Agus Yodi Gunawan
Industrial & Financial Mathematics Research Group, Institut Teknologi Bandung, Jl. Ganesha 10, Bandung 40132, Indonesia

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

EXPLORING PHYSICS-INFORMED NEURAL NETWORKS FOR SOLVING BOUNDARY LAYER PROBLEMS Pratama, Muchamad Harry Yudha; Gunawan, Agus Yodi
Journal of Fundamental Mathematics and Applications (JFMA) Vol 6, No 2 (2023)
Publisher : Diponegoro University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jfma.v6i2.20084

Abstract

In this paper, we explore a cutting-edge technique called as Physics- Informed Neural Networks (PINN) to tackle boundary layer problems. We here examine four different cases of boundary layers of second-order ODE: a linear ODEwith constant coefficients, a nonlinear ODE with homogeneous boundary conditions, an ODE with non-constant coefficients, and an ODE featuring multiple boundary layers. We adapt the line of PINN technique for handling those problems, and our results show that the accuracy of the resulted solutions depends on how we choose the most reliable and robust activation functions when designing the architecture of the PINN. Beside that, through our explorations, we aim to improve our understanding on how the PINN technique works better for boundary layer problems. Especially, the use of the SiLU (Sigmoid-Weighted Linear Unit) activation function in PINN has proven to be particularly remarkable in handling our boundary layer problems.
Effects of Inversion Layer on The Atmospheric Pollutant Dispersion from A High Chimney Zai, Fidelis Nofertinus; Gunawan, Agus Yodi
Journal of the Indonesian Mathematical Society VOLUME 29 NUMBER 3 (NOVEMBER 2023)
Publisher : IndoMS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22342/jims.29.3.1597.299-310

Abstract

An inversion layer is a layer in the lower atmosphere at a certain height through which there is no transport of pollutants. It plays as a significant factor in the formation of air pollutants where they are trapped. In this paper, a mathematical model describing an atmospheric pollutant dispersion from a high chimney in the presence of an inversion layer is constructed. The aim of the model is to predict the concentration of pollutants at ground level. The advection-diffusion equation governs the concentration of a pollutant released into the air. An analytical solution procedure via the integral transforms is presented for the steady-state case. Solutions are entirely determined by two parameters, i.e., the source strength emanating from the chimney and the height of the inversion layer. The pollutant concentration on the ground level with some multiple source formations will be explored, and also for various values of inversion layer height. Results show that the lower the inversion layer, the higher the pollutant concentration on the ground level is.