# PolSAR Image Classification on Flevoland NASA/JPL AIRSAR 1989 99% (test)

Source: [PolSAR Image Classification on Flevoland NASA/JPL AIRSAR 1989 99% (test)](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test>)

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

Data updated: 2026-06-01T09:34:53.842Z

Evaluation of PolSAR image classification performance on the specific 99% test split of the NASA/JPL AIRSAR 1989 Flevoland dataset, reporting per-class accuracies for 15 land cover types (e.g., Water, Forest, Buildings) and overall metrics (OA, AA, Kappa).

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 | PolSAR image classification |
| Dataset (including any stated split) | Flevoland NASA/JPL AIRSAR 1989 99% (test) |
| Metric | Water Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Water Accuracy](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Water%20Accuracy>): Higher is better; unit: PERCENT.

- [Forest Accuracy](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Forest%20Accuracy>): Higher is better; unit: PERCENT.

- [Lucerne Accuracy](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Lucerne%20Accuracy>): Higher is better; unit: PERCENT.

- [Grass Accuracy](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Grass%20Accuracy>): Higher is better; unit: PERCENT.

- [Rapeseed Accuracy](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Rapeseed%20Accuracy>): Higher is better; unit: PERCENT.

- [Beet Accuracy](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Beet%20Accuracy>): Higher is better; unit: PERCENT.

- [Potatoes Accuracy](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Potatoes%20Accuracy>): Higher is better; unit: PERCENT.

- [Peas Accuracy](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Peas%20Accuracy>): Higher is better; unit: PERCENT.

- [Stem Beans Accuracy](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Stem%20Beans%20Accuracy>): Higher is better; unit: PERCENT.

- [Bare Soil Accuracy](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Bare%20Soil%20Accuracy>): Higher is better; unit: PERCENT.

- [Wheat Accuracy](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Wheat%20Accuracy>): Higher is better; unit: PERCENT.

- [Wheat 2 Accuracy](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Wheat%202%20Accuracy>): Higher is better; unit: PERCENT.

- [Wheat 3 Accuracy](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Wheat%203%20Accuracy>): Higher is better; unit: PERCENT.

- [Barley Accuracy](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Barley%20Accuracy>): Higher is better; unit: PERCENT.

- [Buildings Accuracy](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Buildings%20Accuracy>): Higher is better; unit: PERCENT.

- [Overall Accuracy (OA)](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Overall%20Accuracy%20(OA)>): Higher is better; unit: PERCENT.

- [Average Accuracy (AA)](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Average%20Accuracy%20(AA)>): Higher is better; unit: PERCENT.

- [Kappa Coefficient](<https://www.sota2.com/research/sota/polsar-image-classification-on-flevoland-nasa-jpl-airsar-1989-99-percent-test.md?metric=Kappa%20Coefficient>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Water Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| HybridCVNet | 99.84 | Not recorded | 6a1d1229dbd7150506f84067 |
| 3D-CNN | 99.46 | Not recorded | 6a1d1229dbd7150506f84067 |
| HybridRVNet | 98.99 | Not recorded | 6a1d1229dbd7150506f84067 |
| WaveletCNN | 98.59 | Not recorded | 6a1d1229dbd7150506f84067 |
| swin | 98.23 | Not recorded | 6a1d1229dbd7150506f84067 |
| PolSARFormer | 98.23 | Not recorded | 6a1d1229dbd7150506f84067 |
| ViT | 96.93 | Not recorded | 6a1d1229dbd7150506f84067 |

### HybridCVNet

Water Accuracy: 99.84. Result ID: 6a1d515bfbc373592c16e0c8.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1229dbd7150506f84067.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d1229dbd7150506f84067.md>)

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

### 3D-CNN

Water Accuracy: 99.46. Result ID: 6a1d515bfbc373592c16e0c2.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1229dbd7150506f84067.md>)

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

### HybridRVNet

Water Accuracy: 98.99. Result ID: 6a1d515bfbc373592c16e0c7.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1229dbd7150506f84067.md>)

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

### WaveletCNN

Water Accuracy: 98.59. Result ID: 6a1d515bfbc373592c16e0c3.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1229dbd7150506f84067.md>)

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

### swin

Water Accuracy: 98.23. Result ID: 6a1d515bfbc373592c16e0c5.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1229dbd7150506f84067.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a8c1e209131cea28b62.md>)

[Implementation](<https://github.com/microsoft/Swin-Transformer>)

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

### PolSARFormer

Water Accuracy: 98.23. Result ID: 6a1d515bfbc373592c16e0c6.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1229dbd7150506f84067.md>)

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

### ViT

Water Accuracy: 96.93. Result ID: 6a1d515bfbc373592c16e0c4.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1229dbd7150506f84067.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0b1e209131cea25b04.md>)

[Implementation](<https://github.com/google-research/vision_transformer>)

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

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