🌲 Forest and trees v.2026-09-10 — per-location benchmark

This page details the validation of the 🌲 Forest and trees v.2026-09-10 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 ← / → 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. The segmentation output is unchanged from v.2026-07-03 (the v.2026-09-10 update refines crown extraction), so these per-location figures carry over. Segmentation evaluation run: 2026-07-03.

← → to browse · ESC to close

Mask colour legend: v.2026-09-10 · v.2025-06-14

菲律宾 — 巴兰加

模型	IOU	F1	精确	记起
v.2026-09-10	0.806	0.892	0.864	0.923
v.2025-06-14	0.593	0.745	0.914	0.628

v.2026-09-10 — Philippines — Balanga — v.2026-09-10

v.2025-06-14 — Philippines — Balanga — v.2025-06-14

西班牙 — 贝利利亚德圣安东尼奥

模型	IOU	F1	精确	记起
v.2026-09-10	0.784	0.879	0.894	0.864
v.2025-06-14	0.008	0.015	0.989	0.008

v.2026-09-10 — Spain — Velilla de San Antonio — v.2026-09-10

v.2025-06-14 — Spain — Velilla de San Antonio — v.2025-06-14

西班牙 — 马德里

模型	IOU	F1	精确	记起
v.2026-09-10	0.813	0.897	0.880	0.915
v.2025-06-14	0.447	0.618	0.973	0.453

v.2026-09-10 — Spain — Madrid — v.2026-09-10

v.2025-06-14 — Spain — Madrid — v.2025-06-14

意大利 — 克罗托内

模型	IOU	F1	精确	记起
v.2026-09-10	0.862	0.926	0.944	0.909
v.2025-06-14	0.803	0.890	0.988	0.811

v.2026-09-10 — Italy — Crotone — v.2026-09-10

v.2025-06-14 — Italy — Crotone — v.2025-06-14

西班牙 — 罗斯

模型	IOU	F1	精确	记起
v.2026-09-10	0.617	0.763	0.699	0.841
v.2025-06-14	0.057	0.108	0.964	0.057

v.2026-09-10 — Spain — Rus — v.2026-09-10

v.2025-06-14 — Spain — Rus — v.2025-06-14

西班牙 — 昆卡

模型	IOU	F1	精确	记起
v.2026-09-10	0.763	0.865	0.859	0.872
v.2025-06-14	0.459	0.629	0.873	0.492

v.2026-09-10 — Spain — Cuenca — v.2026-09-10

v.2025-06-14 — Spain — Cuenca — v.2025-06-14

阿根廷 — 拉班达

模型	IOU	F1	精确	记起
v.2026-09-10	0.576	0.731	0.653	0.829
v.2025-06-14	0.233	0.378	0.958	0.235

v.2026-09-10 — Argentina — La Banda — v.2026-09-10

v.2025-06-14 — Argentina — La Banda — v.2025-06-14

乌兹别克斯坦 — 塔什干

模型	IOU	F1	精确	记起
v.2026-09-10	0.730	0.844	0.905	0.791
v.2025-06-14	0.568	0.724	0.981	0.574

v.2026-09-10 — Uzbekistan — Tashkent — v.2026-09-10

v.2025-06-14 — Uzbekistan — Tashkent — v.2025-06-14

概括

v.2026-09-10 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 → 0.868). The previous version was highly conservative — 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.2026-09-10 keeps precision high (0.837) while recovering the missed canopy, and leads on F1 in every location.