With the support of the Swiss Innovation Agency Innosuisse, in this joint work with Impaakt, we aim to operationalize and evaluate the impact of companies and provide a specialized search engine, targeted at ranking sources for impact analysis. We will build on and extend recent advances in deep learning to analyze various dimensions of impact to reduce the manual curation efforts.
The Earth’s scholarly knowledge about species diversity (biodiversity) is included in a corpus of several hundred million pages of publications spanning over 250 years, with an arbitrary starting point of 1753 for plants and 1758 for animals. Each year an estimated 19,000 animal and plant species and a multiple of augmentations of data are added to the already approximately known 1.9M species. The data about each species are included in highly structured taxonomic treatments and figures. Increasingly these treatments include implicit links to the data used to describe and augment it, such as omic and digitized specimen data produced by SwissBioCollection.
Missions
BiCIKL will catalyse a culture change in the way biodiversity data is identified, linked, integrated and re-used across the research cycle. We will cultivate a more transparent, trustworthy and efficient research ecosystem. Vision
BiCIKL will launch a new European starting community of key research infrastructures, researchers, citizen scientists and other stakeholders in the biodiversity and life sciences based on open science practices through access to data, tools and services.
Results
BiCIKL is building the Biodiversity Knowledge Hub (BKH) - a single knowledge portal to interlinked and machine-readable FAIR data (Findable, Accessible, Interoperable and Reusable) using unique stable identifiers on specimens, genomics, observations, taxonomy and publications.
SIB Text Mining / HES-SO BiTeM contributions
One of the main outcomes of the project will be supported by the SIB Literature Services (https://sibils.text-analytics.ch/), which will power the delivery of Biodiversity PMC (https://sibils.text-analytics.ch/search/).