AI for Energy & Climate
Power grids, renewable energy, industrial assets, weather and climate extremes.
Applied AI for the energy transition and for climate science: forecasting and anomaly detection in power and renewable energy systems, predictive maintenance of industrial and offshore assets, and machine learning for weather, climate extremes and complex systems.
This application domain runs through my whole career:
- Optimization: bio-inspired optimization of wind farm layouts, microgrid topologies and battery scheduling.
- Monitoring energy systems from data: non-technical losses and anomalous consumption in smart-meter data, non-intrusive load monitoring, phase balancing in low-voltage networks and cyberattack detection in SCADA systems.
- Renewable assets (current work): floating offshore wind turbines, wind turbine operation and photovoltaic degradation, where uncertainty quantification and self-supervised learning are essential. Ongoing doctoral theses address photovoltaic systems (Sandra Riaño), offshore renewable energy devices (Maximilian Kammerling) and urban energy communities (Asel Villanueva).
With Sancho Salcedo-Sanz (University of Alcalá) I have worked on wind and energy-demand prediction and on machine learning for climate science, from persistence in complex systems to extreme atmospheric events. With David Pardo (BCAM / EHU) I have worked on deep learning for the inversion of borehole resistivity measurements in geosteering.
Main contributions
- Power systems and grids: robustness of power grids viewed as complex networks (Cuadra et al., 2015), electricity consumption during the COVID-19 pandemic (Khan et al., 2023), energy demand estimation (Salcedo-Sanz et al., 2015), detection of non-technical losses and anomalous consumption (Villar-Rodriguez et al., 2017; Mendia et al., 2024), non-intrusive load monitoring (Gonzalez-Pardo et al., 2015), phase swapping in low-voltage networks (Mendia et al., 2017), cyberattack detection in smart grids (Gumaei et al., 2020) and fault location in transmission lines (de Anchieta Araújo Marques et al., 2025).
- Renewable energy: randomization-based learning for renewable energy prediction (Del Ser et al., 2022), wind speed and wind power forecasting (Salcedo-Sanz et al., 2015; Carrillo et al., 2017), wind farm layout and microgrid design (Manjarres et al., 2014; Camacho-Gomez et al., 2019; Jimenez-Fernandez et al., 2019; Salcedo-Sanz et al., 2016), uncertainty-aware motion prediction of floating offshore wind turbines (Tamuly et al., 2026), anomaly detection in wind turbine operation (Abanda et al., 2024) and degradation estimation in photovoltaic systems (Riaño et al., 2026).
- Industry and energy efficiency: data fusion and machine learning for industrial prognosis (Diez-Olivan et al., 2019), stream learning in combined cycle power plants (Lobo et al., 2020) and energy-aware production scheduling (Para et al., 2022; Garcia-Santiago et al., 2015).
- Geophysics: deep learning for the inversion of borehole resistivity measurements and geosteering (Shahriari et al., 2020; Shahriari et al., 2021; Shahriari et al., 2018).
- Climate, weather and environment: persistence in complex systems (Physics Reports) (Salcedo-Sanz et al., 2022), extreme atmospheric events (Salcedo‐Sanz et al., 2024), long-term and urban air temperature prediction (Fister et al., 2023; Delgado-Enales et al., 2025; Delgado-Enales et al., 2023), air pollution (Maciąg et al., 2023; Laña et al., 2016), smoke detection (Khan et al., 2021), wildfire response planning (Bilbao et al., 2015) and remote sensing image fusion (Zhang et al., 2023; Su et al., 2026).
- Agriculture: AI for soil health (Schweng et al., 2026) and soft sensing of leaf wetness in precision agriculture (Arostegi et al., 2022).
Publications in this area (48)
All my publications related to this research line, in reverse chronological order, including those mentioned above.
2026
2025
2024
2023
2022
- International Workshop on Soft Computing Models in Industrial and Environmental Applications
2021
2020
2019
- Workshop on Mathematical and Computational Modelling on The EarthDeep Learning for Geosteering ApplicationsIn Workshop on Mathematical and Computational Modelling on The Earth, 2019
- Sixth Chilean Workshop on Numerical Analysis of Partial Differential Equations (WONAPDE 2019)Inversion of Borehole Resistivity Measurements Using Deep LearningIn Sixth Chilean Workshop on Numerical Analysis of Partial Differential Equations (WONAPDE 2019), 2019
- Computational Sciences and AI in Industry (CSAI) ConferenceInversion of Resistivity Measurements Using Deep LearningIn Computational Sciences and AI in Industry (CSAI) Conference, 2019
2018
- Oil & Gas Conference 2018
2017
2016
2015
2014
- 9th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO)
- 9th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO)
2013
- 15th Applied Stochastic Models and Data Analysis (ASMDA 2013)A Meta-Heuristic Approach for the Optimal Deployment of Aerial Firefighting Fleets Based on Predictive Fire Weather Risk EstimationsIn 15th Applied Stochastic Models and Data Analysis (ASMDA 2013), 2013
2012
- 5th International Conference from Scientific Computing to Computational Engineering (SCCE)Integrating Discrete Event Simulation with Energy Consumption of a Manufacturing Line within the Virtual Factory FrameworkIn 5th International Conference from Scientific Computing to Computational Engineering (SCCE), 2012