It is with great excitement that we release DeepForest 2.0! This is the first major release since the project took shape in its current form. The codebase has been updated to match modern machine learning workflows, including better command line tools, configurations and package management.
Every episode in a tv series starts with a recap. So… Previously, on Portal: the Regime Shift — In fall of 2023, one of the ruling families of Portal — the Desert Pocket Mouse (Chaetodipus penicillatus for my mammalogy friends) — fell from favor with no warning.
When last we left our rodent community at Portal, things were still…weird. Recap: In fall of 2023, one of our most abundant species, Chaetodipus penicillatus (Desert pocket mouse), experienced a population crash right before their seasonal torpor for the winter. Had they hibernated early or had we really lost individuals?
Interested in using computer vision to help understand, manage, and conserve nature? We hiring for a new position to join our team working on models, software, and community outreach in our existing projects using airborne imagery to monitor and understand natural systems at large scales.
Interested in understanding how ecological systems change through time? Morgan Ernest’s Lab at the University of Florida has an opening for a PhD student to start Fall 2025.
* (Blog post) MIT libraries are thriving without Elsevier by Cory Doctorow * (Blog Post) State-Space Vector Autoregressions in mvgam by Nick Clark * (Software) neonutilities
We’re looking for a new PhD student to join weecology! The new student will work on our Everglades project, developing actionable forecasting models for this actively managed ecosystem, with a focus on understanding the influence of scale on ecological forecasting.
One of the things we miss from the golden age of twitter was that it was a great way of sharing things you liked with others. This is certainly still possible in the more fractured social media landscape, but we’re interested in doing more of this type of sharing in a less platform centric manner.
One of weecology’s newest projects involves monitoring wading birds in the Everglades using drones. We need to quickly turn this imagery into data to drive ecological forecasts & guide management decisions. We do this in near real-time using computer vision models to detect birds in imagery & automated workflows to update this data as soon as new imagery is available.
New dataset of canopy tree maps for 100 million trees in the National Ecological Observatory Network with information on location, species identify, and size.