Functionalization of remote sensing and on-site data for simulating surface water dissolved oxygen: Development of hybrid tree-based artificial intelligence models

• Published in: Marine pollution bulletin Vol. 170; no. C; p. 112639
• Main Authors: Tiyasha, Tiyasha, Tung, Tran Minh, Bhagat, Suraj Kumar, Tan, Mou Leong, Jawad, Ali H., Mohtar, Wan Hanna Melini Wan, Yaseen, Zaher Mundher
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.09.2021; Elsevier BV; Elsevier
• Subjects: Adaptive algorithms; Algorithms; Artificial intelligence; Dissolved oxygen; Environmental engineering; Feature selection; Genetic algorithms; Hybrid systems; Hydrology; Mathematical models; Oxygen; Parameters; Performance prediction; Prediction models; Reliability analysis; Remote sensing; Remote sensing data; River engineering; Rivers; Splines; Statistical analysis; Surface water; Surface water quality; Water quality; Feature selection; Remote sensing data; Surface water quality; Dissolved oxygen; Artificial intelligence
• ISSN: 0025-326X; 1879-3363
• DOI: 10.1016/j.marpolbul.2021.112639

Dissolved oxygen (DO) is an important indicator of river health for environmental engineers and ecological scientists to understand the state of river health. This study aims to evaluate the reliability of four feature selector algorithms i.e., Boruta, genetic algorithm (GA), multivariate adaptive regression splines (MARS), and extreme gradient boosting (XGBoost) to select the best suited predictor of the applied water quality (WQ) parameters; and compare four tree-based predictive models, namely, random forest (RF), conditional random forests (cForest), RANdom forest GEneRator (Ranger), and XGBoost to predict the changes of dissolved oxygen (DO) in the Klang River, Malaysia. The total features including 15 WQ parameters from monitoring site data and 7 hydrological components from remote sensing data. All predictive models performed well as per the features selected by the algorithms XGBoost and MARS in terms applied statistical evaluators. Besides, the best performance noted in case of XGBoost predictive model among all applied predictive models when the feature selected by MARS and XGBoost algorithms, with the coefficient of determination (R2) values of 0.84 and 0.85, respectively, nonetheless the marginal performance came up by Boruta-XGBoost model on in this scenario. [Display omitted] •Satellite and site hydrometeorological data are used for water quality prediction.•River dissolved oxygen (DO) was predicted within tropical environment case study.•Hybrid tree-based artificial intelligence models are developed for the DO prediction.•Several feature selection approaches are integrated to optimize the input parameters.•The proposed methodology is provided a robust technology for DO prediction.