Search an Article

@article{gonzalez2024CCNeural,

title = {A neural network to retrieve cloud cover from all-sky cameras: A case of study over Antarctica},

author = {Daniel González-Fernández and Roberto Román and Juan Carlos Antuña-Sánchez and Victoria E. Cachorro and Gustavo Copes and Sara Herrero-Anta and Celia Herrero del Barrio and África Barreto and Ramiro González and Ramón Ramos and Patricia Martín and David Mateos and Carlos Toledano and Abel Calle and Ángel Frutos},

url = {https://rmets.onlinelibrary.wiley.com/doi/abs/10.1002/qj.4834},

doi = {https://doi.org/10.1002/qj.4834},

year  = {2024},

date = {2024-08-28},

journal = {Quarterly Journal of the Royal Meteorological Society},

volume = {n/a},

number = {n/a},

abstract = {Abstract We present a new model based on a convolutional neural network (CNN) to predict daytime cloud cover (CC) from sky images captured by all-sky cameras, which is called CNN-CC. A total of 49,016 daytime sky images, recorded at different Spanish locations (Valladolid, La Palma, and Izaña) from two different all-sky camera types, are manually classified into different CC (oktas) values by trained researchers. Subsequently, the images are randomly split into a training set and a test set to validate the model. The CC values predicted by the CNN-CC model are compared with the observations made by trained people on the test set, which serve as reference. The predicted CC values closely match the reference values within ±$$ ± $$1?oktas in 99% of the cloud-free and overcast cases. Moreover, this percentage is above 93% for the rest of partially cloudy cases. The mean bias error (MBE) and standard deviation (SD) of the differences between the predicted and reference CC values are calculated, resulting in MBE=0.007$$ mathrmMBE=0.007 $$?oktas and SD=0.674$$ mathrmSD=0.674 $$?oktas. The MBE and SD are also represented for different intervals of measured aerosol optical depth and Ångström exponent values, revealing that the performance of the CNN-CC model does not depend on aerosol load or size. Once the model is validated, the CC obtained from a set of images captured every 5?min, from January 2018 to March 2022, at the Antarctic station of Marambio (Argentina) is compared against direct field observations of CC (not from images) taken at this location, which is not used in the training process. As a result, the model slightly underestimates the observations with an MBE of ?$$ - $$0.3?oktas. The retrieved data are analyzed in detail. The monthly and annual CC values are calculated. Overcast conditions are the most frequent, accounting for 46.5% of all observations throughout the year, rising to 64.5% in January. The annual mean CC value at this location is 5.5?oktas, with a standard deviation of approximately 3.1?oktas. A similar analysis is conducted, separating data by hours, but no significant diurnal cycles are observed except for some isolated months.},

keywords = {AI, all-sky camera, Antarctic, cloud cover, convolutional neural network, image identification},

pubstate = {published},

tppubtype = {article}

}

@article{Montero-Martín2023,

title = {Reconstruction of daily global solar radiation under all-sky and cloud-free conditions in Badajoz (Spain) since 1929},

author = {Javier Montero-Martín and Manuel Antón and José Manuel Vaquero and Roberto Román and Javier Vaquero-Martinez and Alejandro J. P. Aparicio and Arturo Sanchez-Lorenzo},

url = {https://rmets.onlinelibrary.wiley.com/doi/abs/10.1002/joc.8042},

doi = {https://doi.org/10.1002/joc.8042},

year  = {2023},

date = {2023-02-16},

journal = {International Journal of Climatology},

volume = {n/a},

number = {n/a},

abstract = {Abstract This work analyses the long-term temporal variability of the annual and seasonal series of reconstructed global solar radiation for both all-sky and cloud-free conditions in Badajoz (Spain) over the 1929–2015 period. Specifically, daily values of global horizontal irradiation (GHI) for all-sky cases are derived from a semiempirical method based on the relationship between the cloud modification factor and sunshine duration records. Additionally, cloud-free situations are selected using cloud cover (CC) information recorded by surface observations. Regarding GHI linear trends for all-sky conditions, three periods are clearly identified: during the 1929–1950 period, there is a positive and statistically significant trend of +4.18?W·m?2·decade?1. It is followed by a significant dimming with a trend of ?3.72?W·m?2·decade?1 between 1951 and 1984. GHI levels increase again from 1985 to 2015 with a statistically significant trend of +2.04?W·m?2·decade?1. The seasonal trends are found to be statistically significant only in summer for all the three subperiods. With the goal to find out the possible causes of the reconstructed GHI trends, the temporal variability of the CC was also analysed. It was observed that CC has a statistically significant negative trend between 1985 and 2015 which may partially explain the GHI increase shown for this period. In contrast, not statistically significant trends were found in the annual and seasonal CC series before 1985. The long-term evolution of the GHI under cloud-free conditions exhibits the same pattern as all-sky conditions: an increase during 1929–1950, followed by a decrease in 1951–1984 and then a new increase from 1985 to 2015. Therefore, the positive (negative) linear trends in GHI reported in this study could be partially related to a decrease (increase) in the aerosol load during the analysed three subperiods.},

keywords = {atmospheric aerosols, cloud cover, dimming/brightening, early instrumental data, surface solar radiation},

pubstate = {published},

tppubtype = {article}

}

@article{rs13020169,

title = {Solar Radiation Climatology in Camagüey, Cuba (1981–2016)},

author = {Juan Carlos Antuña-Sánchez and René Estevan and Roberto Román and Juan Carlos Antuña-Marrero and Victoria E Cachorro and Albeth Rodríguez Vega and Ángel M de Frutos},

url = {https://www.mdpi.com/2072-4292/13/2/169},

doi = {10.3390/rs13020169},

issn = {2072-4292},

year  = {2021},

date = {2021-01-01},

journal = {Remote Sensing},

volume = {13},

number = {2},

abstract = {The transition to renewable energies is an unavoidable step to guarantee a peaceful and sustainable future for humankind. Although solar radiation is one of the main sources of renewable energy, there are broad regions of the planet where it has not been characterized appropriately to provide the necessary information for regional and local planning and design of the different solar powered systems. The Caribbean, and Cuba in particular, lacked until very recently at least one long-term series of surface solar radiation measurements. Here we present the first long-term records of solar radiation for this region. Solar radiation measurements manually conducted and recorded on paper were rescued, reprocessed and quality controlled to develop the solar radiation climatology at the Actinometrical Station of Camagüey, in Cuba (21.422°N; 77.850°W; 122 m a.s.l.) for the period 1981-2016. The diurnal cycle based on the average hourly values of the global, direct and diffuse horizontal variables for the entire period have been determined and analyzed showing the dependence on solar zenith angle (SZA) and clouds. The annual cycle of global solar component given by the mean monthly daily values presents two maxima, one in April and another one in July with values of 5.06 and 4.91 kWh m−2, respectively (18.23 and 17.67 MJ m−2 per day for insolation), and the minimum in December (3.15 kWh m−2 or 11.33 MJ m−2). The maxima are governed by the direct solar components and are modulated by cloudiness. Both, diurnal and annual cycles of the diffuse solar component show a smoothed bell shaped behavior. In general solar radiation at this station presents a strong influence of clouds, with little seasonal variation but with higher values during the rainy season. Daily global radiation annual averages showed its maximum value in the year 1983, with 17.45 MJ m−2 explained by very low cloudiness this year, and the minimum value was reported in 2009 with a value of 12.43 MJ m−2 that could not explained by the cloud coverage or the aerosols optical depths registered that year. The effects of the 1982 El Chichón and 1991 Mount Pinatubo volcanic eruptions on the solar radiation variables at Camagüey are also shown and discussed. The results achieved in this study shown the characteristics of solar radiation in this area and their potential for solar power applications.},

keywords = {climatology, cloud cover, cuba, diffuse, direct radiation, insolation, Solar radiation},

pubstate = {published},

tppubtype = {article}

}