Software

Open-source AI software and open data developed by researchers at the University of Sheffield.

Off

PyKale

PyKale logo

PyKale is a Python library providing accessible machine learning from multiple data sources for interdisciplinary research, particularly multimodal learning and transfer learning, named collectively as Knowledge-aware machine learning (Kale).

Multimodal/Transfer Learning
  • Learn from data of multiple sources (modalities / domains) under one roof.
Accessible Machine Learning
  • Separate code and configurations for non-programmers to configure systems without coding.
Unified Pipeline-based API
  • All machine learning workflows follow a standardized six-step pipeline.

Find out more on the PyKale website


AutoEmulate

Autoemulate logo

AutoEmulate is a Python library designed to automatically create accurate and efficient emulators for complex simulations.

It allows users to run a complete machine learning pipeline to compare and optimise a wide range of models, with built-in functions for downstream tasks such as prediction, sensitivity analysis, and calibration.

Simulations are crucial in both research and industry, but their high computational cost often limits their use. AutoEmulate aims to provide an easy-to-use, community-driven tool that makes simulation emulation more accessible to researchers and practitioners alike.

Find out more on the AutoEmulate website

Centres of excellence

The University's cross-faculty research centres harness our interdisciplinary expertise to solve the world's most pressing challenges.