Research
Each research line with the question it asked, how it was done, what was found and what was not, and the code and papers behind it. The individual papers are listed on Publications, and the production work that grew out of some of this is under Work.
Completed · MSc research at Wits; dissertation dated 2022 (the CV lists the MSc as 2018 to 2019) · University of the Witwatersrand
Echo state networks for level set image segmentation
MSc research at Wits: can recurrent models learn the iterative evolution of a level set segmentation? Echo state networks against trained RNN, LSTM and GRU.
MSc candidate and sole author of the dissertation · 1 publication · code on GitHub
- Echo state networks
- Reservoir computing
- Recurrent neural networks
- Image segmentation
- Level set method
- Computer vision
- Deep learning
Published · 2020 to 2022, at IBM Research · IBM Research
Machine learning for seasonal climate forecasting
IBM Research work on forecasting 2m temperature and precipitation weeks to months ahead with machine learning, published at NeurIPS 2020 CCAI and EGU 2022.
Co-author and machine learning research scientist · 2 publications
- Seasonal forecasting
- Climate risk
- Time series
- Recurrent neural networks
- Deep learning
- Geospatial machine learning
Published · 2019
Machine learning for hearing loss risk in mine workers
Two 2019 IFAC papers: a recurrent network estimating hearing threshold shift in mine workers, and a classifier based noise policy advising system.
Co-author (third of four authors on both papers) · 2 publications
- Noise induced hearing loss
- Occupational health and safety
- Recurrent neural networks
- Machine learning
Proposed, not started · PhD in Computer Science at Wits, commencing 2027; proposal in preparation, not registered · University of the Witwatersrand
Proposed: self supervised flood mapping from radar
Proposed doctoral research, not yet registered: physics informed self supervised learning for flood extent mapping from synthetic aperture radar.
Proposed doctoral researcher (not registered)
- Synthetic aperture radar
- Remote sensing
- Climate risk
- Geospatial machine learning
Completed · 2017, BSc Honours at Wits · University of the Witwatersrand
Wildfire estimation with kernel density estimators
BSc Honours project at Wits, 2017.
Honours student
- Machine learning