Improving a Night-Time Weather Estimation Method with Low-Cost Devices using a Support Vector Machine

Because of the increasing density of meteorological observation networks and technological advances in data processing, weather forecast accuracy has improved in the past decades and is projected to increase further, requiring measurements at the local scale.However, their biggest problem is the equipment cost; the ultrasensitive atmospheric light cameras cost approximately ten million yen.This paper introduces a weather observation system designed exclusively with low-cost commercial products.The combined cost of the fabricated device was approximately 100,000 yen.An algorithm was also established to estimate night-time weather from the number of visible stars in all-sky images by assuming that more visible stars imply fewer clouds and more precise weather (the star count method).The resulting weather estimation accuracy was about 80 %.In addition, to improve the accuracy, this paper adopts a supervised machine learning method, Support Vector Machine (SVM), and compares the classification accuracy with the star count method.