Dissolved oxygen (DO) serves as a pivotal indicator, mirroring the intrinsic self-purification capacity of aquatic ecosystems and the overarching quality of the water environment. In the context of the Yangtze Estuary, a crucial hub for biodiversity and economic activities in China, understanding and forecasting levels of DO is instrumental for effective environmental stewardship and management strategies. Considering this, the introduction of sophisticated machine learning algorithms into the monitoring and predictive analytics of dissolved oxygen levels represents an important stride toward leveraging the power of data-driven insights for environmental sustainability. The Yangtze Estuary, characterized by its dynamic and complex hydrological and ecological systems, demands an insightful and nuanced approach to monitoring water quality parameters. To this end, six key monitoring stations were chosen across the estuary, including Xuliujing, Nantong Port, Qidong Port, Qinglong Port, South Port, and North Port, acting as sentinel sites for gauging the health of the water body. Leveraging three cutting-edge modeling techniques-particle swarm optimization-support vector regression (PSO-SVR), artificial neural network (ANN), and random forest (RF)-the research unraveled and forecasted the patterns of dissolved oxygen levels using monthly average water quality data spanning from 2004 to 2020. These models embodied the forefront of machine learning technology, each bringing distinct analytical strengths and perspectives to the table, from the nuanced, non-linear pattern recognition capabilities of ANN to the robustness and interpretability of RF. The meticulous evaluation conducted via the RF model underscored the paramount importance of three water quality variables, namely temperature, five-day biochemical oxygen demand, and ammonia nitrogen, in influencing the spatial-temporal dynamics of dissolved oxygen in the estuary. Comparative analysis of the prediction results yielded by the PSO-SVR, ANN, and RF models illuminated the superior performance of the RF model across the six monitoring stations, with an overall average error margin of 0.19, a testament to its efficacy and reliability. In comparison, the PSO-SVR and ANN models exhibited higher error rates of 0.38 and 0.47, respectively, albeit still contributing valuable insights into the complex dissolved oxygen dynamics in the Yangtze Estuary. The prediction performance of the machine learning models was evaluated, and the overall prediction performance ranking on the training set was RF (=0.971; RMSE=0.341 mg·L) > PSO-SVR (=0.884; RMSE=0.707 mg·L) > ANN (=0.792; RMSE=0.967 mg·L). The overall prediction performance ranking on the test set was RF ( = 0.986; RMSE=0.165 mg·L) > PSO-SVR (=0.951; RMSE=0.332 mg·L) > ANN (=0.800; RMSE=0.633 mg·L). Therefore, the RF model exhibited the best predictive ability on all monitoring sections, showing excellent performance and generalization ability both on the training and the test sets. The PSO-SVR model also performed well on most monitored profiles, with slightly lower predictive performance than that of the RF model though with better stability and generalization ability. However, the ANN model did not perform as perfectly as the other two models in some monitoring profiles and its network structure or parameters may need to be further optimized to improve the prediction accuracy and stability.

Download full-text PDF

Source
http://dx.doi.org/10.13227/j.hjkx.202312111DOI Listing

Publication Analysis

Top Keywords

dissolved oxygen
24
yangtze estuary
12
machine learning
12
water quality
12
prediction performance
12
oxygen levels
8
monitoring stations
8
pso-svr ann
8
ann models
8
performance model
8

Similar Publications

Identifying associations of water quality parameters using cluster analysis: A case study of Biscayne Bay, USA.

Mar Pollut Bull

December 2024

Department of Chemical, Environmental, and Materials Engineering, University of Miami, Coral Gables, FL 33146. Electronic address:

Correlation and cluster analysis protocols for analyzing multiple-parameter water-quality data sets are presented and demonstrated. A novel cluster analysis methodology is developed that identifies parameters that are either directly or indirectly correlated. Application of these analyses was demonstrated using multi-parameter water-quality measurements in Biscayne Bay and the primary drainage canals in South Florida.

View Article and Find Full Text PDF

Water pollution caused by ash from grassland fires alters the molecular, biochemical, and morphological biomarkers of non-biting midge larvae.

J Hazard Mater

December 2024

Post-graduation program in Ecology and Biodiversity Conservation, Federal University of Mato Grosso (UFMT), Mato Grosso, MT 78060-900, Brazil; Post-graduation program in Ecology. Department of Ecology and Zoology, Laboratory of Freshwater Biodiversity, Federal University of Santa Catarina (UFSC), Florianópolis, SC 88040-900, Brazil.

The frequency and intensity of wildfires have been increasing in many parts of the world, which may result in biodiversity loss. Wildfires can devastate plant communities, generating toxic ash that pollutes watercourses through runoff. However, our understanding of the effects of ash exposure on aquatic biodiversity is still limited.

View Article and Find Full Text PDF

Isotopes unveil overestimation of nutrient-driven oxygen deficit in the tidal rivers of Pearl River Delta during the wet season.

Sci Total Environ

December 2024

The Key Laboratory of Water and Air Pollution Control of Guangdong Province, South China Institute of Environmental Sciences, Ministry of Ecology and Environment, Guangzhou 510530, China; National Key Laboratory of Water Environment Simulation and Pollution Control, South China Institute of Environmental Science, Ministry of Ecology and Environment, Guangzhou 510535, China. Electronic address:

A low dissolved oxygen (DO) concentration in summer has been observed in river-estuary systems worldwide. Many studies have caused our stereotype that biochemical oxygen depletion was higher in summer than in winter; however, there was no direct evidence particularly in the tidal river with complex hydrological and biochemical processes. This study employed natural-abundance and labeled isotopes to quantify seasonal apportionment of biochemical oxygen depletion.

View Article and Find Full Text PDF

Tritium, a radioactive isotope produced naturally through cosmic radiation interactions and anthropogenically through nuclear weapons testing, poses potential environmental risks, particularly within the water cycle. This study measured tritium concentrations in surface water across Thailand to establish a baseline dataset for monitoring potential contamination from nuclear activities and accidents. Surface water samples were collected from 14 large reservoirs during the wet season in October 2023 and the dry season in February 2024, providing a total of 28 samples.

View Article and Find Full Text PDF

Towards the standardization of Hydra vulgaris bioassay for toxicity assessments of liquid samples.

Ecotoxicol Environ Saf

December 2024

Aquatic Contaminants Research Division, Environment and Climate Change Canada, Montréal, Québec, Canada. Electronic address:

The Hydra vulgaris bioassay is recognized as sensitive invertebrate test species for toxicity assessment of real-life environmental mixtures for enforcement and monitoring investigations. The purpose of this study was to characterize the intra-laboratory variability, study the influence of environmental variables (temperature, luminosity, inter-individual and day of analysis) on ZnSO toxicity, a reference model toxicant for hydra. The sublethal (effect concentration for 50 % of hydra-EC50) and lethal (lethal concentration for 50 % of hydra-LC50) were determined based on characteristic morphological changes for this species.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!