Program Schedule

Primary tabs

Tuesday, May 15, 2018

Salon A & BSalon E & F & GGateway IV & VGateway IIGateway IIIGateway I
09:00 - 09:15Pre-keynote Announcements (Salon C & D)
09:15 - 10:00 Map Like a Journalist (Salon C & D) You've cleaned a 20,000 row csv, merged it with the strange propriety data format, and miraculously rendered the result into an interactive map. To you, every data point and zoom-level is fascinating. To a casual reader, it's overwhelming and opaque. To reach a wide audience and deliver a memorable conclusion, a map must tell a compelling story. Cartographers can borrow the narrative tricks of journalists to create relatable characters, build stakes, and highlight satisfying resolutions. We'll explore powerful storytelling techniques to help present maps that readers... Map Like a Journalist (Salon C & D) My Schedule Please sign in to add a session to your schedule. Provide Feedback
10:00 - 10:30Post-keynote Break
10:30 - 11:05 PostGIS Query Festival You're part of the SELECT group of PostGIS users, but you want to UPDATE your skills, to INSERT some knowledge on performance and how to structure queries for common spatial analysis problems. You should go to the PostGIS Query Festival! JOIN your friends at the festival main stage, WHERE the headlining act will look at common use cases, like nearest neighbor joins, overlay, calculating with geodetics, automatic form fills, and other classic spatial queries. DELETE your preconcieved notions about relational databases, and learn about how PostGIS can be used with advanced... PostGIS Query Festival My Schedule Please sign in to add a session to your schedule. Provide Feedback Raster Vision: Deep Learning for Aerial and Satellite Imagery Increasingly, deep learning is being used to make sense of the vast quantity of satellite and aerial imagery being generated each day. Although there are many open source libraries for deep learning, they are unable to handle geospatial datasets without the addition of a non-trivial amount of extra data processing glue code. Over the past year, we have prototyped workflows for the computer vision tasks of classification, object detection, and semantic segmentation. After reflecting on these early prototypes, we have assembled a set of objectives and architectural principles for a generic... Raster Vision: Deep Learning for Aerial and Satellite Imagery My Schedule Please sign in to add a session to your schedule. Provide Feedback How To Image the Entire Earth Every Day Planet, a young San Francisco-based company, has put over 150 satellites into space with the goal of imaging the entirety of the earth's surface once a day. This goal was achieved with the completion of Mission 1 in 2017, and Planet's unique data set is now transforming how we are able to monitor our world and see changes as they occur. In order to make this imagery accessible, Planet has built a powerful end-to-end system to process data as it arrives on earth and disseminate it to users through the Internet. This talk will walk through the development of Planet's satellite... How To Image the Entire Earth Every Day My Schedule Please sign in to add a session to your schedule. Provide Feedback Building an Image Processing Pipeline at Scale using Open Source (sponsored by Boundless) Farmers Edge provides innovative agricultural practices that help growers boost crop production and improve sustainability.  After recently acquiring an exclusive industry wide redistribution agreement for Planet data, Farmers turned to Boundless and Open Source GIS to build an image processing pipeline capable of handling the throughput of such a large collection.  Come hear how Spark, GeoTrellis, GeoServer, Elastic and Azure were used to build a first class processing pipeline Building an Image Processing Pipeline at Scale using Open Source (sponsored by Boundless) My Schedule Please sign in to add a session to your schedule. Provide Feedback How Green Was My Valley - Spatial Analytics with PostgreSQL, PostGIS, R, and PL/R Increasingly today, collected data includes a spatial component. PostgreSQL + PostGIS, combined with R via PL/R, provides an awesome tool-chain for advanced spatial analytics on such data! This presentation will introduce the audience to PL/R, discuss the pros and cons of this approach to spatial data analysis, then walk through examples of advanced spatial analysis using PostgreSQL, PostGIS, and PL/R. Overview Tutorial problem set Components Environment setup Ingest   Admin boundaries... How Green Was My Valley - Spatial Analytics with PostgreSQL, PostGIS, R, and PL/R My Schedule Please sign in to add a session to your schedule. Provide Feedback NASA DEVELOP - Free & Open Source Tools for Earth Science The NASA DEVELOP Program conducts interdisciplinary feasibility projects that apply the lens of NASA Earth observations to community concerns around the globe. DEVELOP projects showcase the use of free access satellite imagery and incorporate FOSS4G to ensure that end users have access to the final products. Tools and software from successful projects go through NASA’s software release process and are hosted on public facing repositories. Each project is designed with a specific community concern and end user in mind, yet the methodologies and tools developed can be beneficial to a... NASA DEVELOP - Free & Open Source Tools for Earth Science My Schedule Please sign in to add a session to your schedule. Provide Feedback
11:15 - 11:50 How Not to Use osm2pgsql Osm2pgsql is a command line tool that converts OpenStreetMap data to a Post-GIS enabled PostgreSQL database, where it can be visualized using a wide variety of tools. Although osm2pgsql can import and update large datasets, it is not a one size fits all – or one size fits most – tool. Forced to make a quick decision, our team picked osm2pgsql for automatically loading OSM data into a database, and almost immediately regretted it. Importing large files took hours to complete. Appending files to our database took even longer, and any overlap between two files caused the import to... How Not to Use osm2pgsql My Schedule Please sign in to add a session to your schedule. Provide Feedback R Notebooks: A New Paradigm for Geospatial Data Science Imagine a world where a high quality report is a happy consequence of writing your everyday code. Or maybe you want to render your script directly to an html or pdf file or share maps, plots, and tables by simply sending a link to your colleagues for review? Notebooks provide an easy way to build and share transparent, reproducible analyses that weave together code, text, and graphics into a single, production-quality document. On the data science team at TellusLabs, we have adopted R notebooks as an interactive documentation and communication tool – akin to the physical lab notebook... R Notebooks: A New Paradigm for Geospatial Data Science My Schedule Please sign in to add a session to your schedule. Provide Feedback Best Practice for Serving COG Imagery using MapServer in the Cloud (sponsored by AWS) Recently there has been quite a bit of interest in Cloud Optimized GeoTIFFs (COG) that can be built using GDAL's raster utility programs gdal_translate and gdaladdo. This work has been supported by companies such as Planet and Digital Globe. COGs are GeoTIFFS that are internally structured to support efficient HTTP range-gets (partial file requests) such that they can be used in-situ in object stores such as Amazon S3. That means its unnecessary to initially download the GeoTIFFs to a local file system before use. The bigger the data the greater the... Best Practice for Serving COG Imagery using MapServer in the Cloud (sponsored by AWS) My Schedule Please sign in to add a session to your schedule. Provide Feedback 2.5D !== 3D While 3D virtual globes and maps have been around for over 20 years, advances in JavaScript and WebGL have made them increasingly popular. Unfortunately, this has led to a rash of pseudo 3D maps, which are really just extruded 2D representations (AKA 2.5D) that give real 3D a bad name. So what's wrong with 2.5D and what makes 3D different? Based on our experience creating Cesium, I'll present the unique challenges 3D offers and the important problems it solves in visualization, augmented reality, autonomous vehicles, and more. 2.5D !== 3D My Schedule Please sign in to add a session to your schedule. Provide Feedback Interacting with National Water Model (NWM) Predictions The increasing availability of large-scale cloud computing resources has enabled large-scale environmental predictive models such as the National Water Model (NWM) to be run essentially continuously. Such models generate so many predictions that the output alone presents a big data computing challenge to interact with and learn from. Researchers at the Harvard Center for Geographic Analysis are working with the open-source, GPU-powered database MapD to provide true interactive access to NWM predictions for stream flow and ground saturation across the entire continental US and... Interacting with National Water Model (NWM) Predictions My Schedule Please sign in to add a session to your schedule. Provide Feedback Mobile Awareness GEOINT Environment (MAGE) The Mobile Awareness GEOINT Environment, MAGE, provides dynamic capabilities for mobile situational awareness. Originally developed to support first responders deploying in the event of natural disasters, the MAGE app on your mobile device allows you to create geotagged field reports and observations that contain media such as photos, videos and voice recordings and share them instantly with other members of your team. Using the GPS in your mobile device, MAGE can record user locations in real time. Your locations can be automatically shared only with the other members of your... Mobile Awareness GEOINT Environment (MAGE) My Schedule Please sign in to add a session to your schedule. Provide Feedback
12:00 - 12:35 Breaking the 4th Dimension: temporal data in PostgreSQL and PostGIS It is “well known” that 80% of all data has a spatial component. What is less well known is that 100% of data contains a temporal component. For some data it may simply be the date that the data was released. For other, there may be a separate date/time for each separate row or feature. And yet still for others, such as vehicle tracks, there is time information that changes along a feature itself. This talk will give an overview of some of the issues involved in dealing with temporal data with PostGIS and PostgreSQL. This talk will give an introduction to... Breaking the 4th Dimension: temporal data in PostgreSQL and PostGIS My Schedule Please sign in to add a session to your schedule. Provide Feedback Monitoring critical infrastructure: GeoMesa and NRT analytic development in notebooks 2017 saw critical outages and interruptions that affected air- and maritime-traffic: hurricanes, computer outages, physical threats, and more. In this talk, we show how these events can be detected using rapidly-developed geo-temporal analytics in Zeppelin and Jupyter notebooks, all backed by GeoMesa (and visualized in Stealth). Key points to review include: identify example outages:  Delta airlines outage in January 2017 (also British Airways and others); China's Jupiter container-ship runs aground outside of Antwerp; maritime traffic rerouted by... Monitoring critical infrastructure: GeoMesa and NRT analytic development in notebooks My Schedule Please sign in to add a session to your schedule. Provide Feedback GeoServer & PostGIS in Containers and on Kubernetes You have heard about Docker containers and Kubernetes and wonder how you can use them in your Geo work. The purpose of this workshop is to get you going running some of the usual Geo Suspects in (PostGIS and GeoServer) in containers and in a full Kubernetes instance (the OpenShift distribution) , all from the comfort of your laptop. You will learn about containers, their orchestration, and the benefits they bring to your everyday work. You will be able to bring the work home with you to increase your cloud-native-fu! GeoServer & PostGIS in Containers and on Kubernetes My Schedule Please sign in to add a session to your schedule. Provide Feedback The Road to 200,000 Downloads: The Cesium Story Since its creation, the Cesium community has grown dramatically and now has nearly 150 community contributors and millions of users. This talk shares how, without any traditional marketing, we’ve been so successful in building that community. Much of the momentum around this open source project has come from capturing and focusing the inherent energy in the community, including facilitating effective conversations, encouraging the work of contributors, and amplifying the messages of developers and users. The talk will share strategies that we've found successful and not so... The Road to 200,000 Downloads: The Cesium Story My Schedule Please sign in to add a session to your schedule. Provide Feedback How NASA is Building a Petabyte Scale Geospatial Archive in the Cloud NASA's Earth Observing System Data and Information System (EOSDIS) is working towards a vision of a cloud-based, highly-flexible, ingest, archive, management, and distribution system for its ever-growing and evolving data holdings. This free and open source system, Cumulus, is emerging from its prototyping stages and is poised to make a huge impact on how NASA manages and disseminates its Earth science data. This talk outlines the motivation for this work, present the achievements and hurdles of the past 18 months and charts a course for the future expansion of Cumulus. We... How NASA is Building a Petabyte Scale Geospatial Archive in the Cloud My Schedule Please sign in to add a session to your schedule. Provide Feedback
12:35 - 14:00Lunch (Archview Ballroom)
14:00 - 14:35 A spatial operator walks into a bar and sees two GeoWave tables.. It asks "Can I join you?" Yes, and efficiently! GeoWave has been constantly improving its functionality and support for efficient spatial operations at scale. Spark has been critical to further development of large scale data processing, and while it has many data operations it performs well one of the operations it struggles with is spatially joining large datasets. GeoWave has implemented a way of leveraging its own tiered Hilbert curve indexing methods and a tiered join algorithm with Spark to significantly improve spatial join queries. Resulting in considerably... A spatial operator walks into a bar and sees two GeoWave tables.. My Schedule Please sign in to add a session to your schedule. Provide Feedback Make your own Satellite Imagery Machine Learning Data Label Maker is an open source python library to help in extracting insight from satellite imagery. Label Maker creates custom machine-learning-ready training data for most popular ML frameworks, including Keras, TensorFlow, and MXNet. Supervised machine learning methods require two things: satellite imagery and ground-truth labels. If you’re looking to train a model in Potsdam or a few other select cities, there are good datasets already available. But if you need a custom class label or want to train in areas closer to where you’ll be using the model, you’ll... Make your own Satellite Imagery Machine Learning Data My Schedule Please sign in to add a session to your schedule. Provide Feedback Speed Meets Scale: Analyzing & Visualizing Geospatial Data with GPUs Thanks to the proliferation of geospatial data from sensors, smart phones, social media and transportation data, developers and users can explore and analyze that data to detect anomalies and discover game-changing insights. But, given the lagging query times and speed of traditional computing systems, accessing those insights in a timely manner can be costly. Enter open source GPU-analytics. In this talk, Todd Mostak, CEO & Co-Founder of MapD, will deep dive into the capabilities of open source GPU-analytics and the role they are playing in advancing the visualization and... Speed Meets Scale: Analyzing & Visualizing Geospatial Data with GPUs My Schedule Please sign in to add a session to your schedule. Provide Feedback CityGML, 3D Tiles and Cesium - A Data Fusion Symphony As CityGML's popularity has grown, more cities, governments, and organizations are looking towards CityGML as their primary city data format. While CityGML is a versatile and exhaustive data storage and exchange format for city infrastructure and landscapes, storing data in large XML files does not lend itself very well to high performance streaming and rendering. This talk presents the use cases and results from the Cesium team's participation in the Open Geospatial Consortium (OGC) Testbed 13 Initiative where we developed a tiling pipeline to convert CityGML... CityGML, 3D Tiles and Cesium - A Data Fusion Symphony My Schedule Please sign in to add a session to your schedule. Provide Feedback Using Cesium and Open Source for Visualization of Atmospheric and Space Science Data At the Laboratory for Atmospheric and Space Physics (LASP), we create visualizations of science data from around Earth and Mars in order to provide insight that the raw data does not make readily apparent. In this talk we'll examine life before our adaption of open source and the advantages reaped by switching to a more open tool-chain. We'll showcase our use of Cesium and Highstock (not OSS, but free for non-profits) in plotting geospatial and in-situ orbit data for various satellite missions and show how these tools have helped provide insight to scientists. Using Cesium and Open Source for Visualization of Atmospheric and Space Science Data My Schedule Please sign in to add a session to your schedule. Provide Feedback SIMILARITY ASSESSMENT OF LINEAR HYDROGRAPHIC FEATURES USING HIGH PERFORMANCE COMPUTING SIMILARITY ASSESSMENT OF LINEAR HYDROGRAPHIC FEATURES USING HIGH PERFORMANCE COMPUTING L. V. Stanislawski, J. Wendel, E. Shavers U.S. Geological Survey, Center of Excellence for Geospatial Information Science, 1400 Independence Road, Rolla Missouri, 65401, United States (lstan, jwendel, eshavers)@usgs.gov T. Li University of Illinois at Urbana-Champaign, CyberGIS Center, 2046 Natural History Building M-C 150, 1301 W. Green Street,  Urbana,... SIMILARITY ASSESSMENT OF LINEAR HYDROGRAPHIC FEATURES USING HIGH PERFORMANCE COMPUTING My Schedule Please sign in to add a session to your schedule. Provide Feedback
Academic lstanislawski intermediateintermediateintermediate
14:45 - 15:20 BYOB: Plug and Play Backends with GeoWave As is the case with many modern technologies, there is not a single standard distributed computing framework that is used ubiquitously. While many function similarly, there are numerous options and in practice, there are generally performance tradeoffs that can make a certain framework better for a given task. In this presentation we discuss the work done in the GeoWave framework to natively integrate open source key-value stores such as Accumulo, HBase and Cassandra as well as externally hosted key-value stores such as DynamoDB and BigTable. By drawing on the many... BYOB: Plug and Play Backends with GeoWave My Schedule Please sign in to add a session to your schedule. Provide Feedback Working with OpenStreetMap using Apache Spark and GeoTrellis OpenStreetMap (OSM) is a rich trove of geospatial data. However, the OSM data model of nodes, ways and relations presents challenges to those of us who are used to working with geospatial data encoded into the Points, LineStrings and Polygons we all know and love. On top of this, it's quite a large and unwieldy dataset to work with. In this talk, I'll describe how Azavea and others have been using Apache Spark and GeoTrellis to do analytics on historical OSM data to answer questions like  "how many kilometers of roads have been edited, ever, as part of the #... Working with OpenStreetMap using Apache Spark and GeoTrellis My Schedule Please sign in to add a session to your schedule. Provide Feedback Taming Billions of LIDAR Points with GPU Database MapD LIDAR, or “Light Detection And Ranging” is a technology which generates 3D point clouds by bouncing signal off objects.  It can be deployed from satellite, airplane, drone or ground-mounted sensors, and generates hundreds of millions to billions of data points.  Such datasets can overwhelm conventional visualization tools and databases.  For example, Florida has comprehensively mapped its coastal zones with aerial LIDAR, an open dataset of several billion points. These are managed as thousands of arbitrarily-tiled files, and must often be heavily pre-processed... Taming Billions of LIDAR Points with GPU Database MapD My Schedule Please sign in to add a session to your schedule. Provide Feedback Data Fusion With 3D Tiles There are many point cloud viewers, there are many photogrammetry viewers, there are many BIM and CAD viewers. 3D viewers tend to specialize in a single domain. While there is nothing wrong with this approach, there is a growing need to visualize disparate datasets together in shared space. This need continues to be a driver for 3D Tiles, an open specification for streaming massive heterogeneous 3D geospatial datasets. With 3D Tiles and Cesium we can go beyond toggling different layers and actually "fuse" data together, whether that means coloring a point cloud based on its... Data Fusion With 3D Tiles My Schedule Please sign in to add a session to your schedule. Provide Feedback Smart Citizens for Smart Cities - An open source and crowd sensing system for smart city air sensing What if you can see the air you breath? This talk presents an open-source and crowd-sourced air monitoring system across Canada. More than 200 air quality sensors have been deployed by volunteers across Canada and more than 500 sensors will be deployed before March 2018. This talk will share the system design, the air quality data collected by the IoT nodes, and the insights we were able to extract from the hyper-local air quality data, and the lessons learned from hosting more than 10 make-your-own-sensor workshops. According to a WHO study, ambient air quality has significant... Smart Citizens for Smart Cities - An open source and crowd sensing system for smart city air sensing My Schedule Please sign in to add a session to your schedule. Provide Feedback Leveraging open source technologies to produce insights from UAV-derived ortho mosaics at scale The agricultural industry often uses aircraft to survey and collect information on fields and crops.  Data Scientists use imagery collected by these aircraft to gather several metrics that may include: plant height, plant count, plant health, presence of nutrients, presence of disease, presence of weeds, relative biomass estimates, and 3D / volumetric data. UAVs provide a unique opportunity as the resources needed for collection is a small fraction of manned aircraft.  Using a small fleet of UAVs, an organization is capable of imaging and processing large areas in short... Leveraging open source technologies to produce insights from UAV-derived ortho mosaics at scale My Schedule Please sign in to add a session to your schedule. Provide Feedback
15:20 - 15:45Afternoon Break
15:45 - 16:20 Exposing your Endpoints: A Look into GeoWave's Web Services Even though web services aren’t exactly a new technology, there have been advances in protocols and payloads such as HTTP/2 and protobuf that enable scalability. Even with basic JSON-based services, there are a number of new and meaningful ways that older technologies can be innovatively applied to FOSS4G technologies today. The GeoWave team is excited to present the variety of web services that have been made available in recent releases. Exposing web endpoints allows a user to remotely access the functionalities of GeoWave. These services make it easier for other technologies to... Exposing your Endpoints: A Look into GeoWave's Web Services My Schedule Please sign in to add a session to your schedule. Provide Feedback RasterFrames: Enabling Global-Scale Geospatial Machine Learning RasterFrames™, a proposed LocationTech project, brings the power of Spark SQL and Spark ML to the analysis of global-scale geospatial-temporal raster data. Employing the rich geospatial primitives of LocationTech GeoTrellis and GeoMesa, RasterFrames provides scientists, data scientists and software developers with a unified data and compute model for building image processing pipelines for ETL, data-product creation, statistical analysis, supervised & unsupervised machine learning, and deep learning. Data scientists particularly benefit from the DataFrame-centric entrypoint into... RasterFrames: Enabling Global-Scale Geospatial Machine Learning My Schedule Please sign in to add a session to your schedule. Provide Feedback Birth of the 3D Elevation Program: How a Map Factory became a Big Data Producer For over 130 years, the US Geological Survey (USGS) has been the nation’s premier governmental map making organization. Gone are the days of producing maps from topographic surveys, artistic sketches and printing on copper plates. Today’s topographic maps are derived from high resolution digital data designed to be consumed on a variety platforms. The need for high resolution elevation data is vast and increasing demand has led to the creation of the 3D Elevation Program. The overarching purpose of the 3D Elevation Program is to systematically collect 3D elevation data over the... Birth of the 3D Elevation Program: How a Map Factory became a Big Data Producer My Schedule Please sign in to add a session to your schedule. Provide Feedback mago3D. Let's integrate BIM/AEC with 3D GIS on your web browser. Although there have been numerous attempts to integrate BIM and 3D GIS on a single web platform, the outcome of those attempts are not so satisfactory to date. The difference of data models, the massive number of objects to be rendered, the big volume of data files, and proprietary technologies are among the major barriers that hindered seamless integration of BIM and 3D GIS on a web environment. This session introduces 'mago3D', an open source based GeoBIM platform that can manage, handle, and visualize massive 3D data from BIM and 3D GIS simultaneously on a web browser. It has... mago3D. Let's integrate BIM/AEC with 3D GIS on your web browser. My Schedule Please sign in to add a session to your schedule. Provide Feedback Using GDAL to manage OpenStreetMap data in Oracle Spatial (sponsored by Oracle) Recent enhancements to GDAL/OGR provide improved loading of OpenStreetMap data to Oracle Spatial, including complete capture of tags into natively indexed JSON. We will cover the process to load and configure OpenStreetMap data in Oracle Spatial. This will include a discussion of overall requirements, detailed steps, run-time reporting, and plans for additional GDAL/OGR improvements. In addition, we will present an update on  other tools and use cases for GDAL on Oracle Spatial for raster and vector transformation, loading, and service delivery.  Using GDAL to manage OpenStreetMap data in Oracle Spatial (sponsored by Oracle) My Schedule Please sign in to add a session to your schedule. Provide Feedback Monsanto’s GeoImagery Pipeline – A Holistic Approach to Automatically Ingest and Process Imagery From Multiple Sources At Monsanto, we gather several types and formats of images from multiple platforms and sensors.  In the past, we developed individual processes and services for each imagery sources.  For example, manned aerial images (MAV) were processed by one team for a purpose, while satellite imagery was processed by another team for an entirely different purpose. We are currently in the process of developing one enterprise Geo-Imagery Pipeline designed to receive, ingest, process, and distribute imagery and imagery derived products to all interested stakeholders. This... Monsanto’s GeoImagery Pipeline – A Holistic Approach to Automatically Ingest and Process Imagery From Multiple Sources My Schedule Please sign in to add a session to your schedule. Provide Feedback
16:30 - 17:05 Converging GeoData, Big Data, And Web Applications (sponsored by Red Hat) For most of my lifetime in the computing world, GIS, data crunching and web serving were three very separate worlds. If a web app wanted access to the analysis there was a long process of ETL, DB work, imports and exports, and bribing various network and storage people for the resources you needed. If you were in GIS you could rinse and repeat this cycle. With the rise of containers, orchestration, cheap computing and networking, and over 10 years of people tackling large problems at new scales we have finally come to a convergence. It is now possible for us to actually use the same... Converging GeoData, Big Data, And Web Applications (sponsored by Red Hat) My Schedule Please sign in to add a session to your schedule. Provide Feedback Enabling spatial analysis – point data to multi-polygon layer Collected geospatial data may be in various formats – raster or vector (point, lines or polygons). When the use case requires us to perform analysis on a bound area, vector data in the form of points sometimes cannot facilitate our analysis. In such cases, the points need to be converted into a multi-polygon layer in order to facilitate various functional analysis based on the spatial data. This talk explores the implementation of an approach to build a multi-polygon layer from point vector data. The common approach is to combine point vectors to form lines, combining lines... Enabling spatial analysis – point data to multi-polygon layer My Schedule Please sign in to add a session to your schedule. Provide Feedback Urban Change Monitoring and OSM Urban regions often change rapidly and unevenly - some areas develop and grow while others deteriorate. Public datasets like OpenStreetMap (OSM) can lag behind, often in these crucial areas. A lot of focus in this space has been given to supplementing OSM with automatically detected features, such as through Machine Learning (ML) methods, in order to get the most recent vector datasets. However, for some users, it is change over time that is of interest rather than the latest and most accurate representation. City planners can use this data to track development and help plan for the future... Urban Change Monitoring and OSM My Schedule Please sign in to add a session to your schedule. Provide Feedback Adding weather data to your geospatial applications using Open Source tools (sponsored by IBM) Weather is something that affects everybody's daily life and is closely tied to the geographic location. In the session, you will learn how to integrate weather data from IBM Weather Company in your geospatial application using open source technologies such as Python, Spark and Mapbox GL JS that leverages IBM Watson data and AI platform. Weather Company provides most accurate weather forecast and is used by over 100 million users. If you are building predictive models that needs weather data, then you don’t want to miss this session. You will learn how to build more... Adding weather data to your geospatial applications using Open Source tools (sponsored by IBM) My Schedule Please sign in to add a session to your schedule. Provide Feedback Leveraging open source geospatial technologies at scale in a commercial environment...and the keys to success Open source technologies are sometimes questioned because of how they may scale or may be easily adopted in an enterprise commercial environment. To enable full adoption across the enterprise in an environment that previously used another user-based licensing models there are a few steps that need to be considered. Hybrid models are good but can delay adoption across the company if not chosen carefully. At Monsanto we have gone over a full rework of our geospatial environment in less than 12 months to adopt open source standards. This talk will cover the journey since our newly created... Leveraging open source geospatial technologies at scale in a commercial environment...and the keys to success My Schedule Please sign in to add a session to your schedule. Provide Feedback Machine learning, FOSS, and open data to map deforestation trends in the Brazilian Amazon. Monitoring deforestation across the globe is important for understanding macro-scale impacts on carbon sequestration and climate change. We trained a land cover machine learning model to monitor forest changes anywhere in the world. Our effort combines Apache Spark’s distributed machine learning, raster operations from LocationTech GeoTrellis, and the newly open-sourced RasterFrames library. RasterFrames let us apply GeoTrellis raster operations within Spark SQL, thereby homogenizing imagery queries and streamlining feature engineering. Using approximately 2,000 hand-labelled sites... Machine learning, FOSS, and open data to map deforestation trends in the Brazilian Amazon. My Schedule Please sign in to add a session to your schedule. Provide Feedback
17:05 - 18:30Exhibitors Reception
18:30 - 19:30Reserved for Birds of a Feather (BoF) Sessions
Reserved for Birds of a Feather (BoF) Sessions
Reserved for Birds of a Feather (BoF) Sessions
BoF: SpaceNet and Geospatial Machine Learning Moderator: Todd Bacastow SpaceNet is a partnership initiative between CosmiQ Works, NVIDIA, and Radiant Solutions that fosters open research and innovation in development of machine learning algorithms to automatically extract information from remote sensing data.  During this BoF, we invite all interested in geospatial machine learning, interested in accessing SpaceNet’s public datasets, or those who may have competed in a SpaceNet Challenge to join us for conversation on how these datasets and algorithms are influencing the FOSS4G community. We will discuss future... BoF: SpaceNet and Geospatial Machine Learning My Schedule Please sign in to add a session to your schedule. Provide Feedback
BoF: UK Government's Digital Marketplace - How to tap into the £2.6Bn spent on cloud services by the UK Public Sector The UK Government launched the Digital Marketplace (https://www.digitalmarketplace.service.gov.uk/) several years ago, and it enables the UK Public Sector to puchase cloud hosting, software and support. To date the UK Public Sector has purchased over £2.6Bn of cloud services (https://www.gov.uk/government/collections/digital-marketplace-sales) In this session I propose that we have a discussion about; The Digital Marketplace How to list your Geo services How the UK public sector purchases cloud services Q&A... BoF: UK Government's Digital Marketplace - How to tap into the £2.6Bn spent on cloud services by the UK Public Sector My Schedule Please sign in to add a session to your schedule. Provide Feedback
Reserved for Birds of a Feather (BoF) Sessions

Our Sponsors

For information about becoming a sponsor, please visit the FOSS4G NA 2018 sponsor prospectus page.

Platinum

Gold

Silver

Bronze

Mapping Theme Day

Community

Supporter

Conference App Provider

EclipseCon Support Other Events

Our Other Events

Eclipse events are hosted all over the world!

  • Foss4G NA 2018
  • Eclipsecon France 2018