What is PB-GJAM?

[website under construction]

Predicting Biodiversity with generalized joint attribute models (PB-GJAM) is an interactive web-based tool that provides accurate and timely forecasts of species and community responses to climate change.



The Generalized Joint Attribute Model (GJAM)

GJAM is a generative model that fits individual species at the community scale, i.e., all species jointly. GJAM resolves the three serious challenges for forecasting species distributions using biodiversity data that are 1) multivariate, 2) multifarious (measured in different ways and on different scales), and 3) mostly zeros. Probabilistic inference in GJAM admits multivariate data, disparate scales and massive zero inflation.

Assimilation of biodiversity and habitat data

We have synthesized data from taxonomically diverse communities, from mammals to insects to vascular plants using data from NEON, tree abundances from the USFS Forest Inventory and Analysis, and bird presence data from ebird. For habitat prediction, we have developed automated workflows using Google Earth Engine's python API to gather environmental data related to soils, climate, topography, land cover, and NASA remotely-sensed ecosystem attributes.

Predictions of species abundances & forecasts of climate vulnerability

By combining multiscale analysis of remotely sensed data with biodiversity networks, we deliver a new generation of biodiversity risk predictions. We model important community attributes including the distributions and abundances of each species, the aggregate number of species (species richness), and their association into communities, based on shared responses to the environment and to each other.

Funding

The PB-GJAM tool is supported by the National Science Foundation (NSF) and the National Aeronautics and Space Administration (NASA) Advanced Information Systems Technology program, award number AIST-16-0052. More information about our funded project can be found here.

Get Data: PB-GJAM for decision makers

Our interactive web-based PB-GJAM tool [link coming soon] can be used to visualize and download species abundance and/or distribution (presence) data for many organisms across the United States. We include historical, current, and future forecasts of species-specific abundance/distribution maps for the following organisms:

  1. Vascular plants, small mammals, and beetles near NEON sites
  2. Tree species across the US, using data from the USFS FIA
  3. Bird species across the US, using data from BBS and ebird

Using your own data: PB-GJAM for researchers

If you would like to use your own data, we recommend examining the following tutorials, which display how to download environmental data at your specified locations, fit models using GJAM, perform variable selection, interpret your results, and predict/forecast across your own study area. The developers version of PB-GJAM can be found on GitHub [link coming soon].

  • Tutorial for downloading/installing/uploading data to GEE [link coming soon]
  • Tutorial for downloading environmental and remote sensing data from GEE [link coming soon]
  • Tutorial for merging files downloaded from GEE [link coming soon]
  • Tutorial for inference and prediction using GJAM
  • Tutorial for inference and prediction using GJAM for a time-series [link coming soon]
  • Tutorial for inference and prediction using MASTIF to model mast seeding [link coming soon]

Publications from our team related to our PB-GJAM tool

Clark, J.S., D. Nemergut, B. Seyednasrollah, P. Turner, and S. Zhang. 2017. Generalized joint attribute modeling for biodiversity analysis: Median-zero, multivariate, multifarious data. Ecological Monographs, 87, 34-56. Clark2017EcolMonogr appendixs1

About our research group

Our team includes ecologists, statisticians, remote sensors, and data scientists in the Nicholas School of the Environment at Duke University. The PB-GJAM tool is supported by NSF and NASA's Advanced Information Systems Technology program, award number AIST-16-0052. More information about our funded project can be found here

Jim Clark, coPI
Jennifer Swenson, coPI
John Fay, collaborator
Amanda Schwantes, postdoc
Christoph Hellmayr, postdoc
Brad Tomasek, PhD candidate
Chase Nuñez, PhD candidate
Chris Kilner, PhD student

To contact us

Please use the form below to contact us for help, to suggest an improvement, or to send us feedback. We will get back to you as soon as possible.