Search Results
, avoiding describing complex physical processes. With traditional ML models (e.g., random forest), some studies have achieved satisfactory results on SM prediction (refer to a review study, Ali et al. 2015 ). Compared to traditional ML models, deep learning (DL) models significantly increase the ability to process big data, resulting in better performance ( LeCun et al. 2015 ). Recurrent neural network (RNN) is good at time series prediction among DL models. However, RNN could not learn long-term time
, avoiding describing complex physical processes. With traditional ML models (e.g., random forest), some studies have achieved satisfactory results on SM prediction (refer to a review study, Ali et al. 2015 ). Compared to traditional ML models, deep learning (DL) models significantly increase the ability to process big data, resulting in better performance ( LeCun et al. 2015 ). Recurrent neural network (RNN) is good at time series prediction among DL models. However, RNN could not learn long-term time
Deep Learning for Typhoon Intensity Classification Using Satellite Cloud Imagesabout satellite cloud images. A subfield of machine learning—deep learning (DL), as an extremely generalized approach—has been applied to various domains, such as pattern recognition, computer vision, artificial intelligence, and so on ( Xiao et al. 2010 ; Hinton et al. 2012 ; LeCun et al. 2015 ). As one of most popular deep learning models, convolutional neural networks (CNNs) have been demonstrated as a promising tool for image classification due to its locally connected layers and feasibility
about satellite cloud images. A subfield of machine learning—deep learning (DL), as an extremely generalized approach—has been applied to various domains, such as pattern recognition, computer vision, artificial intelligence, and so on ( Xiao et al. 2010 ; Hinton et al. 2012 ; LeCun et al. 2015 ). As one of most popular deep learning models, convolutional neural networks (CNNs) have been demonstrated as a promising tool for image classification due to its locally connected layers and feasibility
Use of Deep Learning for Weather Radar Nowcastinglearning models for weather nowcasting using radar echo data and compared them with existing models, particularly against two operational models. A common issue with deep learning approaches is that they tend to underestimate the intensity of reflectivity. To address this, we proposed the Composite model, which shows promising results on enhancing the predictions at higher reflectivity values. Although this ensemble can improve any base model, we believe that the primary focus should be put on
learning models for weather nowcasting using radar echo data and compared them with existing models, particularly against two operational models. A common issue with deep learning approaches is that they tend to underestimate the intensity of reflectivity. To address this, we proposed the Composite model, which shows promising results on enhancing the predictions at higher reflectivity values. Although this ensemble can improve any base model, we believe that the primary focus should be put on
A Deep Learning Network for Cloud-to-Ground Lightning Nowcasting with Multisource Dataa good ability to combine the multisource data, and over 99% of the 550 observed initiation of MCS events were detected within 50 km. Deep learning (DL) is a subset of machine learning algorithms that uses multilayer artificial neural networks to deliver state-of-the-art accuracy in many tasks ( Bengio 2009 ; Schmidhuber 2015 ). Similar to traditional machine learning algorithms like artificial neural networks and SVM, DL networks can model complex nonlinear systems. Moreover, these networks
a good ability to combine the multisource data, and over 99% of the 550 observed initiation of MCS events were detected within 50 km. Deep learning (DL) is a subset of machine learning algorithms that uses multilayer artificial neural networks to deliver state-of-the-art accuracy in many tasks ( Bengio 2009 ; Schmidhuber 2015 ). Similar to traditional machine learning algorithms like artificial neural networks and SVM, DL networks can model complex nonlinear systems. Moreover, these networks
( Hsieh and Tang 1998 ), which recently developed into various deep learning algorithms ( Reichstein et al. 2019 ). In this regard, deep learning has exhibited superior performance in detecting weather features such as hurricanes, clouds, and weather fronts ( Liu et al. 2016 ; Racah et al. 2016 ; Xie et al. 2016 ; Biard and Kunkel 2019 ; Prabhat et al. 2021 ). It has been also applied to weather forecasts and climate variability predictions ( Shi et al. 2015 ; Ham et al. 2019 ; Ise and Oba 2019
( Hsieh and Tang 1998 ), which recently developed into various deep learning algorithms ( Reichstein et al. 2019 ). In this regard, deep learning has exhibited superior performance in detecting weather features such as hurricanes, clouds, and weather fronts ( Liu et al. 2016 ; Racah et al. 2016 ; Xie et al. 2016 ; Biard and Kunkel 2019 ; Prabhat et al. 2021 ). It has been also applied to weather forecasts and climate variability predictions ( Shi et al. 2015 ; Ham et al. 2019 ; Ise and Oba 2019
A Dual-Attention Mechanism Deep Learning Network for Mesoscale Eddy Detection by Mining Spatiotemporal Characteristicsmesoscale eddies is reflected in the gridded ADT and UVG data, as shown in section 2 , these two kinds of data have different traits in different eddy regions. Finally, both the spatial and temporal characteristics of the data should be considered, so as to achieve optimal detection. To address these challenges, we propose a dual-attention mechanism deep-learning network. The network has a U-shaped encoding–decoding structure and a skip connection that connects the encoding and decoding parts with
mesoscale eddies is reflected in the gridded ADT and UVG data, as shown in section 2 , these two kinds of data have different traits in different eddy regions. Finally, both the spatial and temporal characteristics of the data should be considered, so as to achieve optimal detection. To address these challenges, we propose a dual-attention mechanism deep-learning network. The network has a U-shaped encoding–decoding structure and a skip connection that connects the encoding and decoding parts with
observatories, and ground stations, the amount of ocean and air data continues to accumulate. Combining deep learning models with big data environments provides us with a new opportunity to predict the track of tropical cyclones. In recent years, data-driven deep learning algorithms have been successfully applied in image processing, natural language processing, target detection, and other fields. Deep learning technology has strong nonlinear fitting capabilities, which have shown great advantages in
observatories, and ground stations, the amount of ocean and air data continues to accumulate. Combining deep learning models with big data environments provides us with a new opportunity to predict the track of tropical cyclones. In recent years, data-driven deep learning algorithms have been successfully applied in image processing, natural language processing, target detection, and other fields. Deep learning technology has strong nonlinear fitting capabilities, which have shown great advantages in
( Cintineo et al. 2018 ). Convolutional neural networks (CNN) are specially designed to learn from spatial grids and often contain many layers, which qualifies them as a deep-learning method (section 1.1.4 of Chollet 2018 ). In traditional ML, spatial grids must be transformed into scalar features, which become the direct inputs to the model. Examples are principal components, spatial statistics (such as means and standard deviations), and raw gridpoint values (where each value in the grid is treated as
( Cintineo et al. 2018 ). Convolutional neural networks (CNN) are specially designed to learn from spatial grids and often contain many layers, which qualifies them as a deep-learning method (section 1.1.4 of Chollet 2018 ). In traditional ML, spatial grids must be transformed into scalar features, which become the direct inputs to the model. Examples are principal components, spatial statistics (such as means and standard deviations), and raw gridpoint values (where each value in the grid is treated as
–Atmosphere Mesoscale Prediction System for Tropical Cyclones (COAMPS-TC) ( Doyle et al. 2014 )]. Simple statistical models based on climatology and persistence (CLP5; NOAA 2017 ) form the baseline for annual skill. However, locating and predicting TCs is still a difficult and time-consuming task. Recently, with the successful application of deep learning, many experts and scholars are exploring the application of deep-learning-based methods in TC track prediction. These methods based on the statistical model hold
–Atmosphere Mesoscale Prediction System for Tropical Cyclones (COAMPS-TC) ( Doyle et al. 2014 )]. Simple statistical models based on climatology and persistence (CLP5; NOAA 2017 ) form the baseline for annual skill. However, locating and predicting TCs is still a difficult and time-consuming task. Recently, with the successful application of deep learning, many experts and scholars are exploring the application of deep-learning-based methods in TC track prediction. These methods based on the statistical model hold
Using Deep Learning to Emulate and Accelerate a Radiative Transfer Modelour work unique. First, we use U-net++ models ( Zhou et al. 2020 ), as opposed to the fully connected networks [sometimes called “dense” or “feed-forward”; see chapter 6 of Goodfellow et al. (2016 )] used in previous work. U-net++ models are a type of deep learning, which can exploit spatial patterns in gridded data to make better predictions. Second, we have built physical constraints and vertical nonlocality into the U-net++ models, allowing them to handle nonadjacent cloud layers and better
our work unique. First, we use U-net++ models ( Zhou et al. 2020 ), as opposed to the fully connected networks [sometimes called “dense” or “feed-forward”; see chapter 6 of Goodfellow et al. (2016 )] used in previous work. U-net++ models are a type of deep learning, which can exploit spatial patterns in gridded data to make better predictions. Second, we have built physical constraints and vertical nonlocality into the U-net++ models, allowing them to handle nonadjacent cloud layers and better
