Multi-Temporal Crop Classification with HLS Imagery across CONUS

This dataset contains temporal Harmonized Landsat-Sentinel (HLS) imagery of diverse crop type and land cover classes across the Contiguous United States (CONUS) for the year 2022. The target labels are derived from USDA's Crop Data Layer (CDL). It's primary purpose is for training segmentation geospatial machine learning models. It includes 3,854 chips of 224 x 224 pixel area at 30m spatial resolution.

Product Details

Visibility: Public
Owner: Clark Center for Geospatial Analytics
Created: 10 Aug 2023
Last Updated: 21 Aug 2025

Product Contents

root

validation_data.txt

Name: validation_data.txt
Size: 9.79 KB
Content Type: text/plain
Last Modified: 14 Aug 2023
Source URL: https://data.source.coop/clarkcga/multi-temporal-crop-classification/validation_data.txt
Cloud URI: s3://us-west-2.opendata.source.coop/clarkcga/multi-temporal-crop-classification/validation_data.txt