What is ArcGIS Analytics for IoT?

ArcGIS Analytics for IoT is a real-time and big data processing and analysis capability of ArcGIS Online. It enables you to ingest, visualize, analyze, store, and act upon data from Internet of Things (IoT) sensors. High-velocity event data can be filtered, processed, and sent to multiple destinations, allowing you to connect virtually any type of streaming data and automatically alert personnel when specified conditions occur. You can also design analytic models to process high-volume historical data and gain insights into patterns, trends, and anomalies.

Analytics for IoT works with your vector and tabular data and can receive real-time observations over HTTP, connect to IoT cloud providers such as Azure and Cisco, or consume from Kafka, MQTT, RabbitMQ, and other messaging technologies. It also works with historical information and can read from your existing ArcGIS feature layers as well as external big data sources like Amazon S3.

Analytics for IoT tools focus on the different spatial analysis approaches: Analyze Patterns, Find Locations, Manage Data, Summarize Data, Use Proximity, and Data Enrichment. Whether you need to perform geofencing, detect incidents, run regression analysis on multiple datasets, or find areas of data clustering, there are many options to explore your data.

All analysis is performed in the cloud. Analytics for IoT uses distributed processing to scale tasks, enabling you to ingest, analyze, and visualize massive velocities and volumes of data. Results from your analysis can be stored as hosted feature layers, written to your own cloud data stores, or disseminated via notifications and messaging systems.

To get started with Analytics for IoT, create roles and assign users in your ArcGIS Online organization that include privileges for real-time ingestion, real-time analysis, and big data analysis. You can then assign users to these roles, which will enable them to log into the Analytics for IoT application. For details, see Get started with ArcGIS Analytics for IoT.

ArcGIS Analytics for IoT uses

ArcGIS Analytics for IoT is useful for workflows dealing with observations coming in from IoT devices and sensors but also for other sources of real-time and big data. It provides easy ways to bring in and immediately visualize real-time information, as well as store observations over time. Analytics for IoT also allows you to build analytical processes to automate workflows and answer questions. Overall, Analytics for IoT provides many of the same capabilities and solves many of the same use cases as ArcGIS GeoEvent Server and ArcGIS GeoAnalytics Server, but provides these capabilities as-a-service in ArcGIS Online.

Analytics for IoT is a good solution for the following:

  • You want to connect to Internet of Things (IoT) systems and visualize sensor observations.
  • You need to geofence areas of interest to detect the spatial proximity of events.
  • Your existing tools and workflows are not processing data fast enough.
  • You need to enrich and filter observations to focus on the most interesting event data.
  • Your data is growing in real-time and you need data management as-a-service.
  • Your data has a lot of noise and you want to explore it to identify important patterns and trends.
  • You want to use spatial statistical analysis and machine learning tools suitable for large datasets.
  • Your organization prefers cloud solutions as opposed to managing a multi-machine deployment for real-time and big data use cases.

Examples of analysis using ArcGIS Analytics for IoT

Below are several examples of types of analysis you can perform with Analytics for IoT:

  • As a city GIS analyst, you can ingest GPS data on all city vehicles, like public works vehicles and snow plows, to see where vehicles have traveled, areas with less coverage, and instances where vehicles exceeded the speed limit.
  • As an electric utility operations officer, you can receive regular readings from smart meters, including indications of power outages, and automatically notify the closest field crew in the area.
  • As an environmental scientist, you can identify times and locations of high ozone levels across the country in a dataset of millions of static sensor reads.
  • As a supply chain analyst at an oil & gas company, you can connect to an Automatic Identification System (AIS) data feed to monitor your vessels, calculate expected arrival information, and understand when vessels enter areas of interest.