- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes SWECast for 7–14 day snow water equivalent forecasting. It combines Soft-DTW-based historical-season retrieval, cross-channel attention, frequency-domain periodicity modeling, weather gating, and FiLM-style prior modulation. Experiments on unseen SNOTEL stations show consistent improvements over the evaluated baselines, including a 13.1% MAE reduction at the 14-day horizon.
Critical strengths
The model is well motivated and combines historical SWE patterns with future meteorological information in a structured way. The station-wise evaluation and ablation studies also provide reasonably strong empirical support for the proposed components.
Critical weaknesses
The main practical concern is that future temperature and precipitation are taken from ERA5-Land over the forecast horizon, which does not reflect uncertainty in operational weather forecasts. Since future meteorology directly affects the proposed weather-gating mechanism, robustness to forecast errors should be evaluated. The paper itself acknowledges this limitation. 38743_SWECast_Enhancing_Snow_W
The methodological novelty is also somewhat limited, as the approach mainly combines existing components such as Soft-DTW, TimesNet-style periodicity modeling, attention, and FiLM. Moreover, recent SWE-specific methods discussed in the related work are not included in the main comparison.
Questions for authors
Are the future Tm and TP inputs realized ERA5-Land values? If so, how does performance change under realistic meteorological forecast errors? Were the input-variable and history-length choices made exclusively using the validation set? Could the authors compare against recent SWE-specific models such as GEMS or ForeSWE, or explain why such comparisons are infeasible?
3 comments
Response to Reviewer Lnbd (2/3)
W2. Methodological contributions of SWECast
“…methodological novelty is also somewhat limited, as the approach mainly combines existing components…”
Response:
SWECast addresses two practical challenges in SWE forecasting: generalization to stations excluded from training and abrupt weather changes during the forecast horizon. The central contribution is a forecasting architecture that uses historical patterns at the forecast station to modulate how a shared model processes current observations and future meteorological information.
1. Historical priors for generalization to unseen stations.
We observed recurring patterns in SWE time series across complete snow seasons at the same station. This suggests that past snow seasons can serve as a reference for forecasting SWE in the current season. We therefore construct a historical prior from the forecast station’s own records to guide the shared model’s predictions at stations excluded from training.
A useful prior requires a historical reference that matches the current conditions despite differences in seasonal timing. For example, a warm spring may cause snowmelt to begin earlier and progress faster than in a cooler year. SWECast therefore searches the preceding snow season for segments with similar SWE and meteorological patterns. Soft-DTW accommodates local differences in their timing and pace during matching. We then extract the matched segment and subsequent historical observations to construct the prior.
The resulting prior guides the forecast through FiLM modulation. Feature-wise scaling and shifting allow the prior to recalibrate the representations learned from current observations and future weather inputs. SWECast generates these modulation parameters for each prediction, enabling the shared network to adapt its forecasts to local SWE patterns.
2. Future meteorological information for responding to weather changes.
Historical SWE patterns alone may not anticipate rapid accumulation or melt caused by weather changes during the forecast period. We therefore include future temperature and precipitation to account for these changes. Cross-Channel Attention models the relation between SWE and meteorological variables. Within each Adaptive Periodicity Block, the weather gate adjusts feature channels according to meteorological conditions. These operations allow the forecast representations to respond to predicted weather changes.
We also conducted an additional comparison under three settings: ERA5-Land future inputs, archived GFS future inputs, and no future weather inputs. All three settings used identical test stations, dates, and forecast windows. The results show that future meteorological inputs improve forecasting performance for most models, even with imperfect weather forecasts. SWECast achieves the best MAE, RMSE, and NSE in each setting in this comparison, supporting the effectiveness of its architecture across different meteorological input conditions. We have provided the complete comparison in Appendix C.5, Table 11, reproduced below.
Table 11. Effects of removing future weather inputs. ↓: lower is better; ↑: higher is better. Bold: improvement over the same model’s w/o setting. w/o: no future weather inputs.
| Model | MAE (mm) ↓ | RMSE (mm) ↓ | NSE ↑ | ||||||
|---|---|---|---|---|---|---|---|---|---|
| ERA5-Land | GFS | w/o | ERA5-Land | GFS | w/o | ERA5-Land | GFS | w/o | |
| Random Forest | 18.58 | 20.06 | 24.94 | 32.77 | 32.80 | 41.23 | 0.924 | 0.917 | 0.885 |
| XGBoost | 17.14 | 19.54 | 24.79 | 28.86 | 29.86 | 40.63 | 0.943 | 0.933 | 0.890 |
| DLinear | 53.45 | 62.99 | 49.13 | 74.78 | 81.04 | 76.22 | 0.603 | 0.434 | 0.586 |
| PatchTST | 35.87 | 37.10 | 33.72 | 53.70 | 51.41 | 50.43 | 0.794 | 0.779 | 0.818 |
| iTransformer | 19.71 | 26.67 | 27.01 | 31.97 | 40.61 | 43.48 | 0.920 | 0.862 | 0.862 |
| TimesNet | 19.09 | 26.35 | 30.04 | 30.54 | 38.47 | 45.18 | 0.929 | 0.877 | 0.854 |
| ForeSWE | 25.48 | 29.86 | 28.40 | 39.94 | 42.65 | 44.98 | 0.877 | 0.845 | 0.856 |
| SWECast | 14.46 | 19.15 | 23.06 | 23.83 | 29.23 | 38.28 | 0.958 | 0.934 | 0.904 |
3. Experimental support for the design choices.
The component ablations support the roles of historical matching, cross-channel attention, periodicity modeling, and prior modulation in the full model (Table 2). For example, MAE increases from 14.46 to 21.93 mm when we remove the Prior Modulation Layer. This result supports the use of historical priors to recalibrate forecast representations. SWECast also achieves the best results against general forecasting models and ForeSWE in Table 1, reproduced in our response to W3 & Q3.
We have revised Figure 1 to clarify how the forecasting challenges motivate our design. We have simplified Figure 2 to make the inputs, outputs, and connections between modules clearer.
Response to Reviewer Lnbd (3/3)
W3 & Q3. Comparison with data-driven SWE forecasting models
“…compare against recent SWE-specific models such as GEMS or ForeSWE, or explain why such comparisons are infeasible?”
Response:
Our original comparison included a broad set of machine-learning and time-series baselines, together with SNOW-17. The consistent gains across these approaches provide strong evidence of SWECast’s forecasting accuracy and its ability to generalize to stations excluded from training.
Your suggestion prompted us to examine GEMS and ForeSWE as additional SWE-specific data-driven forecasting approaches. We found that GEMS used SNOTEL station observations for pretraining (Umirbekov et al., 2024). We therefore did not include its pretrained model to avoid potential data leakage.
We have conducted additional experiments with ForeSWE (Thapa et al., 2026) and updated Table 1 in the main text with the results. We have documented its implementation alongside those of the other baselines in Appendix B.2. We also present the updated table below for your convenience.
Table 1. SWE forecasting with 60 days of current-season observations. Three runs; MAE/RMSE: mean ± SD (mm); NSE: mean. ↓: lower is better; ↑: higher is better. Bold: best; ☆: second-best.
| Model | 7d MAE ↓ | 7d RMSE ↓ | 7d NSE ↑ | 14d MAE ↓ | 14d RMSE ↓ | 14d NSE ↑ |
|---|---|---|---|---|---|---|
| Random Forest | 11.88±0.16 | 19.69±0.51 | 0.968 | 18.87±0.25 | 32.57±0.32 | 0.922 |
| XGBoost | 10.97±0.27☆ | 17.68±0.71☆ | 0.975☆ | 17.06±0.40☆ | 28.31±0.53☆ | 0.942☆ |
| DLinear | 43.64±2.13 | 57.89±0.96 | 0.739 | 54.82±1.81 | 74.59±0.71 | 0.601 |
| PatchTST | 26.02±2.79 | 35.45±3.28 | 0.896 | 34.30±2.27 | 51.00±2.52 | 0.809 |
| iTransformer | 14.03±0.47 | 21.64±0.78 | 0.961 | 20.19±0.42 | 32.37±0.35 | 0.917 |
| TimesNet | 13.70±0.47 | 21.04±1.26 | 0.963 | 19.77±0.61 | 30.97±0.45 | 0.923 |
| ForeSWE | 17.82±2.03 | 26.65±2.11 | 0.941 | 24.86±3.30 | 39.06±4.16 | 0.874 |
| SNOW-17 | 75.38±1.26 | 105.32±2.45 | 0.377 | 76.38±2.44 | 109.38±3.10 | 0.308 |
| SNOW-17† | 58.74±1.97 | 81.75±4.13 | 0.632 | 60.40±1.44 | 84.20±2.09 | 0.568 |
| SWECast (Ours) | 10.10±0.27 | 16.10±0.76 | 0.978 | 14.82±0.37 | 24.20±1.04 | 0.954 |
† SNOW-17 calibrated using all available historical records at each station.
SWECast achieves the best results across all three metrics at both forecast horizons in the expanded comparison. Relative to ForeSWE, it reduces MAE by 43.3% at 7 days and 40.4% at 14 days. This additional comparison extends the evidence for SWECast’s accuracy advantage to a recent model developed specifically for SWE forecasting.
Reference: Umirbekov, A., Essery, R., and Müller, D. (2024). GEMS v1.0: Generalizable Empirical Model of Snow Accumulation and Melt, based on daily snow mass changes in response to climate and topographic drivers. Geoscientific Model Development, 17, 911–929. DOI: 10.5194/gmd-17-911-2024.
Q2. Selection of meteorological inputs and history lengths
“…Were the input-variable and history-length choices made exclusively using the validation set?”
Response:
We selected the meteorological inputs, current-season history length, and number of complete historical snow seasons exclusively based on validation MAE. The meteorological inputs were chosen from physically motivated candidate combinations. We then evaluated the configurations on the test set, as reported in Table 3 and Figure 4. We have clarified this procedure in Section 5.5 and added the corresponding validation results to Appendix C.2, Tables 6–8, reproduced below. These results support our choices of temperature and total precipitation, 60 steps of current-season history, and one complete historical snow season.
Table 6. Validation MAE for meteorological input selection using 60 days of current-season observations and a 14-day forecast horizon. The candidate configurations correspond to those in Table 3. MAE is in mm; ↓ indicates lower is better. Best results are in bold. Tm: temperature; TP: total precipitation.
| Input | Validation MAE ↓ (mm) |
|---|---|
| SWE only | 28.50 |
| SWE + Tm | 27.33 |
| SWE + TP | 21.24 |
| SWE + Tm + TP (Base) | 16.54 |
| Base + Snow | 16.75 |
| Base + Surface | 16.77 |
| Base + Atmospheric | 18.18 |
| Base + Vegetation | 16.94 |
Table 7. Validation MAE for current-season history lengths over 14 prediction steps. MAE in mm; ↓: lower is better; bold: best.
| Current-season history length (steps) | Validation MAE ↓ (mm) |
|---|---|
| 10 | 20.60 |
| 15 | 18.58 |
| 30 | 17.48 |
| 45 | 18.74 |
| 60 | 17.12 |
| 75 | 21.26 |
| 90 | 23.13 |
| 105 | 24.09 |
| 120 | 27.75 |
Table 8. Validation MAE for the number of complete historical snow seasons over 14 prediction steps. MAE in mm; ↓: lower is better; bold: best.
| Complete historical snow seasons | Validation MAE ↓ (mm) |
|---|---|
| 0 (w/o historical priors) | 28.38 |
| 1 | 16.96 |
| 2 | 17.03 |
| 3 | 17.18 |
| 4 | 17.22 |
| 5 | 17.48 |
Response to Reviewer Lnbd (1/3)
Dear Reviewer Lnbd,
Thank you for your careful review and constructive suggestions. We appreciate your recognition of SWECast’s motivation and the empirical support from the station-wise evaluation and ablation studies.
You raised concerns about meteorological forecast errors, methodological novelty, SWE-specific comparisons, and input and history-length selection. We have addressed them through experiments using archived weather forecasts, an expanded comparison with ForeSWE, and validation results documenting these choices. We have also clarified the design rationale and revised
Figures 1 and 2.W1 & Q1. Evaluation with operational weather forecasts
Response:
ERA5-Land provides meteorological data at 0.1° resolution throughout our 1993–2021 station record. The long record supports evaluation across diverse snow seasons, while the fine grid helps represent local meteorological conditions at the stations. These properties provide a suitable basis for comparing forecasting accuracy and generalization to unseen stations. We therefore used ERA5-Land reanalysis for all meteorological inputs in
Table 1, including future temperature and precipitation.Your suggestion allows us to test whether this accuracy advantage persists with imperfect weather forecasts. We therefore conducted additional experiments using archived operational forecasts from the Global Forecast System (GFS) as future meteorological inputs. GFS is run by NCEP within NOAA’s National Weather Service. The available archive begins in January 2015, with a 0.25° grid and forecasts up to 16 days ahead.
The experiments covered five snow seasons during 2016–2021. We used GFS future temperature and precipitation across training, validation, and testing and trained SWECast from scratch. We retained ERA5-Land for historical meteorological inputs. All models received identical future weather forecasts and used the same test stations, dates, and forecast windows. We have added the setup and results to
Appendix C.4, Table 9, reproduced below.Table 9. SWE forecasting with GFS future meteorological inputs and 60 days of current-season observations. MAE/RMSE: mean ± sample SD (mm) across three runs; NSE: mean. Bold: best; ☆: second-best. The same notation applies to
Table 10.The results show that SWECast achieves the lowest MAE and RMSE at both horizons with GFS inputs. Forecasting accuracy decreases relative to the ERA5-Land setting, consistent with the additional challenge of uncertain future meteorological inputs.
SWECast also outperforms most baselines using ERA5-Land inputs across all three metrics at both horizons, even with imperfect GFS forecasts as future inputs. Its RMSE is numerically lower than that of every ERA5-Land baseline at both horizons. We have compiled this descriptive comparison in
Appendix C.4, Table 10, reproduced below. These findings further support SWECast’s potential for practical SWE forecasting.Table 10. SWECast using GFS forecasts compared with baselines using ERA5-Land reanalysis.
† SNOW-17 calibrated using all available historical records at each station.