π² Forest and trees v.2026-07-03 β per-location benchmarkο
This page details the validation of the π² Forest and trees v.2026-07-03 segmentation model on 8 areas of interest (AOI), compared against the previous version v.2025-06-14. For each AOI the two prediction masks are shown side by side; click any image to open it full size, and use the β / β arrow keys to browse between them.
All metrics are area-based: IoU is the intersection-over-union of the predicted and ground-truth vegetation masks, and F1 / Precision / Recall are computed on the overlapping mask area. Evaluation run: 2026-07-03.
Mask colour legend: v.2026-07-03 Β· v.2025-06-14
Philippines β Balangaο
Model |
IoU |
F1 |
Precision |
Recall |
|---|---|---|---|---|
v.2026-07-03 |
0.806 |
0.892 |
0.864 |
0.923 |
v.2025-06-14 |
0.593 |
0.745 |
0.914 |
0.628 |
Spain β Velilla de San Antonioο
Model |
IoU |
F1 |
Precision |
Recall |
|---|---|---|---|---|
v.2026-07-03 |
0.784 |
0.879 |
0.894 |
0.864 |
v.2025-06-14 |
0.008 |
0.015 |
0.989 |
0.008 |
Spain β Madridο
Model |
IoU |
F1 |
Precision |
Recall |
|---|---|---|---|---|
v.2026-07-03 |
0.813 |
0.897 |
0.880 |
0.915 |
v.2025-06-14 |
0.447 |
0.618 |
0.973 |
0.453 |
Italy β Crotoneο
Model |
IoU |
F1 |
Precision |
Recall |
|---|---|---|---|---|
v.2026-07-03 |
0.862 |
0.926 |
0.944 |
0.909 |
v.2025-06-14 |
0.803 |
0.890 |
0.988 |
0.811 |
Spain β Rusο
Model |
IoU |
F1 |
Precision |
Recall |
|---|---|---|---|---|
v.2026-07-03 |
0.617 |
0.763 |
0.699 |
0.841 |
v.2025-06-14 |
0.057 |
0.108 |
0.964 |
0.057 |
Spain β Cuencaο
Model |
IoU |
F1 |
Precision |
Recall |
|---|---|---|---|---|
v.2026-07-03 |
0.763 |
0.865 |
0.859 |
0.872 |
v.2025-06-14 |
0.459 |
0.629 |
0.873 |
0.492 |
Argentina β La Bandaο
Model |
IoU |
F1 |
Precision |
Recall |
|---|---|---|---|---|
v.2026-07-03 |
0.576 |
0.731 |
0.653 |
0.829 |
v.2025-06-14 |
0.233 |
0.378 |
0.958 |
0.235 |
Uzbekistan β Tashkentο
Model |
IoU |
F1 |
Precision |
Recall |
|---|---|---|---|---|
v.2026-07-03 |
0.730 |
0.844 |
0.905 |
0.791 |
v.2025-06-14 |
0.568 |
0.724 |
0.981 |
0.574 |
Summaryο
v.2026-07-03 improves substantially over the previous v.2025-06-14 across all 8 AOIs. Mean area-based F1 rises from 0.513 to 0.850 and IoU from 0.396 to 0.744, driven by a large recall gain (0.407 β 0.868). The previous version was highly conservative β mean precision 0.955, but it missed most vegetation and collapsed on several AOIs (e.g. Velilla de San Antonio F1 0.015, Rus F1 0.108, La Banda F1 0.378). v.2026-07-03 keeps precision high (0.837) while recovering the missed canopy, and leads on F1 in every location.