Articles | Volume 17, issue 3
https://doi.org/10.5194/amt-17-979-2024
© Author(s) 2024. 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-17-979-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
09 Feb 2024
Research article |
| 09 Feb 2024
| 09 Feb 2024
Improved RepVGG ground-based cloud image classification with attention convolution
Chaojun Shi
CORRESPONDING AUTHOR
Department of Electronic and Communication Engineering, North China Electric Power University, Baoding 071003, China
Hebei Key Laboratory of Power Internet of Things Technology, North China Electric Power University, Baoding 071003, China
Leile Han
Department of Electronic and Communication Engineering, North China Electric Power University, Baoding 071003, China
Ke Zhang
Department of Electronic and Communication Engineering, North China Electric Power University, Baoding 071003, China
Hebei Key Laboratory of Power Internet of Things Technology, North China Electric Power University, Baoding 071003, China
Hongyin Xiang
CORRESPONDING AUTHOR
Department of Electronic and Communication Engineering, North China Electric Power University, Baoding 071003, China
Hebei Key Laboratory of Power Internet of Things Technology, North China Electric Power University, Baoding 071003, China
Xingkuan Li
Department of Electronic and Communication Engineering, North China Electric Power University, Baoding 071003, China
Zibo Su
Department of Electronic and Communication Engineering, North China Electric Power University, Baoding 071003, China
Xian Zheng
Department of Electronic and Communication Engineering, North China Electric Power University, Baoding 071003, China
Related subject area
Subject: Clouds | Technique: Remote Sensing | Topic: Validation and Intercomparisons
An intercomparison of EarthCARE cloud, aerosol, and precipitation retrieval products
First results of cloud retrieval from the Geostationary Environmental Monitoring Spectrometer
Thundercloud structures detected and analyzed based on coherent Doppler wind lidar
Assessing Arctic low-level clouds and precipitation from above – a radar perspective
What CloudSat cannot see: liquid water content profiles inferred from MODIS and CALIOP observations
Comparing FY-2F/CTA products to ground-based manual total cloud cover observations in Xinjiang under complex underlying surfaces and different Weather Conditions
Validation of the Cloud_CCI (Cloud Climate Change Initiative) cloud products in the Arctic
The Education and Research 3D Radiative Transfer Toolbox (EaR3T) – towards the mitigation of 3D bias in airborne and spaceborne passive imagery cloud retrievals
Retrieval of microphysical parameters of monsoonal rain using X-band dual-polarization radar: their seasonal dependence and evaluation
Consistency test of precipitating ice cloud retrieval properties obtained from the observations of different instruments operating at Dome C (Antarctica)
Sizing ice hydrometeor populations using the dual-wavelength radar ratio
Impact of the revisit frequency on cloud climatology for CALIPSO, EarthCARE, Aeolus, and ICESat-2 satellite lidar missions
The impact of sampling strategy on the cloud droplet number concentration estimated from satellite data
Horizontal geometry of trade wind cumuli – aircraft observations from a shortwave infrared imager versus a radar profiler
Evaluating the consistency and continuity of pixel-scale cloud property data records from Aqua and SNPP (Suomi National Polar-orbiting Partnership)
Quality assessment of Second-generation Global Imager (SGLI)-observed cloud properties using SKYNET surface observation data
Comparison of scattering ratio profiles retrieved from ALADIN/Aeolus and CALIOP/CALIPSO observations and preliminary estimates of cloud fraction profiles
Evaluation of convective cloud microphysics in numerical weather prediction models with dual-wavelength polarimetric radar observations: methods and examples
Synergistic radar and sub-millimeter radiometer retrievals of ice hydrometeors in mid-latitude frontal cloud systems
Evaluation of satellite retrievals of liquid clouds from the GOES-13 imager and MODIS over the midlatitude North Atlantic during the NAAMES campaign
Evaluation of Visible Infrared Imaging Radiometer Suite (VIIRS) neural network cloud detection against current operational cloud masks
The effect of low-level thin arctic clouds on shortwave irradiance: evaluation of estimates from spaceborne passive imagery with aircraft observations
Validation of the Sentinel-5 Precursor TROPOMI cloud data with Cloudnet, Aura OMI O2–O2, MODIS, and Suomi-NPP VIIRS
Dissecting effects of orbital drift of polar-orbiting satellites on accuracy and trends of climate data records of cloud fractional cover
Calibration of global MODIS cloud amount using CALIOP cloud profiles
Evaluation of the MODIS Collection 6 multilayer cloud detection algorithm through comparisons with CloudSat Cloud Profiling Radar and CALIPSO CALIOP products
An extended radar relative calibration adjustment (eRCA) technique for higher-frequency radars and range–height indicator (RHI) scans
Comparing lightning observations of the ground-based European lightning location system EUCLID and the space-based Lightning Imaging Sensor (LIS) on the International Space Station (ISS)
Microwave and submillimeter wave scattering of oriented ice particles
Shallow cumuli cover and its uncertainties from ground-based lidar–radar data and sky images
Using passive and active observations at microwave and sub-millimetre wavelengths to constrain ice particle models
Comparison of the cloud top heights retrieved from MODIS and AHI satellite data with ground-based Ka-band radar
Cross-comparison of cloud liquid water path derived from observations by two space-borne and one ground-based instrument in northern Europe
The impact of neglecting ice phase on cloud optical depth retrievals from AERONET cloud mode observations
Diurnal and nocturnal cloud segmentation of all-sky imager (ASI) images using enhancement fully convolutional networks
Can liquid cloud microphysical processes be used for vertically pointing cloud radar calibration?
Calibration of a 35 GHz airborne cloud radar: lessons learned and intercomparisons with 94 GHz cloud radars
Airborne validation of radiative transfer modelling of ice clouds at millimetre and sub-millimetre wavelengths
Assessing the impact of different liquid water permittivity models on the fit between model and observations
Cloud liquid water path in the sub-Arctic region of Europe as derived from ground-based and space-borne remote observations
Correction of CCI cloud data over the Swiss Alps using ground-based radiation measurements
Cloud heterogeneity on cloud and aerosol above cloud properties retrieved from simulated total and polarized reflectances
Orographic and convective gravity waves above the Alps and Andes Mountains during GPS radio occultation events – a case study
Neural network cloud top pressure and height for MODIS
Preliminary verification for application of a support vector machine-based cloud detection method to GOSAT-2 CAI-2
Evaluation of Himawari-8 surface downwelling solar radiation by ground-based measurements
Characterization of AVHRR global cloud detection sensitivity based on CALIPSO-CALIOP cloud optical thickness information: demonstration of results based on the CM SAF CLARA-A2 climate data record
Analysis of lightning outliers in the EUCLID network
Characterisation of the artificial neural network CiPS for cirrus cloud remote sensing with MSG/SEVIRI
Analysis and evaluation of WRF microphysical schemes for deep moist convection over south-eastern South America (SESA) using microwave satellite observations and radiative transfer simulations
Shannon L. Mason, Howard W. Barker, Jason N. S. Cole, Nicole Docter, David P. Donovan, Robin J. Hogan, Anja Hünerbein, Pavlos Kollias, Bernat Puigdomènech Treserras, Zhipeng Qu, Ulla Wandinger, and Gerd-Jan van Zadelhoff
Atmos. Meas. Tech., 17, 875–898, https://doi.org/10.5194/amt-17-875-2024, https://doi.org/10.5194/amt-17-875-2024, 2024
Short summary
Short summary
When the EarthCARE mission enters its operational phase, many retrieval data products will be available, which will overlap both in terms of the measurements they use and the geophysical quantities they report. In this pre-launch study, we use simulated EarthCARE scenes to compare the coverage and performance of many data products from the European Space Agency production model, with the intention of better understanding the relation between products and providing a compact guide to users.
Bo-Ram Kim, Gyuyeon Kim, Minjeong Cho, Yong-Sang Choi, and Jhoon Kim
Atmos. Meas. Tech., 17, 453–470, https://doi.org/10.5194/amt-17-453-2024, https://doi.org/10.5194/amt-17-453-2024, 2024
Short summary
Short summary
This study introduces the GEMS cloud algorithm and validates its results using data from GEMS and other environmental satellites. The GEMS algorithm is able to detect the lowest cloud heights among the four satellites, and its effective cloud fraction and cloud centroid pressure are well reflected in the retrieval results. The study highlights the algorithm's usefulness in correcting errors in trace gases caused by clouds in the East Asian region.
Kenan Wu, Tianwen Wei, Jinlong Yuan, Haiyun Xia, Xin Huang, Gaopeng Lu, Yunpeng Zhang, Feifan Liu, Baoyou Zhu, and Weidong Ding
Atmos. Meas. Tech., 16, 5811–5825, https://doi.org/10.5194/amt-16-5811-2023, https://doi.org/10.5194/amt-16-5811-2023, 2023
Short summary
Short summary
A compact all-fiber coherent Doppler wind lidar (CDWL) working at the 1.5 µm wavelength is applied to probe the dynamics and microphysics structure of thunderstorms. It was found that thunderclouds below the 0 ℃ isotherm have significant spectrum broadening and an increase in skewness, and that lightning affects the microphysics structure of the thundercloud. It is proven that the precise spectrum of CDWL is a promising indicator for studying the charge structure of thunderstorms.
Imke Schirmacher, Pavlos Kollias, Katia Lamer, Mario Mech, Lukas Pfitzenmaier, Manfred Wendisch, and Susanne Crewell
Atmos. Meas. Tech., 16, 4081–4100, https://doi.org/10.5194/amt-16-4081-2023, https://doi.org/10.5194/amt-16-4081-2023, 2023
Short summary
Short summary
CloudSat’s relatively coarse spatial resolution, low sensitivity, and blind zone limit its assessment of Arctic low-level clouds, which affect the surface energy balance. We compare cloud fractions from CloudSat and finely resolved airborne radar observations to determine CloudSat’s limitations. Cloudsat overestimates cloud fractions above its blind zone, especially during cold-air outbreaks over open water, and misses a cloud fraction of 32 % and half of the precipitation inside its blind zone.
Richard M. Schulte, Matthew D. Lebsock, and John M. Haynes
Atmos. Meas. Tech., 16, 3531–3546, https://doi.org/10.5194/amt-16-3531-2023, https://doi.org/10.5194/amt-16-3531-2023, 2023
Short summary
Short summary
In order to constrain climate models and better understand how clouds might change in future climates, accurate satellite estimates of cloud liquid water content are important. The satellite currently best suited to this purpose, CloudSat, is not sensitive enough to detect some non-raining low clouds. In this study we show that information from two other satellite instruments, MODIS and CALIOP, can be combined to provide cloud water estimates for many of the clouds that are missed by CloudSat.
Shuai Li, Hua Zhang, Yonghang Chen, Zhili Wang, Xiangyu Li, Yuan Li, and Yuanyuan Xue
Atmos. Meas. Tech. Discuss., https://doi.org/10.5194/amt-2023-21, https://doi.org/10.5194/amt-2023-21, 2023
Revised manuscript accepted for AMT
Short summary
Short summary
In this paper, Xinjiang was taken as the test area, nine evaluation indexes of FY-2F/CTA, which including precision rate, false rate, missing rate, consistency rate, strong rate, weak rate, Bias, AE and RMSE, were calculated and analysed under complex underlying surface (subsurface types, temperature and altitude conditions) and different weather conditions (dust effects and different cloud cover levels), and the precision, consistency and error indexes of FY-2F/CTA were tested and evaluated.
Kameswara S. Vinjamuri, Marco Vountas, Luca Lelli, Martin Stengel, Matthew D. Shupe, Kerstin Ebell, and John P. Burrows
Atmos. Meas. Tech., 16, 2903–2918, https://doi.org/10.5194/amt-16-2903-2023, https://doi.org/10.5194/amt-16-2903-2023, 2023
Short summary
Short summary
Clouds play an important role in Arctic amplification. Cloud data from ground-based sites are valuable but cannot represent the whole Arctic. Therefore the use of satellite products is a measure to cover the entire Arctic. However, the quality of such cloud measurements from space is not well known. The paper discusses the differences and commonalities between satellite and ground-based measurements. We conclude that the satellite dataset, with a few exceptions, can be used in the Arctic.
Hong Chen, K. Sebastian Schmidt, Steven T. Massie, Vikas Nataraja, Matthew S. Norgren, Jake J. Gristey, Graham Feingold, Robert E. Holz, and Hironobu Iwabuchi
Atmos. Meas. Tech., 16, 1971–2000, https://doi.org/10.5194/amt-16-1971-2023, https://doi.org/10.5194/amt-16-1971-2023, 2023
Short summary
Short summary
We introduce the Education and Research 3D Radiative Transfer Toolbox (EaR3T) and propose a radiance self-consistency approach for quantifying and mitigating 3D bias in legacy airborne and spaceborne imagery retrievals due to spatially inhomogeneous clouds and surfaces.
Kumar Abhijeet, Thota Narayana Rao, Nidamanuri Rama Rao, and Kasimahanthi Amar Jyothi
Atmos. Meas. Tech., 16, 871–888, https://doi.org/10.5194/amt-16-871-2023, https://doi.org/10.5194/amt-16-871-2023, 2023
Short summary
Short summary
The present study focuses on retrieving and validating raindrop size distribution (DSD) relations for monsoonal rainfall, which are required for retrieving DSDs with polarimetric radar measurements. The seasonal variation in DSD is quite large and significant, and as a result the coefficients also vary considerably between the seasons and from those existing elsewhere. Among the existing DSD methods, the N-gamma method performs better than the other methods.
Gianluca Di Natale, David D. Turner, Giovanni Bianchini, Massimo Del Guasta, Luca Palchetti, Alessandro Bracci, Luca Baldini, Tiziano Maestri, William Cossich, Michele Martinazzo, and Luca Facheris
Atmos. Meas. Tech., 15, 7235–7258, https://doi.org/10.5194/amt-15-7235-2022, https://doi.org/10.5194/amt-15-7235-2022, 2022
Short summary
Short summary
In this paper, we describe a new approach to test the consistency of the precipitating ice cloud optical and microphysical properties in Antarctica, Dome C, retrieved from hyperspectral measurements in the far-infrared, with the reflectivity detected by a co-located micro rain radar operating at 24 GHz. The retrieved ice crystal sizes were found in accordance with the direct measurements of an optical imager, also installed at Dome C, which can collect the falling ice particles.
Sergey Y. Matrosov, Alexei Korolev, Mengistu Wolde, and Cuong Nguyen
Atmos. Meas. Tech., 15, 6373–6386, https://doi.org/10.5194/amt-15-6373-2022, https://doi.org/10.5194/amt-15-6373-2022, 2022
Short summary
Short summary
A remote sensing method to retrieve sizes of particles in ice clouds and precipitation from radar measurements at two wavelengths is described. This method is based on relating the particle size information to the ratio of radar signals at these two wavelengths. It is demonstrated that this ratio is informative about different characteristic particle sizes. Knowing atmospheric ice particle sizes is important for many applications such as precipitation estimation and climate modeling.
Andrzej Z. Kotarba
Atmos. Meas. Tech., 15, 4307–4322, https://doi.org/10.5194/amt-15-4307-2022, https://doi.org/10.5194/amt-15-4307-2022, 2022
Short summary
Short summary
Space profiling lidars offer a unique insight into cloud properties in Earth’s atmosphere, and are considered the most reliable source of cloud information. However, lidar-based cloud climatologies are infrequently sampled: every 7 to 91 d, and only along the ground track. This study evaluated how accurate are the cloud data from existing (CALIPSO, ICESat-2, Aeolus) and planned (EarthCARE) space lidars, when compared to a cloud climatology obtained with observations taken every day.
Edward Gryspeerdt, Daniel T. McCoy, Ewan Crosbie, Richard H. Moore, Graeme J. Nott, David Painemal, Jennifer Small-Griswold, Armin Sorooshian, and Luke Ziemba
Atmos. Meas. Tech., 15, 3875–3892, https://doi.org/10.5194/amt-15-3875-2022, https://doi.org/10.5194/amt-15-3875-2022, 2022
Short summary
Short summary
Droplet number concentration is a key property of clouds, influencing a variety of cloud processes. It is also used for estimating the cloud response to aerosols. The satellite retrieval depends on a number of assumptions – different sampling strategies are used to select cases where these assumptions are most likely to hold. Here we investigate the impact of these strategies on the agreement with in situ data, the droplet number climatology and estimates of the indirect radiative forcing.
Henning Dorff, Heike Konow, and Felix Ament
Atmos. Meas. Tech., 15, 3641–3661, https://doi.org/10.5194/amt-15-3641-2022, https://doi.org/10.5194/amt-15-3641-2022, 2022
Short summary
Short summary
This study elaborates how aircraft-based horizontal geometries of trade wind cumuli differ whether a one-dimensional profiling radar or a two-dimensional imager is used. Cloud size distributions are examined in terms of sensitivity to sample size, resolution, and instrument field of view. While the radar cannot reproduce the double power law distribution due to coarse resolution and restriction to vertical transects, the imager also reveals the elliptic cloud structure enhancing with wind speed.
Qing Yue, Eric J. Fetzer, Likun Wang, Brian H. Kahn, Nadia Smith, John M. Blaisdell, Kerry G. Meyer, Mathias Schreier, Bjorn Lambrigtsen, and Irina Tkatcheva
Atmos. Meas. Tech., 15, 2099–2123, https://doi.org/10.5194/amt-15-2099-2022, https://doi.org/10.5194/amt-15-2099-2022, 2022
Short summary
Short summary
The self-consistency and continuity of cloud retrievals from infrared sounders and imagers aboard Aqua and SNPP (Suomi National Polar-orbiting Partnership) are examined at the pixel scale. Cloud products are found to be consistent with each other. Differences between sounder products are mainly due to cloud clearing and the treatment of clouds in scenes with unsuccessful atmospheric retrievals. The impact of algorithm and instrument differences is clearly seen in the imager cloud retrievals.
Pradeep Khatri, Tadahiro Hayasaka, Hitoshi Irie, Husi Letu, Takashi Y. Nakajima, Hiroshi Ishimoto, and Tamio Takamura
Atmos. Meas. Tech., 15, 1967–1982, https://doi.org/10.5194/amt-15-1967-2022, https://doi.org/10.5194/amt-15-1967-2022, 2022
Short summary
Short summary
Cloud properties observed by the Second-generation Global Imager (SGLI) onboard the Global Change Observation Mission – Climate (GCOM-C) satellite are evaluated using surface observation data. The study finds that SGLI-observed cloud properties are qualitative enough, although water cloud properties are suggested to be more qualitative, and both water and ice cloud properties can reproduce surface irradiance quite satisfactorily. Thus, SGLI cloud products are very useful for different studies.
Artem G. Feofilov, Hélène Chepfer, Vincent Noël, Rodrigo Guzman, Cyprien Gindre, Po-Lun Ma, and Marjolaine Chiriaco
Atmos. Meas. Tech., 15, 1055–1074, https://doi.org/10.5194/amt-15-1055-2022, https://doi.org/10.5194/amt-15-1055-2022, 2022
Short summary
Short summary
Space-borne lidars have been providing invaluable information of atmospheric optical properties since 2006, and new lidar missions are on the way to ensure continuous observations. In this work, we compare the clouds estimated from space-borne ALADIN and CALIOP lidar observations. The analysis of collocated data shows that the agreement between the retrieved clouds is good up to 3 km height. Above that, ALADIN detects 40 % less clouds than CALIOP, except for polar stratospheric clouds (PSCs).
Gregor Köcher, Tobias Zinner, Christoph Knote, Eleni Tetoni, Florian Ewald, and Martin Hagen
Atmos. Meas. Tech., 15, 1033–1054, https://doi.org/10.5194/amt-15-1033-2022, https://doi.org/10.5194/amt-15-1033-2022, 2022
Short summary
Short summary
We present a setup for systematic characterization of differences between numerical weather models and radar observations for convective weather situations. Radar observations providing dual-wavelength and polarimetric variables to infer information about hydrometeor shapes and sizes are compared against simulations using microphysics schemes of varying complexity. Differences are found in ice and liquid phase, pointing towards issues of some schemes in reproducing particle size distributions.
Simon Pfreundschuh, Stuart Fox, Patrick Eriksson, David Duncan, Stefan A. Buehler, Manfred Brath, Richard Cotton, and Florian Ewald
Atmos. Meas. Tech., 15, 677–699, https://doi.org/10.5194/amt-15-677-2022, https://doi.org/10.5194/amt-15-677-2022, 2022
Short summary
Short summary
We test a novel method to remotely measure ice particles in clouds. This is important because such measurements are required to improve climate and weather models. The method combines a radar with newly developed sensors measuring microwave radiation at very short wavelengths. We use observations made from aircraft flying above the cloud and compare them to real measurements from inside the cloud. This works well given that one can model the ice particles in the cloud sufficiently well.
David Painemal, Douglas Spangenberg, William L. Smith Jr., Patrick Minnis, Brian Cairns, Richard H. Moore, Ewan Crosbie, Claire Robinson, Kenneth L. Thornhill, Edward L. Winstead, and Luke Ziemba
Atmos. Meas. Tech., 14, 6633–6646, https://doi.org/10.5194/amt-14-6633-2021, https://doi.org/10.5194/amt-14-6633-2021, 2021
Short summary
Short summary
Cloud properties derived from satellite sensors are critical for the global monitoring of climate. This study evaluates satellite-based cloud properties over the North Atlantic using airborne data collected during NAAMES. Satellite observations of droplet size and cloud optical depth tend to compare well with NAAMES data. The analysis indicates that the satellite pixel resolution and the specific viewing geometry need to be taken into account in research applications.
Charles H. White, Andrew K. Heidinger, and Steven A. Ackerman
Atmos. Meas. Tech., 14, 3371–3394, https://doi.org/10.5194/amt-14-3371-2021, https://doi.org/10.5194/amt-14-3371-2021, 2021
Short summary
Short summary
Automated detection of clouds in satellite imagery is an important practice that is useful for predicting and understanding both weather and climate. Cloud detection is often difficult at night and over cold surfaces. In this paper, we discuss how a complex statistical model (a neural network) can more accurately detect clouds compared to currently used approaches. Overall, our results suggest that our approach could result in more reliable assessments of global cloud cover.
Hong Chen, Sebastian Schmidt, Michael D. King, Galina Wind, Anthony Bucholtz, Elizabeth A. Reid, Michal Segal-Rozenhaimer, William L. Smith, Patrick C. Taylor, Seiji Kato, and Peter Pilewskie
Atmos. Meas. Tech., 14, 2673–2697, https://doi.org/10.5194/amt-14-2673-2021, https://doi.org/10.5194/amt-14-2673-2021, 2021
Short summary
Short summary
In this paper, we accessed the shortwave irradiance derived from MODIS cloud optical properties by using aircraft measurements. We developed a data aggregation technique to parameterize spectral surface albedo by snow fraction in the Arctic. We found that undetected clouds have the most significant impact on the imagery-derived irradiance. This study suggests that passive imagery cloud detection could be improved through a multi-pixel approach that would make it more dependable in the Arctic.
Steven Compernolle, Athina Argyrouli, Ronny Lutz, Maarten Sneep, Jean-Christopher Lambert, Ann Mari Fjæraa, Daan Hubert, Arno Keppens, Diego Loyola, Ewan O'Connor, Fabian Romahn, Piet Stammes, Tijl Verhoelst, and Ping Wang
Atmos. Meas. Tech., 14, 2451–2476, https://doi.org/10.5194/amt-14-2451-2021, https://doi.org/10.5194/amt-14-2451-2021, 2021
Short summary
Short summary
The high-resolution satellite Sentinel-5p TROPOMI observes several atmospheric gases. To account for cloud interference with the observations, S5P cloud data products (CLOUD OCRA/ROCINN_CAL, OCRA/ROCINN_CRB, and FRESCO) provide vital input: cloud fraction, cloud height, and cloud optical thickness. Here, S5P cloud parameters are validated by comparing with other satellite sensors (VIIRS, MODIS, and OMI) and with ground-based CloudNet data. The agreement depends on product type and cloud height.
Jędrzej S. Bojanowski and Jan P. Musiał
Atmos. Meas. Tech., 13, 6771–6788, https://doi.org/10.5194/amt-13-6771-2020, https://doi.org/10.5194/amt-13-6771-2020, 2020
Short summary
Short summary
Satellites such as NOAA's Advanced Very High Resolution Radiometer can uniquely observe changes in cloud cover but are affected by orbital drift that results in shifted image acquisition times, which in turn lead to spurious trends in cloud cover detected during climatological analyses. Providing a detailed quantification of these trends, we show that climate data records must be analysed with caution, as for some periods and regions they do not comply with the requirements for climate data.
Andrzej Z. Kotarba
Atmos. Meas. Tech., 13, 4995–5012, https://doi.org/10.5194/amt-13-4995-2020, https://doi.org/10.5194/amt-13-4995-2020, 2020
Short summary
Short summary
This paper evaluates the operational approach for producing global (Level 3) cloud amount based on MODIS cloud masks (Level 2). Using CALIPSO we calculate the actual cloud fractions for each cloud mask category, which are 21.5 %, 27.7 %, 66.6 %, and 94.7 % instead of assumed 0 %, 0 %, 100 %, and 100 %. Consequently we find the operational procedure unreliable, especially on a regional/local scale. A method of how to correct and calibrate MODIS global data using CALIPSO detections is suggested.
Benjamin Marchant, Steven Platnick, Kerry Meyer, and Galina Wind
Atmos. Meas. Tech., 13, 3263–3275, https://doi.org/10.5194/amt-13-3263-2020, https://doi.org/10.5194/amt-13-3263-2020, 2020
Short summary
Short summary
Multilayer cloud scenes (such as an ice cloud overlapping a liquid cloud) are common in the Earth's atmosphere and are quite difficult to detect from space. The detection of multilayer clouds is important to better understand how they interact with the light and their impact on the climate. So, for the instrument MODIS an algorithm has been developed to detect those clouds, and this paper presents an evaluation of this algorithm by comparing it with
other instruments.
Alexis Hunzinger, Joseph C. Hardin, Nitin Bharadwaj, Adam Varble, and Alyssa Matthews
Atmos. Meas. Tech., 13, 3147–3166, https://doi.org/10.5194/amt-13-3147-2020, https://doi.org/10.5194/amt-13-3147-2020, 2020
Short summary
Short summary
The calibration of weather radars is one of the most dominant sources of errors hindering their use. This work takes a technique for tracking the changes in radar calibration using the radar clutter from the ground and extends it to higher-frequency research radars. It demonstrates that after modifications the technique is successful but that special care needs to be taken in its application at high frequencies. The technique is verified using data from multiple DOE ARM field campaigns.
Dieter R. Poelman and Wolfgang Schulz
Atmos. Meas. Tech., 13, 2965–2977, https://doi.org/10.5194/amt-13-2965-2020, https://doi.org/10.5194/amt-13-2965-2020, 2020
Short summary
Short summary
The objective of this work is to quantify the similarities and contrasts between the lightning observations from the Lightning Imaging Sensor (LIS) on the International Space Station (ISS) and the ground-based European Cooperation for Lightning Detection (EUCLID) network. This work is timely, given that the Meteosat Third Generation (MTG), which has a lightning imager (LI) on board, is going to be launched in 2 years.
Manfred Brath, Robin Ekelund, Patrick Eriksson, Oliver Lemke, and Stefan A. Buehler
Atmos. Meas. Tech., 13, 2309–2333, https://doi.org/10.5194/amt-13-2309-2020, https://doi.org/10.5194/amt-13-2309-2020, 2020
Short summary
Short summary
Microwave dual-polarization observations consistently show that larger atmospheric ice particles tend to have a preferred orientation. We provide a publicly available database of microwave and submillimeter wave scattering properties of oriented ice particles based on discrete dipole approximation scattering calculations. Detailed radiative transfer simulations, recreating observed polarization patterns, are additionally presented in this study.
Erin A. Riley, Jessica M. Kleiss, Laura D. Riihimaki, Charles N. Long, Larry K. Berg, and Evgueni Kassianov
Atmos. Meas. Tech., 13, 2099–2117, https://doi.org/10.5194/amt-13-2099-2020, https://doi.org/10.5194/amt-13-2099-2020, 2020
Short summary
Short summary
Discrepancies in hourly shallow cumuli cover estimates can be substantial. Instrument detection differences contribute to long-term bias in shallow cumuli cover estimates, whereas narrow field-of-view configurations impact measurement uncertainty as averaging time decreases. A new tool is introduced to visually assess both impacts on sub-hourly cloud cover estimates. Accurate shallow cumuli cover estimation is needed for model–observation comparisons and studying cloud-surface interactions.
Robin Ekelund, Patrick Eriksson, and Simon Pfreundschuh
Atmos. Meas. Tech., 13, 501–520, https://doi.org/10.5194/amt-13-501-2020, https://doi.org/10.5194/amt-13-501-2020, 2020
Short summary
Short summary
Atmospheric ice particles (e.g. snow and ice crystals) are an important part of weather, climate, and the hydrological cycle. This study investigates whether combined satellite measurements by radar and radiometers at microwave wavelengths can be used to find the most likely shape of such ice particles. The method was limited when using only currently operating sensors (CloudSat radar and the GPM Microwave Imager) but shows promise if the upcoming Ice Cloud Imager is also considered.
Juan Huo, Daren Lu, Shu Duan, Yongheng Bi, and Bo Liu
Atmos. Meas. Tech., 13, 1–11, https://doi.org/10.5194/amt-13-1-2020, https://doi.org/10.5194/amt-13-1-2020, 2020
Short summary
Short summary
Cloud top height (CTH) is one of the important cloud parameters providing information about the vertical structure of cloud water content. To better understand the accuracy of CTH derived from passive satellite data, 2 years of ground-based Ka-band radar measurements are compared with CTH inferred from Terra/Aqua MODIS and Himawari AHI. It is found that MODIS and AHI underestimate CTH relative to radar by −1.10 km. Both MODIS and AHI CTH retrieval accuracy depend strongly on cloud depth.
Vladimir S. Kostsov, Anke Kniffka, Martin Stengel, and Dmitry V. Ionov
Atmos. Meas. Tech., 12, 5927–5946, https://doi.org/10.5194/amt-12-5927-2019, https://doi.org/10.5194/amt-12-5927-2019, 2019
Short summary
Short summary
Cloud liquid water path (LWP) is one of the target atmospheric parameters retrieved remotely from ground-based and space-borne platforms. The LWP data delivered by the satellite instruments SEVIRI and AVHRR together with the data provided by the ground-based radiometer RPG-HATPRO near St. Petersburg, Russia, have been compared. Our study revealed considerable differences between LWP data from SEVIRI and AVHRR in winter over ice-covered relatively small water bodies in this region.
Jonathan K. P. Shonk, Jui-Yuan Christine Chiu, Alexander Marshak, David M. Giles, Chiung-Huei Huang, Gerald G. Mace, Sally Benson, Ilya Slutsker, and Brent N. Holben
Atmos. Meas. Tech., 12, 5087–5099, https://doi.org/10.5194/amt-12-5087-2019, https://doi.org/10.5194/amt-12-5087-2019, 2019
Short summary
Short summary
Retrievals of cloud optical depth made using AERONET radiometers in “cloud mode” rely on the assumption that all cloud is liquid. The presence of ice cloud therefore introduces errors in the retrieved optical depth, which can be over 25 in optically thick ice clouds. However, such clouds are not frequent and the long-term mean optical depth error is about 3 for a sample of real clouds. A correction equation could improve the retrieval further, although this would require extra instrumentation.
Chaojun Shi, Yatong Zhou, Bo Qiu, Jingfei He, Mu Ding, and Shiya Wei
Atmos. Meas. Tech., 12, 4713–4724, https://doi.org/10.5194/amt-12-4713-2019, https://doi.org/10.5194/amt-12-4713-2019, 2019
Short summary
Short summary
Cloud segmentation plays a very important role in astronomical observatory site selection. At present, few researchers segment cloud in nocturnal all-sky imager (ASI) images. We propose a new automatic cloud segmentation algorithm to segment cloud pixels from diurnal and nocturnal ASI images called an enhancement fully convolutional network (EFCN). Experiments showed that the proposed EFCN was much more accurate in cloud segmentation for diurnal and nocturnal ASI images.
Maximilian Maahn, Fabian Hoffmann, Matthew D. Shupe, Gijs de Boer, Sergey Y. Matrosov, and Edward P. Luke
Atmos. Meas. Tech., 12, 3151–3171, https://doi.org/10.5194/amt-12-3151-2019, https://doi.org/10.5194/amt-12-3151-2019, 2019
Short summary
Short summary
Cloud radars are unique instruments for observing cloud processes, but uncertainties in radar calibration have frequently limited data quality. Here, we present three novel methods for calibrating vertically pointing cloud radars. These calibration methods are based on microphysical processes of liquid clouds, such as the transition of cloud droplets to drizzle drops. We successfully apply the methods to cloud radar data from the North Slope of Alaska (NSA) and Oliktok Point (OLI) ARM sites.
Florian Ewald, Silke Groß, Martin Hagen, Lutz Hirsch, Julien Delanoë, and Matthias Bauer-Pfundstein
Atmos. Meas. Tech., 12, 1815–1839, https://doi.org/10.5194/amt-12-1815-2019, https://doi.org/10.5194/amt-12-1815-2019, 2019
Short summary
Short summary
This study gives a summary of lessons learned during the absolute calibration of the airborne, high-power Ka-band cloud radar HAMP MIRA on board the German research aircraft HALO. The first part covers the internal calibration of the instrument where individual instrument components are characterized in the laboratory. In the second part, the internal calibration is validated with external reference sources like the ocean surface backscatter and different air- and spaceborne cloud radars.
Stuart Fox, Jana Mendrok, Patrick Eriksson, Robin Ekelund, Sebastian J. O'Shea, Keith N. Bower, Anthony J. Baran, R. Chawn Harlow, and Juliet C. Pickering
Atmos. Meas. Tech., 12, 1599–1617, https://doi.org/10.5194/amt-12-1599-2019, https://doi.org/10.5194/amt-12-1599-2019, 2019
Short summary
Short summary
Airborne observations of ice clouds are used to validate radiative transfer simulations using a state-of-the-art database of cloud ice optical properties. Simulations at these wavelengths are required to make use of future satellite instruments such as the Ice Cloud Imager. We show that they can generally reproduce observed cloud signals, but for a given total ice mass there is considerable sensitivity to the cloud microphysics, including the particle shape and distribution of ice mass.
Katrin Lonitz and Alan J. Geer
Atmos. Meas. Tech., 12, 405–429, https://doi.org/10.5194/amt-12-405-2019, https://doi.org/10.5194/amt-12-405-2019, 2019
Short summary
Short summary
Permittivity models for microwave frequencies of liquid water below 0°C are poorly constrained due to limited laboratory experiments and observations, especially for high microwave frequencies. This uncertainty translates directly into errors in retrieved liquid water paths of up to 80 %. This study investigates the effect of different liquid water permittivity models including models based on the most recent observations.
Vladimir S. Kostsov, Anke Kniffka, and Dmitry V. Ionov
Atmos. Meas. Tech., 11, 5439–5460, https://doi.org/10.5194/amt-11-5439-2018, https://doi.org/10.5194/amt-11-5439-2018, 2018
Short summary
Short summary
Clouds are a very important component of the climate system and of the hydrological cycle in the Arctic and sub-Arctic. A joint analysis of the cloud parameters obtained remotely from satellite and ground-based observations near St Petersburg, Russia, has been made. Our study has revealed considerable differences between the cloud properties over land and over water areas in the region under investigation.
Fanny Jeanneret, Giovanni Martucci, Simon Pinnock, and Alexis Berne
Atmos. Meas. Tech., 11, 4153–4170, https://doi.org/10.5194/amt-11-4153-2018, https://doi.org/10.5194/amt-11-4153-2018, 2018
Short summary
Short summary
Above mountainous regions, satellites may have difficulty in discriminating snow from clouds: this study proposes a new method that combines different ground-based measurements to assess the sky cloudiness with high temporal resolution. The method's output is used as input to a model capable of identifying false satellite cloud detections. Results show that 62 ± 13 % of these false detections can be identified by the model when applied to the AVHRR-PM and MODIS Aqua data sets of the Cloud_cci.
Céline Cornet, Laurent C.-Labonnote, Fabien Waquet, Frédéric Szczap, Lucia Deaconu, Frédéric Parol, Claudine Vanbauce, François Thieuleux, and Jérôme Riédi
Atmos. Meas. Tech., 11, 3627–3643, https://doi.org/10.5194/amt-11-3627-2018, https://doi.org/10.5194/amt-11-3627-2018, 2018
Short summary
Short summary
Simulations of total and polarized cloud reflectance angular signatures such as the ones measured by the multi-angular and polarized radiometer POLDER3/PARASOL are used to evaluate cloud heterogeneity effects on cloud parameter retrievals. Effects on optical thickness, albedo of the cloudy scenes, effective radius and variance of the cloud droplet size distribution, cloud top pressure and aerosol above cloud are analyzed.
Rodrigo Hierro, Andrea K. Steiner, Alejandro de la Torre, Peter Alexander, Pablo Llamedo, and Pablo Cremades
Atmos. Meas. Tech., 11, 3523–3539, https://doi.org/10.5194/amt-11-3523-2018, https://doi.org/10.5194/amt-11-3523-2018, 2018
Short summary
Short summary
This paper analyzed the collocated GPS radio occultation profiles near the convective systems identified from ISCCP over two orographic regions of the Alps and Andes. Gravity wave (GW) analysis over both selected regions was also carried out. The gravity wave signature from the two case studies were investigated using mesoscale WRF simulations, ERA-Interim reanalysis data, and measured RO temperature profiles. The absence of fronts or jets during both case studies reveals similar relevant GWs.
Nina Håkansson, Claudia Adok, Anke Thoss, Ronald Scheirer, and Sara Hörnquist
Atmos. Meas. Tech., 11, 3177–3196, https://doi.org/10.5194/amt-11-3177-2018, https://doi.org/10.5194/amt-11-3177-2018, 2018
Short summary
Short summary
In this paper a new algorithm for cloud top height retrieval from imager instruments like MODIS is presented. It uses artificial neural networks and reduces the mean absolute error by 32 % compared to two other operational cloud height algorithms. This means that improved cloud height retrieval for nowcasting, as input to models and in cloud climatologies is possible.
Yu Oishi, Haruma Ishida, Takashi Y. Nakajima, Ryosuke Nakamura, and Tsuneo Matsunaga
Atmos. Meas. Tech., 11, 2863–2878, https://doi.org/10.5194/amt-11-2863-2018, https://doi.org/10.5194/amt-11-2863-2018, 2018
Short summary
Short summary
Preparations are continuing for the launch of the Greenhouse Gases Observing Satellite 2 (GOSAT-2) in the fiscal year 2018. To improve the accuracy of the estimates of greenhouse gases concentrations, we need to refine the existing cloud discrimination algorithm. In this paper we showed a new cloud discrimination algorithm of pre-launch version for GOSAT-2, and compared the existing algorithm with the new algorithm.
Alessandro Damiani, Hitoshi Irie, Takashi Horio, Tamio Takamura, Pradeep Khatri, Hideaki Takenaka, Takashi Nagao, Takashi Y. Nakajima, and Raul R. Cordero
Atmos. Meas. Tech., 11, 2501–2521, https://doi.org/10.5194/amt-11-2501-2018, https://doi.org/10.5194/amt-11-2501-2018, 2018
Short summary
Short summary
The Tohoku Earthquake of March 2011 stressed the need for energy source diversity, and the governmental policy in Japan has been stimulating a broader use of
renewable energy. Solar power is potentially able to mitigate climate change triggered by greenhouse gas emissions, but its instability caused by cloudiness
is a critical issue for suppliers. To develop an appropriate control system, surface solar radiation data must be made available as accurately as possible.
Karl-Göran Karlsson and Nina Håkansson
Atmos. Meas. Tech., 11, 633–649, https://doi.org/10.5194/amt-11-633-2018, https://doi.org/10.5194/amt-11-633-2018, 2018
Short summary
Short summary
Data from the high-sensitivity CALIOP cloud lidar onboard the CALIPSO satellite have been used to evaluate cloud amounts estimated from satellite imagery and, specifically, from the climate data record CLARA-A2. The main purpose has been to study the limit of how thin clouds that can be detected efficiently (i.e., detected at the 50 % level) in CLARA-A2 data and how this limit varies globally. The study revealed very large geographical differences in the cloud detection efficiency.
Dieter R. Poelman, Wolfgang Schulz, Rudolf Kaltenboeck, and Laurent Delobbe
Atmos. Meas. Tech., 10, 4561–4572, https://doi.org/10.5194/amt-10-4561-2017, https://doi.org/10.5194/amt-10-4561-2017, 2017
Short summary
Short summary
Lightning data as observed by the European Cooperation for Lightning Detection network EUCLID are used in combination with radar data to retrieve the temporal and spatial behavior of lightning outliers, i.e. discharges located in a wrong place, over a 5-year period from 2011 to 2016 in Belgium and Austria.
Johan Strandgren, Jennifer Fricker, and Luca Bugliaro
Atmos. Meas. Tech., 10, 4317–4339, https://doi.org/10.5194/amt-10-4317-2017, https://doi.org/10.5194/amt-10-4317-2017, 2017
Short summary
Short summary
We characterise the the performance of a set of artificial neural networks used for the remote sensing of cirrus clouds from the geostationary Meteosat Second Generation satellites. The retrievals show little interference with the underlying land surface type as well as with possible liquid water clouds or aerosol layers below the cirrus cloud. We also characterise the retrievals as a funtion of optical thickness and top height and gain better understanding of the retrival uncertainties of CiPS
Victoria Sol Galligani, Die Wang, Milagros Alvarez Imaz, Paola Salio, and Catherine Prigent
Atmos. Meas. Tech., 10, 3627–3649, https://doi.org/10.5194/amt-10-3627-2017, https://doi.org/10.5194/amt-10-3627-2017, 2017
Short summary
Short summary
Three meteorological events with deep convection and severe weather, characteristic of the SESA region, are considered. High-resolution models, a powerful tool to study convection, can be operated with different microphysics schemes (predict the development of hydrometeors, their interactions, growth, precipitation). We present a systematic evaluation of the microphysical schemes available in the WRF model by a direct comparison between satellite-based simulated and observed microwave radiances.
Cited articles
Alonso-Montesinos, J., Martinez-Durban, M., del Sagrado, J., del Aguila, I. M., and Batlles, F. J.: The application of Bayesian network classifiers to cloud classification in satellite images, Renew. Energ., 97, 155–161, https://doi.org/10.1016/j.renene.2016.05.066, 2016.
Calbó, J. and Sabburg, J.: Feature Extraction from Whole-Sky Ground-Based Images for Cloud-Type Recognition, J. Atmos. Ocean. Tech., 25, 3–14, https://doi.org/10.1175/2007JTECHA959.1, 2008.
Cazorla, A., Olmo, F. J., and 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.
Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., and Sun, J.: RepVGG: Making VGG-style ConvNets Great Again, in: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 20–25 June 2021, Nashville, TN, USA, IEEE, 13728–13737, https://doi.org/10.1109/CVPR46437.2021.01352, 2021.
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., and Houlsby, N.: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, International Conference on Learning Representations, 4 May 2021, Vienna, Austria, arXiv [preprint], https://doi.org/10.48550/arXiv.2010.11929, 22 October 2020.
Fabel, Y., Nouri, B., Wilbert, S., Blum, N., Triebel, R., Hasenbalg, M., Kuhn, P., Zarzalejo, L. F., and Pitz-Paal, R.: Applying self-supervised learning for semantic cloud segmentation of all-sky images, Atmos. Meas. Tech., 15, 797–809, https://doi.org/10.5194/amt-15-797-2022, 2022.
Goren, T., Rosenfeld, D., Sourdeval, O., and Quaas, J.: Satellite Observations of Precipitating Marine Stratocumulus Show Greater Cloud Fraction for Decoupled Clouds in Comparison to Coupled Clouds, Geophys. Res. Lett., 45, 5126–5134, https://doi.org/10.1029/2018GL078122, 2018.
Gorodetskaya, I. V., Kneifel, S., Maahn, M., Van Tricht, K., Thiery, W., Schween, J. H., Mangold, A., Crewell, S., and Van Lipzig, N. P. M.: Cloud and precipitation properties from ground-based remote-sensing instruments in East Antarctica, The Cryosphere, 9, 285–304, https://doi.org/10.5194/tc-9-285-2015, 2015.
Gyasi, E. K. and Swarnalatha, P.: Cloud-MobiNet: An Abridged Mobile-Net Convolutional Neural Network Model for Ground-Based Cloud Classification, Atmosphere, 14, 280, https://doi.org/10.3390/atmos14020280, 2023.
He, K., Zhang, X., Ren, S., and Sun, J.: Deep Residual Learning for Image Recognition, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 27–30 June 2016, Las Vegas, NV, USA, IEEE, 770–778, https://doi.org/10.1109/CVPR.2016.90, 2016.
He, T., Zhang, Z., Zhang, H., Zhang, Z., Xie, J., and Li, M.: Bag of Tricks for Image Classification with Convolutional Neural Networks, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 15–20 June 2019, Los Alamitos, USA, IEEE, 558–567, https://doi.org/10.1109/CVPR.2019.00065, 2019.
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.
Hu, J., Shen, L., and Sun, G.: Squeeze-and-Excitation Networks, in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 18–23 June 2018, Salt Lake City, UT, USA, IEEE, 7132–7141, https://doi.org/10.1109/CVPR.2018.00745, 2018.
Ioffe, S. and Szegedy, C.: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, in: International Conference on Machine Learning, 6 July 2015, Lille, France, arXiv [preprint], https://doi.org/10.48550/arXiv.1502.03167, 11 February 2015.
Kalisch, J. and Macke, A.: Estimation of the total cloud cover with high temporal resolution and parametrization of short-term fluctuations of sea surface insolation, Meteorol. Z., 17, 603–611, https://doi.org/10.1127/0941-2948/2008/0321, 2008.
Kingma, D. P. and Ba, J.: Adam: A Method for Stochastic Optimization, 3rd International Conference for Learning Representations, 7 May 2015, San Diego, USA, arXiv [preprint], https://doi.org/10.48550/arXiv.1412.6980, 23 July 2015.
Krizhevsky, A., Sutskever, I., and Hinton, G. E.: ImageNet classification with deep convolutional neural networks, Commun. ACM, 60, 84–90, https://doi.org/10.1145/3065386, 2017.
Li, X., Qiu, B., Cao, G., Wu, C., and Zhang, L.: A Novel Method for Ground-Based Cloud Image Classification Using Transformer, Remote Sens., 14, 3978, https://doi.org/10.3390/rs14163978, 2022.
Li, Z., Kong, H., and Wong, C.-S.: Neural Network-Based Identification of Cloud Types from Ground-Based Images of Cloud Layers, Appl. Sci., 13, 4470, https://doi.org/10.3390/app13074470, 2023.
Lin, F., Zhang, Y., and Wang, J.: Recent advances in intra-hour solar forecasting: A review of ground-based sky image methods, Int. J. Forecast., 39, 244–265, https://doi.org/10.1016/j.ijforecast.2021.11.002, 2023.
Liu, S.: TJNU Multimodal Ground-based cloud Database, GitHub [data set], https://github.com/shuangliutjnu/Multimodal-Ground-based-Cloud-Database (last access: 25 July 2023), 2020a.
Liu, S.: TJNU-Ground-based-Remote-Sensing-Cloud-Database, GitHub [data set], https://github.com/shuangliutjnu/TJNU-Ground-based-Remote-Sensing-Cloud-Database (last access: 17 September 2023), 2020b.
Liu, S., Li, M., Zhang, Z., Cao, X., and Durrani, T. S.: Ground-Based Cloud Classification Using Task-Based Graph Convolutional Network, Geophys. Res. Lett., 47, e2020GL087338, https://doi.org/10.1029/2020GL087338, 2020a.
Liu, S., Li, M., Zhang, Z., Xiao, B., and Durrani, T. S.: Multi-Evidence and Multi-Modal Fusion Network for Ground-Based Cloud Recognition, Remote Sens., 12, 464, https://doi.org/10.3390/rs12030464, 2020b.
Liu, S., Duan, L., Zhang, Z., Cao, X., and Durrani, T. S.: Multimodal Ground-Based Remote Sensing Cloud Classification via Learning Heterogeneous Deep Features, IEEE T. Geosci. Remote, 58, 7790–7800, https://doi.org/10.1109/TGRS.2020.2984265, 2020c.
Liu, S., Duan, L., Zhang, Z., Cao, X., and Durrani, T. S.: Ground-Based Remote Sensing Cloud Classification via Context Graph Attention Network, IEEE T. Geosci. Remote, 60, 1–11, https://doi.org/10.1109/TGRS.2021.3063255, 2022.
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B.: Swin Transformer: Hierarchical Vision Transformer using Shifted Windows, in: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 10–17 October 2021, Montreal, QC, Canada, IEEE, 9992–10002, https://doi.org/10.1109/ICCV48922.2021.00986, 2021.
Long, C., Li, X., Jing, Y., and Shen, H.: Bishift Networks for Thick Cloud Removal with Multitemporal Remote Sensing Images, Int. J. Intell. Syst., 2023, e9953198, https://doi.org/10.1155/2023/9953198, 2023.
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.
Meng, Q., Zhao, S., Huang, Z., and Zhou, F.: MagFace: A Universal Representation for Face Recognition and Quality Assessment, in: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 20—25 June 2021, Nashville, TN, USA, IEEE, 14220–14229, https://doi.org/10.1109/CVPR46437.2021.01400, 2021.
Norris, J. R., Allen, R. J., Evan, A. T., Zelinka, M. D., O'Dell, C. W., and Klein, S. A.: Evidence for climate change in the satellite cloud record, Nature, 536, 72–75, https://doi.org/10.1038/nature18273, 2016.
Nouri, B., Kuhn, P., Wilbert, S., Hanrieder, N., Prahl, C., Zarzalejo, L., Kazantzidis, A., Blanc, P., and Pitz-Paal, R.: Cloud height and tracking accuracy of three all sky imager systems for individual clouds, Sol. Energ., 177, 213–228, https://doi.org/10.1016/j.solener.2018.10.079, 2019.
Pfister, G., McKenzie, R. L., Liley, J. B., Thomas, A., Forgan, B. W., and Long, C. N.: Cloud Coverage Based on All-Sky Imaging and Its Impact on Surface Solar Irradiance, J. Appl. Meteorol. Clim., 42, 1421–1434, https://doi.org/10.1175/1520-0450(2003)042<1421:CCBOAI>2.0.CO;2, 2003.
Qu, Y., Xu, J., Sun, Y., and Liu, D.: A temporal distributed hybrid deep learning model for day-ahead distributed PV power forecasting, Appl. Energ., 304, 117704, https://doi.org/10.1016/j.apenergy.2021.117704, 2021.
Sarukkai, V., Jain, A., Uzkent, B., and Ermon, S.: Cloud Removal in Satellite Images Using Spatiotemporal Generative Networks, in: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), 1–5 March 2020, Snowmass, CO, USA, IEEE, 1785–1794, https://doi.org/10.1109/WACV45572.2020.9093564, 2020.
Shi, C., Wang, C., Wang, Y., and Xiao, B.: Deep Convolutional Activations-Based Features for Ground-Based Cloud Classification, IEEE Geosci. Remote Sens. Lett., 14, 816–820, https://doi.org/10.1109/LGRS.2017.2681658, 2017.
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.
Simonyan, K. and Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition, arXiv [preprint], https://doi.org/10.48550/arXiv.1409.1556, 10 April 2015.
Singh, M. and Glennen, M.: Automated ground-based cloud recognition, Pattern Anal. Appl., 8, 258–271, https://doi.org/10.1007/s10044-005-0007-5, 2005.
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A.: Going deeper with convolutions, in: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 7–12 June 2015 , Boston, MA, USA, IEEE, 1–9, https://doi.org/10.1109/CVPR.2015.7298594, 2015.
Tan, M. and Le, Q. V.: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks, in: International Conference on Machine Learning, 9 June 2019, Long Beach, California, USA, arXiv [preprint], https://doi.org/10.48550/arXiv.1905.11946, 28 May 2019.
Tang, Y., Yang, P., Zhou, Z., Pan, D., Chen, J., and Zhao, X.: Improving cloud type classification of ground-based images using region covariance descriptors, Atmos. Meas. Tech., 14, 737–747, https://doi.org/10.5194/amt-14-737-2021, 2021.
Taravat, A., Del Frate, F., Cornaro, C., and Vergari, S.: Neural Networks and Support Vector Machine Algorithms for Automatic Cloud Classification of Whole-Sky Ground-Based Images, IEEE Geosci. Remote Sens. Lett., 12, 666–670, https://doi.org/10.1109/LGRS.2014.2356616, 2015.
Wang, M., Zhou, S., Yang, Z., and Liu, Z.: CloudA: A Ground-Based Cloud Classification Method with a Convolutional Neural Network, J. Atmos. Ocean. Tech., 37, 1661–1668, https://doi.org/10.1175/JTECH-D-19-0189.1, 2020.
Wang, M., Zhuang, Z., Wang, K., Zhou, S., Zhou, S., and Liu, Z.: Intelligent classification of ground-based visible cloud images using a transfer convolutional neural network and fine-tuning, Opt. Express, 29, 41176–41190, https://doi.org/10.1364/OE.442455, 2021.
Wu, X., Zhan, C., Lai, Y.-K., Cheng, M.-M., and Yang, J.: A Large-Scale Benchmark Dataset for Insect Pest Recognition, in: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 15–20 June 2019, Long Beach, CA, USA, IEEE, 8779–8788, https://doi.org/10.1109/CVPR.2019.00899, 2019.
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.
Yu, A., Tang, M., Li, G., Hou, B., Xuan, Z., Zhu, B., and Chen, T.: A Novel Robust Classification Method for Ground-Based Clouds, Atmosphere, 12, 999, https://doi.org/10.3390/atmos12080999, 2021.
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, X., Zhou, X., Lin, M., and Sun, R.: ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices, in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 18–23 June 2018, New York, USA, IEEE, 6848–6856, https://doi.org/10.1109/CVPR.2018.00716, 2018.
Zhang, Y., Liu, H., and Hu, Q.: TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation, in: Medical Image Computing and Computer Assisted Intervention – MICCAI 2021, 27 September 2021, Strasbourg, France, Springer, Cham, Switzerland, 12901, 14–24, https://doi.org/10.1007/978-3-030-87193-2_2, 2021.
Zhao, Z., Xu, G., Qi, Y., Liu, N., and Zhang, T.: Multi-patch deep features for power line insulator status classification from aerial images, in: 2016 International Joint Conference on Neural Networks (IJCNN), 24–29 July 2016, Vancouver, BC, Canada, IEEE, 3187–3194, https://doi.org/10.1109/IJCNN.2016.7727606, 2016.
Zheng, Y., Rosenfeld, D., Zhu, Y., and Li, Z.: Satellite-Based Estimation of Cloud Top Radiative Cooling Rate for Marine Stratocumulus, Geophys. Res. Lett., 46, 4485–4494, https://doi.org/10.1029/2019GL082094, 2019.
Zhong, B., Chen, W., Wu, S., Hu, L., Luo, X., and Liu, Q.: A Cloud Detection Method Based on Relationship Between Objects of Cloud and Cloud-Shadow for Chinese Moderate to High Resolution Satellite Imagery, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 10, 4898–4908, https://doi.org/10.1109/JSTARS.2017.2734912, 2017.
Zhu, W., Chen, T., Hou, B., Bian, C., Yu, A., Chen, L., Tang, M., and Zhu, Y.: Classification of Ground-Based Cloud Images by Improved Combined Convolutional Network, Appl. Sci., 12, 1570, https://doi.org/10.3390/app12031570, 2022.
Zhuo, W., Cao, Z., and Xiao, Y.: Cloud Classification of Ground-Based Images Using Texture–Structure Features, J. Atmos. Ocean. Tech., 31, 79–92, https://doi.org/10.1175/JTECH-D-13-00048.1, 2014.
Short summary
This article mainly studies the problem of ground cloud classification and significantly improves the accuracy of ground cloud classification by applying an improved deep-learning method. The research results show that the method proposed in this article has a significant impact on the classification results of ground cloud images. These conclusions have important implications for providing new insights and future research directions in the field of ground cloud classification.
This article mainly studies the problem of ground cloud classification and significantly...
