Nutrient thresholds to protect water quality, coral reefs, and nearshore fisheries

Assessing Derawan Island's Coral Reefs over Two Decades: A Machine Learning Classification Perspective

This study aims to understand the dynamic changes in the coral reef habitats of Derawan Island over two decades (2003, 2011, and 2021) using advanced machine learning classification techniques. The motivation stems from the urgent need for accurate, detailed environmental monitoring to inform conservation strategies, particularly in ecologically sensitive areas like coral reefs. We employed non-parametric machine learning algorithms, including Random Forest (RF), Support Vector Machine (SVM), and Classification and Regression Tree (CART), to assess spatial and temporal changes in coral habitats. Our analysis utilized high-resolution data from Landsat 9, Landsat 7, Sentinel-2, and Multispectral Aerial Photos. The RF algorithm proved to be the most accurate, achieving an accuracy of 71.43% with Landsat 9, 73.68% with Sentinel-2, and 78.28% with Multispectral Aerial Photos. Our findings indicate that the classification accuracy is significantly influenced by the geographic resolution and the quality of the field and satellite/aerial image data. Over the two decades, there was a notable decrease in the coral reef area from 2003 to 2011, with a reduction to 16 hectares, followed by a slight increase in area but with more heterogeneous densities between 2011 and 2021. The study underscores the dynamic nature of coral reef habitats and the efficacy of machine learning in environmental monitoring. The insights gained highlight the importance of advanced analytical methods in guiding conservation efforts and understanding ecological changes over time.

Localising terrestrially derived pollution inputs to threatened near-shore coral reefs through stable isotope, water quality and oceanographic analysis

Near-shore coral reefs are at high-risk of exposure to pollution from terrestrial activities. Pollution impacts can vary with site-specific factors that span sources, rainfall and oceanographic characteristics. To effectively manage pollution, we need to understand how these factors interact. In this study, we detect terrestrially derived nutrient inputs on near-shore reefs at Norfolk Island, South Pacific by analysis of dissolved inorganic nitrogen (DIN) and stable isotopes. When compared to a reef site with predominantly oceanic inputs, we found that both the lagoon and a small reef adjacent to a catchment have signatures of human-derived DIN shown through depleted δ¹⁵N signatures in macroalgae. We find pollution exposure of reef sites is associated with known and unknown sources, rainfall and mixing of water with the open ocean. In characterising exposure of reef sites we highlight the role of site-specific context in influencing pollution exposure for benthic communities even in remote island systems.

Response of coral bacterial composition and function to water quality variations under anthropogenic influence

Microbial communities play key roles in the adaptation of corals living in adverse environments, as the microbiome flexibility can enhance environmental plasticity of coral holobiont. However, the ecological association of coral microbiome and related function to locally deteriorating water quality remains underexplored. In this work, we used 16S rRNA gene sequencing and quantitative microbial element cycling (QMEC) to investigate the seasonal changes of bacterial communities, particularly their functional genes related to carbon (C), nitrogen (N), phosphorus (P) and sulfur (S) cycle, of the scleractinian coral Galaxea fascicularis from nearshore reefs exposed anthropogenic influence. We used nutrient concentrations as the indicator of anthropogenic activities in coastal reefs, and found a higher nutrient pressure in spring than summer. The bacterial diversity, community structure and dominant bacteria of coral shifted significantly due to seasonal variations dominated by nutrient concentrations. Additionally, the network structure and nutrient cycling gene profiles in summer under low nutrient stress was distinct from that under poor environmental conditions in spring, with lower network complexity and abundance of CNPS cycling genes in summer compared with spring. We further identified significant correlations between microbial community (taxonomic composition and co-occurrence network) and geochemical functions (abundance of multiple functional genes and functional community). Nutrient enrichment was proved to be the most important environmental fluctuation in controlling the diversity, community structure, interactional network and functional genes of the coral microbiome. These results highlight that seasonal shifts in coral-associated bacteria due to anthropogenic activities alter the functional potentials, and provide novel insight about the mechanisms of coral adaptation to locally deteriorating environments.