Data Workflows

Generating traffic-based building occupancy schedules in Chattanooga, Tennessee from a grid of traffic sensors featured image

Generating traffic-based building occupancy schedules in Chattanooga, Tennessee from a grid of traffic sensors

An overview of the methodology presented in this paper, guided by the data workflow. The left-hand side of the figure, (a)-(d), illustrates the traffic data workflow: the data is …

avatar
Andreas Berres
Read more
Distribution of potential savings from urban-scale energy modeling of a utility featured image

Distribution of potential savings from urban-scale energy modeling of a utility

Comparison of annual electricity savings for different vintages (color) and energy conservation measures.

Brett Bass
Read more
Explorative Visualization for Traffic Safety using Adaptive Study Areas featured image

Explorative Visualization for Traffic Safety using Adaptive Study Areas

The calendar view shows the incident distribution of a selected dataset over time. Each day’s incidents are displayed as a tile on the calendar. When the tile for a day is …

avatar
Andreas Berres
Read more
Multiscale and Multivariate Transportation System Visualization for Shopping District Traffic and Regional Traffic featured image

Multiscale and Multivariate Transportation System Visualization for Shopping District Traffic and Regional Traffic

Chord charts for intersection-level visualization for a single day (Tuesday, April 2, 2019) in Chattanooga, Tennessee. The horizontally placed charts represent the intersections …

avatar
Andreas Berres
Read more
A Mobility-Driven Approach to Modeling Building Energy featured image

A Mobility-Driven Approach to Modeling Building Energy

Left: The traffic simulation area (yellow) within the Chicago area (red). Middle: Simulated buildings in the Chicago Loop (blue). Right: 3D rendering of buildings in the Chicago …

avatar
Andreas Berres
Read more
Performance analysis and optimization for scalable deployment of deep learning models for country-scale settlement mapping on Titan supercomputer featured image

Performance analysis and optimization for scalable deployment of deep learning models for country-scale settlement mapping on Titan supercomputer

Meanshift clustering based Image workload partitioning. Different clusters are represented by different colors. Images belongs to a cluster will be assigned to an independent job. …

Kuldeep Kurte
Read more
Ramifications of Evolving Misbehaving Convolutional Neural Network Kernel and Batch Sizes featured image

Ramifications of Evolving Misbehaving Convolutional Neural Network Kernel and Batch Sizes

Building footprint detection. This depicts detected building footprints, highlighted in purple, by applying a CNN model to satellite imagery.

Mark Coletti
Read more
EWN-KDF: A Knowledge Discovery Framework to Understand the Energy Water Nexus featured image

EWN-KDF: A Knowledge Discovery Framework to Understand the Energy Water Nexus

Main view of the user interface of the Energy-Water Nexus Knowledge Discovery Framework, displaying NCEI data on the Web World Wind Globe view. The chart at the bottom shows a …

avatar
Andreas Berres
Read more
Video Compression for Ocean Simulation Image Databases featured image

Video Compression for Ocean Simulation Image Databases

Progression of video compression results for kinetic energy. From left to right: original quality, encoding only, completely usable (CRF=30), marginally acceptable (CRF=34), and …

avatar
Andreas Berres
Read more