A Cloud Detection Algorithm with Reduction of Sunlight Interference in Ground-Based Sky Images

Abstract

Cloud detection for ground-based sky images has attracted much attention in cloud-related fields. In this paper, we proposed a cloud detection algorithm that reduced the sunlight interference in the image. The solar location method was introduced to track the sun in the image used for feature calculation, which was suitable for the case where the camera could not be calibrated. Following this, the adjustable red green difference (ARGD) feature using red and green channels was proposed. The red weight in the feature was determined by the layering region division, which classified the degree of sunlight interference in the image, and the sky state, which discriminated whether there was sunlight interference in the image. Finally, a fixed zero threshold was applied to feature images in order to obtain the cloud detection results. Experimental results showed that the proposed algorithm performs better than the other algorithms and can effectively reduce the sunlight interference.

24-hour cloud cover calculation using ground-based imager with machine learning

“…Relatively, the bias and RMSE were large and R was low. In spring and autumn, sunrise and sunset images were learned at similar times (sunrise: 0600-0700 LST, sunset: 1800-1900 LST); however, differences between the winter (sunrise: 0700-0800 LST, sunset: 1700-1800 LST) and summer (sunrise: 0500-0600 LST, sunset: 1900-2000 results are apparent because sunrise and sunset occurred late or early and exhibited different features from the data features learned for those times (Liu et al, 2015;Li et al, 2019). That is, owing to the sunrise/sunset glow, high cloud cover calculation errors are obtained at sunrise/sunset, when it is difficult to distinguish between the sky and clouds because of the reddish sky on a clear day and the bluish cloud on a cloudy day (Kim et al, 2021).…”

“…In that approach, cloud cover calculation errors may occur at sunrise and sunset. Therefore, if a day and night continuous cloud cover calculation algorithm is considered, the calculation error for this discontinuous time period should be reduced (Huo and Lu, 2009;Li et al, 2019). Figure 7 shows the daily mean cloud cover results based on the observed and calculated cloud cover for the test set.…”

Solar Irradiance Forecast Based on Cloud Movement Prediction

“…The data shown covers the period on 13 July 2020. from 13:45 to 14:40 and from 12:00 to 12:45. Figures [12][13][14][15][16][17][18][19] show the situation in the sky where several clouds were moving towards the sun and corresponding error levels. The red curve, which represents the real-time sun un-coverage level on images that compare the real-time and predicted sun-uncoverage level, shows that the visible area of the sun changes significantly in a nonlinear manner as the clouds begin to cover or uncover the sun.…”

“…where EI(t) represents estimated irradiance in W m 2 , PI(t) is the estimated sun un-coverage level measured in percentages (represented by the blue curves in Figures 12,14,16 and 18), PAI(1h) MHS represents predicted average irradiance estimation of direct solar irradiance based on the 1-h time period provided by the meteorological and hydrological service measured in W m 2 , and PSUL(1h) Calculated represents the predicted average value of predicted sun un-coverage level (measured in percentage from 0 to 100%).…”

“…The development of cloud detection algorithms based on sky images has also received many variants. One of the approaches analyzed the way of reducing sunlight interference in ground-based sky images [14]. It has been shown that HSV color space gives the best results, so the same approach is used in this work to accurately detect the cloud edges, cloud centroid, and cloud motion.…”