arXiv subjects

Ji Wei Yoon

Publications and source records attributed to Ji Wei Yoon.

6 recordsLinked to original sources

arXiv2024

XMOL: Explainable Multi-property Optimization of Molecules

Molecular optimization is a key challenge in drug discovery and material science domain, involving the design of molecules with desired properties. Existing methods focus predominantly on single-property optimization, necessitating repetitive runs to target multiple properties, which is inefficient and computationally expensive. Moreover, these methods often lack transparency, making it difficult for researchers to understand and control the optimization process. To address these issues, we propose a novel framework, Explainable Multi-property Optimization of Molecules (XMOL), to optimize multiple molecular properties simultaneously while incorporating explainability. Our approach builds on state-of-the-art geometric diffusion models, extending them to multi-property optimization through the introduction of spectral normalization and enhanced molecular constraints for stabilized training. Additionally, we integrate interpretive and explainable techniques throughout the optimization process. We evaluated XMOL on the real-world molecular datasets i.e., QM9, demonstrating its effectiveness in both single property and multiple properties optimization while offering interpretable results, paving the way for more efficient and reliable molecular design.

cs.LG↗

arXiv2024

SG-NNP: Species-separated Gaussian Neural Network Potential with Linear Elemental Scaling and Optimized Dimensions for Multi-component Materials

Accurate simulations of materials at long-time and large-length scales have increasingly been enabled by Machine-learned Interatomic Potentials (MLIPs). There have been increasing interest on improving the robustness of such models. To this end, we engineer a novel set of Gaussian-type descriptors that scale linearly with the number of atoms, reduce informational degeneracy for multi-component atomic environments and apply them in Species-separated Gaussian Neural Network Potentials (SG-NNPs). The robustness of our method was tested by analyzing the impact of various design choices and hyperparameters on Molybdenum (Mo) SG-NNP performance during training and inference/simulation. With less dimensions, SG-NNPs are shown to have superior atomic forces and total energy predictions than other traditional and ML descriptor-based interatomic potentials on diverse set of materials - Ni, Cu, Li, Mo, Si, Ge, NiMo, Li3N and NbMoTaW. From the obtained results we can observe that the proposed method improves the performance of atomic descriptors of complex environments with multiple species.

cond-mat.mtrl-sci↗

arXiv2024

Explainable machine learning to enable high-throughput electrical conductivity optimization and discovery of doped conjugated polymers

The combination of high-throughput experimentation techniques and machine learning (ML) has recently ushered in a new era of accelerated material discovery, enabling the identification of materials with cutting-edge properties. However, the measurement of certain physical quantities remains challenging to automate. Specifically, meticulous process control, experimentation and laborious measurements are required to achieve optimal electrical conductivity in doped polymer materials. We propose a ML approach, which relies on readily measured absorbance spectra, to accelerate the workflow associated with measuring electrical conductivity. The classification model accurately classifies samples with a conductivity > 25 to 100 S/cm, achieving a maximum of 100 % accuracy rate. For the subset of highly conductive samples, we employed a regression model to predict their conductivities, yielding an impressive test R2 value of 0.984. We tested the models with samples of the two highest conductivities (498 and 506 S/cm) and showed that they were able to correctly classify and predict the two extrapolative conductivities at satisfactory levels of errors. The proposed ML-assisted workflow results in an improvement in the efficiency of the conductivity measurements by 89 % of the maximum achievable using our experimental techniques. Furthermore, our approach addressed the common challenge of the lack of explainability in ML models by exploiting bespoke mathematical properties of the descriptors and ML model, allowing us to gain corroborated insights into the spectral influences on conductivity. Through this study, we offer an accelerated pathway for optimizing the properties of doped polymer materials while showcasing the valuable insights that can be derived from purposeful utilization of ML in experimental science.

physics.app-ph↗

arXiv2024

Self-evolving Autoencoder Embedded Q-Network

In the realm of sequential decision-making tasks, the exploration capability of a reinforcement learning (RL) agent is paramount for achieving high rewards through interactions with the environment. To enhance this crucial ability, we propose SAQN, a novel approach wherein a self-evolving autoencoder (SA) is embedded with a Q-Network (QN). In SAQN, the self-evolving autoencoder architecture adapts and evolves as the agent explores the environment. This evolution enables the autoencoder to capture a diverse range of raw observations and represent them effectively in its latent space. By leveraging the disentangled states extracted from the encoder generated latent space, the QN is trained to determine optimal actions that improve rewards. During the evolution of the autoencoder architecture, a bias-variance regulatory strategy is employed to elicit the optimal response from the RL agent. This strategy involves two key components: (i) fostering the growth of nodes to retain previously acquired knowledge, ensuring a rich representation of the environment, and (ii) pruning the least contributing nodes to maintain a more manageable and tractable latent space. Extensive experimental evaluations conducted on three distinct benchmark environments and a real-world molecular environment demonstrate that the proposed SAQN significantly outperforms state-of-the-art counterparts. The results highlight the effectiveness of the self-evolving autoencoder and its collaboration with the Q-Network in tackling sequential decision-making tasks.

cs.LG↗

arXiv2023

Generating Nanoporous Graphene from Point and Stone-Wales Defects: A Study with Dimensionally Restricted Molecular Dynamics (DR-MD)

Defects in graphene are both a boon and a bane for applications - they can induce uncontrollable effects but can also provide novel ways to manipulate the properties of pristine graphene. Nanoporous Graphene, which contains nanoscopic holes, has found impactful applications in sustainability domains, e.g. gas separation, water filtration membranes and battery technologies. For this report, we investigate pore formation in graphene with no defect, one and two mono-vacancies, and two di-vacancies using bespoke Dimensionally Restricted Molecular Dynamics (DR-MD) designed for the purpose. We show DR-MD to be superior to free-standing or substrate suspended configurations for simulating stable defected structures. Applying DR-MD, stable pore configurations are identified, and their formation mechanisms elucidated. We also investigated formation mechanisms due to two Stone-Wales 55-77 defects, and the formation energies of their linearly extended structures, along the zigzag and armchair directions, and when they are placed in different relative orientations. This study offers a way to identify stable porous defect structures in graphene and insights into atomistic pore formation mechanisms for an environmentally important material.

cond-mat.mtrl-sci↗

arXiv2016

Microscopic Statistical Characterisation of the Congested Traffic Flow and Some Salient Empirical Features

We present large scale and detailed analysis of the microscopic empirical data of the traffic flow, focusing on the non-linear interactions between the vehicles when the traffic is congested. By implementing a "renormalisation" procedure that averages over relatively unimportant factors, we extract the effective dependence of the acceleration on the vehicle headway, velocity and relative velocity, that characterises not just a few vehicles but the traffic system as a whole. Several interesting features of the detailed vehicle-to-vehicle interactions are revealed, including the stochastic distribution of human responses, relative importance of non-linear terms in different density regimes, symmetric response to the relative velocity, and the insensitivity of the acceleration to the velocity within a certain headway and velocity range. The latter leads to a multitude of steady-states without a fundamental diagram, showing strong evidence of the "synchronised phase", substantiated with additional microscopic details. We discuss the richness of the available data for the understanding of the human driving behaviours, and its usefulness in construction and calibration of both deterministic and stochastic microscopic traffic models.

nlin.AO↗