MC-OIWQR: Multimodal Contrastive Learning for Optically Inactive Water Quality Retrieval

Retrieving optically inactive nutrients from satellite observations remains challenging because TN, TP, and NH3-N are only indirectly linked to water reflectance and may respond to different environmental contexts. Here, we propose MC-OIWQR, a multimodal framework that combines spatiotemporal contrastive learning from unlabeled HLS Sentinel-2 imagery with meteorological, land-use, and nighttime-light information through cross-attention fusion. Evaluated on long-term in situ observations from Lake Ontario, the framework was analyzed through modality ablation and SHAP-based attribution. Across 10 repeated stratified data partitions, MC-OIWQR achieved mean test R2 values of 0.9208, 0.8663, and 0.9409 for TN, TP, and NH3-N, respectively, obtaining the highest mean R2 and lowest mean RMSE among the evaluated baselines. SHAP-based analysis suggested that TN predictions were associated with land-use and nighttime-light proxies of watershed anthropogenic activity, TP predictions with hydrometeorological forcing related to precipitation and wind, and NH3-N predictions with multivariate environmental context, indicating parameter-specific attribution patterns in the trained model. Long-term retrieval maps from 2016 to 2025 revealed persistent nearshore–offshore nutrient gradients and event-driven variability in Quinte Bay. Cross-lake experiments on Lake Huron and Lake Erie provided preliminary evidence that MC-OIWQR may be adapted through lake-specific re-pretraining for TN and TP retrieval. These results suggest that optically inactive nutrient retrieval benefits from parameter-specific multimodal information rather than a uniform optical regression strategy.