# Quantitative Precipitation Estimation on QPEBench CONUS (3-fold cross-validation)

Source: [Quantitative Precipitation Estimation on QPEBench CONUS (3-fold cross-validation)](<https://www.sota2.com/research/sota/quantitative-precipitation-estimation-on-qpebench-conus-3-fold-cross-validation>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-14T09:07:19.449Z

Evaluation of Quantitative Precipitation Estimation models using RMSE, MAE, and correlation-based metrics (rr,coll, FSSR) on the CONUS domain of the QPEBench dataset, evaluated via 3-fold cross-validation.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Quantitative Precipitation Estimation |
| Dataset (including any stated split) | QPEBench CONUS (3-fold cross-validation) |
| Metric | RMSE (r) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 2 of 2 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [RMSE (r)](<https://www.sota2.com/research/sota/quantitative-precipitation-estimation-on-qpebench-conus-3-fold-cross-validation.md?metric=RMSE%20(r)>): Lower is better; unit: SCALAR.

- [MAE (r)](<https://www.sota2.com/research/sota/quantitative-precipitation-estimation-on-qpebench-conus-3-fold-cross-validation.md?metric=MAE%20(r)>): Lower is better; unit: SCALAR.

- [RMSE (g)](<https://www.sota2.com/research/sota/quantitative-precipitation-estimation-on-qpebench-conus-3-fold-cross-validation.md?metric=RMSE%20(g)>): Lower is better; unit: SCALAR.

- [MAE (g)](<https://www.sota2.com/research/sota/quantitative-precipitation-estimation-on-qpebench-conus-3-fold-cross-validation.md?metric=MAE%20(g)>): Lower is better; unit: SCALAR.

- [Correlation (rr, coll)](<https://www.sota2.com/research/sota/quantitative-precipitation-estimation-on-qpebench-conus-3-fold-cross-validation.md?metric=Correlation%20(rr%2C%20coll)>): Higher is better; unit: SCALAR.

- [FSSR](<https://www.sota2.com/research/sota/quantitative-precipitation-estimation-on-qpebench-conus-3-fold-cross-validation.md?metric=FSSR>): Higher is better; unit: PERCENT.

## Recorded results

| Method | RMSE (r) | Result date | Report paper |
| --- | --- | --- | --- |
| NSP | 2.818 | Not recorded | 69ddca3d7d0172140ec79c07 |
| DDPM | 7.482 | Not recorded | 69ddca3d7d0172140ec79c07 |

### NSP

RMSE (r): 2.818. Result ID: 69de03c347f34ce924c5a007.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca3d7d0172140ec79c07.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca3d7d0172140ec79c07.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DDPM

RMSE (r): 7.482. Result ID: 69de03c347f34ce924c5a006.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca3d7d0172140ec79c07.md>)

Recorded evaluation configuration: {"type":"conditional generative baseline"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.