Hive

What is Hive?

Now that the CloudWatcher is able to measure more weather data than ever—ambient temperature, sky-reflected IR, humidity, atmospheric pressure, rain, and wind—we are reactivating an old project to apply machine learning to cloud and rain detection. The idea is to collect a huge amount of data, CloudWatcher sensor data and all-sky images, preprocess it, and apply a self-learning algorithm.

The findings will be made public and will directly inform future improvements to CloudWatcher detection algorithms.

How to participate

Participants contribute the following data, shared via the Hive project website:

• Hourly CloudWatcher sensor readings
• One all-sky camera image per hour, synchronised with the sensor data
• GPS coordinates and altitude of the observatory—kept confidential, never disclosed

What Lunatico commits to

• All findings will be publicly disclosed
• Improved cloud detection, either with improved K-factors and limits for the current algorithm, or with a new and more accurate system, depending on the outcome of the research
• Participants are invited to help characterize the data—identifying the sky in the images according to the cloud formations present

Project timeline