An AI-derived theme

Geospatial data infrastructure

Cloud-native geospatial formats, catalogues (e.g. STAC), web GIS and reproducible geospatial pipelines for biodiversity data.

7 talks & discussions
Across rooms and sessions

Explore the conversation.

talk · 22 Sept · 16:35–⁠16:45 · SAL A

Future interfaces for BHL

Modern AI tools make new BHL interfaces feasible now (better OCR, image and map search, chatbots); the community must decide which are worth building.

Roderic Page ↗
talk · 24 Sept · 08:35–⁠08:49 · SAL B

The BMD Cubing Engine: Harmonizing Biodiversity and Earth Observation Data

BMD's cubing engine turns a declarative YAML recipe into reproducible, provenance-documented data cubes that harmonise GBIF occurrences with climate and Earth observation data on one grid.

Mathias Dillen ↗
talk · 24 Sept · 09:17–⁠09:31 · SAL B

From Buzzwords to Blueprints: What It Really Takes to Operationalise Biodiversity Digital Twins

Use buzzwords to get funded, then break them down into concrete blueprints: metadata, catalogues, governance and stewardship in the middle layer.

Sharif Islam ↗
talk · 24 Sept · 16:14–⁠16:26 · FORUM

Marine Regions as a backbone for the TDWG Marine GeoScheme

Marine Regions supplies the identifiers, boundaries and hierarchy that make a marine geoscheme maintainable.

Britt Lonneville ↗
talk · 24 Sept · 16:15–⁠16:30 · SAL C

From NetCDF to Web Maps: Building an Open-Source Web GIS for Biodiversity Data Cubes

A simple open-source stack of NetCDF, THREDDS/ncWMS and vanilla JavaScript makes multidimensional biodiversity data cubes browsable and analysable in the browser.

Christian Langer ↗
talk · 24 Sept · 16:26–⁠16:38 · FORUM

The new World Geographical Scheme for Recording (not only) Plant Distributions: process, progress and challenges

The terrestrial update is complete and the standard is nearly ready for public review, with packaging, naming and polygon hosting still to decide.

Francisco Pando ↗
talk · 25 Sept · 09:30–⁠09:45 · FORUM

Evaluating Four Machine Learning Using Google Earth Engine for Analyzing LULC Dynamics of Sandwip Island, Bangladesh

Random Forest in Google Earth Engine gave the most accurate land cover classification of the highly dynamic Sandwip Island, revealing large increases in built-up area and mangroves alongside strong shoreline erosion and accretion.

Md Abrar Al Foysol ↗