Experimental Investigation and Modeling of Aeration Efficiency at Labyrinth Weirs

Document Type : Regular Article


1 Civil Engineering Department, National Institute of Technology, Kurukshetra, India

2 Civil Engineering Department, Panipat Institute of Engineering and Technology, Samalkha, India

3 Civil Engineering Department, Shoolini University, Solan, India


For maintaining healthy streams and rivers, a high concentration of oxygen is desired and hydraulic structures act as natural aerators where oxygen transfer occurs by creating turbulence in the water. Aeration studies of conventional weirs are carried out widely in the past but at the same time, labyrinth weirs, where the weir crest is cranked thereby enhancing their crest length, have got a little notice. The test records were obtained through 180 laboratory observations on nine physical models to estimate aeration efficiency (E20) at labyrinth weirs (LWs). The E20 increases with the number of key as well as drop height and it is found to be highest for rectangular shape in comparison of the triangular and trapezoidal LWs, however, E20 decreases with the increase of discharge. Further, this work unravels the novel idea and potential of the M5P model tree (M5P), support vector regression machine (SVM), and Random Forest (RF) methods for estimation of aeration efficiency (E20) at LWs. The results depicted that the RF model performs best in determining the E20 at LWs. The results of sensitivity analysis further illustrated that drop height is the parameter that affects the prediction of E20 at the LWs most.


  • Experimental investigation of aeration efficiency at Labyrinth weirs is determined with different geometry, number of keys, and drop height.
  • Aeration efficiency of Labyrinth weirs is predicted using three artificial intelligence-based techniques; SVM, RF, and M5P.
  • A sensitivity study is done to find out the most critical input parameters


Main Subjects

[1]     Gentilini B. Stramazzi con cresta a pianta obliqua ea zig-zag. Società Editrice Riviste Industrie Eletriche; 1941.
[2]     Taylor G. The performance of labyrinth weirs 1968.
[3]     Hay N, Taylor G. Performance and Design of Labyrinth Weirs. J Hydraul Div 1970;96:2337–57. doi:10.1061/JYCEAJ.0002766.
[4]     Crookston BM, Tullis BP. Discharge Efficiency of Reservoir-Application-Specific Labyrinth Weirs. J Irrig Drain Eng 2012;138:564–8. doi:10.1061/(ASCE)IR.1943-4774.0000451.
[5]     Christensen NA. Flow characteristics of arced labyrinth weirs. Utah State University; 2012.
[6]     Gameson ALH. Weirs and aeration of rivers. J. Inst. Water Eng., 11. 1957.
[7]     Van der Kroon GTN, Schram AH. Weir aeration-part I: Single free fall. H20 1969;22:528–37.
[8]     Nakasone H. Study of Aeration at Weirs and Cascades. J Environ Eng 1987;113:64–81. doi:10.1061/(ASCE)0733-9372(1987)113:1(64).
[9]     Avery ST, Novak P. Oxygen Transfer at Hydraulic Structures. J Hydraul Div 1978;104:1521–40. doi:10.1061/JYCEAJ.0005100.
[10]    Gulliver JS, Rindels AJ. Measurement of Air‐Water Oxygen Transfer at Hydraulic Structures. J Hydraul Eng 1993;119:327–49. doi:10.1061/(ASCE)0733-9429(1993)119:3(327).
[11]    Wilhelms SC, Gulliver JS, Parkhill K. Reaeration at low-head hydraulic structures. ARMY ENGINEER WATERWAYS EXPERIMENT STATION VICKSBURG MS HYDRAULICS LAB; 1993.
[12]    Wormleaton PR, Soufiani E. Aeration Performance of Triangular Planform Labyrinth Weirs. J Environ Eng 1998;124:709–19. doi:10.1061/(ASCE)0733-9372(1998)124:8(709).
[13]    Wormleaton PR, Tsang CC. Aeration Performance of Rectangular Planform Labyrinth Weirs. J Environ Eng 2000;126:456–65. doi:10.1061/(ASCE)0733-9372(2000)126:5(456).
[14]    Singh B. Prediction of the sodium absorption ratio using data-driven models: a case study in Iran. Geol Ecol Landscapes 2020;4:1–10. doi:10.1080/24749508.2019.1568129.
[15]    Baylar A, Bagatur T. Study of aeration efficiency at weirs. Turkish J Eng Environ Sci 2000;24:255–64.
[16]    Baylar A, Hanbay D, Batan M. Application of least square support vector machines in the prediction of aeration performance of plunging overfall jets from weirs. Expert Syst Appl 2009;36:8368–74. doi:10.1016/j.eswa.2008.10.061.
[17]    Vand AS, Sihag P, Singh B, Zand M. Comparative Evaluation of Infiltration Models. KSCE J Civ Eng 2018;22:4173–84. doi:10.1007/s12205-018-1347-1.
[18]    Kumar M, Ranjan S, Tiwari NK. Oxygen transfer study and modeling of plunging hollow jets. Appl Water Sci 2018;8:1–15.
[19]    Kumar M, Ranjan S, Tiwari NK, Gupta R. Plunging hollow jet aerators - oxygen transfer and modelling. ISH J Hydraul Eng 2018;24:61–7. doi:10.1080/09715010.2017.1348264.
[20]    Bilhan O, Emin Emiroglu M, Kisi O. Application of two different neural network techniques to lateral outflow over rectangular side weirs located on a straight channel. Adv Eng Softw 2010;41:831–7. doi:10.1016/j.advengsoft.2010.03.001.
[21]    Emiroglu ME, Bilhan O, Kisi O. Neural networks for estimation of discharge capacity of triangular labyrinth side-weir located on a straight channel. Expert Syst Appl 2011;38:867–74. doi:10.1016/j.eswa.2010.07.058.
[22]    Kisi O, Emin Emiroglu M, Bilhan O, Guven A. Prediction of lateral outflow over triangular labyrinth side weirs under subcritical conditions using soft computing approaches. Expert Syst Appl 2012;39:3454–60. doi:10.1016/j.eswa.2011.09.035.
[23]    Zhang W, Li H, Li Y, Liu H, Chen Y, Ding X. Application of deep learning algorithms in geotechnical engineering: a short critical review. Artif Intell Rev 2021. doi:10.1007/s10462-021-09967-1.
[24]    Pal M, Singh NK, Tiwari NK. Pier scour modelling using random forest regression. ISH J Hydraul Eng 2013;19:69–75. doi:10.1080/09715010.2013.772763.
[25]    Zhang W, Zhang R, Wu C, Goh ATC, Lacasse S, Liu Z, et al. State-of-the-art review of soft computing applications in underground excavations. Geosci Front 2020;11:1095–106. doi:10.1016/j.gsf.2019.12.003.
[26]    Pandhiani SM, Sihag P, Shabri A Bin, Singh B, Pham QB. Time-Series Prediction of Streamflows of Malaysian Rivers Using Data-Driven Techniques. J Irrig Drain Eng 2020;146:04020013. doi:10.1061/(ASCE)IR.1943-4774.0001463.
[27]    Roushangar K, Alami MT, Majedi Asl M, Shiri J. Modeling discharge coefficient of normal and inverted orientation labyrinth weirs using machine learning techniques. ISH J Hydraul Eng 2017;23:331–40. doi:10.1080/09715010.2017.1327333.
[28]    Ohtsu I, Yasuda Y, Takahashi M. Discussion of onset of skimming flow on stepped spillways. J Hydraul Eng ASCE 2001;127:522–4.
[29]    Tsang C. Hydraulic and aeration performance of labyrinth weirs. 1987.
[30]    Gulliver JS, Thene JR, Rindels AJ. Indexing Gas Transfer in Self‐Aerated Flows. J Environ Eng 1990;116:503–23. doi:10.1061/(ASCE)0733-9372(1990)116:3(503).
[31]    Tebbutt THY. Reaeration performance of stepped cascades. J. Inst. of Water Engrs. and Sci., 31, 285-297. 1977.
[32]    Cortes C, Vapnik V. Support-vector networks. Mach Learn 1995;20:273–97. doi:10.1007/BF00994018.
[33]    Vapnik V. Statistical Learning Theory, New York 1998.
[34]    Quinlan JR. Learning with continuous classes. 5th Aust. Jt. Conf. Artif. Intell., WORLD SCIENTIFIC; 1992, p. 343–8. doi:10.1142/9789814536271.
[35]    Breiman L. Random forests—random features 1999.
[36]    Karami H, Ghazvinian H, Dehghanipour M, Ferdosian M. Investigating the Performance of Neural Network Based Group Method of Data Handling to Pan’s Daily Evaporation Estimation (Case Study: Garmsar City). J Soft Comput Civ Eng 2021;5:1–18.