Karst phenomena arise through dissolution and the resulting landscapes are characterised by caves which focus the transport of water underground. To better understand geometry of these conduits at various scales, we mapped caves with laser scanners and built models of the walls to constitute the KarstConduitCatalogue. These mapping techniques allow us to measure cave geometries accurately. This paper describes how we acquired and curated the dataset, and explores possible geoscientific uses.

To manage groundwater effectively, it's important to understand subsurface water systems. Geophysical methods can characterize subsurface layers, but relying on just one method can be misleading. This study combines two methods – Transient electromagnetics and surface nuclear magnetic resonance – in a K-means clustering scheme to better resolve freshwater and saltwater zones. Two case studies showed how a combined approach improves characterization of these hydrogeological important layers.

From the surface, it is hard to tell where underground cave systems are located. We developed a computer model to create maps of the probable cave network in an area, based on the geologic setting. We then applied our approach in reverse: in a region where an old cave network was mapped, we used modeling to test what the geologic setting might have been like when the caves formed. This is useful because understanding past cave formation can help us predict where unmapped caves are located today.

Temporal drain flow dynamics and understanding of their underlying controlling factors are important for water resource management in tile-drained agricultural areas. This study examine whether simpler, more efficient machine learning (ML) models can provide acceptable solutions compared to traditional physics based models. We predicted drain flow time series in multiple catchments subject to a range of climatic and landscape conditions.

To apply a deep learning (DL) algorithm to electromagnetic (EM) methods, subsurface resistivity models and/or the corresponding EM responses are often required. To date, there are no standardized EM datasets, which hinders the progress and evolution of DL methods due to data inconsistency. Therefore, we present a large-scale physics-driven model database of geologically plausible and EM-resolvable subsurface models to incorporate consistency and reliability into DL applications for EM methods.