index
These are some of the projects the team has been working on.
ODIN (Optical Diagnosis INstrumentation)
/image1.png)
This project focused on developing a searchable web platform for publishing and exploring experimental datasets related to the screening of chemical compounds for possible use as reactants in Atomic Layer Deposition (ALD).
LLM Survey Simulation
This project developed a platform to simulate survey responses using large language models, exploring how different populations might answer standardized questionnaires.
SHE Corpus Web Visualization Extension
This project focused on extending the SHE Corpus web interface by porting a frequency-comparison visualization module from the older Java-based ModNLP desktop application to a browser-based workflow.
SHAREbrain Project
The SHAREbrain project focused on developing an AI-based workflow for mapping heterogeneous neuroscience datasets into a structured metadata representation.
TRUST project platform
This project developed a digital platform built on Microsoft SharePoint to collect, organize, and monitor research proposals within the TRUST center.
SMITracker
SMITracker is an interactive computational platform for analyzing DNA-scanning single-molecule imaging data, addressing the bottleneck of manual trajectory detection in single-molecule experiments.
Insight Oslofjord
Insight Oslofjord is an online platform using data from student-led boat trips on the Oslofjord, organized by Inspiria Science Center. The data, collected with sensors, is processed and visualized in an R Shiny app. The platform supports both education and research by providing tools for data exploration and hypothesis testing.
Update: Insight Oslofjord
2025 Update: dScience is a partner in the Frisk Oslofjord Skoletokt project which focuses on education and data collection around the Oslofjord (see earlier post). We contribute by providing data transfer, storage, analysis and visualization, as well as technical and domain knowledge for running the scientific equipment and interpreting the data. The project results are visualized in the Innsikt Oslofjord app, an interactive website created by dScience, which is available to all school classes participating in school cruises on the fjord.
GeoVis
The ‘Geovis’ project, initiated by METOS researchers at the University of Oslo, aimed to develop a custom 3D visualization tool for climate datasets, improving upon the limitations of existing tools like “ncview” by enabling geographic projections and enhanced user interactions for better communication of complex climate data.
OCR-GPT pipeline
The OCR-GPT pipeline was developed to improve text data preparation for the IUROPA project by combining Adobe’s OCR for better paragraph recognition and GPT-4 for correcting character recognition errors in older EU court judgments.
Domain-adapted word embedding
Assisting a research group at the Center for Computing in Science Education in combining qualitative methods with NLP to analyse educational texts. The work includes exploring domain-adapted models and developing tools for efficient text extraction.
Neural Ratio Estimation
This project explores how neural networks can support the search for axion-like particles (ALPs) in cosmic gamma-ray data. By using Neural Ratio Estimation (NRE), researchers aim to overcome the limitations of traditional statistical methods and enable more efficient inference of ALP properties. The work is carried out by Heidi Sandaker’s group, with contributions from dSAG on high-performance computing and machine learning support.
POICE Image Processing Platform
The POICE platform is an image processing pipeline that adheres to Ecotaxa metadata standards, enabling the generation of files ready for upload to Ecotaxa server for data collected by two separate modules: CPICS and Planktoscope.
Drøbak Lander
The lander is an underwater observatory in Drøbak sund, Oslofjord, monitoring fish and currents as part of the Frisk Oslofjord project. In collaboration with dScience, data is collected for research, with findings shared through the Insight Oslofjord app for educational use.
NOMAD for Data Curation
This project focused on designing and deploying a digital solution for curation, analysis and publication of data produced in the Temporal Analysis of Products project by exploring and implementing NOMAD within EduCloud. Key outcomes included a successful private deployment of NOMAD, a shift towards a modular code design for improved extensibility, and the provision of deployment instructions and example scripts for ease of access.
Read more.