Air pollution, especially at the ground level, poses a high risk for human health as it can have serious negative effects on the population of certain areas. The high variability of this type of data, which are affected by weather conditions and human activities, makes it difficult for conventional methods to precisely detect anomalous values or outliers. In this paper, classical analysis, statistical process control, and functional data analysis are compared for this purpose. The results obtained motivate the development of a new outlier detector based on the concept of functional directional outlyingness. The validation of this algorithm is perfomed on real air quality data from the city of Gijón, Spain, aiming to detect the proven reduction in ${\mathrm{NO}}_2$ levels during the COVID-19 lockdown in that city. Three more variables (${\mathrm{SO}}_2$, ${\mathrm{PM}}_{10}$, and ${\mathrm{O}}_3$) are studied with this technique. The results demonstrate that functional data analysis outperforms the two other methods, and the proposed outlier detector is well suited for the accurate detection of outliers in data with high variability.

The mechanical behavior of block-in-matrix materials is heavily dependent on their block content. This parameter is in most cases obtained through visual analyses of the ground through digital imagery, which provides the areal block proportion (ABP) of the area analyzed. Nowadays, computer vision models have the capability to extract knowledge from the information stored in these images. In this research, we analyze and compare classical feature-detection algorithms with state-of-the-art models for the automatic calculation of the ABP parameter in images from surface and underground outcrops. The outcomes of this analysis result in the development of a framework for ABP calculation based on the Segment Anything Model (SAM), which is capable of performing this task at a human level when compared with the results of 32 experts in the field. Consequently, this model can help reduce human bias in the estimation of mechanical properties of block-in-matrix materials as well as contain underground technical problems due to mischaracterization of rock block quantities and dimensions. The methodology used to obtain the ABP at different outcrops is combined with estimates of the rock matrix properties and other characterization techniques to mechanically characterize the block-in-matrix materials. The combination of all these techniques has been applied to analyze, understand and try, for the first time, to model Roman gold-mining strategies in an archaeological site in NW Spain. This mining method is explained through a 2D finite-element method numerical model.

The traceability of granite blocks consists in identifying each block with a finite number of colour bands that represent a numerical code. This code has to be read several times throughout the manufacturing process, but its accuracy is subject to human errors, leading to cause faults in the traceability system. A computer vision system is presented to address this problem through colour detection and the decryption of the associated code. The system developed makes use of colour space transformations and various thresholds for the isolation of the colours. Computer vision methods are implemented, along with contour detection procedures for colour identification. Lastly, the analysis of geometrical features is used to decrypt the colour code captured. The proposed algorithm is trained on a set of 109 pictures taken in different environmental conditions and validated on a set of 21 images. The outcome shows promising results with an accuracy rate of 75.00% in the validation process. Therefore, the application presented can help employees reduce the number of mistakes in product tracking.

Acid mine drainage events have a negative influence on the water quality of fluvial systems affected by coal mining activities. This research focuses on the analysis of these events, revealing hidden correlations among potential factors that contribute to the occurrence of atypical measures and ultimately proposing the basis of an analytical tool capable of automatically capturing the overall behavior of the fluvial system. For this purpose, the hydrological and water quality data collected by an automated station located in a coal mining region in the NW of Spain (Fabero) were analyzed with advanced mathematical methods: statistical Bayesian machine learning (BML) and functional data analysis (FDA). The Bayesian analysis describes a structure fully dedicated to explaining the behavior of the fluvial system and the characterization of the pH, delving into its statistical association with the rest of the variables in the model. FDA allows the definition of several time-dependent correlations between the functional outliers of different variables, namely, the inverse relationship between pH, rainfall, and flow. The results demonstrate that an analytical tool structured around a Bayesian model and functional analysis automatically captures different patterns of the pH in the fluvial system and identifies the underlying anomalies.

Detecting anomalies in water quality data is critical for ensuring safe and reliable water supplies. This study introduces an explainable, iterative, multitemporal machine learning algorithm based on decision trees to detect and characterize temporal anomalies. The model partitions time series into sliding windows at three temporal scales, capturing multivariate relationships across distinct chronological levels. Iterative training enables the classification of new data subsets, progressively refining the learned expert criteria and expanding the anomaly set. To improve interpretability, we developed the Visual Decision Paths Representation (VDPR) algorithm, which provides visual insights into variable importance, learned thresholds, and sample-level classification reasoning. Across all monitoring stations, the model achieved an average F1 score of 99% and an error rate below 1%. By comparing individual samples with the broader dataset, VDPR delivers deeper interpretability than state-of-the-art methods that focus fundamentally on variable importance while preserving strong predictive performance across varied environmental conditions and stations.