@inproceedings{8690d097448248c0be851027a82d70f3,
title = "ICroplandNet: An Open Distributed Training Dataset for Irrigated Cropland Detection",
abstract = "Irrigated cropland takes only 16 percent of the world's arable land but contributes to more than 36 percent of the global harvest. Accurate detections of irrigated cropland are important for crop growers and decision makers in precision irrigation farming. ICroplandNet is an irrigated cropland training dataset built up using the Cropland Data Layer data between 1997 and 2021 for the Contiguous United States. To assure the accuracy of irrigated land, we only consider the cropland intersected with those pivotal irrigated areas detected by machine learning algorithms. Geometrical shapes and temporal extent (crop planting and harvest time) are recorded to support the retrieval scene or time series of remotely sensed data or its products. Standard geospatial Web services are used in serving the training dataset as well as retrieving training features in public cloud.",
keywords = "API-EDR, irrigated cropland, machine learning, OGC API, remote sensing",
author = "Yu, \{Eugene G.\} and Liping Di and Meyer, \{David J.\} and Peisheng Zhao and Li Lin and Chen Zhang and Sreten Cvejovic",
note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 10th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2022 ; Conference date: 11-07-2022 Through 14-07-2022",
year = "2022",
doi = "10.1109/Agro-Geoinformatics55649.2022.9859073",
language = "English",
series = "2022 10th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2022",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2022 10th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2022",
}