ForeSay: Tell the Future in Words, Branch the Details in Noise for Precipitation Nowcasting
Organizations: University of Electronic Science and Technology of China · Yibin University · Chengdu Textile College
Abstract
Precipitation nowcasting involves two distinct scales of uncertainty: macroscopic storm evolution and fine-scale local convective variations. Current generative ensemble methods entangle both scales within independent random noise draws. This coupling causes two practical limitations: every ensemble member must execute the full sampling trajectory from scratch, so an N-member ensemble costs N times a single forecast; moreover, divergent trajectories spatially misalign heavy-rain echoes across members, causing standard pixel-wise averaging to blur critical high-intensity extremes. We present ForeSay, a generative nowcasting framework that decouples macroscopic evolution prediction from local stochastic detail generation. Given historical radar frames, a vision-language model first predicts a textual scenario of future storm dynamics to condition a Rectified Flow generator. Guided by this shared macroscopic prior, ensemble members share early trunk sampling steps to establish the storm trajectory and branch with fresh noise only in later steps to explore local convective details. Because members then differ mainly in local details, self-anchored support-consensus decoding replaces pixel averaging with discrete support voting to preserve sharp heavy-rain cores. Across six datasets, ForeSay achieves the best CSI at the highest precipitation thresholds, with relative improvements over the strongest baseline on each dataset ranging from over 10% to 84%. Our 8-member ensemble retains the forecasting skill and diversity of eight independently sampled runs while reducing computational cost from 8x to 5.2x that of a single forecast.
Figures & tables
| SEVIR ( ) | MeteoNet ( ) | Shanghai ( ) | CIKM ( ) | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CSI | HSS | SSIM | LPIPS | CSI | HSS | SSIM | LPIPS | CSI | HSS | SSIM | LPIPS | CSI | HSS | SSIM | LPIPS | |||||||||
| Method | 160 | 181 | 219 | 18 | 24 | 32 | 30 | 35 | 40 | 30 | 35 | 40 | ||||||||||||
| MIMO-VP [ 29 ] | .1492 | .1102 | .0280 | .3792 | .6822 | .3576 | .3838 | .2469 | .0505 | .4016 | .8212 | .2732 | .3722 | .2586 | .1171 | .4332 | .7886 | .2532 | .1933 | .1351 | .0752 | .3198 | .6624 | .3853 |
| SwinLSTM [ 41 ] | .1585 | .1188 | .0373 | .3892 | .6775 | .3309 | .4558 | .3631 | .1762 | .5129 | .8203 | .2404 | .4409 | .3460 | .2141 | .5212 | .7708 | .2831 | .2990 | .2002 | .0799 | .3885 | .6058 | .3485 |
| DiffCast [ 49 ] | .1740 | .1435 | .0750 | .4017 | .6536 | .1983 | .4427 | .3496 | .1767 | .5004 | .8148 | .2364 | .4072 | .3254 | .2286 | .4986 | .7648 | .1658 | .2792 | .2161 | .1261 | .4002 | .6676 | .3091 |
| AlphaPre [ 20 ] | .1754 | .1332 | .0535 | .4100 | .6818 | .3520 | .4315 | .3461 | .1807 | .4936 | .8065 | .2336 | .4514 | .3591 | .2287 | .5267 | .7463 | .3195 | .2604 | .1810 | .1070 | .3674 | .6359 | .2936 |
| Swedish | MRMS | |||||||
|---|---|---|---|---|---|---|---|---|
| Method | CSI | CSI | SSIM | LPIPS | CSI | CSI | SSIM | LPIPS |
| PySteps [ 31 ] | 0.473 | 0.049 | 0.589 | 0.284 | 0.338 | 0.024 | 0.871 | 0.187 |
| DGMR [ 33 ] | 0.433 | 0.039 | 0.702 | 0.204 | 0.367 | 0.022 | 0.883 | 0.137 |
| DiffCast [ 49 ] | 0.439 | 0.029 | 0.660 | 0.292 | 0.328 | 0.018 | 0.869 | 0.183 |
| SSLDM-ISI [ 21 ] | 0.558 | 0.040 | 0.718 | 0.191 | 0.416 | 0.024 | 0.897 | 0.120 |
| AlphaPre [ 20 ] | 0.541 | 0.025 | 0.647 | 0.333 | 0.360 | 0.024 | 0.891 | 0.197 |
| w/o branching ( ) | w/ branching ( ) | ||||
|---|---|---|---|---|---|
| Condition | CSI | CSI | SSIM | FSS | CSI |
| Radar only | 0.578 | 0.0895 | 0.736 | 0.910 | 0.1273 |
| + history text | 0.584 | 0.0949 | 0.743 | 0.914 | 0.1275 |
| + future text | 0.593 | 0.0984 | 0.747 | 0.915 | 0.1357 |
| Motion direction | Intensity and structure | ||||||
|---|---|---|---|---|---|---|---|
| Main | L/R | U/D | 8-way | Intens. | Decay | Split | Merge |
| 95.1 | 90.9 | 90.8 | 84.2 | 76.7 | 73.6 | 75.4 | 90.8 |
| CSI , highest tier | (%), other metrics | |||||||
|---|---|---|---|---|---|---|---|---|
| Dataset | Base. | Anchor | Ours | (%) | CSI 2nd | SSIM | LPIPS | CRPS |
| Swedish | .074 | .0984 | .1357 | +37.9 | 0.0 | 0.0 | +0.1 | 6.8 |
| MRMS | .031 | .0278 | .0360 | +29.5 | 0.0 | 0.0 | 0.2 | 0.3 |
| SEVIR | .1199 | .1202 | .1458 | +21.3 | +4.1 | +0.6 | +0.6 | +1.9 |
| MeteoNet | .2679 | .2747 | .2971 | +8.2 | +0.3 | +0.2 | +0.1 | +0.5 |
| Shanghai | .3032 | .3217 | .3387 | +5.3 | +0.4 | 0.0 | +0.1 | 0.1 |
| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | |
|---|---|---|---|---|---|---|---|---|
| CSI | .1760 | .1740 | .1518 | .1266 | .1036 | .0821 | .0608 | .0420 |
| FB | 1.92 | 1.05 | 0.70 | 0.50 | 0.37 | 0.27 | 0.19 | 0.12 |
| 1 | 2 | 4 | 6 | 8 | 16 | |||
| CSI | .1239 | .0893 | .1399 | .1649 | .1740 | .1867 | ||
| FB | 0.66 | 0.33 | 0.65 | 0.88 | 1.05 | 1.53 |
Appendix figures & tables24 assets
Supplementary material from the paper’s appendix.
Appendix
| Setting | Steps | Cost | CSI (all 16 frames) (of ) | CSI ( – ) (of ) | Member IoU ( ) |
|---|---|---|---|---|---|
| , | ( ) | ( ) | |||
| , | ( ) | ( ) | |||
| , (default) | ( ) | ( ) | |||
| , | ( ) | ( ) | |||
| , | ( ) | ( ) | |||
| , | ( ) | ( ) |
| CSI (all 16 frames) | CSI ( – ) | FB (closer to is better) | |
|---|---|---|---|
| Cost | CSI ( – ) | CSI ( – ) | CSI (all 16 frames) | FB (closer to is better) | |
|---|---|---|---|---|---|
| (anchor, no vote) | |||||
| Dataset | Evaluation split | Samples | Condition frames forecast frames | Intensity thresholds |
|---|---|---|---|---|
| SEVIR (VIL) | official test | |||
| MeteoNet | test | |||
| Shanghai | official test | |||
| CIKM | test |
| SEVIR ( ) | MeteoNet ( ) | Shanghai ( ) | CIKM ( ) | |||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Method | CSI-M | CSI-16 | CSI-74 | CSI-133 | CSI-160 | CSI-181 | CSI-219 | CSI-M | CSI-12 | CSI-18 | CSI-24 | CSI-32 | CSI-M | CSI-20 | CSI-30 | CSI-35 | CSI-40 | CSI-M | CSI-20 | CSI-30 | CSI-35 | CSI-40 |
| MIMO-VP [ 29 ] | 0.2931 | 0.6643 | 0.5562 | 0.2509 | 0.1492 | 0.1102 | 0.0280 | 0.2878 | 0.4701 | 0.3838 | 0.2469 | 0.0505 | 0.3108 | 0.4954 | 0.3722 | 0.2586 | 0.1171 | 0.2492 | 0.5932 | 0.1933 | 0.1351 | 0.0752 |
| SwinLSTM [ 41 ] | 0.3110 | 0.6761 | 0.6015 | 0.2738 | 0.1585 | 0.1188 | 0.0373 | 0.3778 | 0.5161 | 0.4558 | 0.3631 | 0.1762 | 0.3839 | 0.5347 | 0.4409 | 0.3460 | 0.2141 | 0.3002 | 0.6217 | 0.2990 | 0.2002 | 0.0799 |
| DiffCast [ 49 ] | 0.3083 | 0.6586 | 0.5410 | 0.2578 | 0.1740 | 0.1435 | 0.0750 | 0.3693 | 0.5084 | 0.4427 | 0.3496 | 0.1767 | 0.3655 | 0.5010 | 0.4072 | 0.3254 | 0.2286 | 0.3067 | 0.6053 | 0.2792 | 0.2161 | 0.1261 |
| AlphaPre [ 20 ] | 0.3249 | 0.6984 | 0.6007 | 0.2883 | 0.1754 | 0.1332 | 0.0535 | 0.3627 | 0.4926 | 0.4315 | 0.3461 | 0.1807 | 0.3972 | 0.5497 | 0.4514 | 0.3591 | 0.2287 | 0.2853 | 0.5928 | 0.2604 | 0.1810 | 0.1070 |
| PercpCast [ 8 ] | 0.3492 | 0.6856 | 0.5844 | 0.3101 | 0.2203 | 0.1929 | 0.1022 | 0.4039 | 0.5279 | 0.4737 | 0.3933 | 0.2207 | 0.3995 | 0.5316 | 0.4459 | 0.3628 | 0.2577 | 0.3163 | 0.6108 | 0.2766 | 0.2223 | 0.1553 |
| Metric | Protocol | SEVIR | MeteoNet | Shanghai | CIKM |
|---|---|---|---|---|---|
| CSI-M | |||||
| HSS | |||||
| SSIM | |||||
| Swedish | MRMS | |
|---|---|---|
| CSI , highest | ( ) | ( ) |
| CSI , weak | ( ) | ( ) |
| FSS | ||
| SSIM | ||
| CRPS | ||
| LPIPS |
| SEVIR ( ) | MeteoNet ( ) | Shanghai ( ) | CIKM ( ) | |
| CSI by intensity level, highest to lowest ( protocol) | ||||
| Highest | (219) | (32) | (40) | (40) |
| 2nd highest | (181) | (24) | (35) | (35) |
| 3rd | (160) | (18) | (30) | (30) |
| 4th | (133) | (12) | (20) | (20) |
| 5th | (74) | — | — | — |
| Method | CSI | CSI | FSS | CRPS | SSIM | LPIPS |
|---|---|---|---|---|---|---|
| PySteps [ 31 ] | 0.473 | 0.049 | 0.872 | 0.144 | 0.589 | 0.284 |
| DGMR [ 33 ] | 0.433 | 0.039 | 0.882 | 0.143 | 0.702 | 0.204 |
| DiffCast [ 49 ] | 0.439 | 0.029 | 0.903 | 0.149 | 0.660 | 0.292 |
| SSLDM-ISI [ 21 ] | 0.558 | 0.040 | 0.906 | 0.122 | 0.718 | 0.191 |
| AlphaPre [ 20 ] | 0.541 | 0.025 | 0.894 | 0.149 | 0.647 | 0.333 |
| DTCA [ 16 ] | 0.572 | 0.046 | 0.911 | 0.115 | 0.732 | 0.180 |
| Method | CSI | CSI | FSS | CRPS | SSIM | LPIPS |
|---|---|---|---|---|---|---|
| PySteps [ 31 ] | 0.338 | 0.024 | 0.579 | 0.167 | 0.871 | 0.187 |
| DGMR [ 33 ] | 0.367 | 0.022 | 0.633 | 0.154 | 0.883 | 0.137 |
| DiffCast [ 49 ] | 0.328 | 0.018 | 0.613 | 0.168 | 0.869 | 0.183 |
| SSLDM-ISI [ 21 ] | 0.416 | 0.024 | 0.704 | 0.135 | 0.897 | 0.120 |
| AlphaPre [ 20 ] | 0.360 | 0.024 | 0.699 | 0.144 | 0.891 | 0.197 |
| DTCA [ 16 ] | 0.423 | 0.026 | 0.711 | 0.131 | 0.899 | 0.118 |
| Generator | |
|---|---|
| Backbone | DiT, layers, width , heads, patch over (time, height, width) |
| Parameters | M ( M visual backbone M text cross-attention) |
| Frames (condition forecast) | Swedish precipitation / MRMS , SEVIR / MeteoNet / Shanghai , CIKM |
| Tokens per sample | Swedish precipitation / MRMS , SEVIR / MeteoNet / Shanghai , CIKM |
| Objective | Rectified Flow |
| Sampler | Euler, steps |
Precipitation Nowcasting
Precipitation nowcasting predicts rainfall over minutes to hours from radar, satellite, station, and numerical weather data.
See all 42 papers