Skip to content

1.4 A Major Leap Forward for Wherobots

Wherobots 1.4 delivers significant advancements with a host of new features.

Here's a look at the highlights of this major release, including updates to WherobotsDB, our cloud-native analytics engine for geospatial workloads, and WherobotsAI, our scalable AI and machine learning engine for geospatial data analysis.

This table highlights key features available for each Organization tier1:

Feature Available in Professional and Enterprise Editions Available in Community Edition
Job Run Automation with Airflow ✅ ✅
Amazon S3 Storage Integration ✅ ❌
WherobotsAI Raster Inference ✅ ❌
Reverse Geocoding ✅ ✅
Long-lived token Management and Service Principals ✅ ❌
Distributed K Nearest Neighbor Join ✅ ✅
Spatial Join Optimizations ✅ ✅
GeoStats Toolbox ✅ ✅

Get Started with a Paid Organization

To create or upgrade an Organization, see the following instructions:

Amazon S3 Integration

Wherobots' integration with Amazon Simple Storage Service (S3) allows Amazon S3 customers to utilize Wherobots as the spatial engine that operates on their data while still using Amazon S3 for data storage.

Accelerate your creation of spatial data products by using data directly from Amazon S3 public or private buckets, bypassing the need for time-consuming data transfers.

Amazon S3 Integration Documentation

Job Run Automation with Airflow

Run scripts on Wherobots Cloud and track their execution status with Job Runs. Integrate Wherobots' geospatial processing into your Airflow workflows using the WherobotsRunOperator, eliminating the need to manage your own cluster.

WherobotsRunOperator Documentation

WherobotsAI Raster Inference

WherobotsAI Raster Inference uses computer vision to gather insights from raster data at planetary scale, extracting actionable insights from vast and complex aerial imagery.

With Wherobots 1.4, WherobotsAI Raster Inference is generally available for Professional and Enterprise Edition Organizations.

WherobotsAI Raster Inference requires a GPU-Optimized runtime

This feature requires a GPU-Optimized runtime. For more information on GPU Optimized runtimes, see Runtime types.

To access this runtime category, do the following:

  1. Sign up for a paid Wherobots Organization Edition (Professional or Enterprise).
  2. Submit a Compute Request for a GPU-Optimized runtime.

WherobotsAI Raster Inference lets you bring your own computer vision model or select from our available hosted models:

  • Classification
  • Object detection
  • Segmentation

More information:

Amazon Web Services (AWS) Marketplace Listing

Create a new Professional Organization or upgrade your existing Community Organization through the Wherobots Spatial Intelligence Cloud Professional Edition Amazon Web Services (AWS) Marketplace page.

More information:

Long-lived token Management and Service Principals

Professional Edition Organization Administrators can use service principals in Wherobots Cloud to enable authentication to APIs through long-lived tokens.

Administrators can create and manage tokens for applications and services, eliminating the need for User(1) role members within your Organization to handle API keys, improving security and simplifying API access management.

  1. Wherobots Organization members can be configured as Users or Admins. For more information, see Organization Roles.

Service Principals Documentation

Reverse Geocoding

ST_ReverseGeocode translates latitude and longitude coordinates into a human-readable address, allowing you to easily understand and interpret a location without needing to manually look up the corresponding street name, city, or other details.

ST_ReverseGeocode Documentation

GeoStats Toolbox

The Geostats Toolbox is a suite of functions that leverages distributed Machine Learning clustering algorithms for a variety of geospatial analysis tasks, such as clustering, outlier detection, and hotspot detection.

WherobotsAI's Python interface supports several geospatial algorithms, including:

Distributed K-Nearest Neighbor Join

WherobotsDB facilitates geospatial data analysis by enabling nearest-neighbor searches. Using the K-Nearest Neighbor (KNN) join method, WherobotsDB can identify the "k" closest neighbors to a given point or area within a dataset, relative to another dataset.

Distributed K-Nearest Neighbor Join Documentation

Spatial Join Optimizations

This release includes performance enhancements for spatial joins, particularly when dealing with large geometries. We've also added support for left and right outer joins in non-broadcast, spatial partitioning based spatial joins.

Learn more about Wherobots

Wherobots Fundamentals serves as an introductory guide to the real-world applications of Wherobots and spatial data.

  1. If a feature is available in a given Edition, this will be indicated by ✅. If a feature is not available in a given Edition, this will be indicated by ❌. ↩