Spatiotemporal patterns and driving factors of nitrogen concentrations in Daya bay via remote sensing

Excessive nitrogen concentrations may degrade coastal ecosystems, potentially causing harmful algae blooms and hypoxia. Total nitrogen (TN) and dissolved inorganic nitrogen (DIN) are key indicators for assessing external nitrogen loads and eutrophication. However, long-term, high-resolution data on coastal nitrogen dynamics remain limited because of sparse monitoring. To address this gap, Landsat-5/7/8/9 imagery (1986-2024) was integrated with in situ measurements to develop and compare multiple inversion models. A Gaussian process regression model (training/test root mean square error: TN = 0.16/0.14 mg/L; DIN = 0.09/0.09 mg/L) was selected to reconstruct nitrogen concentrations in Daya Bay. Throughout the study period, it revealed average TN and DIN concentrations of 0.50 and 0.23 mg/L respectively, with notable spatial clustering near estuaries and coastal waters. Change point analysis revealed abrupt shifts in 2013 (TN) and 1998 (DIN), but the Mann-Kendall test results indicated no significant long-term monotonic trends. Integrated analysis with meteorological data suggested that extreme rainfall events cause short-term spikes in nutrient levels, whereas seasonal regulation causes higher concentrations during the dry season. Comparative analyses of functional zones revealed that estuarine areas exhibited the highest nitrogen concentrations, with average TN and DIN concentrations of 0.75 and 0.44 mg/L, respectively. The variations among different zones were associated with changes in the coastline, land use, wastewater discharge, and fertilizer application. Attribution analysis based on the SHapley Additive exPlanations method indicated that domestic wastewater is the primary driver. This study provides a framework for assessing coastal nitrogen dynamics, with concurrent TN/DIN monitoring supporting future precision management of nitrogen sources in eutrophication control.