# Land Cover Classification on San Francisco L-band AIRSAR 1989 (test) Source: [Land Cover Classification on San Francisco L-band AIRSAR 1989 (test)]() Collection index: [llms.txt]() Data updated: 2026-06-01T09:34:53.880Z Evaluation of Land Cover Classification performance on the test split of the San Francisco L-band AIRSAR 1989 dataset, reporting per-class accuracies (Bare Soil, Mountain, Water, Urban, Vegetation) 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 | Land Cover Classification | | Dataset (including any stated split) | San Francisco L-band AIRSAR 1989 (test) | | Metric | Bare Soil 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 - [Bare Soil Accuracy](): Higher is better; unit: PERCENT. - [Mountain Accuracy](): Higher is better; unit: PERCENT. - [Water Accuracy](): Higher is better; unit: PERCENT. - [Urban Accuracy](): Higher is better; unit: PERCENT. - [Vegetation Accuracy](): Higher is better; unit: PERCENT. - [Overall Accuracy (OA)](): Higher is better; unit: PERCENT. - [Average Accuracy (AA)](): Higher is better; unit: PERCENT. - [Kappa Coefficient](): Higher is better; unit: PERCENT. ## Recorded results | Method | Bare Soil Accuracy | Result date | Report paper | | --- | --- | --- | --- | | WaveletCNN | 86.74 | Not recorded | 6a1d1229dbd7150506f84067 | | HybridRVNet | 86.33 | Not recorded | 6a1d1229dbd7150506f84067 | | 3D-CNN | 85.5 | Not recorded | 6a1d1229dbd7150506f84067 | | ViT | 79.96 | Not recorded | 6a1d1229dbd7150506f84067 | | HybridCVNet | 78.8 | Not recorded | 6a1d1229dbd7150506f84067 | | PolSARFormer | 75.29 | Not recorded | 6a1d1229dbd7150506f84067 | | swin | 68.16 | Not recorded | 6a1d1229dbd7150506f84067 | ### WaveletCNN Bare Soil Accuracy: 86.74. Result ID: 6a1d515bfbc373592c16e0ca. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### HybridRVNet Bare Soil Accuracy: 86.33. Result ID: 6a1d515bfbc373592c16e0ce. [Reporting paper]() Recorded evaluation configuration: {"Description":"Real-valued variation of proposed network"}. This record does not assert independent reproduction. ### 3D-CNN Bare Soil Accuracy: 85.5. Result ID: 6a1d515bfbc373592c16e0c9. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ViT Bare Soil Accuracy: 79.96. Result ID: 6a1d515bfbc373592c16e0cb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### HybridCVNet Bare Soil Accuracy: 78.8. Result ID: 6a1d515bfbc373592c16e0cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Description":"Proposed complex-valued network"}. This record does not assert independent reproduction. ### PolSARFormer Bare Soil Accuracy: 75.29. Result ID: 6a1d515bfbc373592c16e0cd. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### swin Bare Soil Accuracy: 68.16. Result ID: 6a1d515bfbc373592c16e0cc. [Reporting paper]() [Method origin paper]() [Implementation]() 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.