TDWG2026
Home / Talks / SAL A
talk · Tuesday 22 September · 14:40–⁠14:55 · SAL A

BHL and the Planetary Knowledge Base: Structuring Biodiversity Literature for the Next Generation

Qianqian Hiris Gu · BHL at 20: A New Chapter for Biodiversity Literature and Data - Reimagining BHL: Foundations, Partnerships and Future Infrastructure

Recording time 6:22:42–6:41:12Open on Vimeo ↗

Summaries and key moments are machine-produced. Check the recording for the speaker’s exact words.

The short versionNHM is re-OCRing all of BHL with modern models and extracting entities into a knowledge graph, with confidence gating to protect BHL data quality.

Overview

What this was about

Qianqian Hiris Gu described NHM London's work making BHL machine-readable and connecting it to the NHM's Planetary Knowledge Base. Building on Neil Brummitt's decade of trait extraction from English-language BHL literature (about 700,000 trait terms across 81 standardised traits), an AWS prototyping sprint of four weeks on under 40,000 pages of a botanical journal combined modern OCR with computer vision for article title-page detection (~98%, ~100% with a table of contents), entity extraction (taxa, people, localities, institutions, habitats; F1 ~96%) into a knowledge graph and GraphRAG search. Benchmarking with BHL-provided ground truth showed printed text reaching human-level transcription, and word-level confidence from OCR models can gate what goes back into BHL. The work is now in production: re-OCR of the whole corpus by around January 2027, an open gold-standard dataset in early 2027, and an Explorer interface in Q2 2027.

Why it matters. Turning BHL's 64 million pages into structured, linkable data could unlock huge amounts of trait, taxon and specimen information for research and infrastructure links.

Key ideas

In the room

  • Four pages of a 2002 publication contained 142 data points; BHL has about 64 million pages.
  • Previous trait extraction covered only English literature and 17% of accepted flowering plants.
  • Earlier pipelines needed a separate model per task; LLMs/VLMs allow more in one pass.
  • Article segmentation via title page detection enables assigning DOIs and references.
  • Word-level OCR confidence creates a barrier against ingesting hallucinated text into BHL.
  • Production also extracts specimen identifiers to link back to GBIF and stratigraphy data.
Jump in

Notable moments

In their words

Transcript

Automatically generated captions can contain mistakes, especially in names and technical terms. Times are relative to the room recording.

Read the transcript ↓
Loading transcript…
Keep exploring

Related talks.

See the map ↗
talk · 22 Sept · 14:55–⁠15:10 · SAL A

Possibilities to enhance the semantic navigation of BHL: further developing the 'unit of work'

Letting user communities carve BHL into branded, pre-filtered 'hosted portals' could serve diverse needs, satisfy funders and drive innovation.

Nicky Nicolson
talk · 24 Sept · 15:14–⁠15:26 · FORUM

Species trait literature mining to support integrative biodiversity distribution modelling

Demonstrating research use cases like trait-informed distribution modelling is key to persuading funders to support literature mobilisation infrastructure.

Robert Waterhouse
talk · 25 Sept · 09:48–⁠10:00 · SAL A

Extracting Structured Biodiversity Knowledge from Literature with AI-Assisted Workflows

A hybrid text-layer/OCR tool can free tables from grey-literature PDFs into CSV with about 83% precision, but it misses a third of tables, especially narrow ones.

Yağmur Güleç
Programme abstract

BHL and the Planetary Knowledge Base: Structuring Biodiversity Literature for the Next Generation

Qianqian Hiris Gu

As BHL enters its second decade, the Natural History Museum (NHM) is assisting in its evolution into a machine-actionable, FAIR-aligned biodiversity information infrastructure. This work is connected to NHM's Planetary Knowledge Base (PKB), which integrates fragmented natural history literature, collections, observations, genetic and environmental data into an explainable system for research, policy and action for nature.

The BHL work focuses on developing a biodiversity knowledge-extraction and discovery layer that operates alongside the BHL, linking users back to BHL pages, publications and metadata while enabling new forms of structured search and analysis. NHM has prototyped workflows that transform BHL's page-centric volumes into structured, machine-actionable scholarly resources through modern OCR, article-level segmentation, figure and table extraction, persistent identifier assignment, and entity extraction for taxa, people, institutions, localities, specimen identifiers, habitats and stratigraphy.

These outputs will support semantic discovery, programmatic reuse, knowledge graph construction, and alignment with biodiversity infrastructures such as GBIF, Catalogue of Life, Wikidata, GRSciColl, etc. All extracted entities and relationships retain provenance links to the original BHL pages and bibliographic records, with confidence and workflow metadata. The dataset also serves as a foundational evidentiary layer for the Planetary Knowledge Base (PKB), helping ground biodiversity knowledge in the underlying BHL literature.

These activities position BHL as a distributed, resilient, interoperable evidentiary layer for biodiversity research, connected to specimens, taxa, collections, observations, and external datasets.

Submitted to the conference programme before the talk, so the talk itself may differ.