Pre-trained feature aggregated deep learning-based monitoring of overshooting tops using multi-spectral channels of GeoKompsat-2A advanced meteorological imagery

Lee, Juhyun; Kim, Miae; Im, Jungho; Han, Hyangsun; Han, Deahyeon

doi:10.1080/15481603.2021.1960075

Cited by 20 publications

(9 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, a temporal analysis was conducted using summer monsoon rainfall events across the Korean Peninsula in August 2020 to examine the model performance for heavy rainfall phenomena. The summer monsoon rainfall in Korea in 2020 lasted 54 days, from 24 June to 16 August (Lee et al, 2020;Mun et al, 2020). More than 66% of the annual average precipitation during this period fell, with significant regional variation.…”

Section: Discussionmentioning

confidence: 99%

“…More than 66% of the annual average precipitation during this period fell, with significant regional variation. In particular, 400-600 mm of rainfall fell over the southern part of the Korean Peninsula between 7 and 8 August (Lee et al, 2020;Kim et al, 2020a). Therefore, the specific evaluation period was set up from 02:30 KST on August 7 to 20:00 KST on August 9, including record-breaking rainfall in the southwestern region.…”

Section: Discussionmentioning

confidence: 99%

“…CNNs have been widely adopted in various DL-QPN studies because of their outstanding performance in spatial modeling in various remote sensing and environmental studies including atmosphere (Lee et al, 2021;Gardoll and Boucher, 2022;Geiss et al, 2022;Chattopadhyay et al, 2022), ocean (Chinita et al, 2022;Barth et al, 2022), urban and land (Wu et al, 2022 and Ise, 2022), and cryosphere (Lu et al, 2022;Kim et al, 2020b). The crucial part of CNNs is finding optimal convolutional filters to predict the target value with input data.…”

Section: Deep Learning Algorithms: U-net and Convlstmmentioning

confidence: 99%

See 2 more Smart Citations

Key factors for quantitative precipitation nowcasting using ground weather radar data based on deep learning

Han

Shin²,

Im³

et al. 2023

Preprint

View full text Add to dashboard Cite

Abstract. Quantitative precipitation nowcasting (QPN) may assist to mitigate the tremendous socioeconomic harm caused by severe weather. Because of the rapid atmospheric variability, the QPN has been a challenging problem to solve. Recent QPN research has presented data-driven models that make use of deep learning (DL) and ground weather radar. Previous research has mostly concentrated on constructing DL models, while other elements for DL-QPN have received less attention. This research looks at four crucial aspects in the DL-QPN and their impact on predicting performance. The prediction strategy (single, recursive, and multiple predictions), deep learning model (U-Net and convolutional long short term memory; ConvLSTM), input past sequence length (60 and 120 min), and output future sequence length were the four key factors (60 and 120 min). Using weather radar data from South Korea, twelve schemes have been developed to assess the influence of each factor. A long-term operational study for 2018–2020 was conducted, and a summer high rainfall event was examined to investigate the extreme case. In both situations, U-Net outperformed the critical score index (CSI) using a multiple prediction design. While ConvLSTM did not show a definite CSI difference across input sequence length, U-Net performed better with shorter input sequences (i.e., 60 min) than with longer input sequences (i.e., 120 min). The length of future sequences has little influence on model performance. As the lead time increased, all of the DL-QPN schemes showed underestimation and blurry outcomes. U-Net was shown to be significantly reliant on the most recent input time (i.e., 0 previous minutes) in sensitivity analysis, while ConvLSTM was more responsive to multiple time steps. This work may give a modeling technique and contingency plan for future DL-QPN employing weather radar data by explicitly comparing critical elements.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Deep Learning Algorithms: U-net and Convlstmmentioning

confidence: 99%

See 1 more Smart Citation

Key factors for quantitative precipitation nowcasting using ground weather radar data based on deep learning

Han

Shin²,

Im³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, machine learning has emerged as a cutting-edge technology for the reconstruction and estimation of ocean data, which can resolve the nonlinear relationship among high-dimensional and heterogeneous data [26][27][28][29][30][31][32][33]. A variety of machine learning techniques for reconstructing SST have been evaluated, including Artificial Neural Network (ANN), the patch-based NN with Kalman filter, and Random Forest (RF) [18,32,34].…”

Section: Introductionmentioning

confidence: 99%

High-Resolution Seamless Daily Sea Surface Temperature Based on Satellite Data Fusion and Machine Learning over Kuroshio Extension

Jung

Yoo

2022

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Sea SurfaceTemperature (SST) is a critical parameter for monitoring the marine environment and understanding various ocean phenomena. While SST can be regularly retrieved from satellite data, it often suffers from missing data due to various reasons including cloud contamination. In this study, we proposed a novel two-step data fusion framework for generating high-resolution seamless daily SST from multi-satellite data sources. The proposed approach consists of (1) SST reconstruction based on Data Interpolate Convolutional AutoEncoder (DINCAE) using the SSTs derived from two satellite sensors (i.e., Moderate Resolution Imaging Spectroradiometer (MODIS) and Advanced Microwave Scanning Radiometer 2(AMSR2)), and (2) SST improvement through data fusion using random forest for consistency with in situ measurements with two schemes (i.e., scheme 1 using the reconstructed MODIS SST variables and scheme 2 using both MODIS and AMSR2 SST variables). The proposed approach was evaluated over the Kuroshio Extension in the Northwest Pacific, where a highly dynamic SST pattern can be found, from 2015 to 2019. The results showed that the reconstructed MODIS and AMSR2 SSTs through DINCAE yielded very good performance with Root Mean Square Errors (RMSEs) of 0.85 and 0.60 °C and Mean Absolute Errors (MAEs) of 0.59 and 0.45 °C, respectively. The results from the second step showed that scheme 2 and scheme 1 produced RMSEs of 0.75 and 0.98 °C and MAEs of 0.53 and 0.68 °C, respectively, compared to the in situ measurements, which proved the superiority of scheme 2 using multi-satellite data sources. Scheme 2 also showed comparable or even better performance than two operational SST products with similar spatial resolution. In particular, scheme 2 was good at simulating features with fine resolution (~50 km). The proposed approach yielded promising results over the study area, producing seamless daily SST products with high quality and high feature resolution.

show abstract

“…Several ML and DL techniques combined with the Korean geostationary weather satellites have been studied for hourly surface solar irradiance using CNN [34]. These include monitoring the overshooting tops in convective clouds related to severe weather events, such as lightning, hail, and heavy rainfall using 2D-and 3D-CNN [35]; improving thunderstorm detection method using an ML-based logistic regression method with GK-2A/AMI, ground radars, lightning, and numerical model data [36]; virtual nighttime VIS image generation using cGAN with single [31] or multiple [16] bands observation data from the Meteorological Imager (MI) sensor of the COMS satellite; and simulating nighttime reflectance and daytime radiance of the COMS/MI 3.75 μm band using the CGAN method [32].…”

mentioning

confidence: 99%

Hypothetical Visible Bands of Advanced Meteorological Imager Onboard the Geostationary Korea Multi-Purpose Satellite -2A Using Data-To-Data Translation

Han

Jang

Ryu

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

True-color imagery of satellites provides various atmospheric and surface information for intuitive understanding and visualization. This study presents a conditional generative adversarial network method for generating daytime and nighttime hypothetical visible (VIS) bands of the Advanced Meteorological Imager (AMI) sensor onboard the Geostationary Korea Multi-Purpose Satellite. The AMI datasets in the form of albedo and brightness temperature (𝑻 𝑩 ) were normalized and denormalized between 0 and 1 data-to-data (D2D) translation. The D2D model was trained and tested using data pair of the albedos at AMI VIS bands and AMI infrared (IR) bands or 𝑻 𝑩 differences between two AMI IR bands. The constructed D2D model showed that the statistical results of bias, root-mean-square-error, and correlation coefficient between the observed and D2D-generated AMI VIS bands during daytime were -0.006 and 0.047 in albedo, and 0.941 for the blue band; -0.007 and 0.05 in albedo and 0.939 for the green band; -0.01 and 0.061 in albedo, and 0.917 for the red band, respectively. The proposed D2D method is being officially used by the Korea Meteorological Administration. Except for simulating desert areas as clouds at night, the D2D model demonstrated excellent performance, generating hypothetical AMI VIS bands at day and night. Consequently, this study could significantly contribute to the monitoring and understanding of meteorological phenomena over one-third of the Earth. Additionally, the method can be extended to other geostationary weather satellites, including Himawari-8, Fengyun-4A, Meteosat Third Generation, and Geostationary Operational Environmental Satellites.

show abstract

Pre-trained feature aggregated deep learning-based monitoring of overshooting tops using multi-spectral channels of GeoKompsat-2A advanced meteorological imagery

Cited by 20 publications

References 46 publications

Key factors for quantitative precipitation nowcasting using ground weather radar data based on deep learning

Key factors for quantitative precipitation nowcasting using ground weather radar data based on deep learning

High-Resolution Seamless Daily Sea Surface Temperature Based on Satellite Data Fusion and Machine Learning over Kuroshio Extension

Hypothetical Visible Bands of Advanced Meteorological Imager Onboard the Geostationary Korea Multi-Purpose Satellite -2A Using Data-To-Data Translation

Contact Info

Product

Resources

About