I arrive in Hermanus, a picturesque South African coastal village an hour-and-a-half from Cape Town, at about 11am on a sunny October morning. Ignoring the restaurants and art galleries on the main drag and the throngs of tourists watching southern right whales from the cliff path, I drive straight to the harbour to meet Els Vermeulen, the Belgium-born scientist who heads up the whale unit for the University of Pretoria's Mammal Research Institute. She is waiting for her colleagues to return from the last whale-tagging sortie of the 2024 season. "I would normally be out on the boat with the team," says Vermeulen, who is dressed in a bold geometric print dress and a denim jacket. "But I had to drop my kids at school and couldn't get down here early enough." The water next to the concrete pier is so clear that I can see a giant orange starfish inching its way along the rocky seabed.

On my desk right now, sitting beside my ultra-modern gaming PC, there is a strange device resembling the spaceship control panel from a 1970s sci-fi movie. It has no keyboard, no monitor, just several neat lines of coloured switches below a cascade of flashing lights. If you thought the recent spate of retro video game consoles such as the Mini SNES and the Mega Drive Mini was a surprising development in tech nostalgia, meet the PiDP-10, a 2:3 scale replica of the PDP-10 mainframe computer first launched by the Digital Equipment Corporation (DEC) in 1966. Designed and built by an international group of computer enthusiasts known as Obsolescence Guaranteed, it is a thing of beauty. Oscar Vermeulen, a Dutch economist and lifelong computer collector, wanted to build a single replica of a PDP-8 mainframe, a machine he had been obsessed with since childhood.

This study presents a systematic machine learning approach for creating efficient hybrid models and discovering sorption uptake models in non-linear advection-diffusion-sorption systems. It demonstrates an effective method to train these complex systems using gradient based optimizers, adjoint sensitivity analysis, and JIT-compiled vector Jacobian products, combined with spatial discretization and adaptive integrators. Sparse and symbolic regression were employed to identify missing functions in the artificial neural network. The robustness of the proposed method was tested on an in-silico data set of noisy breakthrough curve observations of fixed-bed adsorption, resulting in a well-fitted hybrid model. The study successfully reconstructed sorption uptake kinetics using sparse and symbolic regression, and accurately predicted breakthrough curves using identified polynomials, highlighting the potential of the proposed framework for discovering sorption kinetic law structures.

Imagine some day in the future you are sitting at your computer and suddenly it starts playing soothing music to help alleviate your stress levels. Or after a long morning, it advises you to take a break as you are starting to look tired. Although such ideas will either sound like a great approach to health and wellbeing, or rather creepy, depending on your point of view, much of the technology to transform such notions into reality already exists. For example, neuromarketers, who study the brain's responses to both marketing and advertising, have for some time been using facial coding software via webcams to read consumers' expressions to understand their emotional reactions. So it is not a huge leap to think of these systems being reapplied in the workplace to boost employee engagement, which remains a key preoccupation of many leaders.

Imagine some day in the future you are sitting at your computer and suddenly it starts playing soothing music to help alleviate your stress levels. Or after a long morning, it advises you to take a break as you are starting to look tired. Although such ideas will either sound like a great approach to health and wellbeing, or rather creepy, depending on your point of view, much of the technology to transform such notions into reality already exists. For example, neuromarketers, who study the brain's responses to both marketing and advertising, have for some time been using facial coding software via webcams to read consumers' expressions to understand their emotional reactions. So it is not a huge leap to think of these systems being reapplied in the workplace to boost employee engagement, which remains a key preoccupation of many leaders.