SSA-UNet: Advanced Precipitation Nowcasting via Channel Shuffling

• URL: http://arxiv.org/abs/2504.18309v1
• Date: Fri, 25 Apr 2025 12:36:31 GMT
• Title: SSA-UNet: Advanced Precipitation Nowcasting via Channel Shuffling
• Authors: Marco Turzi, Siamak Mehrkanoon,
• Abstract summary: This work presents a novel design, Small Shuffled Attention UNet (SSA-UNet)<n>It enhances SmaAt-UNet's architecture by including a shuffle channeling mechanism to optimize performance and diminish complexity.<n>Three output configurations of the proposed architecture are evaluated, yielding outputs of 1, 6, and 12 precipitation maps.
• Score: 1.642094639107215
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Weather forecasting is essential for facilitating diverse socio-economic activity and environmental conservation initiatives. Deep learning techniques are increasingly being explored as complementary approaches to Numerical Weather Prediction (NWP) models, offering potential benefits such as reduced complexity and enhanced adaptability in specific applications. This work presents a novel design, Small Shuffled Attention UNet (SSA-UNet), which enhances SmaAt-UNet's architecture by including a shuffle channeling mechanism to optimize performance and diminish complexity. To assess its efficacy, this architecture and its reduced variant are examined and trained on two datasets: a Dutch precipitation dataset from 2016 to 2019, and a French cloud cover dataset containing radar images from 2017 to 2018. Three output configurations of the proposed architecture are evaluated, yielding outputs of 1, 6, and 12 precipitation maps, respectively. To better understand how this model operates and produces its predictions, a gradient-based approach called Grad-CAM is used to analyze the outputs generated. The analysis of heatmaps generated by Grad-CAM facilitated the identification of regions within the input maps that the model considers most informative for generating its predictions. The implementation of SSA-UNet can be found on our Github\footnote{\href{https://github.com/MarcoTurzi/SSA-UNet}{https://github.com/MarcoTurzi/SSA-UNet}}

Related papers

• Investigating the contribution of terrain-following coordinates and conservation schemes in AI-driven precipitation forecasts [0.0]
  This study integrates terrain-following coordinates with global mass and energy conservation schemes into AIWP models.<n>The conservation schemes are found to reduce drizzle bias, whereas using terrain-following coordinates improves the estimation of extreme events and precipitation intensity spectra.<n>The proposed solution of this study can benefit a wide range of AIWP models and bring insights into how atmospheric domain knowledge can support the development of AIWP models.
  arXiv  Detail & Related papers  (2025-03-01T03:44:46Z)
• Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models [56.00251589760559]
  Large language models (LLMs) can act as gradient priors in a zero-shot setting. We introduce LM-GC, a novel method that integrates LLMs with arithmetic coding. Experiments indicate that LM-GC surpasses existing state-of-the-art lossless compression methods.
  arXiv  Detail & Related papers  (2024-09-26T13:38:33Z)
• OPUS: Occupancy Prediction Using a Sparse Set [64.60854562502523]
  We present a framework to simultaneously predict occupied locations and classes using a set of learnable queries. OPUS incorporates a suite of non-trivial strategies to enhance model performance. Our lightest model achieves superior RayIoU on the Occ3D-nuScenes dataset at near 2x FPS, while our heaviest model surpasses previous best results by 6.1 RayIoU.
  arXiv  Detail & Related papers  (2024-09-14T07:44:22Z)
• Towards Explainable LiDAR Point Cloud Semantic Segmentation via Gradient Based Target Localization [13.291152913893029]
  This paper introduces pGS-CAM, a novel method for generating saliency maps in neural network activation layers. Inspired by Grad-CAM, which uses gradients to highlight local importance, pGS-CAM is robust and effective on a variety of datasets.
  arXiv  Detail & Related papers  (2024-02-19T12:27:39Z)
• GA-SmaAt-GNet: Generative Adversarial Small Attention GNet for Extreme Precipitation Nowcasting [1.642094639107215]
  We present the GA-SmaAt-GNet model, a novel generative adversarial framework for extreme precipitation nowcasting. We evaluate the performance of SmaAt-GNet and GA-SmaAt-GNet using real-life precipitation data from the Netherlands.
  arXiv  Detail & Related papers  (2024-01-18T10:53:45Z)
• Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton Sequence [56.092059713922744]
  We show that using high-level contextualized features as prediction targets can achieve superior performance. Specifically, we propose Skeleton2vec, a simple and efficient self-supervised 3D action representation learning framework. Our proposed Skeleton2vec outperforms previous methods and achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2024-01-01T12:08:35Z)
• 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)
• SAR-UNet: Small Attention Residual UNet for Explainable Nowcasting Tasks [4.213427823201119]
  The accuracy and explainability of data-driven nowcasting models are of great importance in many socio-economic sectors reliant on weather-dependent decision making. This paper proposes a novel architecture called Small Attention Residual UNet (SAR-UNet) for precipitation and cloud cover nowcasting.
  arXiv  Detail & Related papers  (2023-03-12T13:56:59Z)
• Conditioned Human Trajectory Prediction using Iterative Attention Blocks [70.36888514074022]
  We present a simple yet effective pedestrian trajectory prediction model aimed at pedestrians positions prediction in urban-like environments. Our model is a neural-based architecture that can run several layers of attention blocks and transformers in an iterative sequential fashion. We show that without explicit introduction of social masks, dynamical models, social pooling layers, or complicated graph-like structures, it is possible to produce on par results with SoTA models.
  arXiv  Detail & Related papers  (2022-06-29T07:49:48Z)
• CAFE: Learning to Condense Dataset by Aligning Features [72.99394941348757]
  We propose a novel scheme to Condense dataset by Aligning FEatures (CAFE) At the heart of our approach is an effective strategy to align features from the real and synthetic data across various scales. We validate the proposed CAFE across various datasets, and demonstrate that it generally outperforms the state of the art.
  arXiv  Detail & Related papers  (2022-03-03T05:58:49Z)
• Short-Term Load Forecasting using Bi-directional Sequential Models and Feature Engineering for Small Datasets [6.619735628398446]
  This paper presents a deep learning architecture for short-term load forecasting based on bidirectional sequential models. In the proposed architecture, the raw input and hand-crafted features are trained at separate levels and then their respective outputs are combined to make the final prediction. The efficacy of the proposed methodology is evaluated on datasets from five countries with completely different patterns.
  arXiv  Detail & Related papers  (2020-11-28T14:11:35Z)
• SmaAt-UNet: Precipitation Nowcasting using a Small Attention-UNet Architecture [5.28539620288341]
  We show that it is possible to produce an accurate precipitation nowcast using a data-driven neural network approach. We evaluate our approaches on a real-life datasets using precipitation maps from the region of the Netherlands and binary images of cloud coverage of France.
  arXiv  Detail & Related papers  (2020-07-08T20:33:10Z)

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.