Predicting Wetland Nitrogen Levels Through Microbial Signatures: A Taxonomy-Based Approach Validated by Machine Learning

Wetland ecosystems harbour diverse microbial communities that play a key role in regulating biogeochemical cycles, yet their potential to predict abiotic soil conditions remains underexplored. This study investigates whether microbial community composition can be used to infer environmental conditions, focusing on five abiotic factors: pH, calcium, total carbon, respiration, and total nitrogen. Using 16S rRNA amplicon sequencing data processed in QIIME2, total nitrogen emerged as the only abiotic factor significantly associated with microbial alpha and beta diversity. Low-nitrogen wetlands exhibited greater microbial richness and evenness, while high-nitrogen soils were dominated by fewer, specialized taxa. Core microbiome and indicator species analyses identified eight indicator species that were uniquely linked to either high- or low-nitrogen conditions, reflecting distinct microbial signatures tied to nitrogen availability. These indicator species were used to train a Random Forest model that classified nitrogen levels with high levels of accuracy. Overall, microbial signatures proved to be reliable bioindicators of nitrogen conditions, and this machine learning-driven, taxonomy-based framework offers practical applications in ecological monitoring, precision agriculture, and sustainable land management.