Articles | Volume 15, issue 6
https://doi.org/10.5194/amt-15-1829-2022
© Author(s) 2022. 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-15-1829-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
25 Mar 2022
Research article |
| 25 Mar 2022
| 25 Mar 2022
Identification of tropical cyclones via deep convolutional neural network based on satellite cloud images
Biao Tong
Research Center for Wind Engineering and Engineering Vibration, Guangzhou University, Guangzhou, China
Xiangfei Sun
Guangdong Key Laboratory of Environmental Pollution and Health, School of Environment, Jinan University, Guangzhou, China
Jiyang Fu
CORRESPONDING AUTHOR
Research Center for Wind Engineering and Engineering Vibration, Guangzhou University, Guangzhou, China
Research Center for Wind Engineering and Engineering Vibration, Guangzhou University, Guangzhou, China
Pakwai Chan
Hong Kong Observatory, Hong Kong, China
Related authors
No articles found.
Yujie Liu, Yuncheng He, Pakwai Chan, Aiming Liu, and Qijun Gao
Nat. Hazards Earth Syst. Sci., 25, 2255–2269, https://doi.org/10.5194/nhess-25-2255-2025, https://doi.org/10.5194/nhess-25-2255-2025, 2025
Short summary
Short summary
Offshore wind turbines are sensitive to tropical cyclones (TCs). Wind data from super typhoons Mangkhut and Saola, impacting south China, are vital for design and operation. Despite Saola's higher intensity, it caused less damage. Both had concentric eyewall structures, but Saola completed an eyewall replacement before landfall, becoming more compact. Mangkhut decayed but affected a wider area. Their wind characteristics provide insights for turbine maintenance and operation.
Arianna Cauteruccio, Mattia Stagnaro, Luca G. Lanza, and Pak-Wai Chan
Atmos. Meas. Tech., 16, 4155–4163, https://doi.org/10.5194/amt-16-4155-2023, https://doi.org/10.5194/amt-16-4155-2023, 2023
Short summary
Short summary
Adjustments for the wind-induced bias of traditional rainfall gauges are applied to data from the Hong Kong Observatory using numerical simulation results. An optical disdrometer allows us to infer the collection efficiency of the rainfall gauge. Due to the local climatology, adjustments are limited but result in a significant amount of available freshwater resources that would be missing from the calculated hydrological budget of the region should the adjustments be neglected.
Wei Li, Shuo Leng, Sunwei Li, Zhenzhong Hu, and Pakwai Chan
EGUsphere, https://doi.org/10.5194/egusphere-2023-482, https://doi.org/10.5194/egusphere-2023-482, 2023
Preprint archived
Short summary
Short summary
A trans-scale simulation framework integrating the open-source WRF and OpenFOAM codes is proposed to numerically simulate the urban wind environment under specific weather conditions.
Lei Li, Chao Lu, Pak-Wai Chan, Zi-Juan Lan, Wen-Hai Zhang, Hong-Long Yang, and Hai-Chao Wang
Atmos. Chem. Phys. Discuss., https://doi.org/10.5194/acp-2021-579, https://doi.org/10.5194/acp-2021-579, 2021
Revised manuscript not accepted
Short summary
Short summary
The COVID-19 induced lockdown provided a time-window to study the impact of emission decrease on atmospheric environment. A 350 m meteorological tower in the Pearl River Delta recorded the vertical distribution of pollutants during the lockdown period. The observation confirmed that an extreme emission reduction, can reduce the concentrations of fine particles and the peak concentration of ozone at the same time, which had been taken as difficult to realize in the past in many regions.
Mattia Stagnaro, Matteo Colli, Luca Giovanni Lanza, and Pak Wai Chan
Atmos. Meas. Tech., 9, 5699–5706, https://doi.org/10.5194/amt-9-5699-2016, https://doi.org/10.5194/amt-9-5699-2016, 2016
Short summary
Short summary
The research presented in this work involves field data analysis, numerical modelling techniques and approaches to a long-standing problem of liquid precipitation measurements: the sampling and the interpretation of the tipping-bucket sensor signal. The present study shows relevant implications of the adopted data processing methods for the accuracy of the rainfall intensity measurements provided by traditional tipping-bucket gauges.
F. Peng, M. S. Wong, J. E. Nichol, and P. W. Chan
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B2, 55–62, https://doi.org/10.5194/isprs-archives-XLI-B2-55-2016, https://doi.org/10.5194/isprs-archives-XLI-B2-55-2016, 2016
G. Kuhlmann, Y. F. Lam, H. M. Cheung, A. Hartl, J. C. H. Fung, P. W. Chan, and M. O. Wenig
Atmos. Chem. Phys., 15, 5627–5644, https://doi.org/10.5194/acp-15-5627-2015, https://doi.org/10.5194/acp-15-5627-2015, 2015
Short summary
Short summary
Regional NO2 distributions can be simulated by models or retrieved from satellite observations. We developed a custom OMI NO2 data product for the Pearl River delta region which reduces biases compared to the standard product. The product is used for the evaluation of a regional air quality model for which it is a useful addition to ground measurements. The unbiased NO2 data product can be very helpful for air pollution studies in urban areas.
Related subject area
Subject: Others (Wind, Precipitation, Temperature, etc.) | Technique: Remote Sensing | Topic: Data Processing and Information Retrieval
Combining commercial microwave links and weather radar for classification of dry snow and rainfall
Improved consistency in solar-induced fluorescence retrievals from GOME-2A with the SIFTER v3 algorithm
An information content approach to diagnosing and improving CLIMCAPS retrieval consistency across instruments and satellites
Characterizing urban planetary boundary layer dynamics using 3-year Doppler wind lidar measurements in a western Yangtze River Delta city, China
Radar-based high-resolution ensemble precipitation analyses over the French Alps
Gravity waves above the northern Atlantic and Europe during streamer events using Aeolus
Observations of tall-building wakes using a scanning Doppler lidar
A new method to retrieve relative humidity profiles from a synergy of Raman lidar, microwave radiometer and satellite
Mid-Atlantic nocturnal low-level jet characteristics: a machine learning analysis of radar wind profiles
Mitigating radome-induced bias in X-band weather radar polarimetric moments using an adaptive discrete Fourier transform algorithm
GNSS-RO residual ionospheric error (RIE): a new method and assessment
Best Estimate of the Planetary Boundary Layer Height from Multiple Remote Sensing Measurements
Benchmarking KDP in rainfall: a quantitative assessment of estimation algorithms using C-band weather radar observations
Assimilation of GNSS Zenith Delays and Tropospheric Gradients: A Sensitivity Study utilizing sparse and dense station networks
Comparative experimental validation of microwave hyperspectral atmospheric soundings in clear-sky conditions
Propagating Information Content: An Example with Advection
Global Navigation Satellite System (GNSS) radio occultation climatologies mapped by machine learning and Bayesian interpolation
Use of commercial microwave links as scintillometers: potential and limitations towards evaporation estimation
Determination of low-level temperature profiles from microwave radiometer observations during rain
Aeolus lidar surface return (LSR) at 355 nm as a new Aeolus Level-2A product
Sampling the diurnal and annual cycles of the Earth's energy imbalance with constellations of satellite-borne radiometers
Retrieval of top-of-atmosphere fluxes from combined EarthCARE lidar, imager, and broadband radiometer observations: the BMA-FLX product
Analysis of the measurement uncertainty for a 3D wind lidar
Improving solution availability and temporal consistency of an optimal-estimation physical retrieval for ground-based thermodynamic boundary layer profiling
Reconstruction of 3D precipitation measurements from FY-3G MWRI-RM imaging and sounding channels
An improved geolocation methodology for spaceborne radar and lidar systems
Combining low- and high-frequency microwave radiometer measurements from the MOSAiC expedition for enhanced water vapour products
An LES Exploration of the Assumptions used in Retrieving Entrainment from a Mixing Diagram Approach with Ground-Based Remote Sensors
HAMSTER: Hyperspectral Albedo Maps dataset with high Spatial and TEmporal Resolution
Retrieving Tropospheric Refractivity Structure using Interferometry of Aircraft Radio Transmissions
TanSat-2: a new satellite for mapping solar-induced chlorophyll fluorescence at both red and far-red bands with high spatio-temporal resolution
Global-scale gravity wave analysis methodology for the ESA Earth Explorer 11 candidate CAIRT
Evolution of Wind Field in the Atmospheric Boundary Layer with using of Multiple Sources Observations during the Transit of Super Typhoon Doksuri (2305)
Retrieval of pseudo-BRDF-adjusted surface reflectance at 440 nm from the Geostationary Environmental Monitoring Spectrometer (GEMS)
Drop size distribution retrieval using dual-polarization radar at C-band and S-band
Thermal tides in the middle atmosphere at mid-latitudes measured with a ground-based microwave radiometer
Global sensitivity analysis of simulated remote sensing polarimetric observations over snow
Improving the Gaussianity of radar reflectivity departures between observations and simulations using symmetric rain rates
On the temperature stability requirements of free-running Nd:YAG lasers for atmospheric temperature profiling through the rotational Raman technique
Limitations in wavelet analysis of non-stationary atmospheric gravity wave signatures in temperature profiles
A new non-linearity correction method for the spectrum from the Geostationary Inferometric Infrared Sounder on board Fengyun-4 satellites and its preliminary assessments
Observing atmospheric rivers using multi-GNSS airborne radio occultation: system description and data evaluation
Determination of high-precision tropospheric delays using crowdsourced smartphone GNSS data
Unfiltering of the EarthCARE Broadband Radiometer (BBR) observations: the BM-RAD product
Variance estimations in the presence of intermittent interference and their applications to incoherent scatter radar signal processing
A clustering-based method for identifying and tracking squall lines
A multi-instrument fuzzy logic boundary-layer-top detection algorithm
Sensitivity of thermodynamic profiles retrieved from ground-based microwave and infrared observations to additional input data from active remote sensing instruments and numerical weather prediction models
Scale separation for gravity wave analysis from 3D temperature observations in the mesosphere and lower thermosphere (MLT) region
A Machine-learning Based Marine Planetary Boundary Layer (MPBL) Moisture Profile Retrieval Product from GNSS-RO Deep Refraction Signals
Erlend Øydvin, Renaud Gaban, Jafet Andersson, Remco (C. Z.) van de Beek, Mareile Astrid Wolff, Nils-Otto Kitterød, Christian Chwala, and Vegard Nilsen
Atmos. Meas. Tech., 18, 2279–2293, https://doi.org/10.5194/amt-18-2279-2025, https://doi.org/10.5194/amt-18-2279-2025, 2025
Short summary
Short summary
We present a novel method for classifying rain and snow by combining data from commercial microwave links (CMLs) with weather radar. We compare this to a reference method using dew point temperature for precipitation type classification. Evaluations with nearby disdrometers show that CMLs improve the classification of dry snow and rainfall, outperforming the reference method.
Juliëtte C. S. Anema, K. Folkert Boersma, Lieuwe G. Tilstra, Olaf N. E. Tuinder, and Willem W. Verstraeten
Atmos. Meas. Tech., 18, 1961–1979, https://doi.org/10.5194/amt-18-1961-2025, https://doi.org/10.5194/amt-18-1961-2025, 2025
Short summary
Short summary
Long-term records of plant fluorescence offer vital insights into changing vegetation activity. The GOME-2A sensor provides extensive global observations but suffers from calibration and instrument degradation, which affects data consistency. This study presents the SIFTER v3 algorithm, which effectively resolves these issues and includes other improvements, resulting in robust, accurate, and consistent GOME-2A fluorescence measurements from 2007 to 2017.
Nadia Smith and Christopher D. Barnet
Atmos. Meas. Tech., 18, 1823–1839, https://doi.org/10.5194/amt-18-1823-2025, https://doi.org/10.5194/amt-18-1823-2025, 2025
Short summary
Short summary
CLIMCAPS extends the Aqua AIRS+AMSU record with retrievals from CrIS+ATMS on Suomi National Polar-orbiting Partnership (SNPP) and Joint Polar Satellite System series (JPSS-1 to JPSS-4). With “continuous”, we mean a data record that is consistent in its characterization of natural variation despite changes in source instrumentation. Here we investigate how sounding continuity can improve across the full CLIMCAPS record (2002 to the present day), spanning multiple instruments and satellites.
Tianwen Wei, Mengya Wang, Kenan Wu, Jinlong Yuan, Haiyun Xia, and Simone Lolli
Atmos. Meas. Tech., 18, 1841–1857, https://doi.org/10.5194/amt-18-1841-2025, https://doi.org/10.5194/amt-18-1841-2025, 2025
Short summary
Short summary
This study analyzes three years of wind lidar measurements to explore the dynamics of the urban planetary boundary layer in Hefei, China. Results reveal that nocturnal low-level jets are most frequent in spring and intensify in summer, significantly enhancing turbulence and shear near the surface, particularly at night. Additionally, cloud cover raises the mixing layer height by approximately 100 m at night due to the greenhouse effect but reduces it by up to 200 m in the afternoon.
Matthieu Vernay, Matthieu Lafaysse, and Clotilde Augros
Atmos. Meas. Tech., 18, 1731–1755, https://doi.org/10.5194/amt-18-1731-2025, https://doi.org/10.5194/amt-18-1731-2025, 2025
Short summary
Short summary
This paper provides a comprehensive evaluation of the quality of radar-based precipitation estimation in mountainous areas and presents a method to mitigate the main shortcomings identified. It then compares three different ensemble analysis methods that combine radar-based precipitation estimates with forecasts from an ensemble numerical weather prediction model.
Sabine Wüst, Lisa Küchelbacher, Franziska Trinkl, and Michael Bittner
Atmos. Meas. Tech., 18, 1591–1607, https://doi.org/10.5194/amt-18-1591-2025, https://doi.org/10.5194/amt-18-1591-2025, 2025
Short summary
Short summary
Information on the energy transported by atmospheric gravity waves (GWs) is crucial for improving atmosphere models. Most space-based studies report the potential energy. We use Aeolus wind data to estimate the kinetic energy (density). However, the data quality is a challenge for such analyses, as the accuracy of the data is in the range of typical GW amplitudes. We find a temporal coincidence between enhanced or breaking planetary waves and enhanced gravity wave kinetic energy density.
Natalie E. Theeuwes, Janet F. Barlow, Antti Mannisenaho, Denise Hertwig, Ewan O'Connor, and Alan Robins
Atmos. Meas. Tech., 18, 1355–1371, https://doi.org/10.5194/amt-18-1355-2025, https://doi.org/10.5194/amt-18-1355-2025, 2025
Short summary
Short summary
A Doppler lidar was placed in a highly built-up area in London to measure wakes from tall buildings during a period of 1 year. We were able to detect wakes and assess their dependence on wind speed, wind direction, and atmospheric stability.
Chengli Ji, Qiankai Jin, Feilong Li, Yuyang Liu, Zhicheng Wang, Jiajia Mao, Xiaoyu Ren, Yan Xiang, Wanlin Jian, Peitao Zhao, and Zhenyi Chen
EGUsphere, https://doi.org/10.5194/egusphere-2025-1171, https://doi.org/10.5194/egusphere-2025-1171, 2025
Short summary
Short summary
This study presents the humidity measurements with a synergetic algorithm combining Raman lidar, MVR, and satellite. The results from 47 sites in China show the best correlation over 0.9 concerning the radiosonde measurements. It validates the RH accuracy with various data integrations. Three representative sites present the different seasonal characteristics indicating the geographic and height influences on the RH vertical distribution.
Maurice Roots, John T. Sullivan, and Belay Demoz
Atmos. Meas. Tech., 18, 1269–1282, https://doi.org/10.5194/amt-18-1269-2025, https://doi.org/10.5194/amt-18-1269-2025, 2025
Short summary
Short summary
This paper presents a supervised-machine-learning approach for the automatic isolation of nocturnal low-level jets (NLLJs) using observations from a radar wind profiler. This analysis isolated 90 southwesterly NLLJs observed from May to September 2017–2021, highlighting key features in the evolution and morphology of the mid-Atlantic NLLJ.
Padmanabhan Thiruvengadam, Guillaume Lesage, Ambinintsoa Volatiana Ramanamahefa, and Joël Van Baelen
Atmos. Meas. Tech., 18, 1185–1191, https://doi.org/10.5194/amt-18-1185-2025, https://doi.org/10.5194/amt-18-1185-2025, 2025
Short summary
Short summary
This study explores how the joints in a weather radar's protective cover affect its measurements. We developed a new method to correct these errors, improving the accuracy of the radar's data. Our method was tested during an intense cyclone on Réunion Island, demonstrating significant improvements in data accuracy. This research is crucial for enhancing weather predictions and understanding, particularly in challenging terrains.
Dong L. Wu, Valery A. Yudin, Kyu-Myong Kim, Mohar Chattopadhyay, Lawrence Coy, Ruth S. Lieberman, C. C. Jude H. Salinas, Jae N. Lee, Jie Gong, and Guiping Liu
Atmos. Meas. Tech., 18, 843–863, https://doi.org/10.5194/amt-18-843-2025, https://doi.org/10.5194/amt-18-843-2025, 2025
Short summary
Short summary
Global Navigation Satellite System radio occultation data help monitor climate and weather prediction but are affected by residual ionospheric errors (RIEs). A new excess-phase-gradient method detects and corrects RIEs, showing both positive and negative values, varying by latitude, time, and solar activity. Tests show that RIE impacts polar stratosphere temperatures in models, with differences up to 3–4 K. This highlights the need for RIE correction to improve the accuracy of data assimilation.
Damao Zhang, Jennifer Comstock, Chitra Sivaraman, Kefei Mo, Raghavendra Krishnamurthy, Jingjing Tian, Tianning Su, Zhanqing Li, and Natalia Roldán-Henao
EGUsphere, https://doi.org/10.5194/egusphere-2024-3959, https://doi.org/10.5194/egusphere-2024-3959, 2025
Short summary
Short summary
Planetary boundary layer height (PBLHT) is an important parameter in atmospheric process studies and numerical model simulations. We use machine learning methods to produce a best-estimate planetary boundary layer height (PBLHT-BE-ML) by integrating four PBLHT estimates derived from remote sensing measurements. We demonstrated that PBLHT-BE-ML greatly improved the comparisons against sounding-derived PBLHT.
Miguel Aldana, Seppo Pulkkinen, Annakaisa von Lerber, Matthew R. Kumjian, and Dmitri Moisseev
Atmos. Meas. Tech., 18, 793–816, https://doi.org/10.5194/amt-18-793-2025, https://doi.org/10.5194/amt-18-793-2025, 2025
Short summary
Short summary
Accurate KDP estimates are crucial in radar-based applications. We quantify the uncertainties of several publicly available KDP estimation methods for multiple rainfall intensities. We use C-band weather radar observations and employed a self-consistency KDP, estimated from reflectivity and differential reflectivity, as a framework for the examination. Our study provides guidance for the performance, uncertainties, and optimisation of the methods, focusing mainly on accuracy and robustness.
Rohith Thundathil, Florian Zus, Galina Dick, and Jens Wickert
EGUsphere, https://doi.org/10.5194/egusphere-2025-19, https://doi.org/10.5194/egusphere-2025-19, 2025
Short summary
Short summary
Tropospheric gradients provide information on the moisture distribution, whereas ZTDs provide the absolute amount of moisture through integrated water vapor. When TGs are assimilated with ZTDs, it helps the model actuate the moisture fields, correcting its dynamics. In our research, we show evidence that in particular regions with very few GNSS stations, the assimilation of gradients on top of ZTDs can provide the same impact as the assimilation of only ZTDs with dense coverage of GNSS stations.
Lei Liu, Natalia Bliankinshtein, Yi Huang, John R. Gyakum, Philip M. Gabriel, Shiqi Xu, and Mengistu Wolde
Atmos. Meas. Tech., 18, 471–485, https://doi.org/10.5194/amt-18-471-2025, https://doi.org/10.5194/amt-18-471-2025, 2025
Short summary
Short summary
This study evaluates and compares a new microwave hyperspectrometer with an infrared hyperspectrometer for clear-sky temperature and water vapor retrievals. The analysis reveals that the information content of the infrared hyperspectrometer exceeds that of the microwave hyperspectrometer and provides higher vertical resolution in ground-based zenith measurements. Leveraging the ground–airborne synergy between the two instruments yielded optimal sounding results.
David D. Turner, Maria P. Cadeddu, Julia Simonson, and Timothy J. Wagner
EGUsphere, https://doi.org/10.5194/egusphere-2024-4124, https://doi.org/10.5194/egusphere-2024-4124, 2025
Short summary
Short summary
When deriving a geophysical variable from remote sensors, the uncertainty and information content are critical. The latter quantify specifies what fraction of a real perturbation would be observed in the derived variable. This paper outlines, for the first time, a methodology for propagating the information content from multiple remote sensors into a derived product, using horizontal advection as an example.
Endrit Shehaj, Stephen Leroy, Kerri Cahoy, Alain Geiger, Laura Crocetti, Gregor Moeller, Benedikt Soja, and Markus Rothacher
Atmos. Meas. Tech., 18, 57–72, https://doi.org/10.5194/amt-18-57-2025, https://doi.org/10.5194/amt-18-57-2025, 2025
Short summary
Short summary
This work investigates whether machine learning (ML) can offer an alternative to existing methods to map radio occultation (RO) products, allowing the extraction of information not visible in direct observations. ML can further improve the results of Bayesian interpolation, a state-of-the-art method to map RO observations. The results display improvements in horizontal and temporal domains, at heights ranging from the planetary boundary layer up to the lower stratosphere, and for all seasons.
Luuk D. van der Valk, Oscar K. Hartogensis, Miriam Coenders-Gerrits, Rolf W. Hut, Bas Walraven, and Remko Uijlenhoet
EGUsphere, https://doi.org/10.5194/egusphere-2024-2974, https://doi.org/10.5194/egusphere-2024-2974, 2025
Short summary
Short summary
Commercial microwave links (CMLs), part of mobile phone networks, transmit comparable signals as instruments specially designed to estimate evaporation. Therefore, we investigate if CMLs could be used to estimate evaporation, even though they have not been designed for this purpose. Our results illustrate the potential of using CMLs to estimate evaporation, especially given their global coverage, but also outline some major drawbacks, often a consequence of unfavourable design choices for CMLs.
Andreas Foth, Moritz Lochmann, Pablo Saavedra Garfias, and Heike Kalesse-Los
Atmos. Meas. Tech., 17, 7169–7181, https://doi.org/10.5194/amt-17-7169-2024, https://doi.org/10.5194/amt-17-7169-2024, 2024
Short summary
Short summary
Microwave radiometers are usually not able to provide atmospheric quantities such as temperature profiles during rain. We present a method based on a selection of specific frequencies and elevation angles from microwave radiometer observations. A comparison with a numerical weather prediction model shows the presented method allows low-level temperature profiles during rain to be resolved, with rain rates of up to 2.5 mm h−1,, which was not possible before with state-of-the-art retrievals.
Lev D. Labzovskii, Gerd-Jan van Zadelhoff, David P. Donovan, Jos de Kloe, L. Gijsbert Tilstra, Ad Stoffelen, Damien Josset, and Piet Stammes
Atmos. Meas. Tech., 17, 7183–7208, https://doi.org/10.5194/amt-17-7183-2024, https://doi.org/10.5194/amt-17-7183-2024, 2024
Short summary
Short summary
The Atmospheric Laser Doppler Instrument (ALADIN) on the Aeolus satellite was the first of its kind to measure high-resolution vertical profiles of aerosols and cloud properties from space. We present an algorithm that produces Aeolus lidar surface returns (LSRs), containing useful information for measuring UV reflectivity. Aeolus LSRs matched well with existing UV reflectivity data from other satellites, like GOME-2 and TROPOMI, and demonstrated excellent sensitivity to modeled snow cover.
Thomas Hocking, Thorsten Mauritsen, and Linda Megner
Atmos. Meas. Tech., 17, 7077–7095, https://doi.org/10.5194/amt-17-7077-2024, https://doi.org/10.5194/amt-17-7077-2024, 2024
Short summary
Short summary
The imbalance between the energy the Earth absorbs from the Sun and the energy the Earth emits back into space gives rise to climate change, but measuring the small imbalance is challenging. We simulate satellites in various orbits to investigate how well they sample the imbalance and find that the best option is to combine at least two satellites that see complementary parts of the Earth and cover the daily and annual cycles. This information is useful when planning future satellite missions.
Almudena Velázquez Blázquez, Carlos Domenech, Edward Baudrez, Nicolas Clerbaux, Carla Salas Molar, and Nils Madenach
Atmos. Meas. Tech., 17, 7007–7026, https://doi.org/10.5194/amt-17-7007-2024, https://doi.org/10.5194/amt-17-7007-2024, 2024
Short summary
Short summary
This paper focuses on the BMA-FLX processor, in which thermal and solar top-of-atmosphere radiative fluxes are obtained from longwave and shortwave radiances measured along track by the EarthCARE Broadband Radiometer (BBR). The BBR measurements, at three fixed viewing angles (fore, nadir, aft), are co-registered either at the surface or at a reference level. A combined flux from the three BRR views is obtained. The algorithm has been successfully validated against test scenes.
Wolf Knöller, Gholamhossein Bagheri, Philipp von Olshausen, and Michael Wilczek
Atmos. Meas. Tech., 17, 6913–6931, https://doi.org/10.5194/amt-17-6913-2024, https://doi.org/10.5194/amt-17-6913-2024, 2024
Short summary
Short summary
Three-dimensional (3D) wind velocity measurements are of major importance for the characterization of atmospheric turbulence. This paper presents a detailed study of the measurement uncertainty of a three-beam wind lidar designed for mounting on airborne platforms. Considering the geometrical constraints, the analysis provides quantitative estimates for the measurement uncertainty of all components of the 3D wind vector. As a result, we propose optimized post-processing for error reduction.
Bianca Adler, David D. Turner, Laura Bianco, Irina V. Djalalova, Timothy Myers, and James M. Wilczak
Atmos. Meas. Tech., 17, 6603–6624, https://doi.org/10.5194/amt-17-6603-2024, https://doi.org/10.5194/amt-17-6603-2024, 2024
Short summary
Short summary
Continuous profile observations of temperature and humidity in the lowest part of the atmosphere are essential for the evaluation of numerical weather prediction models and data assimilation for better weather forecasts. Such profiles can be retrieved from passive ground-based remote sensing instruments like infrared spectrometers and microwave radiometers. In this study, we describe three recent modifications to the retrieval framework TROPoe for improved temperature and humidity profiles.
Yunfan Yang, Wei Han, Haofei Sun, Jun Li, Jiapeng Yan, and Zhiqiu Gao
Atmos. Meas. Tech. Discuss., https://doi.org/10.5194/amt-2024-175, https://doi.org/10.5194/amt-2024-175, 2024
Revised manuscript accepted for AMT
Short summary
Short summary
Our research improves satellite-based precipitation monitoring by using deep learning to reconstruct radar observations from passive microwave radiances. Active radar is costly, so we focus on a more accessible approach. Using data from the FengYun-3G satellite, we successfully tracked severe weather like Typhoon Khanun and heavy rainfall in Beijing in 2023. This method enhances global precipitation data and helps better understand extreme weather.
Bernat Puigdomènech Treserras and Pavlos Kollias
Atmos. Meas. Tech., 17, 6301–6314, https://doi.org/10.5194/amt-17-6301-2024, https://doi.org/10.5194/amt-17-6301-2024, 2024
Short summary
Short summary
The paper presents a comprehensive approach to improve the geolocation accuracy of spaceborne radar and lidar systems, crucial for the successful interpretation of data from the upcoming EarthCARE mission. The paper details the technical background of the presented methods and various examples of geolocation analyses, including a short period of CloudSat observations when the star tracker was not operating properly and lifetime statistics from the CloudSat and CALIPSO missions.
Andreas Walbröl, Hannes J. Griesche, Mario Mech, Susanne Crewell, and Kerstin Ebell
Atmos. Meas. Tech., 17, 6223–6245, https://doi.org/10.5194/amt-17-6223-2024, https://doi.org/10.5194/amt-17-6223-2024, 2024
Short summary
Short summary
We developed retrievals of integrated water vapour (IWV), temperature profiles, and humidity profiles from ground-based passive microwave remote sensing measurements gathered during the MOSAiC expedition. We demonstrate and quantify the benefit of combining low- and high-frequency microwave radiometers to improve humidity profiling and IWV estimates by comparing the retrieved quantities to single-instrument retrievals and reference datasets (radiosondes).
Tessa E. Rosenberger, Thijs Heus, Girish N. Raghunathan, David D. Turner, Timothy J. Wagner, and Julia M. Simonson
EGUsphere, https://doi.org/10.5194/egusphere-2024-2894, https://doi.org/10.5194/egusphere-2024-2894, 2024
Short summary
Short summary
Entrainment is key in understanding temperature and moisture changes within the boundary layer, but it is difficult to observe using ground-based observations. This work used simulations to verify an assumption that simplifies entrainment estimations from ground-based observational data, recognizing that entrainment is the combination of the transfer of heat and moisture from above the boundary layer into it and the change in concentration of heat and moisture as boundary layer depth changes.
Giulia Roccetti, Luca Bugliaro, Felix Gödde, Claudia Emde, Ulrich Hamann, Mihail Manev, Michael Fritz Sterzik, and Cedric Wehrum
Atmos. Meas. Tech., 17, 6025–6046, https://doi.org/10.5194/amt-17-6025-2024, https://doi.org/10.5194/amt-17-6025-2024, 2024
Short summary
Short summary
The amount of sunlight reflected by the Earth’s surface (albedo) is vital for the Earth's radiative system. While satellite instruments offer detailed spatial and temporal albedo maps, they only cover seven wavelength bands. We generate albedo maps that fully span the visible and near-infrared range using a machine learning algorithm. These maps reveal how the reflectivity of different land surfaces varies throughout the year. Our dataset enhances the understanding of the Earth's energy balance.
Ollie Lewis, Chris Brunt, Malcolm Kitchen, Neill E. Bowler, and Edmund K. Stone
EGUsphere, https://doi.org/10.5194/egusphere-2024-2273, https://doi.org/10.5194/egusphere-2024-2273, 2024
Short summary
Short summary
Humidity observations are crucial for an accurate weather forecast. We propose a new way to measure humidity by measuring how radio signals from commercial aircraft are refracted by the atmosphere. Humidity affects the refractive index of air, allowing its presence to be detected. With thousands of flights in the airspace over the United Kingdom every day, there is the potential for a large increase in the number of humidity measurements for use in weather forecasting models.
Dianrun Zhao, Shanshan Du, Chu Zou, Longfei Tian, Meng Fan, Yulu Du, and Liangyun Liu
EGUsphere, https://doi.org/10.5194/egusphere-2024-3118, https://doi.org/10.5194/egusphere-2024-3118, 2024
Short summary
Short summary
The TanSat-2 satellite is designed for global carbon monitoring. It provides high-resolution, dual-band observations of solar-induced chlorophyll fluorescence, a key indicator of plant photosynthesis. Through simulations, we optimized the satellite's data processing and found it can retrieve this fluorescence with great accuracy. These findings suggest that TanSat-2 will enhance global monitoring of carbon cycles and vegetation health, offering valuable insights for climate change research.
Sebastian Rhode, Peter Preusse, Jörn Ungermann, Inna Polichtchouk, Kaoru Sato, Shingo Watanabe, Manfred Ern, Karlheinz Nogai, Björn-Martin Sinnhuber, and Martin Riese
Atmos. Meas. Tech., 17, 5785–5819, https://doi.org/10.5194/amt-17-5785-2024, https://doi.org/10.5194/amt-17-5785-2024, 2024
Short summary
Short summary
We investigate the capabilities of a proposed satellite mission, CAIRT, for observing gravity waves throughout the middle atmosphere and present the necessary methodology for in-depth wave analysis. Our findings suggest that such a satellite mission is highly capable of resolving individual wave parameters and could give new insights into the role of gravity waves in general atmospheric circulation and atmospheric processes.
Xiaoye Wang, Jing Xu, Songhua Wu, Qichao Wang, Guangyao Dai, Peizhi Zhu, Zhizhong Su, Sai Chen, Xiaomeng Shi, and Mengqi Fan
Atmos. Meas. Tech. Discuss., https://doi.org/10.5194/amt-2024-156, https://doi.org/10.5194/amt-2024-156, 2024
Revised manuscript accepted for AMT
Short summary
Short summary
In this paper, we proposed a data fusion method to obtain the no-blind zone wind speed profiles covering the whole Atmospheric Boundary Layer based on the joint measurements of coherent Doppler lidar (CDL), radar wind profiler (RWP) and automatic weather station (AWS). Since above instruments are widely deployed in China, we believe this method has broad application prospects on the improvement of the boundary layer parameterization scheme in numerical forecast models.
Suyoung Sim, Sungwon Choi, Daeseong Jung, Jongho Woo, Nayeon Kim, Sungwoo Park, Honghee Kim, Ukkyo Jeong, Hyunkee Hong, and Kyung-Soo Han
Atmos. Meas. Tech., 17, 5601–5618, https://doi.org/10.5194/amt-17-5601-2024, https://doi.org/10.5194/amt-17-5601-2024, 2024
Short summary
Short summary
This study evaluates the use of background surface reflectance (BSR) derived from a semi-empirical bidirectional reflectance distribution function (BRDF) model based on GEMS satellite images. Analysis shows that BSR provides improved accuracy and stability compared to Lambertian-equivalent reflectivity (LER). These results indicate that BSR can significantly enhance climate analysis and air quality monitoring, making it a promising tool for accurate environmental satellite applications.
Daniel Durbin, Yadong Wang, and Pao-Liang Chang
Atmos. Meas. Tech., 17, 5397–5411, https://doi.org/10.5194/amt-17-5397-2024, https://doi.org/10.5194/amt-17-5397-2024, 2024
Short summary
Short summary
A method for determining drop size distributions (DSDs) for rain using radar measurements from two frequencies at two polarizations is presented. Following some preprocessing and quality control, radar measurements are incorporated into a model that uses swarm intelligence to seek the most suitable DSD to produce the input measurements.
Witali Krochin, Axel Murk, and Gunter Stober
Atmos. Meas. Tech., 17, 5015–5028, https://doi.org/10.5194/amt-17-5015-2024, https://doi.org/10.5194/amt-17-5015-2024, 2024
Short summary
Short summary
Atmospheric tides are global-scale oscillations with periods of a fraction of a day. Their observation in the middle atmosphere is challenging and rare, as it requires continuous measurements with a high temporal resolution. In this paper, temperature time series of a ground-based microwave radiometer were analyzed with a spectral filter to derive thermal tide amplitudes and phases in an altitude range of 25–50 km at the geographical locations of Payerne and Bern (Switzerland).
Matteo Ottaviani, Gabriel Harris Myers, and Nan Chen
Atmos. Meas. Tech., 17, 4737–4756, https://doi.org/10.5194/amt-17-4737-2024, https://doi.org/10.5194/amt-17-4737-2024, 2024
Short summary
Short summary
We analyze simulated polarization observations over snow to investigate the capabilities of remote sensing to determine surface and atmospheric properties in snow-covered regions. Polarization measurements are demonstrated to aid in the determination of snow grain shape, ice crystal roughness, and the vertical distribution of impurities in the snow–atmosphere system, data that are critical for estimating snow albedo for use in climate models.
Yudong Gao, Lidou Huyan, Zheng Wu, and Bojun Liu
Atmos. Meas. Tech., 17, 4675–4686, https://doi.org/10.5194/amt-17-4675-2024, https://doi.org/10.5194/amt-17-4675-2024, 2024
Short summary
Short summary
A symmetric error model built by symmetric rain rates handles the non-Gaussian error structure of the reflectivity error. The accuracy and linearization of rain rates can further improve the Gaussianity.
José Alex Zenteno-Hernández, Adolfo Comerón, Federico Dios, Alejandro Rodríguez-Gómez, Constantino Muñoz-Porcar, Michaël Sicard, Noemi Franco, Andreas Behrendt, and Paolo Di Girolamo
Atmos. Meas. Tech., 17, 4687–4694, https://doi.org/10.5194/amt-17-4687-2024, https://doi.org/10.5194/amt-17-4687-2024, 2024
Short summary
Short summary
We study how the spectral characteristics of a solid-state laser in an atmospheric temperature profiling lidar using the Raman technique impact the temperature retrieval accuracy. We find that the spectral widening, with respect to a seeded laser, has virtually no impact, while crystal-rod temperature variations in the laser must be kept within a range of 1 K for the uncertainty in the atmospheric temperature below 1 K. The study is carried out through spectroscopy simulations.
Robert Reichert, Natalie Kaifler, and Bernd Kaifler
Atmos. Meas. Tech., 17, 4659–4673, https://doi.org/10.5194/amt-17-4659-2024, https://doi.org/10.5194/amt-17-4659-2024, 2024
Short summary
Short summary
Imagine you want to determine how quickly the pitch of a passing ambulance’s siren changes. If the vehicle is traveling slowly, the pitch changes only slightly, but if it is traveling fast, the pitch also changes rapidly. In a similar way, the wind in the middle atmosphere modulates the wavelength of atmospheric gravity waves. We have investigated the question of how strong the maximum wind may be so that the change in wavelength can still be determined with the help of wavelet transformation.
Qiang Guo, Yuning Liu, Xin Wang, and Wen Hui
Atmos. Meas. Tech., 17, 4613–4627, https://doi.org/10.5194/amt-17-4613-2024, https://doi.org/10.5194/amt-17-4613-2024, 2024
Short summary
Short summary
Non-linearity (NL) correction is a critical procedure to guarantee that the calibration accuracy of a spaceborne sensor approaches a reasonable level. Different from the classical method, a new NL correction method for a spaceborne Fourier transform spectrometer is proposed. To overcome the inaccurate linear coefficient from two-point calibration influencing NL correction, an iteration algorithm is established that is suitable for NL correction of both infrared and microwave sensors.
Bing Cao, Jennifer S. Haase, Michael J. Murphy Jr., and Anna M. Wilson
Atmos. Meas. Tech. Discuss., https://doi.org/10.5194/amt-2024-119, https://doi.org/10.5194/amt-2024-119, 2024
Revised manuscript accepted for AMT
Short summary
Short summary
This paper describes an Airborne Radio Occultation (ARO) observation system installed on reconnaissance aircraft that uses GPS signal refraction in the atmosphere to retrieve information about the temperature and moisture in the storm environment as far away as 400 km surrounding the flight track. The characteristics and quality of 1700 ARO refractivity profiles were assessed. These observations are collected to help understand atmospheric rivers and improve their forecasting.
Yuanxin Pan, Grzegorz Kłopotek, Laura Crocetti, Rudi Weinacker, Tobias Sturn, Linda See, Galina Dick, Gregor Möller, Markus Rothacher, Ian McCallum, Vicente Navarro, and Benedikt Soja
Atmos. Meas. Tech., 17, 4303–4316, https://doi.org/10.5194/amt-17-4303-2024, https://doi.org/10.5194/amt-17-4303-2024, 2024
Short summary
Short summary
Crowdsourced smartphone GNSS data were processed with a dedicated data processing pipeline and could produce millimeter-level accurate estimates of zenith total delay (ZTD) – a critical atmospheric variable. This breakthrough not only demonstrates the feasibility of using ubiquitous devices for high-precision atmospheric monitoring but also underscores the potential for a global, cost-effective tropospheric monitoring network.
Almudena Velázquez Blázquez, Edward Baudrez, Nicolas Clerbaux, and Carlos Domenech
Atmos. Meas. Tech., 17, 4245–4256, https://doi.org/10.5194/amt-17-4245-2024, https://doi.org/10.5194/amt-17-4245-2024, 2024
Short summary
Short summary
The Broadband Radiometer measures shortwave and total-wave radiances filtered by the spectral response of the instrument. To obtain unfiltered solar and thermal radiances, the effect of the spectral response needs to be corrected for, done within the BM-RAD processor. Errors in the unfiltering are propagated into fluxes; thus, accurate unfiltering is required for their proper estimation (within BMA-FLX). Unfiltering errors are estimated to be <0.5 % for the shortwave and <0.1 % for the longwave.
Qihou Zhou, Yanlin Li, and Yun Gong
Atmos. Meas. Tech., 17, 4197–4209, https://doi.org/10.5194/amt-17-4197-2024, https://doi.org/10.5194/amt-17-4197-2024, 2024
Short summary
Short summary
We discuss several robust estimators to compute the variance of a normally distributed random variable to deal with interference. Compared to rank-based estimators, the methods based on the geometric mean are more accurate and are computationally more efficient. We apply three robust estimators to incoherent scatter power and velocity processing, along with the traditional sample mean estimator. The best estimator is a hybrid estimator that combines the sample mean and a robust estimator.
Zhao Shi, Yuxiang Wen, and Jianxin He
Atmos. Meas. Tech., 17, 4121–4135, https://doi.org/10.5194/amt-17-4121-2024, https://doi.org/10.5194/amt-17-4121-2024, 2024
Short summary
Short summary
The squall line is a type of convective system. Squall lines are often associated with damaging weather, so identifying and tracking squall lines plays an important role in early meteorological disaster warnings. A clustering-based method is proposed in this article. It can identify the squall lines within the radar scanning range with an accuracy rate of 95.93 %. It can also provide the three-dimensional structure and movement tracking results for each squall line.
Elizabeth N. Smith and Jacob T. Carlin
Atmos. Meas. Tech., 17, 4087–4107, https://doi.org/10.5194/amt-17-4087-2024, https://doi.org/10.5194/amt-17-4087-2024, 2024
Short summary
Short summary
Boundary-layer height observations remain sparse in time and space. In this study we create a new fuzzy logic method for synergistically combining boundary-layer height estimates from a suite of instruments. These estimates generally compare well to those from radiosondes; plus, the approach offers near-continuous estimates through the entire diurnal cycle. Suspected reasons for discrepancies are discussed. The code for the newly presented fuzzy logic method is provided for the community to use.
Laura Bianco, Bianca Adler, Ludovic Bariteau, Irina V. Djalalova, Timothy Myers, Sergio Pezoa, David D. Turner, and James M. Wilczak
Atmos. Meas. Tech., 17, 3933–3948, https://doi.org/10.5194/amt-17-3933-2024, https://doi.org/10.5194/amt-17-3933-2024, 2024
Short summary
Short summary
The Tropospheric Remotely Observed Profiling via Optimal Estimation physical retrieval is used to retrieve temperature and humidity profiles from various combinations of passive and active remote sensing instruments, surface platforms, and numerical weather prediction models. The retrieved profiles are assessed against collocated radiosonde in non-cloudy conditions to assess the sensitivity of the retrievals to different input combinations. Case studies with cloudy conditions are also inspected.
Björn Linder, Peter Preusse, Qiuyu Chen, Ole Martin Christensen, Lukas Krasauskas, Linda Megner, Manfred Ern, and Jörg Gumbel
Atmos. Meas. Tech., 17, 3829–3841, https://doi.org/10.5194/amt-17-3829-2024, https://doi.org/10.5194/amt-17-3829-2024, 2024
Short summary
Short summary
The Swedish research satellite MATS (Mesospheric Airglow/Aerosol Tomography and Spectroscopy) is designed to study atmospheric waves in the mesosphere and lower thermosphere. These waves perturb the temperature field, and thus, by observing three-dimensional temperature fluctuations, their properties can be quantified. This pre-study uses synthetic MATS data generated from a general circulation model to investigate how well wave properties can be retrieved.
Jie Gong, Dong Liang Wu, Michelle Badalov, Manisha Ganeshan, and Minghua Zheng
EGUsphere, https://doi.org/10.5194/egusphere-2024-973, https://doi.org/10.5194/egusphere-2024-973, 2024
Short summary
Short summary
Marine boundary layer water vapor is among the key factors to couple the ocean and atmosphere, but it is also among the hardest to retrieve from satellite remote sensing perspective. Here we propose a novel way to retrieve MPBL specific humidity profiles using the GNSS Level-1 signal-to-noise ratio. Using a machine learning approach, we successfully obtained a retrieval product that outperforms the ERA-5 reanalysis and operational Level-2 retrievals globally except in the deep tropics.
Cited articles
Chattopadhay, A., Sarkar, A., Howlader, P., and Balasubramanian, V. N.: Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks, in: 2018 IEEE Winter Conference on Applications of Computer Vision, Lake Tahoe, NV, USA, 12–15 March 2018, IEEE WACV, 839–847, https://doi.org/10.1109/WACV.2018.00097, 2018.
Chen, R., Zhang, W., and Wang, X.: Machine learning in tropical cyclone forecast modeling: A review, Atmosphere-Basel, 11, 676, https://doi.org/10.3390/atmos11070676, 2020.
Di Vittorio, A. V. and Emery, W. J.:
An automated, dynamic threshold cloud-masking algorithm for daytime AVHRR images over land, IEEE T. Geosci. Remote., 40, 1682–1694, https://doi.org/10.1109/TGRS.2002.802455, 2002.
Dvorak, V. F.:
Tropical cyclone intensity analysis using satellite data, in: NOAA Technical Report NESDIS, 11, US Department of Commerce, National Oceanic and Atmospheric Administration, National Environmental Satellite, Data, and Information Service, Washington, DC, USA, pp. 1–47, 1984.
Geng, X. Q., Li, Z. W., and Yang, X. F.:
Tropical cyclone auto-identification from stationary satellite imagery,
Journal of Image and Graphics,
19, 964–970, https://doi.org/10.11834/jig.20140618, 2014.
Goerss, J. S.: Tropical cyclone track forecasts using an ensemble of dynamical models, Mon. Weather Rev., 128, 1187–1193, https://doi.org/10.1175/1520-0493(2000)128<1187:TCTFUA>2.0.CO;2, 2000.
Han, L., Fu, S., Zhao, L., Zheng, Y., Wang, H., and Lin, Y.:
3D convective storm identification, tracking, and forecasting—An en-hanced TITAN algorithm, J. Atmos. Ocean. Tech., 26, 719–732, https://doi.org/10.1175/2008JTECHA1084.1, 2009.
Hanley, J. A. and McNeil, B. J.: The meaning and use of the area under a receiver operating characteristic (ROC) curve, Radiology,
143, 29–36, https://doi.org/10.1148/radiology.143.1.7063747, 2006.
Hayatbini, N., Hsu, K., Sorooshian, S., Zhang, Y., and Zhang, F.:
Effective cloud detection and segmentation using a gradient-based algorithm for satellite imagery: Application to improve PERSIANN-CCS, J. Hydrometeorol., 20, 901–913, https://doi.org/10.1175/JHM-D-18-0197.1, 2019.
Jégou, S., Drozdzal, M., Vazquez, D., Romero, A., and Bengio, Y.: The one hundred layers tiramisu: Fully convolutional densenets for semantic segmentation, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA, 21–26 July 2017, IEEE CVPRW, 1175–1183, https://doi.org/10.1109/CVPRW.2017.156, 2017.
Krizhevsky, A., Sutskever, I., and Hinton, G. E.: Imagenet classification with deep convolutional neural networks, Adv Neur. Inf., 60, 84–90, https://doi.org/10.1145/3065386, 2019.
LeCun, Y., Bengio, Y., and Hinton, G.: Deep learning, Nature, 521, 436–444, https://doi.org/10.1038/nature14539, 2015.
Lee, J., Im, J., Cha, D., Park, H., and Sim, S.:
Tropical cyclone intensity estimation using multi-dimensional convolutional neural networks from geostationary satellite data,
Remote Sens.-Basel,
12, 108, https://doi.org/10.3390/rs12010108, 2020.
Liao, X. L., Tian, Y. G., and Liu, J.: Research on the TC Segmentation Method with Priori Features, Remote Sensing for Land and Resources, 23, 37–42, http://en.cgsjournals.com/zgdzdcqkw-data/gtzyyg/2011/3/PDF/gtzyyg201103007.pdf (last access: 15 March 2022), 2011.
Lin, T., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S.: Feature pyramid networks for object detection, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017, IEEE CVPR, 936–944, https://doi.org/10.1109/CVPR.2017.106, 2017.
Liu, C., Zhang, Y., Chen, P., Lai, C., Chen, Y., Cheng, J., and Ko, M.:
Clouds classification from Sentinel-2 imagery with deep residual learning and semantic image segmentation, Remote Sens.-Basel, 11, 119, https://doi.org/10.3390/rs11020119, 2019.
Lopez-Ornelas, E., Laporterie-Dejean, F., and Flouzat, G.:
Satellite image segmentation using graph representation and morpho-logical processing,
Proc. SPIE,
5238, 104–113, https://doi.org/10.1117/12.511221, 2004.
Lu, J., Zhang, C. J., Zhang, X., Yang, B., and Duanmu, C.J.: Auto-recognition of typhoon cloud based on boundary features, J. Remote Sens., 14, 990–1003, http://www.gissky.net/paper/UploadFiles_4495/201208/2012080521453763.pdf (last access: 15 March 2022), 2010.
Lu, X., Yu, H., Ying, M., Zhao, B., Zhang, S., Lin, L., Bai, L., and Wan, R.:
Western north pacific tropical cyclone database created by the China meteorological administration, Adv. Atmos. Sci., 38, 690–699, https://doi.org/10.1007/s00376-020-0211-7, 2021 (data available at: http://tcdata.typhoon.org.cn/, last access: 29 November 2021).
Meteorological Satellite Research Cooperation Institute, University of Wisconsin-Madison (CIMSS): Tropical Cyclones ... A Satellite Perspective, CIMSS, http://tropic.ssec.wisc.edu/, last access: 29 November 2021.
Miller, R. J., Schrader, A. J., Sampson, C. R., and Tsui, T. L.: The Automated Tropical Cyclone Forecasting System (ATCF), Weather Forecast.,
5, 653–660, https://doi.org/10.1175/1520-0434(1990)005<0653:TATCFS>2.0.CO;2, 1990.
Molodianovitch, K., Faraggi, D., and Reiser, B.: Comparing the areas under two correlated ROC curves: parametric and nonparametric approaches, Biometrical J., 48, 745–757, https://doi.org/10.1002/bimj.200610223, 2006.
National Institute of Informatics (NII): Digital Typhoon: Typhoon Images and Information, NII, http://agora.ex.nii.ac.jp/digital-typhoon/, last access: 29 November 2021.
Olander, T. L. and Velden, C. S.: The Advanced Dvorak Technique (ADT) for estimating tropical cyclone intensity: Update and new capabilities,
Weather Forecast., 34, 905–922, https://doi.org/10.1175/WAF-D-19-0007.1, 2019.
Pang, S., Xie, P., Xu, D., Meng, F., Tao, X., Li, B., Li, Y., and Song, T.:
NDFTC: A New Detection Framework of Tropical Cyclones from Meteorological Satellite Images with Deep Transfer Learning,
Remote Sens.-Basel,
13, 1860, https://doi.org/10.3390/rs13091860, 2021.
Powers, D.: Evaluation: From Predcision, Recall and F-Factor to ROC, Informedness, Markedness & Correlation, J. Mach. Learn. Technol.,
2, 37–63, https://doi.org/10.9735/2229-3981, 2011.
Ron, K.: A study of cross-validation and bootstrap for accuracy estimation and model selection, in: Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, Montreal, Quebec, Canada, 20–25 August 1995, IJCAI, 1137–1143, 1995.
Saito, T. and Rehmsmeier, M.:
The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets,
PLoS One,
10, e118432, https://doi.org/10.1371/journal.pone.0118432, 2015.
Sampson, C. R. and Schrader, A. J.: The automated tropical cyclone forecasting system (version 3.2), B. Am. Meteorol. Soc., 81, 1231–1240, https://doi.org/10.1175/1520-0477(2000)081<1231:TATCFS>2.3.CO;2, 2000.
Schmidhuber, J.: Deep learning in neural networks: An overview, Neural Networks, 61, 85–117, https://doi.org/10.1016/j.neunet.2014.09.003, 2015.
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D.: Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization, Int. J. Comput. Vision, 128, 336–359, https://doi.org/10.1007/s11263-019-01228-7, 2020.
Simonyan, K. and Zisserman, A.: Very deep convolutional networks for large-scale image identification,
arXiv [preprint], arXiv:1409.1556, 10 April 2015.
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R.:
Dropout: A Simple Way to Prevent Neural Networks from Overfitting,
J. Mach. Learn. Res.,
15, 1929–1958, http://jmlr.org/papers/volume15/srivastava14a/srivastava14a.pdf (last access: 2 July 2020), 2014.
Sun, L., Wei, J., Wang, J., Mi, X., Guo, Y., Lv, Y., Yang, Y., Gan, P., Zhou, X., and Jia, C.: A universal dynamic threshold cloud de-tection algorithm (UDTCDA) supported by a prior surface reflectance database, J. Geophys. Res.-Atmos., 121, 7172–7196, https://doi.org/10.1002/2015JD024722, 2016.
Sun, X., Xie, L., Shah, S. U., and Shen, X.:
A Machine Learning Based Ensemble Forecasting Optimization Algorithm for Preseason Prediction of Atlantic Hurricane Activity,
Atmosphere-Basel,
12, 522, https://doi.org/10.3390/atmos12040522, 2021.
Velden, C., Harper, B., Wells, F., Beven, J. L., Zehr, R., Olander, T., Mayfield, M., Guard, C. C., Lander, M., and Edson, R.: The Dvorak tropical cyclone intensity estimation technique: A satellite-based method that has endured for over 30 years, B. Am. Meteorol. Soc., 87, 1195–1210, https://doi.org/10.1175/BAMS-87-9-1195, 2006.
Velden, C. S., Olander, T. L., and Zehr, R. M.: Development of an objective scheme to estimate tropical cyclone intensity from digital geostationary satellite infrared imagery, Weather Forecast., 13, 172–186, https://doi.org/10.1175/1520-0434(1998)013<0172:DOAOST>2.0.CO;2, 1998.
Wang, K., Li, X., and Trinder, J. C.: Mathematical morphological analysis of typical cyclone eyes on ocean SAR, in: 2014 IEEE Geoscience and Remote Sensing Symposium, Quebec City, QC, Canada, 13–18 July 2014, 4393–4396, https://doi.org/10.1109/IGARSS.2014.6947464, 2014.
Wang, Y.: Vortex Rossby waves in a numerically simulated tropical cyclone. Part II: The role in tropical cyclone structure and intensity changes,
J. Atmos. Sci., 59, 1239–1262, https://doi.org/10.1175/1520-0469(2002)059<1239:VRWIAN>2.0.CO;2, 2002.
Ying, M., Zhang, W., Yu, H., Lu, X., Feng, J., Fan, Y., Zhu, Y., and Chen, D.: An overview of the China Meteorological Administration tropical cyclone database, J. Atmos. Ocean. Tech., 31, 287–301, https://doi.org/10.1175/JTECH-D-12-00119.1, 2014 (data available at: http://tcdata.typhoon.org.cn/, last access: 29 November 2021).
Zeiler, M. D. and Fergus, R.: Visualizing and Understanding Convolutional Networks, in: Computer Vision – ECCV 2014, Lecture Notes in Computer Science, chapter 53, Springer, Cham, Switzerland, 818–833, https://doi.org/10.1007/978-3-319-10590-1_53, 2014.
Zhang, K., Zhang, Z., Li, Z., and Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks, IEEE Signal Proc. Let., 23, 1499–1503, https://doi.org/10.1109/LSP.2016.2603342 2016.
Zou, Z., Shi, Z., Guo, Y., and Ye, J.: Object detection in 20 years: A survey, arXiv [preprint], arXiv:1905.05055, 16 May 2019.
Short summary
In recent years, there has been numerous research on tropical cyclone (TC) observation based on satellite cloud images (SCIs), but most methods are limited by low efficiency and subjectivity. To overcome subjectivity and improve efficiency of traditional methods, this paper uses deep learning technology to do further research on fingerprint identification of TCs. Results provide an automatic and objective method to distinguish TCs from SCIs and are convenient for subsequent research.
In recent years, there has been numerous research on tropical cyclone (TC) observation based on...
