Skip To Content

Introduction to the model

Banner image for Cooling Tower Detection model

This document explains how to use the Cooling Tower Detection - USA deep learning model available on ArcGIS Living Atlas of the World. The model is used to detect cooling towers in high-resolution imagery.

A cooling tower is a device used to remove excess heat from a process or building by transferring it to the atmosphere. It is commonly used in industrial and commercial settings to cool down water or other fluids, cooling the infrastructure it serves.

Detecting cooling towers in aerial imagery can be useful. Aerial imagery provides a comprehensive view of cooling tower locations, sizes, and conditions. Detecting the cooling towers in aerial imagery allows for identifying and monitoring cooling tower installations in industrial and commercial areas. This information can enable better decision-making and resource allocation for urban planning, environmental studies, and infrastructure management. It also helps in the proper maintenance of these towers.

Manually detecting the cooling towers in aerial imagery can be inefficient and time-consuming. Use this deep learning model to automate this task and reduce the time and effort required for detecting the cooling towers.

License requirements

To complete this workflow, the following are the license requirements:

  • ArcGIS DesktopArcGIS Image Analyst extension for ArcGIS Pro
  • ArcGIS EnterpriseArcGIS Image Server
  • ArcGIS OnlineArcGIS Pro or Professional Plus user type

Model details

This model has the following characteristics:

  • Input—Raster, mosaic dataset, or image service (4-15 centimeter spatial resolution).
  • Output—Feature class containing bounding boxes depicting cooling tower locations.
  • Compute—This workflow is compute intensive, and a GPU with minimum CUDA compute capability of 6.0 is recommended.
  • Applicable geographies—The model is expected to work well in the United States.
  • Architecture—This model uses the MaskRCNN model architecture implemented in ArcGIS API for Python.
  • Accuracy metrics—This model has an average precision score of 0.72.

Access and download the model

Download the Cooling Tower Detection - USA pretrained model from ArcGIS Living Atlas of the World. Alternatively, access the model directly from ArcGIS Pro, or consume it in ArcGIS Image for ArcGIS Online.

  1. Browse to ArcGIS Living Atlas of the World.
  2. Sign in with your ArcGIS Online credentials.
  3. Search for Cooling Tower Detection and open the item page from the search results.
  4. Click the Download button to download the model.

    You can use the downloaded .dlpk file directly in ArcGIS Pro or upload and use it in ArcGIS Enterprise. Additionally, you can fine-tune the pretrained model if necessary.

Release notes

The following are the release notes:

DateDescription

November 2023

First release of Cooling Tower Detection - USA