Amnuyswat, Kittiphong

Loading...
Thumbnail Image
Preferred name
Amnuyswat, Kittiphong
Alternative Name
Amnuyswat, K.
Main Affiliation
Email
kittiphong.am@kmitl.ac.th

Settings

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Thermoelectric Prediction from Material Descriptors Using Machine Learning Technique
    (2023-04-19)
    Sungphueng, Pakawat
    ;
    Amnuyswat, Kittiphong
    In this work, we employed a machine learning framework to predict the thermoelectric power factors of materials based on their composition and structure. To generate a broad range of materials for analysis, we sourced an existing dataset from the Materials Project database. The electronic transport properties, which serve as the output variables, were obtained from the same database via a Boltzmann transport theory calculation beyond ab-initio method. These properties were used to generate input data, or material descriptors, which rely solely on atomic information and crystal structure without recourse to density functional theory calculations. The descriptors were transformed into numerical features using the open-source software Matminer. Non-linear machine learning regression models were trained and tested on the transformed datasets, and their performance was evaluated. The optimized random forest model produced the most accurate predictions, with a yield of 88%. The ultimate goals of this research were to develop material selection strategies that bypass the need for self-consumption in density functional theory calculations, and to demonstrate the potential of machine learning models to describe the thermoelectric properties of existing materials datasets.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Band gap prediction of the alloying halide perovskites using GW compare to DFT-1/2 method
    (2020-10-26)
    Amnuyswat, K.
    ;
    Thanomngam, P.
    The outstanding optoelectronic properties of methylammonium halide perovskites, including the tunable spectral absorption range, high carrier mobilities and low carrier recombination rates, make these materials are interesting for a decade year. In my works, a first-principle calculation based on non-local van der Waals-corrected Density Functional Theory (vdW-DFT) is performed to investigate high accuracy atomic structures and their properties of the alloying halide perovskites (CH3NH3PbIxBr1-x). While DFT generally underestimates the band gap for practically semiconductors and insulators, it provided a surprising accurate value for methylammonium halide perovskites. Unfortunately, this performance is not existing to another hybrid halide perovskite. The relativistic GW approximation is known to be a better-provided band gap more accurately, but at an extremely high computational cost were applied to the study. Here we also report the efficiency and accuracy of the bandgap calculations of methylammonium halide perovskites by using the self-consistent quasiparticle GW method (scGW) incorporated with the spin-orbit coupling comparing to recent develops DFT-1/2 method. The latter computational scheme provides accurate band gaps with the precision of the scGW method with no more computational cost than standard DFT. This method can solve the band gap problem by correcting the half-hole/half-electron occupation in the pseudopotentials. This work yields the possibility of the band gap prediction of alloying halide perovskite material (CH3NH3PbIxBr1-x) that good for optoelectronic design such as planar dye solar cell.