- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The authors propose NowcastDiT, a latent Diffusion Transformer model for precipitation nowcasting. The model is largely based on a standard DiT, with the goal of using a general architecture rather than one specifically designed for precipitation nowcasting. The two components added to the standard DiT are DyPro, which aims to improve temporal coherence through a prior with temporally correlated noise, and timestep-aware GRPO post-training, which shifts the reward emphasis from coarse structure to fine details along the denoising trajectory. Results on SEVIR and MRMS show strong performance compared with the included deterministic and generative baselines across skill and perceptual metrics.
Critical strengths
- Clear and well-motivated paper. The paper is well written and easy to follow. Having a general architecture work well for precipitation nowcasting, rather than relying on a heavily specialized one, is a strong motivation. This direction has been successful in the past (i.e. ConvLSTM, Earthformer, SimVP…).
- Strong results and informative ablations. NowcastDiT achieves strong results across skill and perceptual metrics. Table 6 shows that the standard DiT is already a strong baseline, that 3D RoPE and QK-Norm improve it further, and that both proposed components (DyPro and RL) provide additional gains.
Critical weaknesses
- Novelty and related work. I find the novelty and the standard DiT argument somewhat weak. Applying a standard DiT to precipitation nowcasting is useful but is mainly an application of an existing architecture. The use of general architectures for precipitation nowcasting is also well established (e.g., ConvLSTM, Earthformer, SimVP). Similarly, latent diffusion has already been explored (PreDiff, LDCast, FREUD), and flow matching has also been explored (FlowCast - ICLR 2026). Importantly, several of these closely related works, including FlowCast, LDCast and FREUD, are not discussed. Finally, the best performing NowcastDiT is not just a standard DiT, but relies on DyPro and precipitation-specific RL rewards. I therefore think that the claims around architectural simplicity should be reduced and the paper should focus more on its actual contributions.
- Contributions and experiments. Beyond applying DiT to precipitation nowcasting, the main contributions are DyPro for temporal coherence and RL post-training for improving forecast quality. The ablations show that both components help, but they are only compared against the authors’ own baseline, rather than alternative approaches for temporal coherence or post-training discussed in the related work. The evaluation also misses important recent methods, including FlowCast, LDCast, PercpCast, FREUD, and DuoCast. Finally, the evaluation of a probabilistic model would benefit from metrics such as CRPS, calibration, and ensemble diversity.
Questions for authors
- How does NowcastDiT compare with recent and closely related methods such as FlowCast, LDCast, PercpCast, FREUD and DuoCast?
- How do DyPro and RL compare with alternative approaches for temporal coherence and post-training?
- Can the authors report probabilistic metrics such as CRPS, calibration, and ensemble diversity?
- How does NowcastDiT compare with the baselines in terms of model size and training / inference costs, given the scaling results in Figure 5a?
4 comments
Response to Reviewer 5zhC (Part II)
[W2.1.1, Q2.1] Alternative temporal-coherence methods
To supplement comparison with fixed-correlation noise, we conduct experiments on schedules of Progressive and Mixed noise from PYoCo [10], and Dynamical Diffusion [11]. Our DyPro achieves the highest CSI, HSS, and SSIM scores and the second-lowest LPIPS, demonstrating strong overall forecasting performance.
| Noise construction | CSI ↑ | CSI-181 ↑ | CSI-219 ↑ | HSS ↑ | LPIPS ↓ | SSIM ↑ |
|---|---|---|---|---|---|---|
| IID Gaussian | 0.3012 | 0.1082 | 0.0676 | 0.3647 | 0.1317 | 0.6812 |
| Progressive Noise | 0.3041 | 0.1089 | 0.0612 | 0.3914 | 0.1539 | 0.6930 |
| Mixed Noise | 0.3122 | 0.1173 | 0.0679 | 0.4009 | 0.1512 | 0.7052 |
| Dynamical Diffusion | 0.3148 | 0.1147 | 0.0690 | 0.4033 | 0.1503 | 0.7046 |
| DyPro (ours) | 0.3195 | 0.1204 | 0.0752 | 0.4092 | 0.1486 | 0.7099 |
[W2.1.2, Q2.2] Alternative post-training methods
We acknowledge the concerns on alternative post-training methods. Notably, for post-training, established alternatives for diffusion-based precipitation nowcasting remain limited. To broaden this comparison, we consider general post-training methods [12-14] in diffusion models. As shown in the table below, post-training of NowcastDiT achieves the best CSI, HSS, SSIM and the second-lowest LPIPS, demonstrating strong overall forecasting performance.
| Post-training method | CSI ↑ | HSS ↑ | SSIM ↑ | LPIPS ↓ |
|---|---|---|---|---|
| w/o post-training | 0.3195 | 0.4092 | 0.7099 | 0.1486 |
| FlowGRPO | 0.3202 | 0.4120 | 0.7102 | 0.1505 |
| DanceGRPO | 0.3212 | 0.4116 | 0.7141 | 0.1495 |
| MixGRPO | 0.3218 | 0.4125 | 0.7146 | 0.1473 |
| NowcastDiT | 0.3254 | 0.4160 | 0.7194 | 0.1479 |
[Q3] Scope of probabilistic evaluation
We acknowledge the omission of ensemble metrics. Our evaluation protocol directly follows that established in [4], which focuses on deterministic forecast quality and does not include these metrics. To extend this evaluation, we report ensemble CRPS, ensemble-mean RMSE, and spread for all three configurations on SEVIR. These metrics are computed using four ensemble members, with predictions and observations normalized to [0,1]. Following [9], we disable classifier-free guidance (CFG) when evaluating probabilistic forecast quality.
| Configuration | CSI ↑ | CRPS ↓ | RMSE ↓ | Spread |
|---|---|---|---|---|
| DiT | 0.2706 | 0.02372 | 0.06723 | 0.05362 |
| DiT + DyPro | 0.2934 | 0.02154 | 0.06114 | 0.04114 |
| DiT + DyPro + RL | 0.3109 | 0.02214 | 0.06256 | 0.03855 |
To examine calibration, we compare rank-histogram frequencies for all three configurations. The uniform reference is 20% per bin.
| Configuration | Rank 0 | Rank 1 | Rank 2 | Rank 3 | Rank 4 |
|---|---|---|---|---|---|
| DiT | 34.55% | 18.49% | 14.42% | 14.04% | 18.50% |
| DiT + DyPro | 31.57% | 18.98% | 14.72% | 14.38% | 20.36% |
| DiT + DyPro + RL | 40.16% | 15.46% | 11.84% | 12.16% | 20.38% |
The results highlight two findings:
- DyPro improves CSI, CRPS, and RMSE and produces a more balanced rank distribution, showing that its noise-prior design benefits multiple aspects of forecast quality.
- RL substantially improves individual-forecast skill with a trade-off in ensemble metrics. This is consistent with its focus on per-forecast meteorological and perceptual rewards. These results suggest using DiT with DyPro when prioritizing ensemble forecast quality, and the post-trained model when prioritizing individual-forecast skill.
Response to Reviewer 5zhC (Part III)
[Q4] Model size and computational costs
To contextualize the scaling results in Figure 5a, we report model sizes, training costs, and inference throughput below. Detailed measurement protocols and configurations are provided in the appendix.
| Method | Params (M) | Training cost (GPU-h) ↓ | Throughput (seq/s) ↑ | NFE/sequence ↓ | CSI ↑ |
|---|---|---|---|---|---|
| SimVP | 11.06 | 260.39 | 42.80 | — | 0.2951 |
| AlphaPre | 89.03 | 467.13 | 20.82 | — | 0.2980 |
| DiffCast | 49.36 | 212.52 | 0.39 | 1000 | 0.2977 |
| CasCast | 81.71 + 349.36 | 525.16 | 2.99 | 20 | 0.2905 |
| NowcastDiT-S | 81.71 + 32.72 | 150.90 | 5.50 | 20 | 0.3119 |
| NowcastDiT-B | 81.71 + 130.32 | 228.73 | 3.41 | 20 | 0.3195 |
NowcastDiT-S outperforms all listed baselines in CSI while requiring the lowest measured training cost, and achieves higher inference throughput than DiffCast and CasCast. Scaling to NowcastDiT-B further improves CSI at increased computational cost. Deterministic models offer higher inference throughput, while NowcastDiT delivers stronger forecast skill.
References
[1] William Peebles and Saining Xie. Scalable Diffusion Models with Transformers. ICCV, 2023.
[2] Zhihan Gao et al. Earthformer: Exploring Space-Time Transformers for Earth System Forecasting. NeurIPS, 2022.
[3] Kenghong Lin et al. AlphaPre: Amplitude-Phase Disentanglement Model for Precipitation Nowcasting. CVPR, 2025.
[4] Demin Yu et al. DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting. CVPR, 2024.
[5] Jussi Leinonen et al. Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantification. arXiv:2304.12891, 2023.
[6] Wenzhi Feng et al. Perceptually Constrained Precipitation Nowcasting Model. ICML, 2025.
[7] Bernardo Perrone Ribeiro and Jana Faganeli Pucer. FlowCast: Advancing Precipitation Nowcasting with Conditional Flow Matching. ICLR, 2026.
[8] Penghui Wen et al. DuoCast: Duo-Probabilistic Diffusion for Precipitation Nowcasting. AAAI, 2026.
[9] Johannes Schusterbauer et al. Probabilistic Precipitation Nowcasting with Rectified Flow Transformers. CVPR, 2026.
[10] Songwei Ge et al. Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models. ICCV, 2023.
[11] Xingzhuo Guo et al. Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models. ICLR, 2025.
[12] Jie Liu et al. Flow-GRPO: Training Flow Matching Models via Online RL. NeurIPS, 2025.
[13] Zeyue Xue et al. DanceGRPO: Unleashing GRPO on Visual Generation. arXiv:2505.07818, 2025.
[14] Junzhe Li et al. MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE. ECCV, 2026.
Request of Reviewer's Attention and Feedback
Dear Reviewer,
This is a kind reminder that three days remain in the discussion period. We would appreciate your feedback on whether our response has addressed your concerns.
Following your suggestions, we have:
- Clarified the contribution of exploring standard DiT foundation for nowcasting .
- Added comparisons with LDCast, PercpCast, FlowCast, DuoCast, and FREUD.
- Reduced repetitive claims about architectural simplicity.
- Compared alternative noise priors and post-training methods.
- Added ensemble metrics and calibration diagnostics.
- Reported model sizes and training/inference costs.
Thanks again for your valuable review. We look forward to your feedback and are happy to clarify any remaining points.
Response to Reviewer 5zhC (Part I)
We sincerely thank Reviewer 5zhC for the insightful review and constructive comments. Below, we address your concerns in detail.
[W1.1, W1.2] Contribution of the standard DiT foundation
We acknowledge that applying a standard DiT [1] is architecturally straightforward. Yet we believe our contribution also lies in systematically validating its effectiveness as a general-purpose foundation for precipitation nowcasting.
Taken together, these findings establish a standard DiT as an effective foundation for precipitation nowcasting, enabling subsequent research to build on advances in general-purpose generative modeling.
[W1.3, W2.2, Q1] Additional Baseline Comparisons
We acknowledge the omission of these baselines from the main comparison. LDCast, PercpCast, FlowCast, and DuoCast follow the evaluation protocol established by AlphaPre [3], whose test split differs from the DiffCast [4] protocol used in our main experiments. For a fair comparison, we re-evaluate NowcastDiT under the same protocol.
FREUD [9] uses a different temporal configuration, predicting 12 frames from 13 input frames, together with a higher spatial resolution of 384×384. We therefore separately retrain NowcastDiT under the same 13-to-12 configuration and evaluate both methods at 128×128 for a fair comparison.
Across both evaluation settings, NowcastDiT outperforms all compared methods on reported metric, demonstrating consistent advantages in meteorological skill, perceptual quality, and probabilistic forecast quality.
[W1.4] Reducing overclaims of “simplicity”
We acknowledge the reviewer’s concern about the overemphasis on architectural simplicity. We thank the reviewer for this suggestion and have removed repetitive references to “standard” and “simple,” retaining them only where appropriate.