FusionCast: Enhancing Precipitation Nowcasting with Asymmetric Cross-Modal Fusion and Future Radar Priors

• URL: http://arxiv.org/abs/2603.13298v1
• Date: Mon, 02 Mar 2026 03:41:38 GMT
• Title: FusionCast: Enhancing Precipitation Nowcasting with Asymmetric Cross-Modal Fusion and Future Radar Priors
• Abstract summary: This paper proposes a novel precipitation nowcasting optimisation framework called FusionCast.<n>It incorporates three types of data: historical precipitable water vapour (PWV) data derived from global navigation satellite system (GNSS) inversions, historical radar based quantitative precipitation estimation (QPE)<n> Experimental results show that FusionCast significantly improves nowcasting performance.
• Score: 17.839934984801882
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning has significantly improved the accuracy of precipitation nowcasting. However, most existing multimodal models typically use simple channel concatenation or interpolation methods for data fusion, which often overlook the feature differences between different modalities. This paper therefore proposes a novel precipitation nowcasting optimisation framework called FusionCast. This framework incorporates three types of data: historical precipitable water vapour (PWV) data derived from global navigation satellite system (GNSS) inversions, historical radar based quantitative precipitation estimation (QPE), and forecasted radar QPE serving as a future prior. The FusionCast model comprises two core modules: the future prior radar QPE processing Module, which forecasts future radar data; and the Radar PWV Fusion (RPF) module, which uses a gate mechanism to efficiently combine features from various sources. Experimental results show that FusionCast significantly improves nowcasting performance.

Related papers

• CastFlow: Learning Role-Specialized Agentic Workflows for Time Series Forecasting [74.29761960394848]
  We propose CastFlow, a dynamic agentic forecasting framework for large language models (LLMs)<n>CastFlow organizes the forecasting process into planning, action, forecasting, and reflection, establishing an agentic workflow.<n>Third, CastFlow adopts a role-specialized design that combines general-purpose reasoning with specialized numerical forecasting.
  arXiv  Detail & Related papers  (2026-04-30T13:24:42Z)
• TS-Memory: Plug-and-Play Memory for Time Series Foundation Models [63.21390142212087]
  Time Series Foundation Models (TSFMs) achieve strong zero-shot forecasting through large-scale pre-training.<n>Existing solutions face a trade-off: Parametric Adaptation can cause catastrophic forgetting, while Non-Parametric Retrieval improves forecasts but incurs high latency due to datastore search.<n>We propose Parametric Memory Distillation and implement it as TS-Memory, a lightweight memory adapter that augments frozen TSFMs.
  arXiv  Detail & Related papers  (2026-02-12T04:16:19Z)
• HRRRCast: a data-driven emulator for regional weather forecasting at convection allowing scales [1.3834027455392646]
  We introduce HRRRCast, a data-driven emulator built with advanced machine learning techniques.<n>ResHRRR is a ResNet-based model (ResHRRR) and a Graph Neural Network-based model (GraphHRRR)<n>ResHRRR outperforms HRRR forecast at light rainfall threshold (20 dBZ) and achieves competitive performance at moderate thresholds (30 dBZ)
  arXiv  Detail & Related papers  (2025-07-08T04:26:47Z)
• Elucidated Rolling Diffusion Models for Probabilistic Weather Forecasting [52.6508222408558]
  We introduce Elucidated Rolling Diffusion Models (ERDM)<n>ERDM is the first framework to unify a rolling forecast structure with the principled, performant design of Elucidated Diffusion Models (EDM)<n>On 2D Navier-Stokes simulations and ERA5 global weather forecasting at 1.5circ resolution, ERDM consistently outperforms key diffusion-based baselines.
  arXiv  Detail & Related papers  (2025-06-24T21:44:31Z)
• LaDCast: A Latent Diffusion Model for Medium-Range Ensemble Weather Forecasting [1.2277343096128712]
  We introduce LaDCast, the first global latent-diffusion framework for medium-range ensemble forecasting.<n>LaDCast generates hourly ensemble forecasts entirely in a learned latent space.<n>LaDCast achieves deterministic and probabilistic skill close to that of the European Centre for Medium-Range Forecast IFS-ENS.
  arXiv  Detail & Related papers  (2025-06-10T19:17:14Z)
• From Swath to Full-Disc: Advancing Precipitation Retrieval with Multimodal Knowledge Expansion [11.443489040028645]
  PRE-Net aims to enable accurate, infrared-based full-disc precipitation retrievals beyond the scanning swath.<n> PRE-Net transfers knowledge from a multimodal data integration model to an infrared-based model within the scanning swath.<n>In the Full-Disc Adaptation stage, Self-MaskTune refines predictions across the full disc by balancing multimodal and full-disc infrared knowledge.
  arXiv  Detail & Related papers  (2025-06-08T09:15:46Z)
• Tackling Data Heterogeneity in Federated Time Series Forecasting [61.021413959988216]
  Time series forecasting plays a critical role in various real-world applications, including energy consumption prediction, disease transmission monitoring, and weather forecasting. Most existing methods rely on a centralized training paradigm, where large amounts of data are collected from distributed devices to a central cloud server. We propose a novel framework, Fed-TREND, to address data heterogeneity by generating informative synthetic data as auxiliary knowledge carriers.
  arXiv  Detail & Related papers  (2024-11-24T04:56:45Z)
• GPTCast: a weather language model for precipitation nowcasting [0.0]
  GPTCast is a generative deep-learning method for ensemble nowcast of radar-based precipitation. We employ a GPT model as a forecaster to learn precipitation dynamics using tokenized radar images.
  arXiv  Detail & Related papers  (2024-07-02T09:25:58Z)
• ARFA: An Asymmetric Receptive Field Autoencoder Model for Spatiotemporal Prediction [55.30913411696375]
  We propose an Asymmetric Receptive Field Autoencoder (ARFA) model, which introduces corresponding sizes of receptive field modules. In the encoder, we present large kernel module for globaltemporal feature extraction. In the decoder, we develop a small kernel module for localtemporal reconstruction. We construct the RainBench, a large-scale radar echo dataset for precipitation prediction, to address the scarcity of meteorological data in the domain.
  arXiv  Detail & Related papers  (2023-09-01T07:55:53Z)
• Deep Learning for Day Forecasts from Sparse Observations [60.041805328514876]
  Deep neural networks offer an alternative paradigm for modeling weather conditions. MetNet-3 learns from both dense and sparse data sensors and makes predictions up to 24 hours ahead for precipitation, wind, temperature and dew point. MetNet-3 has a high temporal and spatial resolution, respectively, up to 2 minutes and 1 km as well as a low operational latency.
  arXiv  Detail & Related papers  (2023-06-06T07:07:54Z)
• MS-nowcasting: Operational Precipitation Nowcasting with Convolutional LSTMs at Microsoft Weather [1.7780828990105975]
  We present the encoder-forecaster convolutional long short-term memory (LSTM) deep-learning model that powers Microsoft Weather's operational precipitation nowcasting product. This model takes as input a sequence of weather radar mosaics and deterministically predicts future radar reflectivity at lead times up to 6 hours.
  arXiv  Detail & Related papers  (2021-11-18T21:55:49Z)
• Inverting the Pose Forecasting Pipeline with SPF2: Sequential Pointcloud Forecasting for Sequential Pose Forecasting [106.3504366501894]
  Self-driving vehicles and robotic manipulation systems often forecast future object poses by first detecting and tracking objects. This detect-then-forecast pipeline is expensive to scale, as pose forecasting algorithms typically require labeled sequences of object poses. We propose to first forecast 3D sensor data and then detect/track objects on the predicted point cloud sequences to obtain future poses. This makes it less expensive to scale pose forecasting, as the sensor data forecasting task requires no labels.
  arXiv  Detail & Related papers  (2020-03-18T17:54:28Z)

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.