Deep learning model to perform mangrove classification on Landsat 8 Imagery. A brief summary of the item is not available. Add a brief summary about the item.
Deep learning package
from
Item created: Sep 23, 2021 Item updated: Dec 27, 2024 Number of downloads: 5,915
Description
Mangroves are critical to the maintenance and conservation of healthy coastal ecosystems. They are extremely rich in biodiversity and are home to a diverse set of plant and animal species. Mangroves protect inland coastal areas from erosion and storm surge impacts such as from tsunamis. These factors make mangrove monitoring and conservation an important activity. Due to various climatic phenomena and coastal activity such as reclamation for development, mangrove forests are rapidly shrinking. This warrants active monitoring and conservation efforts of mangroves. This deep learning model enables rapid monitoring of mangrove forests.
Using the model
Follow this guide to use the model. Before using this model, ensure that the supported deep learning libraries are installed. For more details, check Deep Learning Libraries Installer for ArcGIS.
Fine-tuning the model
This model can be fine-tuned using the Train Deep Learning Model tool. Follow the guide to fine-tune this model.
Input
Surface Reflectance (Collection 2 Level 2) imagery acquired by the Landsat 8 Sensor in form of a raster, mosaic dataset or image service.
Output
Classified raster containing two classes: mangrove and other.
Applicable geographies
This model is expected to work well globally.
Model architecture
This model uses the UNet model architecture implemented in ArcGIS API for Python.
Accuracy metrics
The mangrove class has a precision of 0.85, recall of 0.80 and F1 score of 0.82.
Training data
This model has been trained on the Global Mangrove Watch dataset with Landsat 8 Scenes from the same time.
Sample results
Here are a few results from the model.
An in-depth description of the item is not available.
Layers
Tools
Tables
Basemap
Project Contents:
Solution Contents
Contents
Layers
Screenshots
Terms of Use
This work is licensed under the Esri Master License Agreement.
View Landsat Terms of Use | View Summary | View Esri Terms of Use
No special restrictions or limitations on using the item's content have been provided.
Details
Dashboard views: Desktop
Source:
Creating data in:
Published as:
Other Views:
Dependent items in the recycle bin
Applicable: 2d
Size: 158.061 MB
ID: 741a56ae6a5340058b9704a8f68f1b9a
Image Count: 0
Image Properties
Layer Drawing
Using tiles from a cache
Dynamically from data
Share
Owner
Folder
Categories
This item has not been categorized.
Credits (Attribution)
No acknowledgements.Esri
Comments (8)
I am working with version 3.1.3 of ArcGIS Pro, when using Classify Pixels Using Deep Learning with ArcGIS_Pro_31_Deep_Learning_Libraries it generates an error.
Can you please share the error trace of Classify Pixels Using Deep Learning tool.
This Mangrove Classification model (Landsat 8) can be used for Sentinel 2 or another deep learning model needs to be developed. I appreciate any information.
The model is trained on Landsat 8 L2A data and only supports Landsat 8.
Thanks for your quick reply. Do I need TIRS (Thermal Infrared Sensor) bands in addition to OLI (Operational Land Imager) bands(B1-B9)?
Hi, use first seven bands.
I have a question about the input data. Which bands are needed for using this model? I can't understand only 3bands(B2, B3, B4) or more are needed.
Hi, this model works with surface reflectance composite raster consisting all bands of Landsat 8.