Modeling river water dissolved organic matter using ensemble computing and genetic programming techniques

Created by W.Langdon from gp-bibliography.bib Revision:1.8414

@Article{Zounemat-Kermani:2025:ecohyd,

• author = "Mohammad Zounemat-Kermani and Soudabeh {Golestani Kermani} and Marzieh Fadaee and Ammar Aldallal and Ozgur Kisi and Abdollah Ramezani-Charmahineh",
• title = "Modeling river water dissolved organic matter using ensemble computing and genetic programming techniques",
• journal = "Ecohydrology and Hydrobiology",
• year = "2025",
• volume = "25",
• number = "2",
• pages = "292--302",
• month = apr,
• keywords = "genetic algorithms, genetic programming, gene expression programming, Committee learning, Environmental modeling, Artificial intelligence, Soft computing, River flow",
• ISSN = "1642-3593",
• URL = "https://www.sciencedirect.com/science/article/pii/S1642359324000430",
• DOI = "doi:10.1016/j.ecohyd.2024.04.003",
• abstract = "Dissolved organic matter (DOM) plays a diverse role in aquatic ecosystems and is a key participant in global carbon budgets; thus, precise simulation and modelling of DOM concentrations in rivers and streams is critical in hydro-environmental projects. Among various modelling strategies, data-driven Machine Learning (ML) approaches - and particularly Ensemble Machine Learning (EML) models - have proven their fair capabilities in simulating environmental issues in aquatic media based on the information available from a limited number of physicochemical and biological parameters of water. In this regard, several MLs (such as Support Vector Regression, SVR, and Extreme Learning Machine, ELM), two EMLs (e.g., Random Forests, RF, and Boosted Trees, BTs), as well as Gene Expression Programming (GEP), are evaluated for predicting fluorescent Dissolved Organic Matter (fDOM) in the Caloosahatchee River in Florida. The modelling strategy of fDOM was based on constructing regular and ensemble ML models using seven quantitative and qualitative independent parameters (flow rate, temperature, specific conductance, dissolved oxygen, pH, turbidity, and nitrate recorded from 2017 to 2019) after all being introduced as influential parameters on the target variable (fDOM) using the best subset regression technique. Based on the k-fold cross-validation method (k = 4), the applied regular MLs (SVR, ELM, and GEP) provided better performance than the traditional multiple linear regression model (on average, 6.8 percent improvement in RMSE). However, the results showed that the EML models (RF and BT) outperformed the regular MLs (on average, 7.2 percent improvement in RMSE) in fDOM prediction",

}

Genetic Programming entries for Mohammad Zounemat-Kermani Soudabeh Golestani Kermani Marzieh Fadaee Ammar Aldallal Ozgur Kisi Abdollah Ramezani-Charmahineh

Citations