Phys-Diff: A Physics-Inspired Latent Diffusion Model for Tropical Cyclone Forecasting

Lei Liu; Xiaoning Yu; Kang Chen; Jiahui Huang; Tengyuan Liu; Hongwei Zhao; Bin Li

cs.LGFeb 28, 2026

Phys-Diff: A Physics-Inspired Latent Diffusion Model for Tropical Cyclone Forecasting

Authors: Lei Liu, Xiaoning Yu, Kang Chen, Jiahui Huang, Tengyuan Liu, Hongwei Zhao, Bin Li

Organizations: University of Science and Technology of China, Hefei, China · Hefei University of Technology, Hefei, China

Abstract

Tropical cyclone (TC) forecasting is critical for disaster warning and emergency response. Deep learning methods address computational challenges but often neglect physical relationships between TC attributes, resulting in predictions lacking physical consistency. To address this, we propose Phys-Diff, a physics-inspired latent diffusion model that disentangles latent features into task-specific components (trajectory, pressure, wind speed) and employs cross-task attention to introduce prior physics-inspired inductive biases, thereby embedding physically consistent dependencies among TC attributes. Phys-Diff integrates multimodal data including historical cyclone attributes, ERA5 reanalysis data, and FengWu forecast fields via a Transformer encoder-decoder architecture, further enhancing forecasting performance. Experiments demonstrate state-of-the-art performance on global and regional datasets.

Figures & tables

Figure 1: Comparison of feature representations. Previous methods (e.g., MSCAR [ 9 ] , VQLTI [ 10 ] ) produce coupled features without physical constraints. Our method enforces these constraints, learning disentangled features with improved physical consistency.

Figure 2: Overall architecture of the Phys-Diff model. This is a denoising diffusion model built on a Transformer encoder-decoder framework. During inference, the model starts with random Gaussian noise and progressively generates predictions. The encoder handles multimodal inputs, combining historical cyclone data with environmental field features containing both past and future information. At the core, the Physics-Inspired Decoder features the PIGA module, which uses cross-task attention to model the physical dependencies between task-specific features (trajectory, wind speed, and pressure), ensuring both physical consistency and accuracy in the forecasts.

Basin	Methods	Trajectory Error (km)				Pressure Error (hPa)				Wind Speed Error (m/s)				Model	Training/
Basin	Methods	6h	12h	18h	24h	6h	12h	18h	24h	6h	12h	18h	24h	size	Inference Time
Global	GRU(2014)	53.30	101.99	190.01	298.62	4.10	5.50	7.20	9.10	3.20	4.10	5.30	6.80	322.88K	3h/0.35s
	GBRNN (2019)	42.91	65.34	103.77	147.12	–	–	–	–	–	–	–	–	1.50M	11.2h/0.27s
	FengWu (2023)	50.26	67.96	67.09	93.08	2.87	4.04	5.66	8.25	13.62	15.24	17.32	19.94	427M	–/0.58s
	ECMWF	41.50	52.60	65.80	72.51	6.03	6.18	6.54	6.75	–	–	–	–	–	–
	MSCAR(2024)	–	–	–	–	2.28	3.60	4.66	5.62	1.64	2.72	3.56	4.30	–	–

Table 1: Comprehensive TC forecast performance comparison across different basins and time horizons. Lower values indicate better performance. The GBRNN model predicts only trajectory, and MSCAR and VQLTI predict only intensity.

h

represents hours,

s

represents seconds, and inference time refers to a single sample.

Settings	Trajectory Error (km)				Pressure Error (hPa)				Wind Speed Error (m/s)
Settings	6h	24h	48h	120h	6h	24h	48h	120h	6h	24h	48h	120h
w/o PIGA	18.15	65.40	105.70	211.30	2.85	3.12	3.95	5.51	1.93	1.74	2.56	3.42
w/o FengWu	15.12	54.85	95.25	182.60	2.36	2.45	3.23	4.58	1.54	1.23	2.15	2.88
w/o both	30.25	70.10	115.50	235.80	4.07	4.61	5.89	8.63	2.74	2.53	3.89	5.37
Phys-Diff	15.26	54.35	81.11	151.80	2.32	2.41	3.18	4.42	1.51	1.24	2.08	2.78
Phys-Diff (Ensemble)	14.82	52.18	79.20	145.50	2.15	2.28	2.95	4.08	1.38	1.12	1.92	2.58

Table 2: Ablation study on key model components (lower is better). Since Phys-Diff is generative, we form an ensemble by sampling N=50 members from different Gaussian noise initializations; the ensemble mean improves accuracy over single-shot predictions.

Figure 3: t-SNE visualization of learned task-specific features by the PIGA module.

Figure 4: Visualization of our trajectory forecasting results and comparison with FengWu. The five small plots visualize the ground truth (red solid line), our trajectory forecasting results (blue dashed line), and FengWu’s trajectory forecasting results (green solid line), with representative trajectories selected.

Tropical Cyclone Intensity Forecasting

See all 14 papers

Tianmu-TC: Physics-constraints Generative Artificial Intelligence for Global Tropical Cyclone Forecasting
Aug 19, 2026Shiqi Zhang, Pan Mu, Cheng Huang +6Tropical Cyclone Intensity Forecasting Weather Forecasting
College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou & 310023, China. · School of Control Science and Engineering, Shandong University, Jinan & 250061, China. · School of Computer Science and Engineering, Tianjin University of Technology, Tianjin & 300384, China. +1
CycloneMAE: A Scalable Multi-Task Learning Model for Global Tropical Cyclone Probabilistic Forecasting
Apr 14, 2026Renlong Hang, Zihao Xu, Jiuwei Zhao +3Tropical Cyclone Intensity Forecasting Weather Forecasting
School of Computer Science, School of Software, Nanjing University of Information Science and Technology, Nanjing, 210044, China. · School of Atmospheric Sciences, Nanjing University of Information Science and Technology, Nanjing, 210044, China. · Shanghai Typhoon Institute, China Meteorological Administration, Shanghai, 200030, China. +1
Tropical Cyclone Forecasting via Latent Rectified Flow using Satellite Imagery and Atmospheric Fields
Aug 8, 2026Meheru Zannat, Sk. Md. Masudul AhsanRectified Flow Tropical Cyclone Intensity Forecasting
Department of Computer Science and Engineering Khulna University of Engineering & Technology Khulna 9203, Bangladesh

Aug 19, 2026J/K move · Enter open · S save

Tianmu-TC: Physics-constraints Generative Artificial Intelligence for Global Tropical Cyclone Forecasting

Shiqi Zhang, Pan Mu, Cheng Huang, Hanting Yan+5

College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou & 310023, China. · School of Control Science and Engineering, Shandong University, Jinan & 250061, China. · School of Computer Science and Engineering, Tianjin University of Technology, Tianjin & 300384, China.+1

Tropical Cyclone Intensity Forecasting Weather Forecasting Physics-Informed Generative Modeling Spatiotemporal Forecasting Probabilistic Forecasting

Open paper AskPDF arXiv

Tropical cyclones (TCs) pose severe risks from strong winds and heavy rainfall. However, forecasting their track and intensity remains challenging due to chaotic atmosphere and the rapid amplification of initial condition errors, leading to growing forecast uncertainty. While numerical weather prediction (NWP) and deep learning models have made progress, they remain computationally demanding and often fail under complex meteorological scenarios. Here, we present Tianmu-TC, a physics-constraints generative framework for global TC forecasting. Trained on Western North Pacific data, Tianmu-TC leverages physics-constraints to generate controllable outputs with reduced uncertainty thus improving forecast reliability. Experiments show Tianmu-TC outperforms deterministic and ensemble meteorological artificial intelligence models and authoritative NWP systems such as ECMWF in global ocean basins, with significantly lower computational cost. We further show Tianmu-TC performs well in challenging scenarios such as data sparsity, anomaly tracks, rapid intensification and weakening. These findings suggest physics-constraints generative AI offers a promising approach for reliable, efficient global TC forecasting.

Abstract

Tropical Cyclone Intensity Forecasting

Explore similar work

Tianmu-TC: Physics-constraints Generative Artificial Intelligence for Global Tropical Cyclone Forecasting

CycloneMAE: A Scalable Multi-Task Learning Model for Global Tropical Cyclone Probabilistic Forecasting

Tropical Cyclone Forecasting via Latent Rectified Flow using Satellite Imagery and Atmospheric Fields