MMMilena Marycz

Milena Marycz

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Milena Marycz has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Artificial Intelligence and Machine Learning for Bioenergy Generation from Anaerobic Digestion: Data Processing Pipelines, Predictive Models, and Intelligent Control

    by Milena Marycz, Bartłomiej Tokarski, Adam Zasiński, Grzegorz Jasiński, Piotr Jasiński

    Anaerobic digestion (AD) plays a central role in renewable energy generation and sustainable waste management. However, the operation of AD systems remains challenging due to the complex interactions among microbial communities, substrate variability, and non-linear process dynamics. Traditional monitoring and control approaches often fail to anticipate disturbances or maintain optimal conditions. Recent advances in artificial intelligence (AI) and machine learning (ML) provide new opportunities to model, predict, and control AD processes by leveraging high-resolution sensor data and data-driven algorithms. This review synthesizes current progress in ML- and AI-based approaches for prediction, optimization, and intelligent control of AD, with particular emphasis on data processing pipelines, neural network architectures, soft sensors, digital twins, and explainable AI.

  • Top Cited Papers
    Open Access

    Artificial Intelligence in Anaerobic Digestion: A Review of Sensors, Modeling Approaches, and Optimization Strategies

    by Milena Marycz, Izabela Turowska, Szymon Glazik, Piotr Jasiński

    Anaerobic digestion (AD) is increasingly recognized as a key technology for renewable energy generation and sustainable waste management within the circular economy. However, its performance is highly sensitive to feedstock variability and environmental fluctuations, making stable operation and high methane yields difficult to sustain. Conventional monitoring and control systems, based on limited sensors and mechanistic models, often fail to anticipate disturbances or optimize process performance. This review discusses recent progress in electrochemical, optical, spectroscopic, microbial, and hybrid sensors, highlighting their advantages and limitations in artificial intelligence (AI)-assisted monitoring. The role of soft sensors, data preprocessing, feature engineering, and explainable AI is emphasized to enable predictive and adaptive process control. Various machine learning (ML) techniques, including neural networks, support vector machines, ensemble methods, and hybrid gray-box models, are evaluated for yield forecasting, anomaly detection, and operational optimization. Persistent challenges include sensor fouling, calibration drift, and the lack of standardized open datasets. Emerging strategies such as digital twins, data augmentation, and automated optimization frameworks are proposed to address these issues. Future progress will rely on more robust sensors, shared datasets, and interpretable AI tools to achieve predictive, transparent, and efficient biogas production supporting the energy transition.


  • Open Access

    A state of the art review on the use of fungi in biofiltration to remove volatile hydrophobic pollutants

    by Milena Marycz, Anna Brillowska-Dąbrowska, Raúl Muñoz, Jacek Gębicki

    The physical/chemical abatement of gas pollutants creates many technical problems, is costly and entails significant environmental impacts. Biological purification of off-gases is a cheap and ecologically safe way of neutralization of gas pollutants. Despite the recent advances, the main technological challenge nowadays is the purification of volatile organic compounds (VOCs) of hydrophobic character due to their low solubility in water. Among all known biological methods of air purification, the most cost-effective biodegradation of hydrophobic VOCs is conducted by biotrickling filters. In this context, fungi have gained an increasing interest in this field based on their ability to biodegrade hydrophobic VOCs. In addition, biotrickling filtration using fungi can support a superior hydrophobic VOC abatement when compared to the bacterial biofilters. This paper aims at reviewing the latest research results concerning biocatalytic activity of fungi and evaluating the possibilities of their practical application in biofiltration systems to remove hydrophobic VOCs.


  • Open Access

    Evaluation of Immobilization of Selected Peat-Isolated Yeast Strains of the Species Candida albicans and Candida subhashii on the Surface of Artificial Support Materials Used for Biotrickling Filtration

    by Milena Marycz, Anna Brillowska-Dąbrowska, Jacek Gębicki

    The paper describes the process of n-butanol abatement by unicellular fungi, able to deplete n-butanol content in gas, by using n-butanol as source of carbon. Isolated and identified fungi species Candida albicans and Candida subhashii were subjected to a viability process via assimilation of carbon from hydrophilic and hydrophobic compounds. The isolates, which exhibited the ability to assimilate carbon, were immobilized on four different types of artificial support materials used for biotrickling filtration. Application of optical microscopy, flow cytometry and the tests employing propidium iodide and annexin V revealed viability of the fungi isolated on support materials’ surfaces at the average level of 95%. The proposed method of immobilization and its evaluation appeared to be effective, cheap and fast. Based on performed comparative analyses, it was shown that polyurethane foam and Bialecki rings (25 × 25) could be attractive support materials in biotrickling filtration.