Latest Contributions by KelleyArroyo

  Join us for a webinar highlighting new developments, available via both the desktop and the web, for ArcGIS Maritime.   In this webinar, we will demonstrate new capabilities in ArcGIS Pro that greatly simplify the management, validation, and generation of S-57 products. Additionally, we will illustrate how, in just a few clicks, you can leverage Web GIS to generate custom paper nautical charts directly from electronic navigational chart data. With the latest release of ArcGIS Maritime for the server, these fully automated custom chart products are capable of leveraging custom symbology, including traditional INT1 paper chart symbols.   Two dates and times available! March 23, 2021 | 7:00 p.m. (PST) March 24, 2021 | 7:00 a.m. (PST)   Register Now! ... View more

  Learn how new technologies and standards work best in hydrospatial systems to organize data, create information products, and support decision-making anywhere and at any time through sensors, artificial intelligence, and experts far apart from each other.   This webinar will cover the following: How to work with voxels and do multidimensional analysis Taking advantage of the Internet of Things (IoT) and big data using software as a service (SaaS) for mapping and analytics How to quickly create effective web services The role of the IHO S-100 series   Two dates and times available! February 16, 2021 | 7:00 p.m. (PST) February 17, 2021 | 7:00 a.m. (PST) Register Now!   ... View more

Unlocking Your Data's Potential with Spatial Analysis and Data Science in ArcGIS   National Government Webinar Series   This webinar explores how you can discover patterns and trends in your data with capabilities across the ArcGIS suite, from ArcGIS Pro to ArcGIS Notebooks and ArcGIS Insights. Topics covered include the following: Discovering the newest tools for data engineering and spatiotemporal outlier detection and ways you can leverage deep learning algorithms with no coding required Taking workflows to the web using ArcGIS Notebooks and ArcGIS API for Python to integrate open-source Python libraries with organizational data feeds and automate the process of collecting, updating, and visualizing your data in a web app Using ArcGIS Insights to quickly perform location-enabled data analysis, create interactive charts and maps, and save and publish results in a report that can be shared with customers and colleagues   Questions?  If you have any questions about this presentation, please comment below in the "Replies" area of this post and engage with our Esri Team!    Additional Resources: Presentation Slide Deck PDF Spatial Data Science  Python Libraries  R-ArcGIS Bridge  Spatial Stats  Learn ArcGIS  ArcGIS.Learn Documentation Sample Notebooks  Spatial Data Science MOOC  Courses Deep Learning Libraries Installer for ArcGIS Pro 2.7  Sample notebook from the Esri Spatial Analysis webinar ... View more

Authored By: Steve Snow Esri Senior National Government Industry Strategy Specialist Part 4 of  a 7 part series exploring GIS and Artificial Intelligence   Welcome to part 4 of my AI and GeoAI Series that will cover the more technical aspects of GeoAI and ArcGIS. Previously, part 1 of this series covered the Future Impacts of AI on Mapping and Modernization which introduced the concept of GeoAI and why you should care about having an AI as a future coworker. Part 2 of the series, GIS, Artificial Intelligence, and Automation in the Workplace covered specific geospatial professions that will be drastically effected by introduction of GeoAI technology in the workplace. Part 3 addressed Teaming with the Machine - AI in the workplace the emergence of the new geospatial working relationship between information, humans, and artificial intelligence to be successful in an organizations mission. For part 4, we will address 3 specific GeoAI areas in ArcGIS that will help you with your journey to developing your Deep Learning workflows. Tools to Generate Training Data Tools & APIs for Training Models Tools to perform inferencing, such as object detection, land cover classification and more...   Tools to Generate Training Data ArcGIS has many tools that help with GeoAI workflows for data preparation and analysis, training deep learning models, inferencing, and sharing data for collaboration with web services and maps. The tools for creating AI training can be found in ArcGIS Pro Image Analyst and ArcGIS Image Server. ArcGIS Image Analyst has tools for labeling objects and exporting training model for deep learning and using trained models for feature extraction or classification. ArcGIS Image Server in the ArcGIS Enterprise 10.7 and above has the same capabilities and allows scaling through distributed computing using clouds on premise, off premise, or hybrid cloud approaches. Besides using prebuilt tools within the ArcGIS products, users can also work through scripting and notebooks.   Tools & API’s for Training Models Training models can be done either through ArcGIS notebooks, ArcGIS Learn API, or in ArcGIS Pro. ArcGIS Notebooks enable a one-click access to pre-configured Jupyter Notebooks. This includes time-saving deep learning libraries using a gallery of pre-configured notebooks that contain deep learning models for easy training and deployment. The arcgis.learn is a module in the ArcGIS API for Python which enable organizations to easily adopt and apply deep learning in their workflows. arcgis.learn enables simple and intuitive training of state-of-the-art deep learning models. arcgis.learn allows for much faster training and removes the guesswork in the training process. It integrates seamlessly with the ArcGIS platform by consuming the exported training samples directly, and the models that it creates can be used directly for inferencing in ArcGIS Pro and ArcGIS Image Server. ArcGIS Pro users can utilize Deep Learning training methods for classification of remotely sensed data. Pixel classification, image classification, object classification, and detection can all be done with ArcGIS pro. More detailed information can be found at deep learning in ArcGIS Pro help pages. This means with notebooks being available in ArcGIS Pro and ArcGIS Online people can start experimenting with Deep Learning in the Desktop. One exciting area using ArcGIS for training is taking advantage of pretrained models. If you’re interested in these capabilities, please check out the following document for trained deep learning models and their backbones in the model_type and backbone_model parameters: Train Deep Learning Model.   Inferencing – should my organization use ArcGIS Image Analyst or ArcGIS Image Server? Inferencing is the process of applying the trained model, developed from the training data, and applying it against a previously unused or new data set to create a new set of annotation and labeling. ArcGIS has long been utilized for machine learning capabilities and tools. It can be used to solve a variety of geospatial problems, such as Identification of objects and image classification. With deep learning in ArcGIS, the tools are available in both the ArcGIS Image Analyst and ArcGIS Image Server which is part of ArcGIS Enterprise. You might be wondering when you should use a) ArcGIS Image Analyst vs b) ArcGIS Image Server for inferencing?   Inferencing with ArcGIS Pro Image Analyst If you don’t have access to ArcGIS Enterprise, you can use the ArcGIS Image Analyst (desktop) to do the inferencing/processing with a graphics card meant for deep learning. ArcGIS Image Analyst works well with on average size projects, but for larger products staff have the option of scaling their workflows for larger datasets with ArcGIS Image Server.   Inferencing with ArcGIS Image Server Automating Object detection takes time. When your project is not small and you need to scale and optimize your AI operations, then ArcGIS Image Server should be used when running large jobs. Using ArcGIS Imager Server will always be the fastest and most efficient option. One added benefit of using ArcGIS Image Server for inferencing will be by sharing inferenced outputs that are accessible and shared directly through your own spatial data infrastructure inside and outside the organization. If you have a high end GPU and need more tips on when to use ArcGIS Pro vs ArcGIS Enterprise I recommend you read this great article Which is better for deep learning ArcGIS Pro or ArcGIS Enterprise? from my Esri Colleagues Vinay Vishwambharan and Emily Windahl.   Tools – a few popular inferencing tools Inferencing tools Classify Pixels Using Deep Learning - In a raster analysis deployment, this tool runs a trained deep learning model on an input image to produce a classified raster published as a hosted imagery layer in your portal.   Object Detection Using Deep Learning - In a raster analysis deployment, this tool runs a trained deep learning model on an input raster to produce a feature class containing the objects it identifies. The feature class can be shared as a hosted feature layer in your portal. The features can be bounding boxes or polygons around the objects found, or points at the centers of the objects.     Non-Maximum Suppression - Identifies duplicate features from the output of the Detect Objects Using Deep Learning tool as a postprocessing step and creates a new output with no duplicate features. The Detect Objects Using Deep Learning tool can return more than one bounding box or polygon for the same object, especially as a tiling side effect. If two features overlap more than a given maximum ratio, the feature with the lower confidence value will be removed.   I would like to thank everyone for following this series. For part 5 of the next installment I will be focusing on Providing National Scalability – Modernizing National Mapping Capabilities with AI and National 3D Basemaps. If you missed the previous 3 sections of this 7-part series feel free to visit the previous articles. Part 1: Future Impacts by AI on Mapping and Modernization Part 2: GIS, Artificial Intelligence, and Automation in the Workplace Part 3: Teaming with the Machine: AI in the Workplace         ... View more

Authored By: Steve Snow Esri Senior National Government Industry Strategy Specialist Part 3 of  a 7 part series exploring GIS and Artificial Intelligence   As part of a seven-part blog, we originally covered the introduction of automation, AI, and new technologies into the workplace. These new technologies are helping workers to free work time so that workers can focus on creativity, reducing mundane tasks, and solving complex problems in the workplace. Studies like Will Robots Take My Job (Covered in Part 2 of this series) showcased many scenarios where geospatial industry workers are impacted. The main take away from this is that AI is here to stay and that workers will need to adapt and leverage the technology to become more competitive. Leveraging this new technology will ultimately lead to greater ROI and organizational mission success.   Focusing on Mission – Human and AI The mission of national geospatial authorities is to support a rapidly changing civilian and defense stakeholder’s decision-making capabilities.   These customer needs include supporting larger volumes of data, working with less resources, more powerful analysis of higher resolution remote sensing sources, and production with quicker delivery times. To achieve quicker delivery, organizations are turning to GeoAI. Organizations are creating Human and Machine teams that works jointly with data to meet their business goals.    The Human and Machine Team With the pairing humans and AI, organizations can create an efficient and dynamic data production environment where human workers are enabled with the strengths of AI. This means that the human and Machine pairing can complement each other’s strengths. The result is a stronger team that solves problems and tasks quickly. Problems can be solved by leveraging the strengths of both the human and machine in the below areas: Data is the common component in any workflow that links the Human and machine team. Data is the catalyst in future workplace where humans are empowered by AI. This new modern workplace will be the future environment for interactions between the Human and Machine team.           Read Part 4 of 7: Teaming with the Machine – AI in the Workplace   Additional Blogs in the Series: Part 1: Future Impacts by AI on Mapping and Modernization Part 2: GIS, Artificial Intelligence, and Automation in the Workplace ... View more

Authored By: Steve Snow Esri Senior National Government Industry Strategy Specialist Part 2 of  a 7 part series exploring GIS and Artificial Intelligence   Many professions are being impacted by the introduction of Artificial Intelligence (AI) in the workplace. Future employment and career choices will be forever changed by how susceptible they are to automation and computerization. One study that focuses on the impacts of AI and Automation in the Workplace is from the website Will Robots Take My Job? This website started from a report by Carl Benedikt Frey and Michael A. Osborne title “The Future of Employment: How susceptible are jobs to computerization?”. The authors estimate about 47 % of US employment is at risk due to automation by 2033. Of concern are AI automation impacts on geospatial staff. Using the websites interface on Will Robots Take my job, it was found that there were 4 geospatial job types that are expected to be impacted by 2033. The following 4 job searches: Civil Engineers, Geographers, Cartographers and Photogrammetrists, and Surveying and Mapping Technicians delivered interesting results. As you can see from the below results, Civil Engineers have a likely replacement of about 2% and are safe from automation. Geographers have a higher replacement risk of 25%. When we get to both Cartographers and Photogrammetrists and Surveying and Mapping Technicians the risks are very high. One possible reason for this is that there are highly repeatable workflows which lend them to the strengths of a machine such as GeoAI to automate. The results of the below Image stress the reason why AI skill sets in the future will be more important than ever as a job skill. I will be covering more on AI and human teams in Part 3 of this series.   Example 1 Automation Today (not including GeoAI) One example of automation (not including GeoAI) in the workplace is the Dutch Kadaster who is the National Mapping Agency of the Netherlands. The Dutch Kadaster originally was looking at ArcGIS automation for their 1:50,000 map series for the country. The series typically required 28 cartographers and 5 years to update the system manually. After implementing ArcGIS automation (non-GeoAI) the mapping agency went down to 1 cartographer with completion of series in 3 weeks of processing using a 100% automated approach with an infrastructure of 6 computers utilizing 6 CPU’s each. The Return on Investment using ArcGIS was a 5000% reduction in time and resources. You can find out more by visiting the article Transforming National Map Production.   Example 2 Automation Today (using GeoAI) A second example of automation using GeoAI was by the AAM Group for Electric Utilities in Australia. The basic problem was how to automate the manual classification of Lidar Point clouds. GeoAI was used to automate the Lidar workflow over a large geographic region. After creating the GeoAI workflow in ArcGIS the Return on Investment resulted in 50,000 man hours and 5 million dollars saved on the project! One of the added benefits of using GeoAI with ArcGIS was that the buildings and vegetation were also classified by the AI. Additionally, further benefits were that the GeoAI LiDAR model is now being applied to other projects. You can read more be reading the article PointCNN Replacing 50-000 man hours with AI.   GeoAI in Dynamic Environments An area that GeoAI will be a future asset to geospatial organizations will be in the areas of navigation, sea level rise, disasters, and predicting coastal flooding during storms. The human and AI team can quickly perform feature extraction from littoral and coastal areas where there is constant and rapid change. Extraction of shoreline and the land/water interface is important for many federal, state, and local government agencies. Currently much of this is still a manual process, but a human and AI team could rapidly update products to map and provide authoritative information to rapidly changing environment and situations.   Read Part 3 of 7: Teaming with the Machine – AI in the Workplace   Additional Blogs in the Series:  Part 1: Future Impacts by AI on Mapping and Modernization   ... View more

An Integrated Hydrospatial Workflow   Satellite Derived Bathymetry in an Integrated Hydrospatial Workflow in ArcGIS Pro and ArcGIS Bathymetry From satellite imagery to charting for rapid response and change detection in coastal waters: This workshop demonstrates the combined capabilities of satellite derived bathymetry produced within a modern hydrospatial infrastructure to provide up-to-date, accurate, and vital spatial information for coastal areas where the seafloor is most dynamic to survey using marine vessels. Topics covered include: An overview of satellite derived bathymetry technology The ArcGIS Pro toolbox workflow Applications, and use cases Bathymetric data management, product generation, and analysis   Additional Resources:   TCarta Storymap: Satellite Derived Bathymetry 101 TCarta Storymap: Trident NSF SBIR Phase II TCarta Storymap: Satellite Derived Bathymetry for Improved Hydrographic Mapping Sea Technology Article, June 2020: ICESat-2 Space-Based Laser ArcGIS Online Bathymetry Service ArcGIS Maritime and Bathymetry Product Support resources Caribbean GeoPortal SDB Data in the Caribbean Geoportal ... View more

  Transformation Through Automation This 3-part webinar series shows how modern National Mapping and Geospatial Authorities are transforming themselves through automation in the collection, management, production, and sharing of their information. National Mapping agencies provide the foremost authoritative baseline of geospatial data for a country, serving as a point-of-truth for data that supports issues of national importance. Through automation, agencies are quickly providing their customers with a self-service products at the point of need, which is dramatically reducing costs and decreasing time to deliver information to decision-makers. Hear how your colleagues have done this and see how you can implement it in your organization. Watch the full series:  Part 1 - Automation to Transformation in Geospatial Authorities Part 2 - Making Your Organization Scalable with Multi-Resolution Mapping Part 3 - Sensing and Imaging the Future ... View more

  Making Your Organization Scalable with Multi-Resolution Mapping This is the second in the 3-part series "National Mapping Modernization: Transformation Through Automation Webinar Series" for the National Mapping Industry. GIS enables Multi-Resolution geospatial production and mapping using automated processes to drastically scale-down the production time and costs, and dramatically increase the variety of information products at various scale resolutions they deliver.   Continue the series:  Part 1 -  Automation to Transformation in Geospatial Authorities Part 3 - Sensing and Imaging the Future ... View more

  Automation to Transformation in Geospatial Authorities The first webinar in a 3-part series "National Mapping Modernization: Transformation Through Automation Webinar Series" for the National Mapping Industry. Automated mapping is enabling Geospatial Authorities to reduce costs, free-up resources, and meet customers’ needs through implementing timely and efficient workflows, as well as new ways for customer’s to generate products on demand. GIS can automate your organization’s production of national mapping data through new automated workflows that streamline production. Continue the series:  Part 2 -  Making Your Organization Scalable with Multi-Resolution Mapping Part 3 - Sensing and Imaging the Future ... View more

  From Sensor to Decision The third and final webinar in the 3-part series "National Mapping Modernization: Transformation Through Automation Webinar Series" for the National Mapping Industry. The availability of remotely-sensed imagery has increased significantly in the last few years enabling us to efficiently capture more information to support our missions. Changes in the environment and new features can be identified and extracted quickly to keep our organizations data current.   Continue the series:  Part 1 -  Automation to Transformation in Geospatial Authorities Part 2 - Making Your Organization Scalable With Multi-Resolution Mapping ... View more

  Solving National Problems with GIS ArcGIS is your system of engagement for sharing valuable information to enable evidence-based decision-making. This webinar highlights the many ways sharing information across national government and society can: Stimulate economic development by focusing on location-based information to create opportunities. Empower government to quickly respond to disasters with relevant and timely information. Track progress of national commitments to initiatives such as the United Nations Sustainable Development Goals.   ... View more

  Making Census 2020 Count with GIS National statistics offices continue to seek the most effective ways to quickly and accurately measure socioeconomic indicators for better governance and decision-making. This 3-part webinar series shows how Esri's ArcGIS technology can increase your efficiency and the quality of your data. Preenumeration planning costs can be reduced by accurately mapping enumeration areas and even households. Enumeration operations are more efficient with easy-to-use apps for enumeration and dashboards to effectively manage and redirect field enumerators. Improved postenumeration results provide your country with accurate information to support decisions of national importance. Watch the full series:  Part 1 - Introduction to Official Statistics Part 2 - Imagery and Official Statistics Part 3 - SDGs and Dissemination ... View more

  SDGs and Dissemination This is the third and final webinar in a 3-part series "Making Census 2020 Count with GIS Webinar Series" for Official Statistics.    See how Web GIS enables information dissemination, collaboration, and decision-making around the SDGs, as well as any other type of communities working on shared agendas. Topics covered include:  SDGs and the Role of Statistics and GIS Web GIS and Dissemination Federated Information System for the SDGs (FISS4DGs)   Continue the series: Part 1 - Introduction to Official Statistics Part 2 -  Imagery and Official Statistics ... View more

  Imagery for Understanding and Counting a Changing World   This is the second webinar in a 3-part series: "Making Census 2020 Count with GIS Webinar Series" for Official Statistics.  Up-to-date imagery is a key source of information for a changing world. There is no other source of geospatial content that provides the comprehensiveness of high-resolution imagery. When integrated with a modern GIS, imagery can become the foundation, capable of supporting the enumeration framework and planning and field operations. Imagery can be used in preenumeration planning to do in-office address canvassing or validate existing enumeration areas. Imagery analysis can also be conducted to understand areas of change, such as agricultural or forested areas or disaster-impacted regions. Continue the series: Part 1 -  Introduction to Official Statistics Part 3 - SDGs and Dissemination  ... View more