Volunteer Develops Machine-Learning Tool to Identify Rare Clouds
Certain kinds of clouds are misbehaving – appearing more often and lower in the sky than they used to. To help identify the factors influencing these changes, scientists have asked people around the world with cameras to submit fresh images of these clouds as a part of the NASA-supported Space Cloud Watch project.
Certain clouds, known as noctilucent or night-shining clouds (NLCs), are appearing more frequently and at lower altitudes than before. To investigate the changes, scientists have turned to citizen science through the NASA-supported Space Cloud Watch project, asking people worldwide to submit photographs of these clouds. However, differentiating NLCs from similar lower-altitude clouds has proven challenging, leading to extra work for project leaders.
Namai Chandra, a Space Cloud Watch volunteer, has addressed this issue by developing a machine learning tool. Recognizing that NLC images were being manually verified by project leaders, Namai proposed using a human-in-the-loop machine learning pipeline. He reached out to the project scientists, Drs. Chihoko Cullens and Brentha Thurairajah, who enthusiastically supported his idea.
After training the pipeline on various images, including both NLCs and look-alike clouds, Namai released the NLC identification tool. This tool assists cloud contributors in determining whether their observations are NLCs and enables project scientists to flag images for review. The tool can be accessed by anyone interested in joining the Space Cloud Watch project and contributing to understanding our changing atmosphere.
Written by urgent.news from NASA's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
- Volunteer Develops Machine-Learning Tool to Identify Rare Clouds science.nasa.gov
