Nicolas Samelson is working on his Master’s thesis at The University of Auckland under the supervsion by Dr Jörg Wicker and Dr Katharina Dost. His thesis is process-based models in data-lmited scenarios where he combines machine learning and process-based models to produce transferable and generalisable patterns.
Title: Enhancing Process-Based Environmental Models with Machine Learning in Data-Limited Scenarios
Abstract:
Environmental modelling in New Zealand often faces challenges due to fragmented, location-specific projects that lack standardisation and adaptability to climate changes. Resource constraints limit the use of best practices like ensemble modelling, confining decisions to single models, and the exclusion of community input further complicates participatory processes. This thesis explores an innovative approach to embed empirical equations into a Graph Auto-Encoder, aiming to discover transferable and generalisable patterns by combining multiple models. The proposed method is then applied to a real-world scenario of freshwater quantity modelling, specifically the water balance in soils, where data availability is limited. Through this research, we seek to connect environmental models, opening new avenues for improved environmental management and decision-making.
For more information, get in touch here.
Nicolas – Student at Wickerlab