Statistical Methods Series: Ecological Modeling with AI and Python

0:00 Sara Beery and Timm Haucke presented on "Ecological Modeling with AI and Python" on March 3, 2025 for the “Statistical Methods” webinar series. This series is hosted by the Ecological Forecasting Initiative and the Ecological Society of America's Statistical Ecology Section. 26:55 Timm and Sara walk through the Python code 1:08:59 The Q&A starts. Details about the seminar series can be found at: https://ecoforecast.org/workshops/statistical-methods-seminar-series/ The Python code used in the presentation is available at: https://github.com/eco4cast/Statistical-Methods-Seminar-Series/tree/main/beery-haucke_biolith Links to other resources and projects were shared during the presentation which you can find below. Access the data/code at: https://colab.research.google.com/drive/1828fk-7DEsDL9reK5oYSOrsYA68cim-W?usp=sharing Biolith project repo: https://github.com/timmh/biolith SpeciesNet (general camera trap classifier): https://github.com/google/cameratrapai List of species supported by SpeciesNet: https://www.kaggle.com/models/google/speciesnet?select=taxonomy_release.txt The three-week intensive program Sara leads on Computer Vision Methods for Ecology which empowers ecologists to accurately and efficiently analyze large image, audio, or video datasets using computer vision. https://cv4ecology.caltech.edu/ Gadot, T., et al.: To crop or not to crop: comparing whole-image and cropped classification on a large dataset of camera trap images. IET Comput. Vis. 18(8), 1193–1208 (2024). https://doi.org/10.1049/cvi2.12318 Data sets related to biology and conservation, intended as a resource for both machine learning (ML) researchers and those who want to harness ML for biology and conservation: https://lila.science