Hyun‐Seob Song

Modeling Microbial Regulatory Feedback in Organic Matter Decomposition Identifies Copiotrophic Traits as Key Drivers of Positive Priming

This paper models microbial regulatory feedback in organic matter decomposition, finding copiotrophic traits drive positive priming effects.

Harnessing artificial intelligence to automate environmental predictions

The paper uses AI to iteratively improve environmental predictions by combining field sampling with machine learning, significantly enhancing sediment oxygen consumption forecasts across the U.S.

Diversity in Chemical Subunits and Linkages: A Key Molecular Determinant of Microbial Richness, Microbiota Interactions, and Substrate Utilization

The paper develops a novel measure, CheSL Shannon diversity, to quantify carbohydrate complexity's effects on microbial diversity, interactions, and function in human fecal samples.

Coupling Flux Balance Analysis with Reactive Transport Modeling through Machine Learning for Rapid and Stable Simulation of Microbial Metabolic Switching

The paper develops an ANN-based reduced-order model to accelerate FBA integration with RTMs, enabling efficient simulation of microbial metabolic switching in Shewanella oneidensis.

Kinetics-based Inference of Environment-Dependent Microbial Interactions and Their Dynamic Variation

The paper introduces a framework to model environment-dependent microbial interactions using growth kinetics and Lotka-Volterra models, validated with synthetic E. coli data.

ModelSEED v2: High-throughput genome-scale metabolic model reconstruction with enhanced energy biosynthesis pathway prediction

ModelSEED v2 improves genome-scale metabolic model reconstruction with enhanced energy metabolism and better pathway curation, leading to more accurate and comprehensive models.

Representing Organic Matter Thermodynamics in Biogeochemical Reactions via Substrate-Explicit Modeling

This paper introduces a new biogeochemical modeling approach that explicitly represents organic matter thermodynamics to improve predictions of microbial degradation processes and their environmental impacts.