Publications 2025

Remote sensing framework for geological mapping via stacked autoencoders and clustering

by

Supervised machine learning methods for geological mapping via remote sensing face limitations due to the scarcity of accurately labelled training data that can be addressed by unsupervised learning, such as dimensionality reduction and clustering. Dimensionality reduction methods have the potential to play a crucial role in improving the accuracy of geological maps. Although conventional dimensionality … Read more…

Magnetization of Oceanic Lithosphere From Modeling of Satellite Observations

by

Magnetic observations from the oceans have made fundamental contributions to our knowledge of plate motions and the evolution of the geomagnetic field over the past ∼200 Myr. Here we construct updated models of magnetization for the oceanic lithosphere, taking advantage of the most recent models for Earth’s past plate motions. We then evaluate these models using … Read more…

Machine Learning and Big Data Mining Reveal Earth’s Deep Time Crustal Thickness and Tectonic Evolution: A New Chemical Mohometry Approach

by

Quantitative analysis of crustal thickness evolution across deep time poses critical insights into the planet’s geological history. It may help uncover new areas with potential critical mineral deposits and reveal the impacts of crustal thickness and elevation changes on the development of the atmosphere, hydrosphere, and biosphere. However, most existing estimation methods are restricted to … Read more…

Machine Learning-Based Spatio-Temporal Prospectivity Modeling of Porphyry Systems in the New Guinea and Solomon Islands Region

by

Abstract. The discovery of new economic copper deposits is critical for the development of renewable energy infrastructure and zero-emissions transport. The majority of existing copper mines are located within current or extinct continental arc systems, but our understanding of the tectonic and geodynamic conditions favoring the formation of porphyry systems is still incomplete. Traditionally, exploration … Read more…

Phanerozoic icehouse climates as the result of multiple solid-Earth cooling mechanisms

by

The Phanerozoic climate has been interrupted by two long “icehouse” intervals, including the current icehouse of the last ~34 million years. While these cool intervals correspond to lower atmospheric CO2, it is unclear why CO2 levels fell, with hypotheses suggesting changes in CO2 degassing rates or modification of silicate weathering through changing continental lithology or paleogeography. Here, … Read more…

Lamprophyres, gold and orogenies: a mineral systems perspective

by

The common spatial and temporal association of calk alkaline lamprophyres with orogenic gold deposits has been recognized for more than a century, although interpretations regarding the significance of this association have varied greatly. A persistent lack of consensus on Archean geodynamics and the deposits themselves presented a challenge to the use of a Mineral Systems … Read more…

pide: Petrophysical Interpretation tools for geoDynamic Exploration

by

pide is a Python library for calculating geophysical parameters (e.g., electrical conductivity, seismic velocity), employing the results from experimental petrology, mineral/rock physics, and thermomechanical modelling studies. pide can calculate the theoretical electrical conductivity of any Earth material that exists in the literature. pide can also calculate seismic velocity utilising the external ‘sister’ library SAnTex. Using … Read more…