Hyperspectral in situ remote sensing of water surface nitrate in the Fitzroy River estuary, Queensland, Australia, using deep learning

TL;DR

This study demonstrates that hyperspectral remote sensing combined with deep learning can accurately predict water surface nitrate levels in estuarine environments, aiding monitoring of nutrient pollution affecting coral reefs.

Contribution

It introduces a novel approach integrating hyperspectral reflectance and salinity data with deep learning to estimate nitrate concentrations in estuarine waters.

Findings

Predicted nitrate correlated with in-situ measurements with R^2 of 0.86.

Hyperspectral reflectance effectively indicates optically active water quality parameters.

The method enables non-invasive, real-time nitrate monitoring in estuaries.

Abstract

Nitrate ($\text{NO}_3^-$) is a form of dissolved inorganic nitrogen derived primarily from anthropogenic sources. The recent increase in river-discharged nitrate poses a major risk for coral bleaching in the Great Barrier Reef (GBR) lagoon. Although nitrate is an optically inactive (i.e., colourless) constituent, previous studies have demonstrated there is an indirect, non-causal relationship between water surface nitrate and water-leaving reflectance that is mediated through optically active water quality parameters such as total suspended solids and coloured dissolved organic matter. This work aims to advance our understanding of this relationship with an effort to measure time-series nitrate and simultaneous hyperspectral reflectance at the Fitzroy River estuary, Queensland, Australia. Time-series observations revealed periodic cycles in nitrate loads due to the tidal influence in the estuarine study site. The water surface nitrate loads were predicted from hyperspectral reflectance and water salinity measurements, with hyperspectral reflectance indicating the concentrations of optically active variables and salinity indicating the mixing of river water and seawater proportions. The accuracy assessment of model-predicted nitrate against in-situ measured nitrate values showed that the predicted nitrate values correlated well with the ground-truth data, with an $R^2$ score of 0.86, and an RMSE of 0.03 mg/L. This work demonstrates the feasibility of predicting water surface nitrate from hyperspectral reflectance and salinity measurements.