40+ Sessions from Incredible Speakers!

Scientific applications often deal with deeply geotemporal data. These can include distributed sensor data streams, or high-repeat frequency satellite data. In this practical session, we review how to work with LIDAR, Sentinel-2 imagery, weather data and species telemetry data. Applications include climate change planning, continuous monitoring of fire and flood risk, and biodiversity analysis.

Want to learn how AI-Ready Infrastructure’s unlock OmniSCI's speed and scale for big data analytics? Three lessons learned about how compute and storage building blocks accelerate deep-learning based analytics workflows and data curation.

The Gaia space telescope has observed 1.7 billion stars in the Galaxy, creating a wealth of data about stars and their characteristics. In this session, we will use OmniSci Immerse to explore this dataset. We will draw insights about stars - where they are, what they look like, how they move - and the Milky Way galaxy at large, the place we call home.

Don’t sacrifice performance or availability. For massive datasets exceeding a single node, OmniSci can be distributed to handle even more. In this session, learn how a distributed architecture can be optimized to maximize performance.

Just like a Ferrari, an Australian Shepherd, or a scuba diving habit, managing and orchestrating GPUs can be time consuming, high-maintenance, and expensive. Find out how wrangling OmniSci and Nvidia GPUs into the world's first on-demand GPU analytics SaaS product took JP Harvey on a journey from GPU-naive to Nvidia Ninja in three months.

California faces a housing affordability crisis. Municipalities like Los Angeles regulate land use and zoning of private property. But even in this time of crisis, the City of Los Angeles lacks the capacity and/or desire to calculate and identify the unused density among the myriad of ordinances, restrictive overlays, and development incentives they administer. In this session, learn how Pactriglo is able to visualize tens of millions of data points from disparate sources to create a seamless real-time real estate data dashboard that guides real estate development projects to the path of least resistance.

We are good at many things, but our decisions are highly influenced by the quality of the information we use and the limited amount of time we have to make them. Let’s explore a world that breaks down traditional workflows. One that puts the vast power of information in context, with a spatio-temporal reference. Enabling cross-discipline conversational analytics integrating multiple data sources across an O&G operator or service company's domain. Presenting the new OmniSci O&G platform coupled with a story from 1962, a concept identified by the American physicist and philosopher Thomas Kuhn, the Paradigm Shift. A change in rules brought about by breakthroughs in GPU-accelerated analytics. Join Dan Gualtieri as he discusses improved workflows for acquisition, asset evaluations, horizontal data integration, and beyond.

Since introducing geometric objects, OmniSci has become an indispensable tool in working interactively with large geospatial graphs that bring ordinary GIS tools to their knees. In this session we will walk you through a real workflow using Graph Neural Networks written in Julia to generate data that is loaded into OmniSci for interactive analysis. Join us to see how we use these tools to bridge the gap between engineers and decision-makers.

In this session we’ll give you a brief overview of the Flint Water Crisis and how we made lead service line discovery more efficient during the City’s recovery. We’ll then present a comparative case study on the efficacy of data-driven models and using machine learning to replace service lines in Flint, versus a non data-driven approach. Finally, we’ll discuss our development and implementation of a public outreach tool: an interactive map for residents to observe replacement efforts, which includes up-to-date model predictions for every home in the city.

Over 80% of data records created today are location-enriched, resulting in a big opportunity to extend location intelligence techniques to conventional big data analytics processes. OmniSci seizes this opportunity with an intuitive visual interface, combining capabilities across a wide spectrum of tabular, spatial, and temporal data. This session is designed for GIS users looking to learn more about OmniSci Immerse. From data import, to chart types, layers, joins, geometry functions, and the latest geo capabilities, and beyond. Attend this session and you’ll quickly be deriving insights from the space and time components of your data, making you a GIS superhero.

Learn how TELUS, a Canadian national telecommunications company, has created an interactive market sizing tool to grow subscribers and optimize network builds. TELUS’ high speed (HS) service can be provisioned over Fibre, Copper or over its mobile network. TELUS Marketing needs to have visibility over where each technology can be deployed, along with the targeting potential (number of households), and where its competitors offer similar services. Each technology type has its own coverage layers, qualification criteria and competitive restrictions, not to mention separate business units that design, implement and support the services they carry. Providing a “one stop shop” where Marketing can assess opportunity to build/grow subscribers as well as potential to improve network build prioritization, was highly desired. In rural areas where TELUS does not have the capability to offer HS over Fibre, HS over copper can be problematic in offering competitive speed plans, not to mention reliable service for customers. In these situations, TELUS offers HS over its LTE network to fixed line customers. With OmniSci, TELUS was able to build an interactive map for showing all of TELUS’ communities, along with, competitor speed information, wHSIA coverage layers, competitor cell sites, LTE coverage layers, household reference data, copper qualification, fibre eligibility, other exclusion layers, and marketable base (taking into account do not contact flags). Join Dustin Wright and Chris Havlin, data scientists at TELUS, as they explain how they created this interactive dashboard and how it’s transforming their marketing efforts.

Enterprise analytics has quickly evolved from a centralized business intelligence function for historical reporting and dashboards to a democratized capability where anyone can access, analyze and act on all available information, often in real-time while employing advanced techniques. But the complex, dynamic and urgent nature of modern data analytics demands a new approach to data integration.

Skyhook Uses Omnisci for Insights in its High Volume, Globally Distributed Mobile Device Datapool Over the past decade and a half Skyhook has built and patented much of the technology used for accurately positioning mobile devices. This is accomplished by mixing Wi-Fi with cell and gps signals to deliver a best hybrid solution with extremely low latency regardless of local sampling challenges. Skyhook pioneered precision location for both iOS and Android and has deployed various solutions across billions of devices in these and other OS pools. In order to remain functionally accurate a global Wi-Fi database must self-heal through active field acquisition, and this requires massive MAU/DAU/HAU activity sustained indefinitely and retained as a structured artifact across multiple years. Skyhook’s various databases, including Wi-Fi access points, cell antennas, ip detections, signal confirmed venues and individual returned device locations produce high temporally and positionally accurate samples tens of billions of times daily. This raw output is refined and fractioned into specific data products that are useful to big data consumers in multiple industries and governments. Omnisci has proven itself highly performant in managing large volumes of point-based, time- and place-anchored data in a low latency analysis environment. We will show examples in areas where GPU-resident analytics permit Skyhook to scale and leverage vast data extracts into actionable insight in areas of crowd characterization, crisis-driven population dynamics, commercial consumer behavior and system pathology detection.

Global mobile data traffic will exceed 49 exabytes per month by 2021. What new business opportunities does this data bring? How are telecom companies responding to the analytics challenges of data at this scale? We’ve brought together several telecom industry experts to discuss the future of telecom analytics.

The digitization of the world has brought us Big Data, but it’s fraught with challenges of speed and scale. GPU databases like OmniSci are uniquely positioned to solve these challenges. In this session, we’ll start with an introduction to OmniSci, followed by financial terms related to risk management, as well as the basics of Apache Spark. Then we’ll demo OmniSci on a financial risk management use case, bringing together an OmniSci Docker image, OmniSci CLI, OmniSci Immerse, Minikube/Kubernetes, Spark, Scala, and BlackSchole/Finite Difference.

This talk will focus on performance optimizations that improved OmniSci in data ingress and dataframe-like operations. We will show how the Arrow library is helpful in data ingress/egress operations and how building unified layered architecture with standardized Pandas-like API, the intermediate layer with DAG, task and IR representations and optimized implementation layer will be beneficial to the ecosystem in general and allows implementers to focus on performance layer to bring the best possible solutions to the end customers.

StormSense, an award-winning smart cities regional project of Hampton Roads, has integrated NOAA's National Water Model (NWM) 25-year retrospective simulation dataset for past hurricanes as well as forecast data with real-time water level sensors to review flood inundation perspectives that leverages streaming data. Such integrations with geo-spatial data have been made possible with OmniSci Cloud. This will enable our understanding of data with a data science perspective through simulated patterns in the future.

This talk will explore VPC Flow logs and how they can be used to increase your company's security posture. Flow Logs is an AWS feature that enables you to capture information about the IP traffic going to and from network interfaces in your AWS VPC. I'll also have tons of memes.

Image Recognition and Object Detection are one of the most common applications within the field of Artificial Intelligence and Deep Learning. AI algorithms are already being used in productive environments creating value in various processes from development to manufacturing. Learn about how the BMW Group has implemented and trained a Deep Learning model for inline quality inspection in the assembly line. Gain insight into how the BMW Group is using the parallel processing power of GPUs to train and predict models for visual inspection and quality control. Join Caroline Persson, Data Scientist at the BMW Group, as she explains how Deep Learning and GPUs have become a permanent and indispensable part of the manufacturing line at the BMW Group. Persson will show how the Data Scientists team at the BMW Group has built and trained a Deep Learning model for Object Detection ensuring the quality of their products and reducing manual efforts and rework time.

Data science and big data have always been friends, now OmniSci brings them together in a way that no one else has. Take a statistically significant look into OmniSci's Jupyter integration with Mike Hinchey and JP Harvey - how it works and how data science and data analytics are converging.

The maritime traffic control centers are overloaded with large information coming from satellite based Automatic Identification System (AIS) sources. With these large stream of data coming rapidly the human operators are at task in understanding and discovering different traffic patterns to stay alert of any critical situation. They are often made to wait for the static reports that the analysts take time to prepare. However, the new computing trend and innovation is helping to solve many important challenges and I want to highlight the use of state-of-the-art interactive visualization, database, and data mining tool through this work.

A short discussion of the pros and cons between data science on a workstation vs cloud. This presentation will outline where each solution provides the best fit for your data science needs. We will explore the performance of an edge device and how it fits with the current and future cloud architecture; this will include cost of operating in the cloud vs edge and where it makes sense to diversify the two. The future of data science will see a convergence of edge and cloud compute working seamlessly together to deliver on our information needs.

See how NVIDIA, RAPIDS and the open source ecosystem are advancing data science. In this session, we will explore RAPIDS, the open source data science platform from NVIDIA. Learn how to get started using these open-source libraries for faster performance and easier development on GPUs. See the latest engineering work and new release features, including, benchmarks, roadmaps, and demos. Finally, hear how customers are leveraging RAPIDS in production, benefiting from early adoption, and outperforming CPU equivalents.

AWS delivers an integrated suite of services that provide everything needed to quickly and easily build and manage analytic platforms. AWS-powered analytic solutions can handle the scale, and have the agility and flexibility required to combine different types of data and analytics approaches to gain deeper insights, in ways that traditional data silos and data warehouses cannot. In this Session, we will go over how OmniSci’s GPU accelerated platform makes use of different services in AWS to provide data analytics at GPU scale.

Join us for an overview of how GPU-accelerated workflows are taken to a new-level with dual NVIDIA Quadro RTX 8000 GPUs on a Z by HP Data Science Solution. This session will walkthrough Z8 on-edge workflow experiences from Lockheed Martin and share how NVIDIA & Z by HP compliment data science platforms through increased power, usability and speed.

OmniSci’s broader open source and data ecosystem integration make end-to-end business intelligence (BI) analytics a breeze. In this session you’ll see how to run your own BI workflow, from start to finish. Learn about loading data, ETL, and prep using third party BI ecosystem tools to publish dashboards and obtain related reporting.

In this session, learn how Sentry leverages OmniSci to assess and overcome transportation challenges in order to cost-effectively provide high-acuity patients with more efficient access to care in New York State. Medicaid Non-Emergency Medical Transportation (NEMT) is a benefit that provides populations with access to transportation to and from medical care using available public transportation, taxis, specialty vehicles, ambulances, and even sometimes helicopters. Unfortunately, comprehensive information and research regarding the benefit, its costs, utilization, and impact on care outcomes is difficult to gather. By leveraging OmniSci, Sentry has optimized its day-to-day operations (currently, over 5,000 daily trips serviced by over 100 different transportation providers), helped address geographical inefficiencies in its provider network, and has more readily identified outlier behavior in transportation providers, drivers, and passengers for fraud waste & abuse investigations. Sentry has also used the OmniSci platform to deliver cost savings through dedicated trip route and grouping management for one of the largest Programs of All-Inclusive Care for the Elderly (PACE) plans in the country.

What happens when the value of your data analytics department is challenged? How and when are you incorporating domain knowledge into your data? What sustainable approaches are you taking to measure ROI on data collection and presentation? Join Will Webb, part of Insight Sourcing Group’s advanced analytics leadership team, as he demonstrates how to use an analytics dashboard to answer these questions and help you drive bottom-line improvements.

Join Sean Griffin to hear how Disaster Intelligence leverages OmniSci to parse huge amounts of data to make smart decisions before and during disasters. During the second half of this interactive session, attendees will work a disaster scenario with Sean to see how OmniSci can be used to accelerate time to better decisions.

The convergence of existing systems and modern hardware brings new opportunities to address business challenges around data science productivity and efficiency. In this panel, industry experts from NVIDIA, HP, and Microsoft, weigh-in on modern GPU and CPU technologies and how customer needs are met, and exceeded, to drive faster, better insights and competitive advantage.

Wes McKinney will take the stage to provide insights into the development of open source over the past decade, open source’s contribution to the modern data science stack, and why community-led open source is at a critical point. Wes is the creator of Pandas, Ibis, author of Python for Data Analysis, co-founder and former CEO of DataPad, current Director of Ursa Labs, and member of the project management committee for Apache Arrow.

During this session we’ll dive into OmniSci’s roadmap and the exciting innovations OmniSci is driving in Data Science, Machine Learning and Artificial Intelligence. Key themes include: - Data Fusion and enrichment for analytical breadth - Continued differentiation with Performance at Scale, and Enterprise Maturity - Machine Learning + Data Science - for analytical depth Connecting with Open Source Communities to Thrive Thrive in a Data-Driven World Join industry thought leader Travis Oliphant, creator of the most widely used Python packages in data science and machine learning such as SciPy, NumPy, Numba and Dask, as he discusses the future of Tensor computing in Python. Travis will share strategies to cooperate with the open source communities in order to thrive in a data driven world.

Big Data promised us flying cars, but we seem to be stuck on the ground. Analytics tools designed for a bygone era lag far behind the volume and velocity of modern data, leaving analysts overwhelmed and unable to extract meaningful insights. But it doesn’t have to be that way. Join OmniSci co-founder and CEO Todd Mostak, along with special guests, to learn about the latest innovations bridging analytics, data science, and location intelligence, all at scale, into interactive experiences providing faster and more contextualized insights.

From OmniSci Converge 2019. Title: Fireside Chat: An Exclusive Peek into the Brains of OmniSci Abstract: What’s inside the mind and heart of some of the driving forces at OmniSci? In this 30 minute fireside chat, attendees will hear from an expert panel (ranging from product, engineering, and marketing) to round out Community Day. You’ll get to understand how our roadmaps are framed, what we’re doing to help support users and contributors, why we chose specific technical partners, and more of what’s to come.

Aaron Williams of OmniSci kicks off OmniSci Converge Community Day with a series of Lightning Talks presented by: - Pat Patterson from StreamSets: IoT Data Integration with StreamSets for Analytics in OmniSci - Umesh Gupta from NC State University: Real-time Automatic Identification System (AIS) Data Analytics - Madhav Sadhu from Tailored Brands: Lightning Talk: Leveraging Data and Analytics to Custom Fit Retail Logistics - Jacci Cenci from NVIDIA: AI-Ready Building Blocks for Deep-learning Based Accelerated Workflow and Data Curation - Alan Lipe from i2enabled: The Future of Energy Market Analytics with OmniSci