Aug 2026· Biotechnology Advances· Vol 92, pp.
109006
· 0 citations· 145 references
Medicine
TL;DR
Machine learning has exhibited significant potential in elevating BES design, manufacture, operation and application, however, constrained by data scarcity and heterogeneity, present models are with limited transferability across scales.
Abstract
Bioelectrochemical systems (BES) represent an interdisciplinary convergence of biology, electrochemistry, materials science, environmental engineering and mechanical engineering, offering transformative potential for renewable energy generation, wastewater treatment and resource valorization. However, the inherent structural intricacy and mechanistic complexity of BES pose significant challenges to system understanding and optimization. With robust capabilities in pattern recognition and nonlinear system modeling, machine learning (ML) appears to be a good approach to decipher the complex mechanisms of BES. A systematic literature review reveals that ML applications in BES date back to 2006, with a marked surge around 2021, reflecting the growing research interest in this interdisciplinary field. The application domains primarily fall into four categories: (1) analysis and prediction of microbial communities, (2) intelligent design of system components, (3) performance prediction and system optimization, and (4) real-time monitoring and assisted intelligent control. Among these, performance prediction and system optimization constitute the dominant application area, and model interpretability and generalization are cross-cutting requirements for reliable and transferable ML deployment in BES. Among the BES subtypes that have employed ML, microbial fuel cells (MFC) account for the largest share (42.4%), followed by electrochemical biosensor (EB, 37.6%) and microbial electrolysis cells (MEC, 10.9%), with other types occupying smaller proportions. Regarding algorithmic choices, artificial neural networks are the most frequently used method (30.9%), followed by support vector machines or support vector regression (17.3%), principal component analysis (14.5%), and regression trees (13.1%). ML has exhibited significant potential in elevating BES design, manufacture, operation and application. However, constrained by data scarcity and heterogeneity, present models are with limited transferability across scales. Further efforts are warranted to promote the application of ML in BES by expanding data accumulation, diversifying datasets, and developing targeted models. This will ultimately enable a deeper understanding, enhanced optimization and broader deployment of BES.
With growing concerns over climate change, electrochemical CO2 reduction (CO2RR) has attracted significant attention for converting CO2 into valuable products under mild conditions, but catalyst design remains challenging because traditional, experiment-driven approaches are inefficient and time-consuming. Recently, machine learning (ML), as an advanced data-driven technology, has been widely applied to catalyst design and performance prediction, providing new approaches for rapid screening, structural optimization, and mechanistic exploration of catalysts. Building on these recent advances, this review summarizes the latest applications of ML in CO2RR technology, focusing on ML applications in catalyst performance prediction, key descriptor discovery, catalyst screening, mechanistic investigation, and optimization of synthesis parameters. Additionally, this review discusses the challenges faced by ML in CO2RR catalyst development, including data scarcity, poor model generalization, and difficulties in multiobjective optimization, while looking ahead to future directions such as transfer learning, the establishment of automated synthesis platforms, and the integration of multiobjective optimization frameworks, thereby providing a roadmap for the rational design of next-generation CO2RR catalysts that aims to guide the development of data-driven catalyst design approach.
Machine learning (ML) is progressively being integrated into materials science, exhibiting great potential for optimizing chemical synthesis and structural regulation, thereby accelerating intelligent design and efficient exploration of novel materials. Carbon-based emitters (CBEs), as emerging functional materials, have attracted considerable attention due to their tunable photoluminescence properties, abundant precursor sources, and structural versatility. To date, extensive research on CBEs has generated a substantial data foundation, laying the groundwork for ML driven structural screening and property prediction. Although the application of ML in CBEs remains in its early stages compared to that of inorganic semiconductors and organic-inorganic hybrid perovskites, its potential to accelerate material screening and reveal structure-property relationships is becoming increasingly evident. Given the transformative role ML has played in other functional materials, it is expected to drive a paradigm shift in CBEs research from conventional trial-and-error approaches to data-driven, intelligence-guided design, substantially accelerating material discovery and expanding their functional applications. Therefore, this review systematically summarizes recent advances in ML applications in CBEs, focusing on the general ML workflow, property prediction and structural design strategies for organic small-molecules and carbon dots (CDs), and their applications in organic light-emitting diodes (OLEDs), quantum dot light-emitting diodes (QLEDs), information encryption, biomedicine, and sensing. Finally, this review discusses the key challenges currently facing the field and offers perspectives on future directions for ML-driven CBEs research, aiming to provide guidance for the rational design and efficient development of such materials.
Electro-osmotic dewatering (EOD) is a promising technology for enhanced sludge dewatering and volume reduction. However, its engineering application is constrained by multiphysics coupling, partially observed internal states, sludge variability, and trade-offs among dewatering efficiency, energy consumption, treatment time, and electrode stability. Machine learning (ML) offers opportunities to represent nonlinear process behavior, estimate difficult-to-measure states, and support optimization and control. Nevertheless, existing studies remain fragmented and lack standardized feature definitions and data-reporting practices, task-oriented workflows, cross-condition validation, and consistent mechanistic interpretation. This review links EOD mechanisms and process-variable evolution to specific ML requirements and organizes applications into four categories, namely point prediction, time-series forecasting, visual soft sensing, and multi-objective optimization. The suitability of different ML methods is critically examined, with emphasis on hybrid and physics-informed modeling, interpretability, uncertainty evaluation, and generalization under limited-data conditions. Four interrelated priorities are identified for developing reliable and deployable ML-enabled EOD systems. The first is to standardize features, metadata, and benchmark evaluation, and the second is to integrate data-driven models with physical constraints. The third is to strengthen external validation, model transferability, and uncertainty quantification, and the fourth is to advance toward intelligent closed-loop EOD systems. These priorities can be implemented through short-, medium-, and long-term stages, progressing from reproducible data foundations through transferable models to adaptive engineering systems. By distinguishing direct EOD evidence from transferable methodological examples, this review provides a task-oriented and deployment-aware roadmap for credible ML-enabled EOD research.
Xing Zhang, Yu Huang, Yafei Shi et al.· Waste Management· 0 citations
Artificial intelligence (AI) has emerged as a transformative technology capable of addressing complex engineering challenges through advanced data-driven modeling, prediction, and optimization techniques. In the context of sustainable energy systems, hydrogen production via water electrolysis has attracted considerable attention as a promising pathway toward carbon-neutral energy generation. However, the widespread deployment of electrolyzer technologies remains constrained by challenges related to energy efficiency, operational stability, system degradation, and dynamic process control. In response, machine learning (ML) techniques have increasingly been integrated into electrolyzer systems to enhance performance prediction, adaptive control, predictive maintenance, and operational optimization. This review presents a comprehensive and engineering-oriented analysis of recent advancements in ML applications for hydrogen production via electrolysis. The study first outlines the fundamental principles of ML, including major learning paradigms, data processing approaches, and commonly adopted algorithms for electrochemical systems. Subsequently, the review critically examines ML-driven strategies for hydrogen production optimization, hyperparameter tuning, intelligent process control, system design enhancement, and degradation monitoring in electrolyzer technologies such as Proton Exchange Membrane Water Electrolyzers (PEMWE) and Anion Exchange Membrane Water Electrolyzers (AEMWE). Comparative analysis of algorithms including Artificial Neural Networks (ANN), Support Vector Machines (SVM), Reinforcement Learning (RL), and Physics-Informed Neural Networks (PINN) is also discussed from both electrochemical and engineering perspectives. Furthermore, current challenges involving data quality, model interpretability, computational complexity, and industrial deployment are critically evaluated. Overall, this review provides strategic insights into future intelligent electrolyzer systems and highlights critical research directions for scalable and sustainable green hydrogen production.
Muhammad Asyraf Abdullah, A. Sulong, E. Majlan et al.· Jurnal Kejuruteraan· 0 citations
The intersection of machine learning (ML) and electrochemical research is catalyzing transformative advancements in energy storage and conversion technologies. This review critically examines the role of ML and deep learning (DL) in optimizing electrochemical systems, focusing on batteries, supercapacitors, fuel cells, and sensors. ML-driven approaches facilitate accelerated material discovery, precise property predictions, and enhanced device performance monitoring, surpassing conventional trial-and-error methodologies. Integrating computational materials science, including density functional theory (DFT) and molecular dynamics (MD), with ML enables predictive modelling of electrochemical processes at an unprecedented scale. However, challenges such as data heterogeneity, model interpretability, and computational cost continue to limit widespread adoption. This review identifies key strategies to overcome these barriers, including establishing standardized data repositories, developing hybrid physics-informed ML models, and implementing explainable AI (XAI) for enhanced model transparency. By addressing these challenges, ML has the potential to drive the next wave of breakthroughs in electrochemical energy storage and conversion, accelerating the transition toward a sustainable and energy-secure future.
Unknown authors· Journal of the Electrochemic...· 0 citations
Two‐Stage Material Screening (TSMS) is developed, an AI‐driven framework that integrates density functional theory (DFT) computations, an active‐learning‐guided experimental feedback loop, and mechanistic interpretation to enable rapid discovery and systematic evaluation of promising electrocatalysts.
Xueyu Hu, Yucun Zhou, Haoyu Li et al.· Advances in Materials· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
