arXiv subjects

Henry Chan

Publications and source records attributed to Henry Chan.

26 records · Page 2Linked to original sources

arXiv2020

BLAST: Bridging Length/time scales via Atomistic Simulation Toolkit

The ever-increasing power of supercomputers coupled with highly scalable simulation codes have made molecular dynamics an indispensable tool in applications ranging from predictive modeling of materials to computational design and discovery of new materials for a broad range of applications. Multi-fidelity scale bridging between the various flavors of molecular dynamics i.e. ab-initio, classical and coarse-grained models has remained a long-standing challenge. Here, we introduce our framework BLAST (Bridging Length/time scales via Atomistic Simulation Toolkit) that leverages machine learning principles to address this challenge. BLAST is a multi-fidelity scale bridging framework that provide users with the capabilities to train and develop their own classical atomistic and coarse-grained interatomic potentials (force fields) for molecular simulations. BLAST is designed to address several long-standing problems in the molecular simulations community, such as unintended misuse of existing force fields due to knowledge gap between developers and users, bottlenecks in traditional force field development approaches, and other issues relating to the accuracy, efficiency, and transferability of force fields. Here, we discuss several important aspects in force field development and highlight features in BLAST that enable its functionalities and ease of use.

cs.CE↗

arXiv2019

Active Learning the Coarse-Grained Energy Landscape For Water Clusters From Sparse Training Data

ANNs are currently trained by generating large quantities (On the order of $10^{4}$ or greater) of structural data in hopes that the ANN has adequately sampled the energy landscape both near and far-from-equilibrium. This can, however, be a bit prohibitive when it comes to more accurate levels of quantum theory. As such it is desirable to train a model using the absolute minimal data set possible, especially when costs of high-fidelity calculations such as CCSD and QMC are high. Here, we present an Active Learning approach that iteratively trains an ANN model to faithfully replicate the coarse-grained energy surface of water clusters using only 426 total structures in its training data. Our active learning workflow starts with a sparse training dataset which is continually updated via a Monte Carlo scheme that sparsely queries the energy landscape and tests the network performance. Next, the network is retrained with an updated training set that includes failed configurations/energies from previous iteration until convergence is attained. Once trained, we generate an extensive test set of ~100,000 configurations sampled across clusters ranging from 1 to 200 molecules and demonstrate that the trained network adequately reproduces the energies (within mean absolute error (MAE) of ~ 2 meV/molecule) and forces (MAE ~ 40 meV/{Å}) compared to the reference model. More importantly, the trained ANN model also accurately captures both the structure as well as the free energy as a function of the various cluster sizes. Overall, this study reports a new active learning scheme with promising strategy to develop accurate force-fields for molecular simulations using extremely sparse training data sets.

physics.comp-ph↗

arXiv2019

A coarse-grained deep neural network model for liquid water

We introduce a coarse-grained deep neural network model (CG-DNN) for liquid water that utilizes 50 rotational and translational invariant coordinates, and is trained exclusively against energies of ~30,000 bulk water configurations. Our CG-DNN potential accurately predicts both the energies and molecular forces of water; within 0.9 meV/molecule and 54 meV/angstrom of a reference (coarse-grained bond-order potential) model. The CG-DNN water model also provides good prediction of several structural, thermodynamic, and temperature dependent properties of liquid water, with values close to that obtained from the reference model. More importantly, CG-DNN captures the well-known density anomaly of liquid water observed in experiments. Our work lays the groundwork for a scheme where existing empirical water models can be utilized to develop fully flexible neural network framework that can subsequently be trained against sparse data from high-fidelity albeit expensive beyond-DFT calculations.

physics.comp-ph↗

arXiv2018

Impact Of Bike Sharing In New York City

The Citi Bike deployment changes the landscape of urban mobility in New York City and provides an example of a scalable solution that many other large cities are already adopting around the world. Urban stakeholders who are considering a similar deployment would largely benefit from a quantitative assessment of the impact of bike sharing on urban transportation, as well as associated economic, social and environmental implications. While the Citi Bike usage data is publicly available, the main challenge of such an assessment is to provide an adequate baseline scenario of what would have happened in the city without the Citi Bike system. Existing efforts, including the reports of Citi Bike itself, largely imply arbitrary and often unrealistic assumptions about the alternative transportation mode people would have used otherwise (e.g. by comparing bike trips against driving). The present paper offers a balanced baseline scenario based on a transportation choice model to describe projected customer behavior in the absence of the Citi Bike system. The model also acknowledges the fact that Citi Bike might be used for recreational purposes and, therefore, not all the trips would have been actually performed, if Citi Bike would not be available. The model is trained using open Citi Bike and other urban transportation data and it is applied to assess direct benefits of Citi Bike trips for the end users, as well as for urban stakeholders across different boroughs of New York City and the nearby Jersey City. Besides estimating the travel time and cost savings, the model also reports the associated gas savings, emissions cut and additional exercise for the customers, covering all three areas of anticipated impacts - economic, social and environmental.

physics.soc-ph↗

arXiv2017

Cost-sensitive detection with variational autoencoders for environmental acoustic sensing

Environmental acoustic sensing involves the retrieval and processing of audio signals to better understand our surroundings. While large-scale acoustic data make manual analysis infeasible, they provide a suitable playground for machine learning approaches. Most existing machine learning techniques developed for environmental acoustic sensing do not provide flexible control of the trade-off between the false positive rate and the false negative rate. This paper presents a cost-sensitive classification paradigm, in which the hyper-parameters of classifiers and the structure of variational autoencoders are selected in a principled Neyman-Pearson framework. We examine the performance of the proposed approach using a dataset from the HumBug project which aims to detect the presence of mosquitoes using sound collected by simple embedded devices.

stat.ML↗

arXiv2017

Mosquito detection with low-cost smartphones: data acquisition for malaria research

Mosquitoes are a major vector for malaria, causing hundreds of thousands of deaths in the developing world each year. Not only is the prevention of mosquito bites of paramount importance to the reduction of malaria transmission cases, but understanding in more forensic detail the interplay between malaria, mosquito vectors, vegetation, standing water and human populations is crucial to the deployment of more effective interventions. Typically the presence and detection of malaria-vectoring mosquitoes is only quantified by hand-operated insect traps or signified by the diagnosis of malaria. If we are to gather timely, large-scale data to improve this situation, we need to automate the process of mosquito detection and classification as much as possible. In this paper, we present a candidate mobile sensing system that acts as both a portable early warning device and an automatic acoustic data acquisition pipeline to help fuel scientific inquiry and policy. The machine learning algorithm that powers the mobile system achieves excellent off-line multi-species detection performance while remaining computationally efficient. Further, we have conducted preliminary live mosquito detection tests using low-cost mobile phones and achieved promising results. The deployment of this system for field usage in Southeast Asia and Africa is planned in the near future. In order to accelerate processing of field recordings and labelling of collected data, we employ a citizen science platform in conjunction with automated methods, the former implemented using the Zooniverse platform, allowing crowdsourcing on a grand scale.

stat.ML↗

arXiv2017

Impact Of Urban Technology Deployments On Local Commercial Activity

While smart city innovations seem to be a common and necessary response to increasing challenges of urbanization, foreseeing their impact on complex urban system is critical for informed decision making. Moreover, often the effect of urban interventions goes beyond the original expectations, including multiple indirect impacts. The present study considers the impact of two urban deployments, Citi Bike (bike sharing system) and LinkNYC kiosks, on the local commercial activity in the affected neighborhoods of New York City. The study uses anonymized and aggregated insights provided through a grant from the Mastercard Center for Inclusive Growth in order to provide initial data-driven evidence towards the hypothesis that proximity of Citi Bike stations incentivizes local sales at eating places, while LinkNYC kiosks help people, especially visitors, to navigate local businesses and thus incentivize commercial activity in different business categories.

cs.CY↗

arXiv2016

Ice grains grow by dissolution, ripening and grain boundary migration

Despite the exponential growth in computing resources and the availability of a myriad of different theoretical water models, an accurate, yet computationally efficient molecular level description of mesoscopic grain growth remains a grand challenge. The underlying phase transitions and dynamical processes in deeply supercooled systems are often rendered inaccessible due to limitations imposed by system sizes and timescales, which is further compounded by their sluggish kinetics. Here, we introduce a machine-learned, bond-order-based potential model (BOP) that more accurately describes the anomalous behavior, as well as structural and thermodynamical properties of both liquid water and ice, with at least two orders of magnitude cheaper computational cost than existing atomistic water models. In a significant departure from conventional force-field fitting, we use a multilevel evolutionary strategy that trains the BOP model against not just energetics but temperature dependent properties inferred from on-the-fly molecular dynamics simulations as well. We use the BOP model to probe the homogeneous ice nucleation and growth process by performing molecular dynamics on multi-million molecule systems for up to microsecond time scales. These massively parallel, long-time simulations naturally capture the competition between cubic, hexagonal, and stacking disordered ice phases during nucleation and early stages of growth leading to the formation of nanometer sized grains. Subsequently, we elucidate the hitherto elusive mechanism of grain coarsening of the crystallized mixed ice phases, which occur through grain dissolution and Ostwald ripening followed by grain boundary migration.

cond-mat.soft↗