The control of ventilation systems is often performed by automatic algorithms which often do not consider the future evolution of the system in its control politics. Digital twins allow system forecasting for a more sophisticated control. This paper explores a novel methodology to create a Machine Learning (ML) model for the predictive control of a ventilation system combining Computational Fluid Dynamics (CFD) with Artificial Intelligence (AI). This predictive model was created to forecast the temperature and humidity evolution of a ventilated room to be implemented in a digital twin for better unsupervised control strategies. To replicate the full range of annual conditions, a series of CFD simulations were configured and executed based on seasonal data collected by sensors positioned inside and outside the room. These simulations generated a dataset used to develop the predictive model, which was based on a Deep Neural Network (DNN) with fully connected layers. The model’s performance was evaluated, yielding final average absolute errors of 0.34 degrees Kelvin for temperature and 2.2 percentage points for relative humidity. The presented results highlight the potential of this methodology to create AI-driven digital twins for the control of room ventilation.

Forecasting influent flow in Wastewater Treatment Plants (WWTPs) is critical for managing operational risks during flash floods, especially in Spain’s Mediterranean coastal regions. These facilities, essential for public health and environmental protection, are vulnerable to abrupt inflow surges caused by heavy rainfall. This study proposes a data-driven approach combining historical flow and rainfall data to predict short-term inflow dynamics. Several models were evaluated, including Random Forest, XGBoost, CatBoost, and LSTM, using metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared (R²). XGBoost outperformed the others, particularly under severe class imbalance, with only 1% of the data representing rainfall events. Hyperparameter tuning and input window size analysis revealed that accurate predictions are achievable with just 14 days of training data from a 10-year (2012–2022) dataset sourced from a single WWTP and on-site weather station. The proposed framework supports proactive WWTP management during extreme weather events.

Fine-bubble aeration is a core process in wastewater treatment plants (WWTPs). However, the physical mechanisms linking bubble plume hydrodynamics to oxygen transfer performance remain insufficiently quantified under configurations representative of full-scale installations. This study presents a local multi-sensor experimental characterization of a multiple bubble plume system using a 4 × 4 array of commercial membrane diffusers in a pilot-scale aeration tank (2 m³), emulating WWTP diffuser density and geometry. Airflow rate was varied to analyze its effects on mixing and oxygen transfer efficiency. The experimental methodology combines three complementary measurement approaches. Oxygen transfer performance is quantified using a dissolved oxygen probe. Liquid-phase velocity fields are then mapped using Acoustic Doppler Velocimetry (ADV). Finally, local two-phase measurements are obtained using dual-tip Conductivity Probe (CP) arrays, which provide bubble size, bubble velocity, void fraction, and Interfacial Area Concentration (IAC). Based on these observations, a zonal hydrodynamic model is proposed to describe plume interaction, wall-driven recirculation, and the formation of a collective plume core at higher airflows. Quantitatively, the results reveal a 29% reduction in Standard Oxygen Transfer Efficiency (SOTE) between 10 and 40 m³/h, driven by a 41% increase in bubble size and an 18% rise in bubble velocity. Bubble chord length also increased with height, by 33%, 19%, and 15% over 0.8 m for 10, 20, and 40 m³/h, respectively. These trends indicate that increasing airflow enhances turbulent mixing but simultaneously enlarges bubbles and accelerates their ascent, thereby reducing residence time and negatively affecting oxygen transfer. Overall, the validated multiphase datasets and mechanistic insights demonstrate the dominant role of diffuser interaction in dense layouts, supporting improved parameterization and experimental benchmarking of fine-bubble aeration systems in WWTPs.

The widely used Euler–Euler two-fluid approach for numerical simulations of bubbly flows requires several closure models. Among them, Bubble Induced Turbulence (BIT) models are needed to model turbulence generation and dissipation due to liquid–gas interactions. Understanding how BIT models affect the average flow quantities is key for the improvement of such models. Explainable Deep Learning is rapidly growing over many research fields as a powerful tool to gain understanding of complex models. In the present work, the Sato BIT model is analyzed by means of SHapley Additive exPlanations values, identifying regions of importance among different flow quantities, such as gas distribution, liquid velocity, and turbulent kinetic energy. The results show that Sato effectively increases the stability of the system through an extra turbulent viscosity, leading to higher energy dissipation. Key regions were identified where important flow instabilities were dampened, exhibiting less sensitivity to temporal velocity fluctuations. This work presents a novel methodology to study BIT models, encouraging further studies comparing different modeling approaches.

Perovskite materials have demonstrated great potential for a wide range of optoelectronic applications due to their exceptional electronic and optical properties. However, synthesising high-quality perovskite films remains a significant challenge, often hindered by batch-wise processes that suffer from limited control over reaction conditions, scalability and reproducibility. In this study, we present a novel approach for synthesising single-crystal perovskites with an optimised continuous-flow reactor. Our methodology utilises a 3D printed system that enables precise control over reactant concentrations, reaction times, and temperature profiles. The reaction chamber was designed and optimised by combining residence time distribution (RTD) studies and computational fluid dynamics (CFD) simulations. High-quality single-crystal perovskites with different formulations were obtained employing seeding and seedless conditions. The possibility of synthesising mixed halide single crystal perovskites with different compositions along its structure was demonstrated by simply shifting the feedstock solution during the crystallisation, demonstrating the versatility of this technology