Global Classification Dataset of Daytime and Nighttime Marine Low-cloud Mesoscale Morphology

The global classification dataset of daytime and nighttime marine low-cloud mesoscale morphology with six cloud types (Solid stratus, Closed MCC, Open MCC, Disorganized MCC, Clustered Cu and Suppressed Cu). The spatial resolution is 1o × 1o  and the temporal resolution is 5 minutes for the years 2018-2022. They were established based on a deep learning model ResNet-50. Trained on daytime radiance data from MODIS (Moderate Resolution Imaging Spectroradiometer) and daytime retrieved COT (Cloud Optical Thickness), this model achieved a high prediction accuracy and can be applied to nighttime cloud classification. For a detailed introduction to the model, please refer to our article.

Technical info

Product information

File ‘day_xxxx_all.h5’: Daytime classification of global marine low-cloud morphology for the year xxxx, with a spatial resolution of 1°×1° and a temporal resolution of 5 minutes 

date: time of the 1°×1° box, format: 'YYYYDDD.HHHH'

lon: central longitude (-180, 180)

lat: central latitude (-60, 60)

cat: category of the cloud morphology. The numbers 0-5 represent each of the six categories: 0-Solid stratus, 1-Closed MCC, 2-Open MCC, 3-Disorganized MCC, 4-Clustered Cu, 5-Suppressed Cu

cert: model certainty, the probability that this cloud morphology belongs to the assigned category

low_cf: the cloud fraction of low clouds

COT_CNN: average cloud optical thickness (COT), retrieved using TIR-CNN model from Wang et al. (2022)

CER_CNN: average cloud effective radius (CER), retrieved using TIR-CNN model from Wang et al. (2022), in the unit of μm

LWP_CNN: average cloud liquid path (LWP), calculated from COT_CNN and CER_CNN, in the unit of g/㎡

Sensor_zenith: scene average sensor zenith angle, from MODIS MYD021, in the unit of degree (°)

File 'night_xxxx_all.h5': Nighttime classification of global marine low-cloud morphology for the year xxxx, with a spatial resolution of 1°×1° and a temporal resolution of 5 minutes  

same variables as daytime

File 'example.xlsx': A sample of the variable data from our cloud classification dataset, showcasing the classification results of a MODIS granule captured on January 1, 2018, at 00:25 UTC. This sample is provided to help users better understand the content of our dataset.

Training, Validation, Test dataset

Originating from the same classification dataset, same variables, only differ in sample size

Files 'training_dataset.h5', 'validation_dataset.h5', and 'test_dataset.h5':

date: time of the 128×128 pixels, format: 'YYYYDDD.HHHH'

lat: central latitude of the 128×128 scene

lon: central longitude of the 128×128 scene

cat: category of the cloud morphology. The numbers 0-5 represent each of the six categories: 0-Solid stratus, 1-Closed MCC, 2-Open MCC, 3-Disorganized MCC, 4-Clustered Cu, 5-Suppressed Cu

CTH: cloud top height, in-cloud average value, in the unit of km

COT_retrieved: cloud optical thickness (COT), retrieved using TIR-CNN model from Wang et al. (2022), 128×128 pixels

LWP: cloud liquid path (LWP) from MODIS MYD06, in-cloud average value, in the unit of g/㎡

Sensor_zenith: scene average sensor zenith angle, from MODIS MYD021, in the unit of degree (°)

emis_29: radiance data from thermal infrared channel 29 (8.7μm), 128×128 pixels

emis_31: radiance data from thermal infrared channel 31 (10.8 μm), 128×128 pixels

emis_32: radiance data from thermal infrared channel 32 (12.0 μm), 128×128 pixels

i: the row number of the top-left pixel of 128 ×128 scene in the MODIS granule

j: the column number of the top-left pixel of 128 ×128 scene in the MODIS granule