Machine learning predicting the transport mechanisms and entrainment characteristics of negative buoyant jets
Source abstract
Abstract
Fountains injected into homogeneous fluids, characterized by combined temperature and concentration effects, are common in both natural and environmental settings. In this study, the capacities of several machine learning models, including support vector regression, multi-layer perceptron, random forests, XGBoost, CatBoost, AdaBoost, and LightGBM, were investigated to clarify the transient flow behavior of fountains. The results indicated that the multi-layer perceptron was superior to the other models as it provided improved coefficient of determination, root mean squared error, and mean absolute error. This study confirmed that the machine learning techniques have great potential to study the transient flow behavior of fountains.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Aerodynamics and Acoustics in Jet Flows · Nuclear Engineering Thermal-Hydraulics · Flow Measurement and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Information Science and Technology, Yunnan Normal University 1 , Kunming 650500,
Key Laboratory of Rural Energy Engineering of Yunnan 2 , Kunming, Yunnan 650500,
Solar Energy Research Institute, Yunnan Normal University 3 , Kunming, Yunnan 650500,
Southwest United Graduate School 4 , Kunming, Yunnan 650092,
Funding
National Natural Science Foundation of China
References (42)
Show source-provided references
1. Fountains in industry and nature10.1146/annurev-fluid-010313-141311 ↗
2. Thermal entrainment in the core regions of transitional plane fountains in linearly stratified ambient fluids10.1142/s175882512250020x ↗
3. Penetration height of transitional round fountains in a linearly stratified fluid10.1016/j.icheatmasstransfer.2016.12.004 ↗
4. Onset of entrainment in transitional round fountains10.1016/j.ijheatmasstransfer.2008.02.047 ↗
5. Experimental investigation of fountains in homogeneous fluid with coexistent temperature and concentration effects using PIV/PLIF10.1063/5.0132126 ↗
6. Behavior of weak axisymmetric fountain in homogeneous fluid with coexistent temperature and concentration effects10.1016/j.csite.2022.102204 ↗
7. Penetration height of weak axisymmetric fountain in homogeneous fluid under the combined temperature and salinity effect10.1063/5.0077345 ↗
8. Experimental investigation into turbulent negatively buoyant jets using combined PIV and PLIF measurements10.1016/j.ijheatfluidflow.2020.108561 ↗
9. The effect of double diffusion on the dynamics of horizontal turbulent thermohaline jets10.1017/jfm.2020.744 ↗
10. Large-eddy simulation of particle-laden isotropic turbulence using machine-learned subgrid-scale model10.1063/5.0098399 ↗
11. A simplified approach to recognize vortex-induced vibration response using machine learning10.1080/10168664.2023.2287460 ↗
12. A measure–correlate–predict model based on neural networks and frozen flow hypothesis for wind resource assessment10.1063/5.0086354 ↗
13. Predicting co-pyrolysis of coal and biomass using machine learning approaches10.1016/j.fuel.2021.122248 ↗
14. Investigations of data-driven closure for subgrid-scale stress in large-eddy simulation10.1063/1.5054835 ↗
15. Data-driven study/optimization of a solar power and cooling generation system in a transient operation mode and proposing a novel multi-turbine modification concept to reduce the sun’s intermittent effect10.1016/j.energy.2024.133043 ↗
16. A review on state-of-the-art applications of data-driven methods in desalination systems10.1016/j.desal.2022.115744 ↗
17. Investigating the barriers and strategies for establishing desalination plants to mitigate water scarcity in Sri Lankan dry zones10.1108/sampj-09-2023-0625 ↗
18. Machine learning-based stealing attack of the temperature monitoring system for the energy internet of things10.1155/2021/6661954 ↗
19. A machine learning based-method to generate random circle-packed porous media with the desired porosity and permeability10.1016/j.advwatres.2024.104631 ↗
20. A review of machine learning for modeling air quality: Overlooked but important issues10.1016/j.atmosres.2024.107261 ↗
21. Machine learning-based predictive model for thermal comfort and energy optimization in smart buildings10.1016/j.rineng.2024.102148 ↗
22. Investigation of the dilution of outfall discharges using computational and neuro-fuzzy techniques
23. Simulation of circular jet outfalls using artificial neural network10.5897/ijps12.254 ↗
24. Multigene genetic-programming-based models for initial dilution of laterally confined vertical buoyant jets10.3390/jmse7080246 ↗
25. Evolutionary modeling of inclined dense jets discharged from multiport diffusers10.2112/jcoastres-d-19-00057.1 ↗
26. Simulations of the concentration fields of rosette-type multiport buoyant discharges using combined CFD and multigene genetic programming techniques10.3390/jmse9111311 ↗
27. CFD-CNN modeling of the concentration field of multiport buoyant jets10.3390/jmse10101383 ↗
28. Applications of ANFIS-type methods in simulation of systems in marine environments10.3390/mca27020029 ↗
29. Reconstruction and analysis of negatively buoyant jets with interpretable machine learning10.1016/j.marpolbul.2023.114881 ↗
30. Learning representations by back-propagating errors10.1038/323533a0 ↗
31. Chrono-validation of near-real-time landslide susceptibility models via plug-in statistical simulations10.1016/j.enggeo.2020.105818 ↗
32. Subgrid modelling for two-dimensional turbulence using neural networks10.1017/jfm.2018.770 ↗
33. Flowfield reconstruction method using artificial neural network10.2514/1.j057108 ↗
34. Support vector regression machines
35. A random feature mapping method based on the AdaBoost algorithm and results fusion for enhancing classification performance10.1016/j.eswa.2024.124902 ↗
36. Insights into geospatial heterogeneity of landslide susceptibility based on the SHAP-XGBoost model10.1016/j.jenvman.2023.117357 ↗
37. An efficient combination of convolutional neural network and LightGBM algorithm for lung cancer histopathology classification10.3390/diagnostics13152469 ↗
38. 2018
39. Random forests10.1023/a:1010933404324 ↗
40. A comparative study of various machine learning methods for performance prediction of an evaporative condenser10.1016/j.ijrefrig.2021.02.009 ↗
41. A comparative analysis of tree-based machine learning algorithms for predicting the mechanical properties of fibre-reinforced GGBS geopolymer concrete10.1007/s41939-023-00355-6 ↗
42. 2023 · 323