Research

Proposes a daily probabilistic model that forecasts 2 m temperature and total precipitation globally, aimed at the skill gap between weather and seasonal forecasting. Physics based ensembles, climate modes and recent climatology are combined as inputs to Extreme Gradient Boosting, U-Net and Natural Gradient Boosting models. The authors report that it consistently outperforms both ECMWF 46 day forecasts and climatology. Co-authored across IBM Research in South Africa, Kenya, Brazil and the US.

Tests whether two machine learning models, a convolutional and a recurrent neural network, can beat climatology when forecasting 2 m temperature up to 52 weeks ahead at six locations. The models improved on climatology up to 30 weeks lead time by correlation and up to 52 weeks by RMSE skill score, but only at some locations, and the authors note further work is needed for the models to add value in the tropics.

Applies recurrent neural networks to estimate hearing threshold shift in mine workers, and compares optimisation methods for training them. The adaptive subgradient method (Adagrad) was preferred for its fast convergence, and the network predicted threshold shift with 95% accuracy. The authors suggest the results could support an early intervention and monitoring system for mines.

Proposes a policy advising system to help mine administrators assign tasks to new employees. Workers are grouped with K-means clustering, then classified with logistic regression, support vector machines, decision trees and random forests using their baseline and predicted future hearing threshold shift, and suitable mining tasks are recommended from the class. Decision trees had the highest accuracy (91.25% average on test data), while logistic regression generalised best.