AgriFieldNet Competition Dataset

This dataset contains crop types of agricultural fields in four states of Uttar Pradesh, Rajasthan, Odisha and Bihar in northern India. There are 13 different classes in the dataset including Fallow land and 12 crop types of Wheat, Mustard, Lentil, Green pea, Sugarcane, Garlic, Maize, Gram, Coriander, Potato, Bersem, and Rice. The dataset is split to train and test collections as part of the AgriFieldNet India Competition. Ground reference data for this dataset is collected by IDinsight’s [Data on Demand](https://www.idinsight.org/services/data-on-demand/) team. Radiant Earth Foundation carried out the training dataset curation and publication. This training dataset is generated through a grant from the Enabling Crop Analytics at Scale ([ECAAS](https://cropanalytics.net/)) Initiative funded by [The Bill & Melinda Gates Foundation](https://www.gatesfoundation.org/) and implemented by [Tetra Tech](https://www.tetratech.com/).

本数据集覆盖印度北部北方邦（Uttar Pradesh）、拉贾斯坦邦（Rajasthan）、奥里萨邦（Odisha）与比哈尔邦（Bihar）四个邦的农田作物类型。数据集共包含13个类别，其中包括休耕地（Fallow land）以及12种作物：小麦（Wheat）、芥菜（Mustard）、小扁豆（Lentil）、青豌豆（Green pea）、甘蔗（Sugarcane）、大蒜（Garlic）、玉米（Maize）、鹰嘴豆（Gram）、芫荽（Coriander）、马铃薯（Potato）、埃及三叶草（Bersem）与水稻（Rice）。本数据集已按照AgriFieldNet印度竞赛的要求划分为训练集与测试集。该数据集的地面参考数据由IDinsight的[数据按需服务（Data on Demand）](https://www.idinsight.org/services/data-on-demand/)团队采集完成。训练数据集的整理与发布工作由Radiant Earth基金会承担。本训练数据集由“规模化作物分析赋能（Enabling Crop Analytics at Scale，ECAAS）”项目资助生成，该项目由比尔及梅琳达·盖茨基金会（The Bill & Melinda Gates Foundation）资助，并由Tetra Tech负责实施。