A5083550503- Machine Learning in Materials Science
- Catalysts for Methane Reforming
- Carbon Dioxide Capture Technologies
- Thermochemical Biomass Conversion Processes
- Digital Transformation in Industry
- Subcritical and Supercritical Water Processes
- Municipal Solid Waste Management
- Biodiesel Production and Applications
- Advanced Combustion Engine Technologies
- CO2 Reduction Techniques and Catalysts
- Covalent Organic Framework Applications
- Data Quality and Management
- Membrane Separation and Gas Transport
- Petroleum Processing and Analysis
- Energy Efficiency and Management
- Lubricants and Their Additives
- Energy and Environment Impacts
- Anaerobic Digestion and Biogas Production
- Electrocatalysts for Energy Conversion
- COVID-19 impact on air quality
- Building Energy and Comfort Optimization
- Fluid Dynamics and Mixing
- Ergonomics and Human Factors
- Energy Load and Power Forecasting
- Adsorption and biosorption for pollutant removal
ETH Zurich
2022-2025
Institute of Catalysis and Petrochemistry
2025
Saveetha University
2023
National University of Singapore
2020-2022
Biochar application is a promising strategy for the remediation of contaminated soil, while ensuring sustainable waste management. heavy metal (HM)-contaminated soil primarily depends on properties biochar, and HM. The optimum conditions HM immobilization in biochar-amended soils are site-specific vary among studies. Therefore, generalized approach to predict efficiency required. This study employs machine learning (ML) approaches biochar soils. nitrogen content (0.3–25.9%) rate (0.5–10%)...
Biomass waste-derived porous carbons (BWDPCs) are a class of complex materials that widely used in sustainable waste management and carbon capture. However, their diverse textural properties, the presence various functional groups, varied temperatures pressures to which they subjected during CO2 adsorption make it challenging understand underlying mechanism adsorption. Here, we compiled data set including 527 points collected from peer-reviewed publications applied machine learning...
In industrial steel plate production, process parameters and grade composition significantly influence the microstructure mechanical properties of produced. But determining exact relationship between is a challenging process. This work aimed to devise deep learning model, predict including yield strength (YS), ultimate tensile (UTS), elongation (EL), impact energy (Akv); based on as well raw steel, apply it online real manufacturing plant. An optimal neural network (DNN) model was formulated...
Biomass waste-derived engineered biochar for CO2 capture presents a viable route climate change mitigation and sustainable waste management. However, optimally synthesizing them enhanced performance is time- labor-intensive. To address these issues, we devise an active learning strategy to guide expedite their synthesis with improved adsorption capacities. Our framework learns from experimental data recommends optimal parameters, aiming maximize the narrow micropore volume of biochar, which...
With the concepts of Industry 4.0 and smart manufacturing gaining popularity, there is a growing notion that conventional will witness transition toward new paradigm, targeting innovation, automation, better response to customer needs, intelligent systems. Within this context, review focuses on concept cyber–physical production system (CPPS) presents holistic perspective role CPPS in three key essential drivers transformation: data-driven manufacturing, decentralized integrated blockchains...
Rhodium-based catalysts offer remarkable selectivities toward higher alcohols, specifically ethanol, via syngas conversion. However, the addition of metal promoters is required to increase reactivity, augmenting complexity system. Herein, we present an interpretable machine learning (ML) approach predict and rationalize performance Rh-Mn-P/SiO2 (P = 19 promoters) using open-source dataset on Rh-catalyzed alcohol synthesis (HAS) from Pacific Northwest National Laboratory (PNNL). A random...
Synthesis protocol exploration is paramount in catalyst discovery, yet keeping pace with rapid literature advances increasingly time intensive. Automated synthesis analysis attractive for swiftly identifying opportunities and informing predictive models, however such applications heterogeneous catalysis remain limited. In this proof-of-concept, we introduce a transformer model task, exemplified using single-atom catalysts (SACs), rapidly expanding family. Our adeptly converts SAC protocols...
Developing efficient catalysts for syngas-based higher alcohol synthesis (HAS) remains a formidable research challenge. The chain growth and CO insertion requirements demand multicomponent materials, whose complex reaction dynamics extensive chemical space defy catalyst design norms. We present an alternative strategy by integrating active learning into experimental workflows, exemplified via the FeCoCuZr family. Our data-aided framework streamlines navigation of composition condition in 86...
With ‘smart’ being the order of day, shift in landscape a typical production‐oriented manufacturing environment to more data‐oriented, automated and smart is imminent. However, what meant by manufacturing? And how can contribute bigger picture acting as enablers cities? Given paucity literature that seeks make sense this direction, herein, first, six indices represent or define city are identified. Then, holistic perspective presented collectively dwelling into concepts cyber physical...
Hydrothermal gasification is an effective and economic technology for production of combustible gases valuable chemicals from wet wastes.In the present work, machine learning (ML), a data-driven approach, employed to predict composition syngas in terms H2, CH4, CO2, CO).A gradient boosting regression (GBR) model with optimal hyperparameters was developed prediction test R 2 0.92, 0.90, 0.95, 0.92 CO prediction, respectively.This ML framework provides useful inference, identify correlation...
As the COVID-19 continues to disrupt global norms, there is requirement of modeling frameworks accurately assess and quantify impact pandemic on electricity sector its emissions. In this study, we devise machine learning models estimate induced reduction in consumption based weather, econometrics, social-distancing parameters for seven major Indian states. per our baseline model, find that dropped by 15–33% 2020 (March-May) during complete lockdown phase, followed 6–13% (June-August) unlock...