Machine Learning-Driven Prediction of Quality Water in the Ebro River from the Ascó Water Quality Monitoring Station Data, Northeast Spain
Source abstract
Abstract
Continuous monitoring of river water quality is essential for understanding hydro-chemical dynamics and supporting adaptive water resource management. This study develops a Gaussian Process Regression (GPR) model with a Matern32 kernel, optimized via the Nelder–Mead (NM) algorithm, to predict turbidity, electrical conductivity, and UV254 absorbance in the Ebro River (Spain), without considering temporal dependencies. The Matern 32 kernel was selected for its ability to model the non-smooth, heterogeneous variability of water quality parameters, and its hyperparameters were tailored to each indicator, revealing unique spatial scales of variability. Using 46,287 high-frequency observations, the model achieves Nash–Sutcliffe Efficiency (NSE) values of 0.8956, 0.9503, and 0.9180 for turbidity, conductivity, and absorbance, respectively. Feature importance analysis reveals flow rate and nitrates as dominant drivers. The GPR framework outperforms multilayer perceptron (MLP), multivariate linear regression (MLR), and M5 model tree (M5P), demonstrating its potential for real-time water quality monitoring.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Hydrological Forecasting Using AI · Water Quality and Pollution Assessment · Water Quality Monitoring Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Mathematics, Faculty of Sciences, University of Oviedo, C/Leopoldo Calvo Sotelo, 18, 33007 Oviedo, Spain
Cantabrian Basin Authority, Spanish Ministry for the Ecological Transition and Demographic Challenge, 33071 Oviedo, Spain
Asturias Water Consortium, C/Santa Susana 15, 33007 Oviedo, Spain
References (83)
Show source-provided references
1. Machine Learning Based Water Quality Evolution and Pollution Identification in Reservoir Type Rivers10.1016/j.envpol.2025.126668 ↗
2. Modeling the Impact of Potentially Harmful Elements on the Groundwater Quality of a Mining Area (Nigeria) by Integrating NSFWQI, HERisk Code, and HCs10.1007/s10661-022-09789-w ↗
3. HERisk and Statistical Clustering Integrated for Health Risk Modelling of PTEs in Natural Water Resources for Drinking and Sanitary Uses10.1080/15569543.2024.2371874 ↗
4. Spatial-Temporal Evolution Analysis of Pollutants in Daitou River Watershed Based on Sentinel-2 Satellite Images10.1016/j.ecolind.2024.112436 ↗
5. Walling, D.E., and Webb, B.W. (1981). The Reliability of Suspended Sediment Load Data. Proceedings of the Florence Symposium, Erosion and Sediment Transport Measuremen, IAHA Publ.
6. Hem, J.D. (1985). Study and Interpretation of the Chemical Characteristics of Natural Water.
7. Evaluation of Specific Ultraviolet Absorbance as an Indicator of the Chemical Composition and Reactivity of Dissolved Organic Carbon10.1021/es030360x ↗
8. Assessment of Surface Water Quality Based on Physical and Chemical Parameters in a GIS, for Three Rivers in Southern Brazil10.1016/j.envpol.2025.126295 ↗
9. Global Water Scarcity Including Surface Water Quality and Expansions of Clean Water Technologies10.1088/1748-9326/abbfc3 ↗
10. Water Contamination and Human Health Risks in Pakistan: A Review10.1007/s12403-022-00512-1 ↗
11. The Quality of Rivers: From Pristine Stage to Global Pollution10.1016/0921-8181(89)90007-6 ↗
12. Nitrogen, Phosphorus, and Eutrophication in Streams10.5268/IW-6.2.909 ↗
13. Wetzel, R.G. (2011). Limnology: Lake and River Ecosystems, Academic Press. [3rd. ed.].
14. Machine Learning Approach for Water Quality Predictions Based on Multispectral Satellite Imageries10.1016/j.ecoinf.2024.102868 ↗
15. A Critical Review of Statistical, Signal Processing and Machine Learning Methods for Continuous and High-Frequency Water Quality Data Improvement10.1016/j.ecoinf.2026.103619 ↗
16. Integrating Modeling, Monitoring, and Management to Reduce Critical Uncertainties in Water Resource Decision Making10.1016/j.jenvman.2016.03.015 ↗
17. Hou, Y., Miao, C., Zhu, D., Li, Z., Du, F., Wang, W., Yang, X., and Cao, Z. (2026). Flow Mechanism of Grouting Slurry in Rough Fracture Based on CFD-DEM Coupling Method. Processes, 14.10.3390/pr14081307 ↗
18. Cao, Z., Miao, C., Du, F., Zhu, D., Teng, T., and Xue, Y. (2026). A Bifurcation Dynamical Analysis of a Non-Darcy Seepage System in Post-Failure Rock Based on a Novel Truncated Spectral Method. Processes, 14.10.3390/pr14091468 ↗
19. Vapnik, V.N. (1998). Statistical Learning Theory, Wiley. Adaptive and learning systems for signal processing, communications, and control.
20. Hastie, T., Tibshirani, R., and Friedman, J.H. (2003). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer.
21. Rasmussen, C.E., and Williams, C.K.I. (2006). Gaussian Processes for Machine Learning, MIT Press. Adaptive computation and machine learning.10.7551/mitpress/3206.001.0001 ↗
22. Schneider, M., and Ertel, W. (2010). Robot Learning by Demonstration with Local Gaussian Process Regression. Proceedings of the 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, Taipei, Taiwan, 18–22 October 2010, IEEE.10.1109/IROS.2010.5650949 ↗
23. Shi, J.Q., and Choi, T. (2011). Gaussian Process Regression Analysis for Functional Data, Chapman and Hall/CRC.10.1201/b11038 ↗
24. Ebden, M. (2015). Gaussian Processes: A Quick Introduction. arXiv.
25. A Survey on Gaussian Processes for Earth-Observation Data Analysis: A Comprehensive Investigation10.1109/MGRS.2015.2510084 ↗
26. Vidales, A. (2019). Machine Learning with Matlab: Gaussian Process Regression, Analysis of Variance and Bayesian Optimization, Independently published.
27. Design Optimization and ML-Based Performance Prediction of Microgrid-Hydrogen Refueling Systems Using Gaussian Process Regression10.1016/j.ijhydene.2025.150382 ↗
28. Combining Electrochemistry and Data-Sparse Gaussian Process Regression for Lithium-Ion Battery Hybrid Modeling10.1016/j.apenergy.2025.126458 ↗
29. An Efficient Prediction Method for Wind Loads on Container Ships Based on Numerical Simulation and Gaussian Process Regression10.1016/j.oceaneng.2025.123384 ↗
30. Springback Estimation in Incremental Sheet Metal Forming Using the Gaussian Process Regression Model
31. Improving Soil Moisture Prediction Using Gaussian Process Regression
32. Gaussian Process Regression on Multiple Drivers and Attributes for Rapid Prediction of Maximum Flood Inundation Extent and Depth10.1016/j.jhydrol.2024.132476 ↗
33. Agrawal, T. (2021). Hyperparameter Optimization in Machine Learning: Make Your Machine Learning and Deep Learning Models More Efficient, Apress.10.1007/978-1-4842-6579-6 ↗
34. Aggarwal, C.C. (2020). Linear Algebra and Optimization for Machine Learning: A Textbook, Springer.10.1007/978-3-030-40344-7 ↗
35. Random Search for Hyper-Parameter Optimization
36. Chong, E.K.P. (2013). An Introduction to Optimization, Wiley. [4th ed.].
37. Kennedy, J., Eberhart, R.C., and Shi, Y. (2009). Swarm Intelligence, Morgan Kaufmann. [8th ed.].
38. Hassoun, M.H. (1995). Fundamentals of Artificial Neural Networks, MIT Press. A Bradford book.
39. Haykin, S.S. (1999). Neural Networks: A Comprehensive Foundation, Prentice-Hall. [2nd ed.].
40. Fine, T.L. (1999). Feedforward Neural Network Methodology, Springer. Statistics for engineering and information science.
41. Shepherd, A.J. (1997). Second-Order Methods for Neural Networks: Fast and Reliable Training Methods for Multi-Layer Perceptrons, Springer. Perspectives in neural computing.10.1007/978-1-4471-0953-2 ↗
42. Vang-Mata, R. (2020). Multilayer Perceptrons: Theory and Applications, Nova Science Publishers. Computer science, technology and applications.
43. Weisberg, S. (2014). Applied Linear Regression, Wiley. [4th ed.].
44. Fox, J., and Fox, J. (2016). Applied Regression Analysis and Generalized Linear Models, SAGE. [3rd ed.].
45. Roback, P., and Legler, J. (2020). Beyond Multiple Linear Regression: Applied Generalized Linear Models and Multilevel Models, CRC Press. [1st ed.]. Chapman and Hall Texts in Statistical Science.10.1201/9780429066665 ↗
46. Montgomery, D.C., Peck, E.A., and Vining, G.G. (2021). Introduction to Linear Regression Analysis, Wiley. [6th ed.].
47. Stone, J.V. (2022). Linear Regression: A Tutorial Introduction to the Mathematics of Regression Analysis, Sebtel Press.
48. Learning with Continuous Classes
49. Mitchell, T.M. (2013). Machine Learning, McGraw-Hill.
50. Pan Evaporation Modeling Using Least Square Support Vector Machine, Multivariate Adaptive Regression Splines and M5 Model Tree10.1016/j.jhydrol.2015.06.052 ↗
51. M5 Model Trees and Neural Networks: Application to Flood Forecasting in the Upper Reach of the Huai River in China10.1061/(ASCE)1084-0699(2004)9:6(491) ↗
52. A Comparison Between Conventional and M5 Model Tree Methods for Converting Pan Evaporation to Reference Evapotranspiration for Semi-Arid Region10.1007/s11269-013-0440-y ↗
53. Predicting Modulus Elasticity of Recycled Aggregate Concrete Using M5′ Model Tree Algorithm10.1016/j.conbuildmat.2015.06.055 ↗
54. M5 Model Tree Based Modelling of Reference Evapotranspiration10.1002/hyp.7266 ↗
55. New Explicit Formulation for Ultimate Bearing Capacity of Shallow Foundations on Granular Soil Using M5’ Model Tree10.1016/j.measurement.2020.108032 ↗
56. Structural Reliability Analysis of Corroded Pipeline Made in X60 Steel Based on M5 Model Tree Algorithm and Monte Carlo Simulation10.1016/j.prostr.2018.12.349 ↗
57. M5 Model Tree for Land Cover Classification10.1080/01431160500256531 ↗
58. (2016). Water Quality. Determination of Turbidity (Standard No. ISO 7027).
59. European Union (2000). Directive 2000/60/EC of the European Parliament and of the Council of 23 October 2000 Establishing a Framework for Community Action in the Field of Water Policy, European Union.
60. Concepts and Utilities of Ecologic Model10.1061/JSEDAI.0001170 ↗
61. Water Column Productivity and Temperature Predict Coral Reef Regeneration across the Indo-Pacific10.1038/srep08273 ↗
62. Responses of Estuarine and Coastal Marine Phytoplankton to Nitrogen and Phosphorus Enrichment10.4319/lo.2006.51.1_part_2.0377 ↗
63. Marsland, S. (2015). Machine Learning: An Algorithmic Perspective, CRC Press, Taylor and Francis Group. [2nd ed.].10.1201/b17476 ↗
64. Forecast of the Higher Heating Value Based on Proximate Analysis by Using Support Vector Machines and Multilayer Perceptron in Bioenergy Resources10.1016/j.fuel.2021.122824 ↗
65. Chong, E.K.P., Lu, W., and Żak, S.H. (2024). An Introduction to Optimization: With Applications to Machine Learning, Wiley. [5th ed.].
66. McClave, J.T., and Sincich, T. (2016). Statistics, Pearson. [13th ed.].
67. Wasserman, L. (2004). All of Statistics: A Concise Course in Statistical Inference, Springer. Springer Texts in Statistics.10.1007/978-0-387-21736-9 ↗
68. Bishop, C.M. (2006). Pattern Recognition and Machine Learning, Springer. Information science and statistics.
69. Freedman, D., Pisani, R., and Purves, R. (2007). Statistics, Norton. [4th ed.].
70. Knalf, G.J., and Ding, K. (2016). Adaptive Regression for Modeling Nonlinear Relationships, Springer.10.1007/978-3-319-33946-7 ↗
71. Cross-Validation of Regression Models10.1080/01621459.1984.10478083 ↗
72. Improvements on Cross-Validation: The 632+ Bootstrap Method
73. Piironen, J. (2026, June 25). Gplite: General Purpose Gaussian Process Modelling, Available online: https://CRAN.R-project.org/package=gplite.
74. Witten, I.H., Frank, E., and Hall, M.A. (2011). Data Mining: Practical Machine Learning Tools and Techniques, Morgan Kaufmann. [3rd ed.].
75. Paananen, T., Piironen, J., Andersen, M.R., and Vehtari, A. (2017). Variable Selection for Gaussian Processes via Sensitivity Analysis of the Posterior Predictive Distribution. arXiv.
76. Peak Flow Responses to Clear-Cutting and Roads in Small and Large Basins, Western Cascades, Oregon10.1029/95WR03493 ↗
77. Wu, W. (2023). Sediment Transport Dynamics, CRC Press.10.1201/9781003343165 ↗
78. Mercury as a Global Pollutant: Sources, Pathways, and Effects10.1021/es305071v ↗
79. Stumm, W., and Morgan, J.J. (1996). Aquatic Chemistry: Chemical Equilibria and Rates in Natural Waters, J. Wiley & Sons. [3rd ed.]. Environmental science and technology.
80. Bridgewater, L.L., Baird, R.B., Eaton, A.D., Rice, E.W., American Public Health Association, American Water Works Association, and Water Environment Federation (2017). Standard Methods for the Examination of Water and Wastewater, American Public Health Association. [23rd ed.].
81. Characterization of Dissolved Organic Carbon in Streams Using in Situ Spectrophotometry
82. Changes in the Character of Stream Water Dissolved Organic Carbon during Flushing in Three Small Watersheds, Oregon10.1029/2005JG000082 ↗
83. Methods for Reactive Oxygen Species (ROS) Detection in Aqueous Environments10.1007/s00027-012-0251-x ↗