- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
Regional Trajectory Conditioning (RTC) uses global forecasts and regional history to first generate an hourly coarse trajectory for each ensemble member. It then generates fine-scale fields that preserve the trajectory’s block averages and uses overlapping denoising windows to extend the forecast horizon. Across four U.S. regions, RTC improves state CRPS, regional-mean trajectory Energy Score, and ensemble-mean errors for hourly 3 km forecasts.
Critical strengths
The method directly addresses how to coordinate predictions across temporal windows. The shared regional trajectory gives fine-scale generation a common condition, while the block-average constraint makes the relationship between the two scales explicit.
Critical weaknesses
-
The controls in Table 3 show benefits in temporal-change metrics, but they do not report state CRPS or regional-mean trajectory Energy Score on the main 2025 test set. This makes it hard to connect these improvements to the paper’s main performance gains, especially since the 2024 validation results show that local coarse conditioning can achieve lower state CRPS. All Table 3 variants also preserve block averages, so this comparison does not establish the constraint’s contribution. Reporting the main scores for these variants and a matched constraint ablation would help clarify what each design choice adds.
-
Fine-scale changes at window boundaries still need a closer look. RTC performs well on the broader detail-trajectory scores, but its boundary-change score is worse than several baselines, and adding overlap helps over 24 hours but not over 10 days. As Appendix A.1 explains, the selected 10-day boundary pairs also coincide with changes in the contributing outer contexts, so the current scores cannot separate these two effects. Comparing transitions where only one window schedule changes, alongside matched interior time pairs, would help identify where the remaining errors come from.
Questions for authors
Can the authors separately evaluate fine-window boundaries, outer-context boundaries, and matched interior times?
Field sequences or time series from individual members would help show where the problem occurs and which adjustments actually improve it. Overall, this paper requires further improvement regarding its presentation and experimental content.
5 comments
Response to Reviewer Y8R9 (W1, Q2)
W1. Main scores of the design variants, and the constraint
We scored the Table 3 variants on the main scores of the 2025 test set and added a variant without the constraint. Each design choice shows a distinct role.
All rows share RTC's mean model. The two coarse controls give every member the same coarse trajectory. Learned deterministic coarse is the control of the paper's Table 15, a coarse generator trained to output a single trajectory. Ensemble-mean coarse uses RTC's own trained models unchanged and gives every member the mean of the 16 coarse trajectories that RTC samples.
| Variant | state CRPS, 24 h | 3-h change CRPS, 24 h | trajectory ES, 24 h | state CRPS, 10 d | 3-h change CRPS, 10 d | trajectory ES, 10 d |
|---|---|---|---|---|---|---|
| Local coarse + fine overlap | 0.14547 | 0.16337 | 0.05062 | 0.32543 | 0.21708 | 0.31485 |
| Shared coarse + fine overlap | 0.14536 | 0.16296 | 0.04976 | 0.33056 | 0.21122 | 0.31289 |
| RTC | 0.14537 | 0.16309 | 0.04976 | 0.33029 | 0.21098 | 0.31289 |
| RTC without projection | 0.14555 | 0.16313 | 0.04956 | 0.33186 | 0.21150 | 0.31394 |
| Learned deterministic coarse | 0.16595 | 0.18312 | 0.06235 | 0.36855 | 0.23885 | 0.33043 |
| Ensemble-mean coarse | 0.16928 | 0.18747 | 0.06336 | 0.37155 | 0.24490 | 0.33240 |
| Full-path residual diffusion | 0.14753 | 0.16335 | 0.05619 | 0.34816 | 0.22525 | 0.33715 |
| Autoregressive 12-hour windows | 0.14787 | 0.16360 | 0.05754 | 0.32957 | 0.21419 | 0.32385 |
1. Shared against local coarse context (fine overlap fixed). The local variant has 1.6% lower 10-day state CRPS, in line with the 2024 result the reviewer cites, while the shared context is lower on the other five scores, with 2.7% lower 10-day change CRPS and 0.6% lower trajectory ES. Under the cross-fade the pattern holds and the gap at the boundary pairs widens. The shared context has 3.9% lower change CRPS, 1.0% lower trajectory ES and a full-field score at (12+24k, 13+24k) of 0.120 against 0.169, and the local one has 1.5% lower state CRPS.
2. The constraint. We added the matched ablation the reviewer asked for, RTC without the projection. Without the projection, block averages deviate from the sampled trajectory by up to 0.20 at 24 hours and 0.24 over 10 days, against numerical precision for RTC. The 24-hour scores differ by less than 0.5%, while the 10-day scores are 0.25–0.48% higher. The constraint therefore mainly makes U each member's actual regional trajectory, with a small 10-day score gain.
3. The stochastic coarse trajectory. RTC has lower scores than the learned deterministic coarse control on all three metrics at both horizons. The ensemble-mean control removes only the coarse spread and keeps RTC's trained models. The loss is as large (state CRPS +16.5% and +12.5%, trajectory ES +27.3% and +6.2%), so it comes from the missing coarse spread and not from the changed training objective.
4. No separate coarse-trajectory sampler (last two rows). Against these two variants RTC has 11.4% and 13.5% lower trajectory ES at 24 hours and 7.2% and 3.4% lower over 10 days. The autoregressive variant has 0.22% lower 10-day state CRPS, and RTC is lower on the other five scores.
Each choice therefore has a distinct role. The stochastic coarse trajectory lowers all three scores. Its separate generator lowers the trajectory ES against same-mean models. Sharing it over 24 hours lowers change and trajectory scores at a 1.5–1.6% cost in 10-day state CRPS. The constraint makes U the trajectory each member follows. The ensemble-mean control changes the coarse spread only, with the trained model unchanged.
Q2. Member-level figures
We added the two figures the reviewer asked for to the revised PDF, as Figures R1 and R2 in Appendix A.1 (marked in red). Figures cannot be shown in this comment, so we describe them and give their numbers here. The first shows all 16 members and the HRRR analysis at one grid point for hours 1–120. The second shows, for each pair of consecutive hours, the error of the members' one-hour block-average changes.
In the example case (2025-01-20, region 0), the mean absolute error of the one-hour T2m change over 16 sites and 16 members falls from 1.52 to 0.57 K at B12 and from 1.86 to 0.91 K at B00 with the cross-fade, and from 0.74 to 0.71 K at interior pairs. These are mean-member absolute errors of one case, not CRPS. They illustrate the table in our answer to W2 and Q1, which gives the scores over all test cases.
Over all test cases the same quantity falls from 1.82 to 0.68 K at B12 (lower in every case), from 1.47 to 0.78 K at B00 (lower in all cases but one), and from 0.66 to 0.63 K at interior pairs.
Response to Reviewer Y8R9 (W2, Q1)
W2 and Q1. Fine-window boundaries, outer-context changes and interior pairs
Over 10 days RTC has the lowest state CRPS and trajectory ES of all methods, and it has the lowest one-hour change scores at the 220 interior pairs. Changing the weights of overlapping contexts, without retraining, brings the full-field scores at the 19 boundary pairs to the level of the best baselines and makes RTC's 3-hour change CRPS the lowest as well. Shifting one window schedule separates the two effects, as the reviewer asked. The remaining detail elevation follows the fine-window boundary.
Main scores over 10 days:
| state CRPS | 3-h change CRPS | trajectory ES | |
|---|---|---|---|
| Vanilla diffusion | 0.3614 | 0.2321 | 0.3537 |
| CorrDiff | 0.3520 | 0.2124 | 0.3559 |
| STVD | 0.3849 | 0.2131 | 0.3935 |
| EnScale | 0.3636 | 0.2107 | 0.3431 |
| StormCast | 0.5131 | 0.2233 | 0.4809 |
| RTC | 0.3303 | 0.2110 | 0.3129 |
| RTC + cross-fade | 0.3263 | 0.2000 | 0.3097 |
One-hour change CRPS over 10 days by pair class, for the full field and for the within-block detail. Both B12 and B00 contain a fine-window boundary and a change of outer contexts.
| Full-field interior | Full-field B12 | Full-field B00 | Detail interior | Detail B12 | Detail B00 | |
|---|---|---|---|---|---|---|
| Vanilla diffusion | 0.1374 | 0.2113 | 0.2471 | 0.0670 | 0.0715 | 0.0822 |
| CorrDiff | 0.1414 | 0.1414 | 0.1600 | 0.0747 | 0.0744 | 0.0829 |
| STVD | 0.1263 | 0.1305 | 0.1533 | 0.0690 | 0.0691 | 0.0803 |
| EnScale | 0.1268 | 0.1220 | 0.1465 | 0.0699 | 0.0687 | 0.0798 |
| StormCast | 0.1282 | 0.1224 | 0.1490 | 0.0695 | 0.0679 | 0.0799 |
| RTC | 0.1225 | 0.1948 | 0.2042 | 0.0664 | 0.0789 | 0.0861 |
| RTC + cross-fade | 0.1206 | 0.1234 | 0.1442 | 0.0662 | 0.0748 | 0.0829 |
1. Fine-window boundary alone, at 24 hours. The pair (12, 13) crosses a fine-window boundary with no change of outer contexts. Its detail score is 0.0734, and 0.0684 with fine overlap.
2. Context weights. Over 10 days RTC averages overlapping 24-hour contexts with uniform weights. Changing only these weights, with the same checkpoints, lowers the block-average change CRPS at B12 from 0.177 to 0.095.
3. Cross-fade. With the fixed weight w(τ) = sin²(π(τ+0.5)/24), applied without any tuning, the full-field B12 and B00 fall by 37% and 29%, and the 10-day state CRPS, 3-hour change CRPS and trajectory ES by 1.2%, 5.2% and 1.0%. State CRPS at the 6-hour lead times rises by only 0.15% (0.14% in 2024). On 2024 validation data, the three scores fall by 1.6%, 4.6% and 1.4%, and the full-field one-hour change CRPS at (12+24k, 13+24k) falls by 34% (0.186 to 0.123).
4. Fine overlap and detail weighting over 10 days. Fine overlap alone does not lower the detail B12 over 10 days (0.0789 to 0.0810 with uniform weights, 0.0748 to 0.0760 with the cross-fade on the mean path and the coarse generator), but with the cross-fade also on the detail branch it falls to 0.0706, inside the baselines' range (0.068–0.074). This costs 0.09% in state CRPS and 2.3% in detail-state CRPS.
5. Transitions where only one window schedule changes (Q1). We moved the fine windows by 6 hours. Their boundaries then fall at lead times 6+12k, and the changes of outer contexts stay at 12k, so each kind of pair contains one transition only. Every pair is compared with the same pair, at the same lead time, in the default schedule. RTC + cross-fade, one-hour change CRPS, lead times 25–216:
| Pairs at 12k | Pairs at 6+12k | Other pairs | |
|---|---|---|---|
| Detail, default schedule | 0.07840 | 0.06223 | 0.06668 |
| Detail, fine windows shifted by 6 hours | 0.07044 | 0.07077 | 0.06673 |
| Full field, default schedule | 0.13294 | 0.11377 | 0.12076 |
| Full field, fine windows shifted by 6 hours | 0.12865 | 0.11866 | 0.12082 |
In the default schedule both transitions fall on the 12k pairs. After the shift the 12k pairs keep only the change of outer contexts, and the 6+12k pairs hold the fine-window boundary. The detail score falls by 10.2% where the fine-window boundary was and rises by 13.7% where it now is, so the remaining detail elevation follows the fine-window boundary.
The full-field score changes by −3.2% and +4.3%. With uniform weights the full-field score at the 12k pairs does not change (+0.05%), so the full-field elevation of the paper's setting belongs to the change of outer contexts.
The shift leaves the main scores unchanged (state CRPS −0.01%, 3-hour change CRPS +0.01%), so the default alignment of the two schedules costs no accuracy.
The full-field boundary scores thus reach the range of the best baselines, and away from the boundary pairs RTC has the lowest full-field and detail scores in the table.
Response to Reviewer Y8R9 (P1)
We thank the reviewer for the careful review and for recognizing that the shared regional trajectory gives fine-scale generation a common condition with an explicit link between the two scales (S1). We first restate what RTC does and contributes, and then answer the two weaknesses. Each design choice has a distinct role, including the constraint. Reweighting the overlapping contexts, without retraining, brings the full-field boundary scores to the level of the best baselines, and shifting one window schedule shows that the remaining detail elevation follows the fine-window boundary.
Setup. The new results use the paper's 2025 test cases and scores, with 16 members. Lower is better, percentages are relative differences on the same cases, and trajectory ES denotes the regional-mean trajectory Energy Score. Detail is a field minus its 8×8 block average. B12 denotes the pairs of consecutive hours (12+24k, 13+24k), B00 the pairs (24k, 24k+1), and interior all other pairs. The cross-fade lets each of the overlapping 24-hour contexts of a 10-day forecast fade in and out with the weight w(τ) = sin²(π(τ+0.5)/24) instead of counting equally, with the trained models unchanged.
P1. Presentation
We restate here, as directly as we can, what RTC does and what the paper contributes. We will revise the paper so that these points are as easy to follow there.