Viral Shah

Viral Shah

Auto-generated profile, based on publicly available information

Viral Shah

Julia Computing, Inc. Cambridge MA USA

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 January 2021 in Journal of Open Source Software
Verified
Journal Article
Open access
PDF file
VLVincent Landau
Vincent Landau
VSViral B. Shah
Viral B. Shah
RARanjan Anantharaman
Ranjan Anantharaman
KHKimberly R. Hall
Kimberly R. Hall

15 March 2021 in Land
Verified
Journal Article
Open access
PDF file
KHKimberly R. Hall
Kimberly R. Hall
RARanjan Anantharaman
Ranjan Anantharaman
VLVincent Landau
Vincent Landau
MCMelissa Clark
Melissa Clark
BDBrett G Dickson
Brett G Dickson
VSViral B. Shah
Viral B. Shah
The conservation field is experiencing a rapid increase in the amount, variety, and quality of spatial data that can help us understand species movement and landscape connectivity patterns. As interest grows in more dynamic representations of movement potential, modelers are often limited by the capacity of their analytic tools to handle these datasets. Technology developments in software and high-performance computing are rapidly emerging in many fields, but uptake within conservation may lag, as our tools or our choice of computing language can constrain our ability to keep pace. We recently updated Circuitscape, a widely used connectivity analysis tool developed by Brad McRae and Viral Shah, by implementing it in Julia, a high-performance computing language. In this initial re-code (Circuitscape 5.0) and later updates, we improved computational efficiency and parallelism, achieving major speed improvements, and enabling assessments across larger extents or with higher resolution data. Here, we reflect on the benefits to conservation of strengthening collaborations with computer scientists, and extract examples from a collection of 572 Circuitscape applications to illustrate how through a decade of repeated investment in the software, applications have been many, varied, and increasingly dynamic. Beyond empowering continued innovations in dynamic connectivity, we expect that faster run times will play an important role in facilitating co-production of connectivity assessments with stakeholders, increasing the likelihood that connectivity science will be incorporated in land use decisions.

1 October 2022 in MRS Bulletin
Verified
Journal Article
Closed access
PDF file
EAEmil Annevelink
Emil Annevelink
RKRachel Kurchin
Rachel Kurchin
EMEric Muckley
Eric Muckley
LKLance Kavalsky
Lance Kavalsky
VHVinay I. Hegde
Vinay I. Hegde
VVVenkatasubramanian Viswanathan
Venkatasubramanian Viswanathan

10 November 2018 in arXiv
Verified
Preprint
Open access
PDF file
MIMichael Innes
Michael Innes
ESElliot Saba
Elliot Saba
KFKeno Fischer
Keno Fischer
DGDhairya Gandhi
Dhairya Gandhi
MRMarco Concetto Rudilosso
Marco Concetto Rudilosso
VSViral Shah
Viral Shah
Machine learning as a discipline has seen an incredible surge of interest in recent years due in large part to a perfect storm of new theory, superior tooling, renewed interest in its capabilities. We present in this paper a framework named Flux that shows how further refinement of the core ideas of machine learning, built upon the foundation of the Julia programming language, can yield an environment that is simple, easily modifiable, and performant. We detail the fundamental principles of Flux as a framework for differentiable programming, give examples of models that are implemented within Flux to display many of the language and framework-level features that contribute to its ease of use and high productivity, display internal compiler techniques used to enable the acceleration and performance that lies at the heart of Flux, and finally give an overview of the larger ecosystem that Flux fits inside of.

9 June 2019 in arXiv
Verified
Preprint
Open access
PDF file
RARanjan Anantharaman
Ranjan Anantharaman
KHKimberly R. Hall
Kimberly R. Hall
VSViral Shah
Viral Shah
AEAlan Edelman
Alan Edelman
Connectivity across landscapes influences a wide range of conservation-relevant ecological processes, including species movements, gene flow, and the spread of wildfire, pests, and diseases. Recent improvements in remote sensing data suggest great potential to advance connectivity models, but computational constraints hinder these advances. To address this challenge, we upgraded the widely-used Circuitscape connectivity package to the high performance Julia programming language. Circuitscape.jl allows users to solve problems faster via improved parallel processing and solvers, and supports applications to larger problems (e.g., datasets with hundreds of millions of cells). We document speed improvements of up to 1800\%. We also demonstrate scaling of problem sizes up to 437 million grid cells. These improvements allow modelers to work with higher resolution data, larger landscapes and perform sensitivity analysis effortlessly. These improvements accelerate the pace of innovation, helping modelers address pressing challenges like species range shifts under climate change. Our collaboration between ecologists and computer scientists has led to the use of connectivity models to inform conservation decisions. Further, these next generation connectivity models will produce results faster, facilitating stronger engagement with decision-makers.

13 May 2022 in arXiv
Verified
Preprint
Open access
PDF file
EAEmil Annevelink
Emil Annevelink
RKRachel Kurchin
Rachel Kurchin
EMEric Muckley
Eric Muckley
LKLance Kavalsky
Lance Kavalsky
VHVinay I. Hegde
Vinay I. Hegde
VVVenkatasubramanian Viswanathan
Venkatasubramanian Viswanathan
Large-scale electrification is vital to addressing the climate crisis, but several scientific and technological challenges remain to fully electrify both the chemical industry and transportation. In both of these areas, new electrochemical materials will be critical, but their development currently relies heavily on human-time-intensive experimental trial and error and computationally expensive first-principles, meso-scale and continuum simulations. We present an automated workflow, AutoMat, that accelerates these computational steps by introducing both automated input generation and management of simulations across scales from first principles to continuum device modeling. Furthermore, we show how to seamlessly integrate multi-fidelity predictions such as machine learning surrogates or automated robotic experiments "in-the-loop". The automated framework is implemented with design space search techniques to dramatically accelerate the overall materials discovery pipeline by implicitly learning design features that optimize device performance across several metrics. We discuss the benefits of AutoMat using examples in electrocatalysis and energy storage and highlight lessons learned.