Everglades bird behavior classifier
aerial imagery model
2 min readupdated
This model analyzes aerial photos from Everglades National Park to tell what a wading bird is doing: nesting or roosting. Built on the DeepForest library (an ecosystem imagery analysis tool) with an ImageNet ResNet-50 architecture (a computer vision model), it processes 100x100-pixel bird crops extracted by a detector. It is a useful tool for ornithologists and ecologists monitoring bird colonies from aerial surveys.
Key features
- Tailored to Everglades species: trained on survey data covering white ibises, wood storks, and other wading birds.
- High accuracy: reaches an overall Accuracy of 0.93 on the validation set.
- Easy integration: works as a CropModel add-on paired with the DeepForest bird detector.
- Balanced training: uses data augmentation, class balancing, and 224-pixel crop windows.
What you can do
- Classify birds in aerial photos: automatically sort detected birds into nesting and roosting groups.
- Analyze colonies: process aerial imagery from wildlife reserves to monitor wetland bird populations.
- Extend ecological pipelines: pair the model with the weecology/everglades-bird-airplane detector.
Example
from deepforest import main
from deepforest.model import CropModel
detector = main.deepforest()
detector.load_model("weecology/everglades-bird-airplane")
crop_model = CropModel.load_model("weecology/everglades-airplane-roosting-classifier")
crop_model.config["cropmodel"]["expand"] = 25
birds = detector.predict_tile(path="DSC_2226.JPG", patch_size=800)
Read more
DetailsMetrics: Accuracy 0.93, mean per-class Recall 0.86
Architecture: DeepForest CropModel (ImageNet ResNet-50)
Limitations: data collected from a single camera type during one season in 2022
Dataset: 4,853 birds across 11 Everglades colonies










Comments