Fields like geology, mining, and construction have long relied on manual rock and soil classification methods, which remain time-consuming and labour-intensive. Accurate rock and soil classification is necessary for hazard assessment, urban management or resource exploration, which the rapid advances in artificial intelligence and remote sensing might facilitate. Though optical imagery has dominated remote sensing in the last decades, thermal data offers unique advantages such as sensitivity to material properties, sunlight independence or seasonal and diurnal changes responsiveness. This study explores the use of thermal imagery, along with SAR and NDVI data as complementary data, to leverage and automate the classification process with deep learning. Therefore, the aim is to develop two deep learning models capable of rock and soil segmentation with multi-modal datasets, and evaluate the performance of these models, Convolutional Neural Networks (CNNs) and Convolutional
Long Short-Term Memory networks (ConvLSTMs) across diurnal, seasonal and multi-source
scenarios as well as the effect of vegetation on the prediction results.
Results show CNN tends to have a strong overall performance, especially with thermal and SAR data. Instead, ConvLSTM excels at capturing temporal dependencies, improving the classification of most datasets and variations. The findings demonstrate the potential of thermal imagery to be used as a powerful classification tool when combined with deep learning methods for rocks and soils. They also demonstrate the slightly negative influence of vegetation on the predictability of the outputs. By combining spatial and temporal dynamics, the models offer an automated, scalable, fast and cost-effective approach to more traditional workflows. This work intends to contribute towards modernizing geological practices for more informed decision-making in geology, mining, urban planning, hazard and resource management.

This study explores the effectiveness of Virtual Reality (VR) compared to the use of 2D interfaces in interpreting point cloud data, focusing on user perception, interaction and relative measurement accuracy. Visualizing point clouds is often challenging due to the limitations in translating three-dimensional data into two-dimensional screens. VR offers a potential solution to enhance depth perception and deepen user understanding. The research utilizes Omnibase, a platform developed by Geodelta, that integrates various spatial data types, including point clouds, for applications such as municipal boundary measurements.

The study involved participants that are either familiar or unfamiliar with point clouds, to evaluate VR versus Omnibase. Quantitative measurements and qualitative feedback were collected on either platform. Results indicate that while VR provides better depth perception and a more immersive experience, it presents a steeper learning curve, especially for inexperienced users, additionally, it comes with physical side effects. The measurements in Omnibase showed higher consistency, though not necessarily greater accuracy, due to depth misinterpretations.

In addition to the study, the VR testing environment was developed using Potree.