Machine Learning Archives

New approaches to high-resolution geological simulations

Written by

Geological models using Mishra and Haese’s workflow have improved predictions of fluid flow and fluid–rock reactions.

Geological and reservoir modelling are critical for geological exploration, resource extraction, and geoengineering projects. Current workflows and datasets record geological variations on metre or decimetre scales. However, many relevant geological structures exist at sub-centimetre scales. Dr Achyut Mishra and Professor Ralf Haese at the University of Melbourne, Australia – part of the international research consortium GeoCquest – have developed a […]

The cold, dark secrets of the Universe in few-body physics

Written by

The AMO physics group at Stony Brook University uses few-body physics, cold and ultracold chemistry as well as machine learning to study fundamental problems in the research field.

Understanding fundamental processes in physics, particularly physics beyond the Standard Model, is no easy task. Experiments and theories looking for new general theories to describe many of the phenomena that are missing in the Standard Model focus on particle physics experiments at places like CERN. Professor Jesús Pérez Ríos of the atomic, molecular, and optical (AMO) physics group at Stony […]

When less is more: Downscaling climate data for improved modelling

Written by

Fullhart’s primary research interests are in hydrological modelling and hydroclimatology.

Accurate climate modelling requires long-term, high-resolution, and high-quality time series data. However, such datasets are often not available, especially in the Global South. Dr Andrew Fullhart (US Department of Agriculture) is utilising global climate datasets and machine learning to improve global coverage of gridded data. The results provide accurate monthly and daily time series for precipitation across Africa and South […]

Which factors are relevant for asset prices?

Written by

Professor Audrino analyses the predictive performance of different machine learning based asset pricing models

Much research effort has focused on developing estimation methodologies and models aiming to identify the relevant factors for pricing the cross-section of stock returns, meaning the change in average returns across different stocks. Traditional asset pricing models with many factors can no longer cope with the dimensionality of present-day problems. Moreover, relying on misleading results could end in disastrous financial […]

Adaptive experiments: Machine learning can help scientific discovery

Written by

Cheng Soon Ong develops statistical machine learning methods and applies machine learning-guided design to biology.

Machine learning can help scientists design experiments. Scientific discovery relies on experiments that build our understanding of natural phenomena, and traditionally has been based on trial and error. Depending on the goal, different machine learning strategies can be used for adaptive experiments: active learning, maximising information gain, Bayesian optimisation, bandit approaches, and reinforcement learning. Cheng Soon Ong, machine learning scientist […]

Pushing boundaries: Peter McLaren on the importance of critical pedagogy inside and outside the classroom

Written by

An interview with Peter McLaren on how critical pedagogy has evolved and where he sees this social movement and philosophy progressing.

Peter McLaren is Distinguished Professor in Critical Studies and Co-Director and International Ambassador for Global Ethics and Social Justice of the Paulo Freire Democratic Project at Chapman University in the USA. Regarded as one of the leading architects of critical pedagogy, McLaren re-envisions the philosophy of Freire in the context of contemporary issues, including the struggle of the LGBTQ community, […]

Computational biology: How mathematical modelling can help cure cancer

Written by

Susan Mertins uses computational modelling to build virtual cells and machine learning to develop new approaches to treating cancer.

Understanding how living cells work is difficult due to the number of varied and complex processes occurring in them. This complexity can be elucidated by breaking these processes down into simpler components and focusing on a particular mechanism. One approach to this study is to use mathematical equations – the basis of computational modelling. Dr Susan Mertins, the founder and […]

Machine Learning Week Europe 2022 is live!

Written by

Machine Learning week 2022 is live in Berlin

Machine Learning Week Europe is live in Berlin! But what even is it? Machine learning is a form of artificial intelligence, where software applications and computers learn how to improve and redesign their ability to do tasks – completely independently from their human creators. When commercially deployed, it’s called predictive analytics. Around the world, these tools are being exponentially rolled-out […]

Predictive discarding for sustainable Industry 5.0

Written by

The computer chip shortage has prompted Dr Geert van Kollenburg and his colleagues at Eindhoven University of Technology, the Netherlands, to find data-driven methods to optimise chip manufacturing processes. As part of the MadeIn4 project, they have developed a predictive discarding framework in which quality predictions from artificial intelligence (AI) algorithms are used to decide on whether to discard an […]

Digital Assyriology: Using artificial intelligence to unlock an ancient lingua franca

Written by

The ancient writing system of cuneiform was used to record millennia of human history, but relatively few of the hundreds of thousands of known cuneiform texts have yet been translated and made available to researchers and the public alike. The Babylonian Engine project, led by Dr Shai Gordin of Ariel University, Israel, has developed two tools – Atrahasis and Akkademia […]