A Cloud Detection Neural Network Approach for the Next Generation Microwave Sounder Aboard EPS MetOp-SG A1

Larosa, Salvatore; Cimini, Domenico; Gallucci, Donatello; Paola, Francesco Di; Nilo, Saverio T.; Ricciardelli, Elisabetta; Ripepi, Ermann; Romano, Filomena

doi:10.3390/rs15071798

Cited by 5 publications

(2 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The comparison with the "Level 2" MLS cloud showed a huge improvement in classification performance. In this study [225] a cloud detection algorithm based on a neural network for Microwave Sounder (MWS) using a large synthetic dataset was developed. The model has been evaluated using AMSU-A and MHS measured data.…”

Section: Microwave Cloud Detectionmentioning

confidence: 99%

The Evolution of Meteorological Satellite Cloud Detection Methodologies

Romano,

Cimini,

Di Paola

et al. 2024

Preprint

View full text Add to dashboard Cite

The accurate detection of clouds is an important first-step in the processing of remotely sensed satellite data analyses and subsequent cloud model predictions. While initial cloud retrieval technology began with the exploitation of one or two bands of satellite imagery, it has accelerated rapidly in recent years as sensor and retrieval technology have exploded, creating a new era in space exploration. Additionally, initial emphasis in satellite retrieval technology focused on cloud detection for cloud forecast models, more recently cloud screening in satellite acquired data is playing an increasingly critical role in the investigation of cloud free data for the retrieval of soil moisture, vegetation cover, ocean colour concentration and sea surface temperatures, as well as environmental monitoring of a host of products, e.g. atmospheric aerosol data, to study the Earth’s atmospheric and climatic systems. With about 60% of the Earth covered by clouds, on average, it is necessary to both accurately detect clouds in remote sensing data to screen cloud contaminate data in remote sensing analyses. In this paper, the evolution of cloud detection technology is highlighted with advancement in sensor hardware technology and possible AI algorithmic advances. Additionally, a discussion is presented on methods to obtain the cloud truth data needed to determine the accuracy of these cloud detection approaches.

show abstract

Section: Microwave Cloud Detectionmentioning

confidence: 99%

The Evolution of Meteorological Satellite Cloud Detection Methodologies

Romano,

Cimini,

Di Paola

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Liu et al [19] proposed an inversion method for the remote sensing of ice clouds at terahertz wavelengths based on a genetic algorithm. Larosa et al [20] described a cloud detection algorithm based on a neural network for the microwave sounders aboard EPS and MetOp-SG. Dong et al [21] presented a retrieval methodology based on the Bayesian neural network (BNN) that inverts the IWP, mean mass-weighted diameter, and cloud height of ice clouds from submillimeter radiometer observations.…”

Section: Introductionmentioning

confidence: 99%

A New Deep-Learning-Based Framework for Ice Water Path Retrieval From Microwave Humidity Sounder-II Aboard FengYun-3D Satellite

Wang,

Xu,

Letu

et al. 2024

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

The derivation of ice water path (IWP) from microwave radiometer measurements is challenging. This study presents a deep learning framework for global retrieval of IWP using observations from the Microwave Humidity Sounder-II (MWHS-II) aboard the FengYun-3D (FY-3D) satellites. Two deep learning models, Deep Forest (DF21) and Quantile Regression Neural Network (QRNN) are constructed to detect ice cloud flags and retrieve IWP. By collocating MWHS-II observations with 2C-ICE, a joint product of CloudSat and CALIPSO, deep learning models learn the characteristics of IWP from MWHS-II brightness temperatures. The test results show that the MWHS-II channels provide more information on IWP than the MWHS channels, particularly the 89 GHz channel and the 118 GHz channels with an offset of ≥ 0.8 GHz. Combining the QRNN and DF21 models, the IWP retrieval results in an RMSE of 707.346 g/m 2 , MAPE of 65.122%, MBE of -104 g/m 2 , determination coefficient (R 2 ) of 0.683, and Pearson correlation coefficient (PCC) of 0.831. Application of the models to MWHS-II observations of Tropical Cyclone CILIDA shows better agreement with 2C-ICE. All datasets exhibit a similar feature on the monthly mean scale, but the magnitudes of IWP differ. Compared to GMI-GPROF, MODIS, and ERA5 IWP products, MWHS-II results are closest to 2C-ICE. Similar results are also shown for the zonal mean data. These results show that deep learning methods efficiently and probabilistically retrieve IWP from longterm observation data of MWHS/MWHS-II.

show abstract

A knowledge-based data-driven (KBDD) framework for all-day identification of cloud types using satellite remote sensing

Nie,

Chen,

et al. 2024

Remote Sensing of Environment

View full text Add to dashboard Cite

A Cloud Detection Neural Network Approach for the Next Generation Microwave Sounder Aboard EPS MetOp-SG A1

Cited by 5 publications

References 61 publications

The Evolution of Meteorological Satellite Cloud Detection Methodologies

The Evolution of Meteorological Satellite Cloud Detection Methodologies

A New Deep-Learning-Based Framework for Ice Water Path Retrieval From Microwave Humidity Sounder-II Aboard FengYun-3D Satellite

A knowledge-based data-driven (KBDD) framework for all-day identification of cloud types using satellite remote sensing

Contact Info

Product

Resources

About