# Sparse-to-dense cross-domain forecasting on NMDB 2001-2023

Source: [Sparse-to-dense cross-domain forecasting on NMDB 2001-2023](<https://www.sota2.com/research/sota/sparse-to-dense-cross-domain-forecasting-on-nmdb-2001-2023>)

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

Data updated: 2026-03-23T10:14:03.359Z

Evaluation of sparse-to-dense cross-domain forecasting performance using the NMDB 2001-2023 dataset, focusing on model efficiency metrics like size and training time.

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 | Sparse-to-dense cross-domain forecasting |
| Dataset (including any stated split) | NMDB 2001-2023 |
| Metric | Model Size (M Parameters) |
| Unit | SIZE |
| Direction | Lower is better |
| Results loaded | 1 of 1 |
| 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

- [Model Size (M Parameters)](<https://www.sota2.com/research/sota/sparse-to-dense-cross-domain-forecasting-on-nmdb-2001-2023.md?metric=Model%20Size%20(M%20Parameters)>): Lower is better; unit: SIZE.

- [Training Time (h)](<https://www.sota2.com/research/sota/sparse-to-dense-cross-domain-forecasting-on-nmdb-2001-2023.md?metric=Training%20Time%20(h)>): Lower is better; unit: TIME.

## Recorded results

| Method | Model Size (M Parameters) | Result date | Report paper |
| --- | --- | --- | --- |
| STONe | 3.1 | Not recorded | 68fa7c501e209131cea8d7fa |

### STONe

Model Size (M Parameters): 3.1. Result ID: 69c1123147f34ce924a90f2d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d7fa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d7fa.md>)

Recorded evaluation configuration: {"Grid Resolution":"Input: 12 points. Output: 1◦ × 1◦ dense grid.","Forecasting Horizon":"180 days (180 steps at 1-day increments)","Input Variables":"180 time steps of 12 sensor variables.","Output Variables":"180 time steps of 1 radiation dose state."}. This record does not assert independent reproduction.

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