Articles | Volume 14, issue 10
https://doi.org/10.5194/amt-14-6695-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/amt-14-6695-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
18 Oct 2021
Research article |
| 18 Oct 2021
| 18 Oct 2021
Twenty-four-hour cloud cover calculation using a ground-based imager with machine learning
Convergence Meteorological Research Department, National Institute of
Meteorological Sciences, Seogwipo, Jeju 63568, Republic of Korea
Joo Wan Cha
Convergence Meteorological Research Department, National Institute of
Meteorological Sciences, Seogwipo, Jeju 63568, Republic of Korea
Ki-Ho Chang
Convergence Meteorological Research Department, National Institute of
Meteorological Sciences, Seogwipo, Jeju 63568, Republic of Korea
Related authors
Joo Wan Cha, Bu-Yo Kim, Miloslav Belorid, Young-Suk Oh, Myeonghun Kang, Seungbum Kim, Young Jun Yoon, Jiyeon Park, and Sang-Jong Park
EGUsphere, https://doi.org/10.5194/egusphere-2026-3543, https://doi.org/10.5194/egusphere-2026-3543, 2026
This preprint is open for discussion and under review for Atmospheric Chemistry and Physics (ACP).
Short summary
Short summary
Ice-nucleating particles trigger ice formation in clouds, shaping precipitation and climate. We measured these particles in real time from a ship in the Arctic Ocean — the first study to do so — and found that biologically produced particles are active at warm temperatures, a signal missed by earlier filter-based methods. Declining sea ice appears to increase their concentrations. Our findings offer new insight into how Arctic clouds respond to ongoing sea-ice loss and climate change.
Bu-Yo Kim, Miloslav Belorid, Joo Wan Cha, Youngmi Kim, and Seungbum Kim
Atmos. Meas. Tech., 18, 3781–3797, https://doi.org/10.5194/amt-18-3781-2025, https://doi.org/10.5194/amt-18-3781-2025, 2025
Short summary
Short summary
This study analyzed NaCl and CaCl2 powder-type hygroscopic materials for cloud seeding, using the Korea Cloud Physics Experimental Chamber (K-CPEC) in South Korea. The aerosol chamber enabled particle analysis in an extremely dry environment, while the cloud chamber, with precise pressure and temperature control, facilitated droplet growth through quasi-adiabatic expansion. Our study provides valuable insights for the development of new seeding materials and advanced cloud seeding experiments.
Bu-Yo Kim, Joo Wan Cha, and Yong Hee Lee
Atmos. Meas. Tech., 16, 5403–5413, https://doi.org/10.5194/amt-16-5403-2023, https://doi.org/10.5194/amt-16-5403-2023, 2023
Short summary
Short summary
A camera-based imager and convolutional neural network (CNN) were used to estimate ground cloud cover. Image data from 2019 were used for training and validation, and those from 2020 were used for testing. The CNN model exhibited high performance, with an accuracy of 0.92, RMSE of 1.40 tenths, and 93% agreement with observed cloud cover within ±2 tenths' difference. It also outperformed satellites and ceilometers and proved to be the most suitable for ground-based cloud cover estimation.
Joo Wan Cha, Bu-Yo Kim, Miloslav Belorid, Young-Suk Oh, Myeonghun Kang, Seungbum Kim, Young Jun Yoon, Jiyeon Park, and Sang-Jong Park
EGUsphere, https://doi.org/10.5194/egusphere-2026-3543, https://doi.org/10.5194/egusphere-2026-3543, 2026
This preprint is open for discussion and under review for Atmospheric Chemistry and Physics (ACP).
Short summary
Short summary
Ice-nucleating particles trigger ice formation in clouds, shaping precipitation and climate. We measured these particles in real time from a ship in the Arctic Ocean — the first study to do so — and found that biologically produced particles are active at warm temperatures, a signal missed by earlier filter-based methods. Declining sea ice appears to increase their concentrations. Our findings offer new insight into how Arctic clouds respond to ongoing sea-ice loss and climate change.
Bu-Yo Kim, Miloslav Belorid, Joo Wan Cha, Youngmi Kim, and Seungbum Kim
Atmos. Meas. Tech., 18, 3781–3797, https://doi.org/10.5194/amt-18-3781-2025, https://doi.org/10.5194/amt-18-3781-2025, 2025
Short summary
Short summary
This study analyzed NaCl and CaCl2 powder-type hygroscopic materials for cloud seeding, using the Korea Cloud Physics Experimental Chamber (K-CPEC) in South Korea. The aerosol chamber enabled particle analysis in an extremely dry environment, while the cloud chamber, with precise pressure and temperature control, facilitated droplet growth through quasi-adiabatic expansion. Our study provides valuable insights for the development of new seeding materials and advanced cloud seeding experiments.
Jeonggyu Kim, Sungmin Park, Greg M. McFarquhar, Anthony J. Baran, Joo Wan Cha, Kyoungmi Lee, Seoung Soo Lee, Chang Hoon Jung, Kyo-Sun Sunny Lim, and Junshik Um
Atmos. Chem. Phys., 24, 12707–12726, https://doi.org/10.5194/acp-24-12707-2024, https://doi.org/10.5194/acp-24-12707-2024, 2024
Short summary
Short summary
We developed idealized models to represent the shapes of ice particles found in deep convective clouds and calculated their single-scattering properties. By comparing these results with in situ measurements, we discovered that a mixture of shape models matches in situ measurements more closely than single-form models or aggregate models. This finding has important implications for enhancing the simulation of single-scattering properties of ice crystals in deep convective clouds.
Bu-Yo Kim, Joo Wan Cha, and Yong Hee Lee
Atmos. Meas. Tech., 16, 5403–5413, https://doi.org/10.5194/amt-16-5403-2023, https://doi.org/10.5194/amt-16-5403-2023, 2023
Short summary
Short summary
A camera-based imager and convolutional neural network (CNN) were used to estimate ground cloud cover. Image data from 2019 were used for training and validation, and those from 2020 were used for testing. The CNN model exhibited high performance, with an accuracy of 0.92, RMSE of 1.40 tenths, and 93% agreement with observed cloud cover within ±2 tenths' difference. It also outperformed satellites and ceilometers and proved to be the most suitable for ground-based cloud cover estimation.
Cited articles
Al Banna, M. H., Taher, K. A., Kaiser, M. S., Mahmud, M., Rahman, M. S.,
Hosen, A. S., and Cho, G. H.: Application of artificial intelligence in
predicting earthquakes: state-of-the-art and future challenges, IEEE Access.,
8, 192880–192923, https://doi.org/10.1109/ACCESS.2020.3029859, 2020.
Al-lahham, A., Theeb, O., Elalem, K., Alshawi, T., and Alshebeili, S.: Sky
Imager-Based Forecast of Solar Irradiance Using Machine Learning, Electronics, 9, 1700, https://doi.org/10.3390/electronics9101700, 2020.
Alonso, J., Batlles, F. J., López, G., and Ternero, A.: Sky camera imagery processing based on a sky classification using radiometric data, Energy, 68, 599–608, https://doi.org/10.1016/j.energy.2014.02.035, 2014.
Alonso-Montesinos, J.: Real-Time Automatic Cloud Detection Using a Low-Cost
Sky Camera, Remote Sens., 12, 1382, https://doi.org/10.3390/rs12091382, 2020.
Azhar, M. A. D. M., Hamid, N. S. A., Kamil, W. M. A. W. M., and Mohamad, N. S.: Daytime Cloud Detection Method Using the All-Sky Imager over PERMATApintar Observatory, Universe, 7, 41, https://doi.org/10.3390/universe7020041, 2021.
Bergstra, J. and Bengio, Y.: Random search for hyper-parameter optimization, J. Mach. Learn. Res., 13, 281–305, 2012.
Blazek, M. and Pata, P.: Colour transformations and K-means segmentation for automatic cloud detection, Meteorol. Z., 24, 503–509, https://doi.org/10.1127/metz/2015/0656, 2015.
Boers, R., De Haij, M. J., Wauben, W. M. F., Baltink, H. K., Van Ulft, L.
H., Savenije, M., and Long, C. N.: Optimized fractional cloudiness determination from five ground-based remote sensing techniques, J. Geophys. Res., 115, D24116, https://doi.org/10.1029/2010JD014661, 2010.
Calbó, J., Long, C. N., González, J. A., Augustine, J., and McComiskey, A.: The thin border between cloud and aerosol: Sensitivity of several ground based observation techniques, Atmos. Res., 196, 248–260,
https://doi.org/10.1016/j.atmosres.2017.06.010, 2017.
Cazorla, A., Olmo, F. J., Alados-Arboledas, L.: Development of a sky imager for cloud cover assessment, J. Opt. Soc. Am. A, 25, 29–39, https://doi.org/10.1364/JOSAA.25.000029, 2008.
Cazorla, A., Husillos, C., Antón, M., and Alados-Arboledas, L.: Multi-exposure adaptive threshold technique for cloud detection with sky imagers, Sol. Energy, 114, 268–277, https://doi.org/10.1016/j.solener.2015.02.006,
2015.
Chauvin, R., Nou, J., Thil, S., and Grieu, S.: Modelling the clear-sky intensity distribution using a sky imager, Sol. Energy, 119, 1–17,
https://doi.org/10.1016/j.solener.2015.06.026, 2015.
Çınar, Z. M., Abdussalam Nuhu, A., Zeeshan, Q., Korhan, O., Asmael, M., and Safaei, B.: Machine learning in predictive maintenance towards
sustainable smart manufacturing in industry 4.0, Sustainability, 12, 8211, https://doi.org/10.3390/su12198211, 2020.
Costa-Surós, M., Calbó, J., González, J. A., and Long, C. N.:
Comparing the cloud vertical structure derived from several methods based on
radiosonde profiles and ground-based remote sensing measurements, Atmos.
Meas. Tech., 7, 2757–2773, https://doi.org/10.5194/amt-7-2757-2014, 2014.
Dev, S., Savoy, F. M., Lee, Y. H., and Winkler, S.: Design of low-cost, compact and weather-proof whole sky imagers for High-Dynamic-Range captures, in: IGARSS 2015–2015 IEEE International Geoscience and Remote Sensing
Symposium, 26–31 July 2015, Milan, Italy, 5359–5362, 2015.
Dev, S., Wen, B., Lee, Y. H., and Winkler, S.: Ground-based image analysis: A
tutorial on machine-learning techniques and applications, IEEE Geosci. Remote Sens. M., 4, 79–93, https://doi.org/10.1109/MGRS.2015.2510448, 2016.
Dev, S., Savoy, F. M., Lee, Y. H., and Winkler, S.: Nighttime sky/cloud image
segmentation, in: ICIP 2017–2017 IEEE International Conference on Image
Processing, 17–20 September 2017, Beijing, China, 345–349, 2017.
Dev, S., Nautiyal, A., Lee, Y. H., and Winkler, S.: Cloudsegnet: A deep network for nychthemeron cloud image segmentation, IEEE Geosci. Remote Sens. Lett., 16, 1814–1818, https://doi.org/10.1109/lgrs.2019.2912140, 2019.
Fa, T., Xie, W., Wang, Y., and Xia, Y.: Development of an all-sky imaging system for cloud cover assessment, Appl. Optics, 58, 5516–5524,
https://doi.org/10.1364/AO.58.005516, 2019.
Friedman, J. H.: Greedy function approximation: A gradient boosting machine,
Ann. Stat., 29, 1189–1232, https://doi.org/10.1214/aos/1013203451, 2001.
Gani, W., Taleb, H., and Limam, M.: Support vector regression based residual
control charts, J. Appl. Stat., 37, 309–324, https://doi.org/10.1080/02664760903002667, 2010.
Geyer, C. J.: Generalized linear models in R, R Reference Document, 1–23, available at: https://www.stat.umn.edu/geyer/5931/mle/glm.pdf (last access: 1 June 2021), 2003.
Ghonima, M. S., Urquhart, B., Chow, C. W., Shields, J. E., Cazorla, A., and
Kleissl, J.: A method for cloud detection and opacity classification based
on ground based sky imagery, Atmos. Meas. Tech., 5, 2881–2892,
https://doi.org/10.5194/amt-5-2881-2012, 2012.
Greenwell, B., Boehmke, B., and Cunningham, J.: GBM Developers: Package `gbm', R Reference Document, 1–39, available at:
https://cran.r-project.org/web/packages/gbm/gbm.pdf (last access: 1 June 2021), 2020.
Heinle, A., Macke, A., and Srivastav, A.: Automatic cloud classification of
whole sky images, Atmos. Meas. Tech., 3, 557–567, https://doi.org/10.5194/amt-3-557-2010, 2010.
Huo, J. and Lu, D.: Cloud determination of all-sky images under low-visibility conditions, J. Atmos. Ocean. Tech., 26, 2172–2181,
https://doi.org/10.1175/2009JTECHA1324.1, 2009.
Kazantzidis, A., Tzoumanikas, P., Bais, A. F., Fotopoulos, S., and Economou, G.: Cloud detection and classification with the use of whole-sky ground-based
images, Atmos. Res., 113, 80–88, https://doi.org/10.1016/j.atmosres.2012.05.005, 2012.
Kim, B. Y. and Cha, J. W.: Cloud Observation and Cloud Cover Calculation at
Nighttime Using the Automatic Cloud Observation System (ACOS) Package, Remote Sens., 12, 2314, https://doi.org/10.3390/rs12142314, 2020.
Kim, B. Y. and Lee, K. T.: Radiation component calculation and energy budget
analysis for the Korean Peninsula region, Remote Sens., 10, 1147,
https://doi.org/10.3390/rs10071147, 2018.
Kim, B. Y. and Lee, K. T.: Using the himawari-8 ahi multi-channel to improve
the calculation accuracy of outgoing longwave radiation at the top of the
atmosphere. Remote Sens., 11, 589, https://doi.org/10.3390/rs11050589, 2019.
Kim, B. Y., Jee, J. B., Zo, I. S., and Lee, K. T.: Cloud cover retrieved from
skyviewer: A validation with human observations. Asia-Pac, J. Atmos. Sci., 52, 1–10, https://doi.org/10.1007/s13143-015-0083-4, 2016.
Kim, B. Y., Lee, K. T., Jee, J. B., and Zo, I. S.: Retrieval of outgoing longwave radiation at top-of-atmosphere using Himawari-8 AHI data, Remote
Sens. Environ., 204, 498–508, https://doi.org/10.1016/j.rse.2017.10.006, 2018.
Kim, B. Y., Cha, J. W., Ko, A. R., Jung, W., and Ha, J. C.: Analysis of the
occurrence frequency of seedable clouds on the Korean Peninsula for precipitation enhancement experiments, Remote Sens., 12, 1487,
https://doi.org/10.3390/rs12091487, 2020a.
Kim, B. Y., Cha, J. W., Jung, W., and Ko, A. R.: Precipitation Enhancement
Experiments in Catchment Areas of Dams: Evaluation of Water Resource Augmentation and Economic Benefits, Remote Sens., 12, 3730, https://doi.org/10.3390/rs12223730, 2020b.
Kim, B. Y., Cha, J. W., Chang, K. H., and Lee, C.: Visibility Prediction over
South Korea Based on Random Forest, Atmosphere, 12, 552, https://doi.org/10.3390/atmos12050552, 2021.
Kreuter, A., Zangerl, M., Schwarzmann, M., and Blumthaler, M.: All-sky imaging: a simple, versatile system for atmospheric research, Appl. Optics, 48, 1091–1097, https://doi.org/10.1364/AO.48.001091, 2009.
Krinitskiy, M. A. and Sinitsyn, A. V.: Adaptive algorithm for cloud cover
estimation from all-sky images over the sea, Oceanology, 56, 315–319,
https://doi.org/10.1134/S0001437016020132, 2016.
Kyba, C. C., Ruhtz, T., Fischer, J., and Hölker, F.: Red is the new black: how the colour of urban skyglow varies with cloud cover, Mon. Notic. Roy. Astron. Soc., 425, 701–708, https://doi.org/10.1111/j.1365-2966.2012.21559.x, 2012.
Lalonde, J. F., Narasimhan, S. G., and Efros, A. A.: What do the sun and the sky tell us about the camera?, Int. J. Comput. Vis., 88, 24–51,
https://doi.org/10.1007/s11263-009-0291-4, 2010.
Lee, S. H., Kim, B. Y., Lee, K. T., Zo, I. S., Jung, H. S., and Rim, S. H.:
Retrieval of reflected shortwave radiation at the top of the atmosphere
using Himawari-8/AHI data, Remote Sens., 10, 213, https://doi.org/10.3390/rs10020213, 2018.
Li, Q., Lu, W., and Yang, J.: A hybrid thresholding algorithm for cloud
detection on ground-based color images, J. Atmos. Ocean. Tech., 28, 1286–1296, https://doi.org/10.1175/JTECH-D-11-00009.1, 2011.
Li, X., Lu, Z., Zhou, Q., and Xu, Z.: A Cloud Detection Algorithm with Reduction of Sunlight Interference in Ground-Based Sky Images, Atmosphere, 10, 640, https://doi.org/10.3390/atmos10110640, 2019.
Liu, S., Zhang, L., Zhang, Z., Wang, C., and Xiao, B.: Automatic cloud detection for all-sky images using superpixel segmentation, IEEE Geosci. Remote Sens. Lett., 12, 354–358, https://doi.org/10.1109/LGRS.2014.2341291, 2014.
Long, C. N., Sabburg, J. M., Calbó, J., and Pagès, D.: Retrieving cloud characteristics from ground-based daytime color all-sky images, J. Atmos. Ocean. Tech., 23, 633–652, https://doi.org/10.1175/JTECH1875.1, 2006.
Lothon, M., Barnéoud, P., Gabella, O., Lohou, F., Derrien, S., Rondi, S., Chiriaco, M., Bastin, S., Dupont, J. C., Haeffelin, M., Badosa, J., Pascal, N., and Montoux, N.: ELIFAN, an algorithm for the estimation of cloud cover from sky imagers, Atmos. Meas. Tech., 12, 5519–5534, https://doi.org/10.5194/amt-12-5519-2019, 2019.
Mantelli Neto, S. L., von Wangenheim, A., Pereira, E. B., and Comunello, E.: The use of Euclidean geometric distance on RGB color space for the
classification of sky and cloud patterns, J. Atmos. Ocean. Tech., 27, 1504–1517, https://doi.org/10.1175/2010JTECHA1353.1, 2010.
Martínez, F., Frías, M. P., Charte, F., and Rivera, A. J.: Time Series Forecasting with KNN in R: the tsfknn Package, R J., 11, 229–242, https://doi.org/10.32614/RJ-2019-004, 2019.
Meyer, D.: Support vector machines. The Interface to libsvm in package e1071, R News, 23–26, available at: https://cran.r-project.org/web/packages/e1071/vignettes/svmdoc.pdf (last access: 1 June 2021), 2001.
Meyer, D., Dimitriadou, E., Hornik, K., Weingessel, A., Leisch, F., Chang, C. C., and Lin, C. C.: Package `e1071', R Reference Document, 1–66, available at: https://cran.r-project.org/web/packages/e1071/e1071.pdf, last access: 1 June 2021.
Nguyen, D. A. and Kleissl, J.: Stereographic methods for cloud base height
determination using two sky imagers, Sol. Energy, 107, 495–509,
https://doi.org/10.1016/j.solener.2014.05.005, 2014.
Olive, D. J.: Multiple linear regression, in: Linear regression. Springer,
Cham, 17–83, 2017.
Peng, Z., Yu, D., Huang, D., Heiser, J., Yoo, S., and Kalb, P.: 3D cloud
detection and tracking system for solar forecast using multiple sky imagers,
Sol. Energy, 118, 496–519, https://doi.org/10.1016/j.solener.2015.05.037, 2015.
Ridgeway, G.: Generalized Boosted Models: A guide to the gbm package, Update,
1, 1–15, 2020.
Ripley, B. and Venables, W.: Package `class', R Reference Document, 1–19,
available at: https://cran.r-project.org/web/packages/class/class.pdf (last access: 1 June 2021), 2021a.
Ripley, B. and Venables, W.: Package `nnet', R Reference Document, 1–11,
available at: https://cran.r-project.org/web/packages/nnet/nnet.pdf (last access: 1 June 2021), 2021b.
Román, R., Cazorla, A., Toledano, C., Olmo, F. J., Cachorro, V. E., de Frutos, A., and Alados-Arboledas, L.: Cloud cover detection combining high
dynamic range sky images and ceilometer measurements, Atmos. Res., 196,
224–236, https://doi.org/10.1016/j.atmosres.2017.06.006, 2017.
Rosa, J. P., Guerra, D. J., Horta, N. C., Martins, R. M., and Lourenço, N. C.: Overview of Artificial Neural Networks, in: Using Artificial Neural
Networks for Analog Integrated Circuit Design Automation, Springer, Cham, 21–44, 2020.
Sazzad, T. S., Islam, S., Mamun, M. M. R. K., and Hasan, M. Z.: Establishment of an efficient color model from existing models for better gamma encoding in image processing, Int. J. Image Process., 7, 90–100, 2013.
Shi, C., Zhou, Y., Qiu, B., He, J., Ding, M., and Wei, S.: Diurnal and nocturnal cloud segmentation of all-sky imager (ASI) images using enhancement fully convolutional networks. Atmos. Meas. Tech., 12, 4713–4724,
https://doi.org/10.5194/amt-12-4713-2019, 2019.
Shi, C., Zhou, Y., and Qiu, B.: CloudU-Netv2: A Cloud Segmentation Method for
Ground-Based Cloud Images Based on Deep Learning, Neural Process. Lett., 53, 2715–2728, https://doi.org/10.1007/s11063-021-10457-2, 2021.
Shields, J. E., Karr, M. E., Johnson, R. W., and Burden, A. R.: Day/night whole sky imagers for 24-h cloud and sky assessment: history and overview, Appl. Optics, 52, 1605–1616, https://doi.org/10.1364/AO.52.001605, 2013.
Shields, J. E., Burden, A. R., and Karr, M. E.: Atmospheric cloud algorithms for day/night whole sky imagers, Appl. Optics, 58, 7050–7062,
https://doi.org/10.1364/AO.58.007050, 2019.
Shimoji, N., Aoyama, R., and Hasegawa, W.: Spatial variability of correlated
color temperature of lightning channels, Results Phys., 6, 161–162,
https://doi.org/10.1016/j.rinp.2016.03.004, 2016.
Shin, J. Y., Kim, B. Y., Park, J., Kim, K. R., and Cha, J. W.: Prediction of
Leaf Wetness Duration Using Geostationary Satellite Observations and Machine
Learning Algorithms, Remote Sens., 12, 3076, https://doi.org/10.3390/rs12183076, 2020.
Singh, A., Kotiyal, V., Sharma, S., Nagar, J., and Lee, C. C.: A machine
learning approach to predict the average localization error with applications to wireless sensor networks, IEEE Access., 8, 208253–208263,
https://doi.org/10.1109/ACCESS.2020.3038645, 2020.
Sunil, S., Padmakumari, B., Pandithurai, G., Patil, R. D., and Naidu, C. V.:
Diurnal (24 h) cycle and seasonal variability of cloud fraction retrieved
from a Whole Sky Imager over a complex terrain in the Western Ghats and
comparison with MODIS, Atmos. Res., 248, 105180, https://doi.org/10.1016/j.atmosres.2020.105180, 2021.
Taghizadeh-Mehrjardi, R., Neupane, R., Sood, K., and Kumar, S.: Artificial bee colony feature selection algorithm combined with machine learning algorithms to predict vertical and lateral distribution of soil organic matter in South Dakota, USA, Carbon Manage., 8, 277–291,
https://doi.org/10.1080/17583004.2017.1330593, 2017.
Valentín, L., Peña-Cruz, M. I., Moctezuma, D., Peña-Martínez, C. M., Pineda-Arellano, C. A., and Díaz-Ponce, A.: Towards the Development of a Low-Cost Irradiance Nowcasting Sky Imager, Appl. Sci., 9, 1131, https://doi.org/10.3390/app9061131, 2019.
Wang, G., Kurtz, B., and Kleissl, J.: Cloud base height from sky imager and
cloud speed sensor, Sol. Energy, 131, 208–221, https://doi.org/10.1016/j.solener.2016.02.027, 2016.
Wang, Y., Liu, D., Xie, W., Yang, M., Gao, Z., Ling, X., Huang, Y., Li, C.,
Liu, Y., and Xia, Y.: Day and Night Clouds Detection Using a Thermal-Infrared
All-Sky-View Camera, Remote Sens., 13, 1852, https://doi.org/10.3390/rs13091852, 2021.
Wright, M. N. and Ziegler, A.: Ranger: A fast implementation of random forests for high dimensional data in C
Wright, M. N., Wager, S., and Probst, P.: Package `ranger', R Reference
Document, 1–25, available at: https://cran.r-project.org/web/packages/ranger/ranger.pdf (last access: 1 June 2021), 2020.
Xie, W., Liu, D., Yang, M., Chen, S., Wang, B., Wang, Z., Xia, Y., Liu, Y.,
Wang, Y., and Zhang, C.: SegCloud: a novel cloud image segmentation model using a deep convolutional neural network for ground-based all-sky-view camera observation, Atmos. Meas. Tech., 13, 1953–1961,
https://doi.org/10.5194/amt-13-1953-2020, 2020.
Xiong, Z., Cui, Y., Liu, Z., Zhao, Y., Hu, M., and Hu, J.: Evaluating
explorative prediction power of machine learning algorithms for materials
discovery using k-fold forward cross-validation, Comput. Mater. Sci., 171,
109203, https://doi.org/10.1016/j.commatsci.2019.109203, 2020.
Yabuki, M., Shiobara, M., Nishinaka, K., and Kuji, M.: Development of a cloud
detection method from whole-sky color images, Polar Sci., 8, 315–326,
https://doi.org/10.1016/j.polar.2014.07.004, 2014.
Yang, J., Min, Q., Lu, W., Yao, W., Ma, Y., Du, J., Lu, T., and Liu, G.: An
automated cloud detection method based on the green channel of total-sky
visible images, Atmos. Meas. Tech., 8, 4671–4679, https://doi.org/10.5194/amt-8-4671-2015, 2015.
Yang, J., Min, Q., Lu, W., Ma, Y., Yao, W., Lu, T., Du, J., and Liu, G.: A total sky cloud detection method using real clear sky background, Atmos. Meas. Tech., 9, 587–597, https://doi.org/10.5194/amt-9-587-2016, 2016.
Ye, L., Cao, Z., and Xiao, Y.: DeepCloud: Ground-based cloud image categorization using deep convolutional features, IEEE T. Geosci. Remote, 55, 5729–5740, https://doi.org/10.1109/TGRS.2017.2712809, 2017.
Ying, X.: An overview of overfitting and its solutions, J. Phys.: Conf. Ser., 1168, 022022, https://doi.org/10.1088/1742-6596/1168/2/022022, 2019.
Yoshida, S., Misumi, R., and Maesaka, T.: Early Detection of Convective Echoes and Their Development Using a Ka-Band Radar Network. Weather Forecast., 36, 253–264, https://doi.org/10.1175/WAF-D-19-0233.1, 2021.
Yun, H. K. and Whang, S. M.: Development of a cloud cover reader from whole sky images, Int. J. Eng. Technol., 7, 252–256, https://doi.org/10.14419/ijet.v7i3.33.21023, 2018.
Zhang, J., Liu, P., Zhang, F., and Song, Q.: CloudNet: Ground-based cloud
classification with deep convolutional neural network, Geophys. Res. Lett.,
45, 8665–8672, https://doi.org/10.1029/2018GL077787, 2018.
Zhang, S., Cheng, D., Deng, Z., Zong, M., and Deng, X.: A novel kNN algorithm
with data-drive k parameter computation, Pattern Recognit. Lett., 109, 44–54, https://doi.org/10.1016/j.patrec.2017.09.036, 2018.
Short summary
This study investigates a method for 24 h cloud cover calculation using a camera-based imager and supervised machine learning methods. The cloud cover is calculated by learning the statistical characteristics of the ratio, difference, and luminance using RGB channels of the image with a machine learning model. The proposed approach is suitable for nowcasting because it has higher learning and prediction speed than the method in which the many pixels of a 2D image are learned.
This study investigates a method for 24 h cloud cover calculation using a camera-based imager...
