Dissolved oxygen concentration predictions for running waters with using hybrid machine learning techniques

被引:27
|
作者
Dehghani, Reza [1 ]
Torabi Poudeh, Hassan [2 ]
Izadi, Zohreh [1 ]
机构
[1] Lorestan Univ, Hydrol Water Struct, Khorramabad, Iran
[2] Lorestan Univ, Dept Water Engn, Khorramabad, Iran
关键词
Dissolved oxygen; Machine learning; Hybrid model; Cumberland river; SUPPORT VECTOR MACHINES; MODEL PERFORMANCE; PRECIPITATION; RUNOFF; CALIBRATION; ALGORITHM; BAY;
D O I
10.1007/s40808-021-01253-x
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Water is one of the most essential elements in nature that forms the basis of human life and contributes to the economic growth and development of societies. Safe water is closely related to environmental health and activities. The lives of all the animals on our planet depend on water and oxygen. Moreover, sufficient dissolved oxygen (DO) is crucial for the survival of aquatic animals. In the present research, temperature (T) and flow (Q) variables were used to predict DO. The time series were monthly and data were related to the Cumberland River in the southern United States from 2008 to 2018. Support vector regression (SVR) was employed for prediction of the model in both standalone and hybrid forms. The employed hybrid models consisted in SVR combined with metaheuristic algorithms of chicken swarm optimization (CSO), social ski-driver (SSD) optimization, Black widow optimization (BWO), and the Algorithm of the innovative gunner (AIG). Pearson correlation coefficient was utilized to select the best input combination. Box plots and Taylor diagrams were employed in the interpretation of the results. It was observed that all the four hybrid models achieved better results. Also according to the evaluation criteria among the models used the following were found: SVR-AIG with the coefficient of determination (R-2 = 0.963), the root mean square error (RMSE = 0.644 mg/l), the mean absolute value of error (MAE = 0.568 mg/l), the Nash-Sutcliffe coefficient (NS = 0.864), and bias percentage (BIAS = 0.001). Overall the research showed that hybrid models increased the accuracy of the single SVR model by 6.52-1.75%.
引用
收藏
页码:2599 / 2613
页数:15
相关论文
共 50 条
  • [1] Dissolved oxygen concentration predictions for running waters with using hybrid machine learning techniques
    Reza Dehghani
    Hassan Torabi Poudeh
    Zohreh Izadi
    [J]. Modeling Earth Systems and Environment, 2022, 8 : 2599 - 2613
  • [2] Hybrid Machine Learning Ensemble Techniques for Modeling Dissolved Oxygen Concentration
    Abba, Sani Isah
    Linh, Nguyen Thi Thuy
    Abdullahi, Jazuli
    Ali, Shaban Ismael Albrka
    Pham, Quoc Bao
    Abdulkadir, Rabiu Aliyu
    Costache, Romulus
    Nam, Van Thai
    Anh, Duong Tran
    [J]. IEEE ACCESS, 2020, 8 : 157218 - 157237
  • [4] Modeling dissolved oxygen concentration using machine learning techniques with dimensionality reduction approach
    Garabaghi, Farid Hassanbaki
    Benzer, Semra
    Benzer, Recep
    [J]. ENVIRONMENTAL MONITORING AND ASSESSMENT, 2023, 195 (07)
  • [5] Modeling dissolved oxygen concentration using machine learning techniques with dimensionality reduction approach
    Farid Hassanbaki Garabaghi
    Semra Benzer
    Recep Benzer
    [J]. Environmental Monitoring and Assessment, 2023, 195
  • [6] Concentration estimation of dissolved oxygen in Pearl River Basin using input variable selection and machine learning techniques
    Li, Wenjing
    Fang, Huaiyang
    Qin, Guangxiong
    Tan, Xiuqin
    Huang, Zhiwei
    Zeng, Fantang
    Du, Hongwei
    Li, Shuping
    [J]. SCIENCE OF THE TOTAL ENVIRONMENT, 2020, 731
  • [7] Machine Learning Based Predictions of Dissolved Oxygen in a Small Coastal Embayment
    Valera, Manuel
    Walter, Ryan K.
    Bailey, Barbara A.
    Castillo, Jose E.
    [J]. JOURNAL OF MARINE SCIENCE AND ENGINEERING, 2020, 8 (12) : 1 - 16
  • [8] Hybrid machine learning models for prediction of daily dissolved oxygen
    Azma, Aliasghar
    Liu, Yakun
    Azma, Masoumeh
    Saadat, Mohsen
    Zhang, Di
    Cho, Jinwoo
    Rezania, Shahabaldin
    [J]. JOURNAL OF WATER PROCESS ENGINEERING, 2023, 54
  • [9] Analysis of dissolved oxygen influencing factors and concentration prediction using input variable selection technique: A hybrid machine learning approach
    Liu, Wei
    Lin, Shu
    Li, Xiaobao
    Li, Wenjing
    Deng, Hong
    Fang, Huaiyang
    Li, Weijie
    [J]. JOURNAL OF ENVIRONMENTAL MANAGEMENT, 2024, 357
  • [10] Simulation of the concentration of dissolved oxygen in river waters using Artificial Neural Networks
    de Araujo Schtz, Fabiana Costa
    Antunes de Lima, Vera Lucia
    Eyng, Eduardo
    Bresolin, Adriano de Andrade
    Schtz, Fernando
    [J]. 2015 11TH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION (ICNC), 2015, : 1252 - 1257