Cloud height and tracking accuracy of three all sky imager systems for individual clouds

• Published in: Solar energy 2019-01, Vol.177, p.213-228
• Main Authors: Nouri, B., Kuhn, P., Wilbert, S., Hanrieder, N., Prahl, C., Zarzalejo, L., Kazantzidis, A., Blanc, P., Pitz-Paal, R.
• Format: Article
• Language: English
• Subjects: 3-D cloud modeling; All sky imager; Atmospheric conditions; Atmospheric models; Cameras; Cloud height; Cloud tracking; Clouds; Engineering Sciences; Error detection; Image processing; Image resolution; Image segmentation; Irradiance; Irradiance map; Multilayers; Nowcasting; Optical properties; Sky; Solar energy; Stereoscopy; Three dimensional models
• ISSN: 0038-092X; 1471-1257
• DOI: 10.1016/j.solener.2018.10.079

•ASI based nowcasting system with individual 3-D cloud objects.•Comparison of three cloud height detection approaches against reference ceilometer.•Comparison of three cloud tracking approaches against reference shadow camera system.•Overall mean absolute error of 648 m (height), 1.3 m/s (speed) and 16.2° (direction) Solar irradiance nowcasts can be derived with sky images from all sky imagers (ASI) by detecting and analyzing transient clouds, which are the main contributor of intra-hour solar irradiance variability. The accuracy of ASI based solar irradiance nowcasting systems depends on various processing steps. Two vital steps are the cloud height detection and cloud tracking. This task is challenging, due to the atmospheric conditions that are often complex, including various cloud layers moving in different directions simultaneously. This challenge is addressed by detecting and tracking individual clouds. For this, we developed two distinct ASI nowcasting approaches with four or two cameras and a third hybridized approach. These three systems create individual 3-D cloud models with unique attributes including height, position, size, optical properties and motion. This enables us to describe complex multi-layer conditions. In this paper, derived cloud height and motion vectors are compared with a reference ceilometer (height) and shadow camera system (motion) over a 30 day validation period. The validation data set includes a wide range of cloud heights, cloud motion patterns and atmospheric conditions. Furthermore, limitations of ASI based nowcasting systems due to image resolution and image perspective constrains are discussed. The most promising system is found to be the hybridized approach. This approach uses four ASIs and a voxel carving based cloud modeling combined with a cloud segmentation independent stereoscopic cloud height and tracking detection. We observed for this approach an overall mean absolute error of 648 m for the height, 1.3 m/s for the cloud speed and 16.2° for the motion direction.