models in terms of forecast skill at 1--2 day lead times.
arXiv Detail & Related papers (2022-10-22T17:21:16Z) - Forecasting large-scale circulation regimes using deformable
convolutional neural networks and global spatiotemporal climate data [86.1450118623908]
We investigate a supervised machine learning approach based on deformable convolutional neural networks (deCNNs)
We forecast the North Atlantic-European weather regimes during extended boreal winter for 1 to 15 days into the future.
Due to its wider field of view, we also observe deCNN achieving considerably better performance than regular convolutional neural networks at lead times beyond 5-6 days.
arXiv Detail & Related papers (2022-02-10T11:37:00Z) - TRU-NET: A Deep Learning Approach to High Resolution Prediction of
Rainfall [21.399707529966474]
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.
arXiv Detail & Related papers (2020-08-20T17:27:59Z)
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.