This dataset is a collection of 321,894 polygons representing crop fields and classified crop types for each examined year across the study period (2005 - 2020) in central California. These classified fields are the result of random forest classification using Landsat and National Agricultural Imagery Program remotely sensed imagery. Training data for this random forest classification comes from the associated child dataset of labeled location point data. Each polygon comes from the California Department of Water Resources 2018 Statewide Crop Map. Nine crop types were classified: rice, pasture, grain, field, citrus and mediterranean, deciduous fruit and nut, vineyard, fallow and young perennial, and truck, nursery, and berry.