# MeTok: An Efficient Meteorological Tokenization with Hyper-Aligned Group Learning for Precipitation Nowcasting

arXiv: https://arxiv.org/abs/2603.13752 · HTML: https://mlsanity.com/paper/2603.13752/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 14 Mar 2026.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [ClimaX: A foundation model for weather and climate](https://mlsanity.com/paper/2301.10343/) (2023)
- [Skillful Precipitation Nowcasting using Deep Generative Models of Radar](https://mlsanity.com/paper/2104.00954/) (2021)
- [WeatherBench: A benchmark dataset for data-driven weather forecasting](https://mlsanity.com/paper/2002.00469/) (2020)
- [WeatherBench 2: A benchmark for the next generation of data-driven global weather models](https://mlsanity.com/paper/2308.15560/) (2023)
- [Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model](https://mlsanity.com/paper/1706.03458/) (2017)
- [Earthformer: Exploring Space-Time Transformers for Earth System Forecasting](https://mlsanity.com/paper/2207.05833/) (2022)
- [Seesaw Loss for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2008.10032/) (2020)
- [PreDiff: Precipitation Nowcasting with Latent Diffusion Models](https://mlsanity.com/paper/2307.10422/) (2023)
- [MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions](https://mlsanity.com/paper/2103.02243/) (2021)
- [Striking the Right Balance: Recall Loss for Semantic Segmentation](https://mlsanity.com/paper/2106.14917/) (2021)

## Abstract (arXiv)

Recently, Transformer-based architectures have advanced meteorological prediction. However, this position-centric tokenizer conflicts with the core principle of meteorological systems, where the weather phenomena undoubtedly involve synergistic interactions among multiple elements while positional information constitutes merely a component of the boundary conditions. This paper focuses primarily on the task of precipitation nowcasting and develops an efficient distribution-centric Meteorological Tokenization (MeTok) scheme, which spatially sequences to group similar meteorological features. Based on the rearrangement, realigned group learning enhances robustness across precipitation patterns, especially extreme ones. Specifically, we introduce the Hyper-Aligned Grouping Transformer (HyAGTransformer) with two key improvements: 1) The Grouping Attention (GA) mechanism uses MeTok to enable self-aligned learning of features from different precipitation patterns; 2) The Neighborhood Feed-Forward Network (N-FFN) integrates adjacent group features, aggregating contextual information to boost patch embedding discriminability. Experiments on the ERA5 dataset for 6-hour forecasts show our method improves the IoU metric by at least 8.2% in extreme precipitation prediction compared to other methods. Additionally, it gains performance with more training data and increased parameters, demonstrating scalability, stability, and superiority over traditional methods.