machine learning

From logs to maintenance decisions: explainable transformer-based anomaly detection and subsystem prioritization at Paranal Observatory

An explainable log-driven maintenance pipeline utilizing a sentiment-aware BERT model and SHAP to prioritize subsystem maintenance at the Paranal Observatory.

Uncertainty-aware ground-based telescope observation scheduling at ALMA

An automated scheduling algorithm, PULSAR, that integrates uncertainty-aware lookahead and adaptive rebalancing to dynamically schedule observations at ALMA.

Interpretable sentiment-aware transformer-based model for individual log anomaly detection in distributed systems using word-level explanations

An interpretable, sentiment-aware transformer model (BERT-ITPT-FiT) combined with SHAP for parser-free, word-level explainable anomaly detection in individual log entries.

IMT2200 Introducción a Ciencia de Datos

Una introducción moderna y aplicada a los fundamentos y herramientas de la ciencia de datos, combinando análisis estadístico, programación y visualización.

Is the change deforestation? Using time-series analysis of satellite data to disentangle deforestation from other forest degradation causes

Protecting natural ecosystems requires monitoring approaches that work as early warning systems to avoid degradation and protect biodiversity. However, separating forest disturbance causes in change-detection pipelines is challenging due to the …