weecology/cropmodel-neon-resnet18-species

NEON Tree Species Classification (ResNet-18)

Classifies tree crowns detected by DeepForest into 167 species using USDA PLANTS codes. Trained on RGB imagery from 30 NEON sites across North America.

Trained with NeonTreeClassification.

Usage

from deepforest import main
from deepforest.model import CropModel

detector = main.deepforest()
detector.load_model("weecology/deepforest-tree")

species_model = CropModel.load_model("weecology/cropmodel-neon-resnet18-species")

results = detector.predict_tile(path="tile.tif", crop_model=species_model)
# results has columns: cropmodel_label, cropmodel_score

Results (Test Set)

Metric	Value
Accuracy	86.9%
Macro F1	0.80
Weighted F1	0.87
Classes	167

Full per-class precision/recall/F1 in classification_report.csv.

Training

Parameter	Value
Architecture	ResNet-18 (torchvision, ImageNet pretrained)
Input	224×224 RGB, ImageNet normalization
Optimizer	AdamW (lr=1e-3, weight_decay=1e-4)
Scheduler	ReduceLROnPlateau
Max epochs	500 (early stopping patience=15)
Best epoch	11 (val_loss=0.62)
Batch size	512
Class weights	None
Seed	42

Dataset

47,971 tree crowns from 30 NEON sites. Labels from NEON Vegetation Structure Taxonomy (VST) field surveys. RGB crown crops extracted at 0.1m resolution.

Split	Samples
Train (70%)	33,579
Val (15%)	7,195
Test (15%)	7,197

Split method: random, seed=42.

Sites: ABBY, BART, BONA, CLBJ, DEJU, DELA, GRSM, GUAN, HARV, HEAL, JERC, KONZ, LENO, MLBS, MOAB, NIWO, ONAQ, OSBS, PUUM, RMNP, SCBI, SERC, SJER, SOAP, SRER, TALL, TEAK, UKFS, UNDE, WREF

License

MIT