Embracing GeoAI with ArcGIS Deep Learning Studio | Esri India
As GIS technology evolves, more organizations are adopting new tools to enhance their production and analysis workflows. One such innovation is GeoAI, which uses AI and deep learning to automate mapping processes.
In large mapping projects, multiple team members often work on different images or image services to map various features. Streamlining this collaborative workflow is crucial, and this is where Deep Learning Studio proves invaluable.
ArcGIS Deep Learning Studio, an exciting new addition to ArcGIS Enterprise, simplifies the collection, visualization, review, and training of data. Users can easily share trained models within their organization. The studio is designed to enable even those with little experience in computer use to make significant progress in machine learning with minimal effort, thanks to its intuitive features.
Example of Team Members & their Privileges
Example of Team Members & their Privileges
Let’s dive deep into how to get started with end-to-end deep learning workflow.
After sample collection, you can export the training data as image chips
After sample collection, you can export the training data as image chips
After sample collection, you can export the training data as image chips
Example: Mapping in Nuzvid, Andhra Pradesh
To illustrate the capabilities of ArcGIS Deep Learning Studio, consider a mapping project in Nuzvid, Andhra Pradesh. The objective is to detect and count trees, and extract roads, buildings, and farm boundaries. With ArcGIS Enterprise configured for Raster Analytics, different team members can be assigned specific roles.
In this project, there are four team members with distinct privileges:
- Samkith and Manjusha can only collect samples.
- Deepanwita can collect training samples, train a model, and run inferencing.
- One member has the privilege to configure the project.
Workflow
Sample Collection: After collecting samples, the training data can be exported as image chips.
Model Training: Once the training data is ready, the model can be trained.
Running Inference: The "Run Inference" tool applies the model to other images. If a model file already exists, this step can be done directly. In this example, a pre-trained model from ArcGIS Living Atlas for Road Extraction (Global) was used.
Sample Collection: After collecting samples, the training data can be exported as image chips.
Model Training: Once the training data is ready, the model can be trained.
Running Inference: The "Run Inference" tool applies the model to other images. If a model file already exists, this step can be done directly. In this example, a pre-trained model from ArcGIS Living Atlas for Road Extraction (Global) was used.
Results
The results of inferencing demonstrate the efficacy of the process. ArcGIS Deep Learning Studio allows users to easily build, train, and deploy deep learning models. Its collaborative technology ensures that both machine learning experts and non-experts can benefit from deep learning without extensive coding or expertise.
To Know More visit : Esri India
Comments
Post a Comment