This is a wheat breeding phenotyping and yield dataset, including canopy height (CH, m), canopy volume (CV, m3), and leaf area index (LAI) collected in the field; vegetation index (VI) generated by multispectral data acquired by UAV remote sensing; trial site weather (Weather); and yield (Yield, kg). The data comes from field trials.

Data acquisition and processing are described in the relevant part of the manuscript.

This study introduces a novel soil texture dataset designed to overcome geographic constraints and improve the generalization of classification models. Using the USDA soil classification triangle as a framework, the dataset is systematically generated by combining pure sand, silt, and clay in varying proportions to create diverse soil texture classes. The soil mixtures are captured using a multispectral sensor with seven bands, ensuring a rich representation of spectral information.

Using the PVIFS-02 whole-sky imagers, we collected 500,000 independent cloud images from 2021 to 2023, captured in a southern city and a northern city in China. The cloud images collected in southern China are clear, with obvious cloud edges. In contrast, the cloud images from northern China appear relatively blurred. This difference is attributed to the geographical characteristics of northern China, where regions are frequently affected by sand and dust, leading to a certain degree of image blurring. It brings challenges to cloud detection and classification.

The EuroSAT-SAR dataset is a SAR version of the EuroSAT dataset. We matched each Sentinel-2 image in EuroSAT with one Sentinel-1 patch according to the geospatial coordinates, ending up with 27,000 dual-pol Sentinel-1 SAR images divided in 10 classes. The EuroSAT-SAR dataset was collected as one downstream task in the work FG-MAE to serve as a CIFAR-like, clean, balanced ML-ready dataset for remote sensing SAR image recognition.