In this talk, we’ll discuss the process of developing an Automotive Geospatial ecosystem, starting with the challenges of defining a mapping team and the potential for scope expansion. We’ll outline the key principles for a successful geospatial framework in the automotive industry and share practical examples of what worked and what we learned.

Geospatial analytics are an important component for telecommunications companies. It is useful to understand who a company can serve and how well they can serve; both can be better understood using a combination of open source and internal datasets. This presentation seeks to cover geospatial analytics performed on open-source datasets, optimization techniques for processing the data, and the need for the analysis at scale.

Join Daniel Lewis, Distinguished Data Scientist, and Matthew Konski, Senior Data Solutions Engineer, as they explore how Geotab, a telematics industry leader, addresses the map matching problem at scale using Google BigQuery. This presentation will detail the advanced framework behind this high-performance solution, applicable to intelligent transportation systems and telematics. Additionally, they will highlight a real-world application on how the data behind this solution was used to inform infrastructure resiliency.

This talk explores the vital intersections of data, analytics, and communications. In a world full of data, analytics, and artificial intelligence, statistical graphics, and visualizations are everywhere; however, many of these complex artifacts leave a lot to be desired. Using examples from the NBA, we will explore how well-designed spatial data graphics have an unprecedented ability to change minds and change the world

We'll be exploring the application of GIS and spatial analytics within the flood insurance industry. We investigate how spatial data can be leveraged to optimize underwriting decisions, enhance risk monitoring through real-time storm tracking, and effectively manage tail risk using catastrophe modeling. By demonstrating the practical implementation of these GIS-driven solutions, we aim to showcase their potential for improving operational efficiency, underwriting accuracy, and risk mitigation in the insurance sector.

Our research applies natural language processing techniques to annual, longitudinal real estate advertisement data from the Multiple Listing Service (MLS) to advance our understanding of neighborhood dynamics. We will showcase two examples. The first uses a semi-supervised text classification method to group property listings based on similarities in their descriptions. We then demonstrate how this classification explains subsequent neighborhood-scale mortgage applicants by race and income, revealing stark racial differences in who responds to the ads. The second explores the evolution of advertisement language in neighborhoods that experienced significant racial changes from 2000-2020.

Advances in AI have led to promising new opportunities to advance the UN SDGs, including SDG 4, which aims to “ensure inclusive and equitable quality education and promote lifelong learning opportunities for all”. Giga, a global initiative by UNICEF and ITU, aims to connect every school to the internet by 2030 by leveraging AI-enabled mapping solutions. We proposed an AI-assisted school mapping and internet connectivity prediction pipeline to support data-driven infrastructure development in underserved communities. We evaluate our models in five pilot countries: Bosnia and Herzegovina, Belize, Botswana, Guinea, and Rwanda. Finally, we demonstrate our end-to-end pipeline to identify new schools and predict their connectivity status within 10 districts in Botswana.

Crafting location intelligent analysis requires geospatial data and lots of it. Finding current, authoritative sources and then applying a disciplined machine learning model is a workflow that will be required for reliable results. This presentation will demonstrate a model for identifying the locations of high potential residential or commercial growth regions to anticipate the need for telecommunication broadband capacity, retail, or other public safety support services as examples. A growth model was developed that evaluates factual, property indicators within the context of growth events, such as land use or ownership changes, and considers factors of time and areal proximity to develop a growth score for each property using machine learning.

Learn how GeoPostcodes partnered with Wherobots to harness the power of Apache Sedona on Wherobots Cloud to better understand population data. Explore the innovative methods that made this possible, and see how this collaboration unlocked new possibilities - slashing processing time from weeks to just hours.

As a purpose driven investment firm, EQT Group has multiple investments across valuation stages that are contributing to climate change mitigation and adaptation, both in the private equity and infrastructure asset classes. The presentation will focus on a high-level, how the internal data science and AI team, Motherbrain Labs, works with geospatial analysis across an investment life cycle: from sourcing and screening high potential investments to driving value creation in portfolio companies with decarbonization goals.

In our increasingly digital world, affordable access to high-speed broadband is a necessity to fully participate in our society, yet there are still millions of American households without internet access. The first step in this process is mapping the digital divide. Which households don’t have access to the internet at home? Where do they live? What are their specific needs? Public data sources aren’t sufficient for building a true understanding of digital inclusion needs. To fill in the gaps in existing data, HR&A creates digital equity surveys to build a more complete picture before developing digital equity plans. HR&A’s used CARTO and Amazon Redshift to process survey findings more efficiently, resulting in a 75% reduction in overall deployment and dashboard management time.

This presentation will delve into the intersection of spatial data and machine learning to predict crop yields. Leveraging advanced spatial analytics, the talk will showcase how data from various sources, including remote sensing and historical crop performance, can be integrated and analyzed to forecast yields with greater accuracy. This approach not only helps farmers optimize their practice but also connects them with markets more effectively, ultimately contributing to a more sustainable agricultural ecosystem.

Geospatial data plays a critical role in many aspects of grocery delivery. This talk follows the journey taken by a fulfilled order, highlighting a few examples of how we use spatial data and tooling, and where we've developed a bottom-up geospatial culture to continually improve the reliability and efficiency of our service.

‍