Broad-UNet: Multi-scale feature learning for nowcasting tasks

Fernández, Jesús García; Mehrkanoon, Siamak

doi:10.1016/j.neunet.2021.08.036

Cited by 49 publications

(37 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can capture rough-and fine-grained features of moving objects by using physical and residual branches, respectively. A series of work [38][39][40][41] further improved the structure of the classical encoder-decoder model, U-Net for specific spatiotemporal sequence prediction tasks.…”

Section: Related Work 21 Models For Spatiotemporal Sequences Predictionmentioning

confidence: 99%

CEMA-LSTM: Enhancing Contextual Feature Correlation for Radar Extrapolation Using Fine-Grained Echo Datasets

Yang¹,

Liu²,

Wu³

et al. 2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

Accurate precipitation nowcasting can provide great convenience to the public so they can conduct corresponding arrangements in advance to deal with the possible impact of upcoming heavy rain. Recent relevant research activities have shown their concerns on various deep learning models for radar echo extrapolation, where radar echo maps were used to predict their consequent moment, so as to recognize potential severe convective weather events. However, these approaches suffer from an inaccurate prediction of echo dynamics and unreliable depiction of echo aggregation or dissipation, due to the size limitation of convolution filter, lack of global feature, and less attention to features from previous states. To address the problems, this paper proposes a CEMA-LSTM recurrent unit, which is embedded with a Contextual Feature Correlation Enhancement Block (CEB) and a Multi-Attention Mechanism Block (MAB). The CEB enhances contextual feature correlation and supports its model to memorize significant features for near-future prediction; the MAB uses a position and channel attention mechanism to capture global features of radar echoes. Two practical radar echo datasets were used involving the FREM and CIKM 2017 datasets. Both quantification and visualization of comparative experimental results have demonstrated outperformance of the proposed CEMA-LSTM over recent models, e.g., PhyDNet, MIM and PredRNN++, etc. In particular, compared with the second-ranked model, its average POD, FAR and CSI have been improved by 3.87%, 1.65% and 1.79%, respectively on the FREM, and by 1.42%, 5.60% and 3.16%, respectively on the CIKM 2017.

show abstract

Section: Related Work 21 Models For Spatiotemporal Sequences Predictionmentioning

confidence: 99%

CEMA-LSTM: Enhancing Contextual Feature Correlation for Radar Extrapolation Using Fine-Grained Echo Datasets

Yang¹,

Liu²,

Wu³

et al. 2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

show abstract

“…Different from CNNs, the decoder path (Figure 8b) of UNet++ used the feature map to perform the corresponding four layers of upsampling, recovering the compressed image up to restoration and outputting the segmented image [45]. To fuse more of the shallow feature information, the symmetric encoder was also channel-merged with the feature maps on the decoder path via skip paths (the black dashed lines in Figure 8), and the features extracted during downsampling were passed directly into the upsampling, thereby adding more details [46].…”

Section: Semantic Segmentation Network Model-unet++mentioning

confidence: 99%

Toward Field Soil Surveys: Identifying and Delineating Soil Diagnostic Horizons Based on Deep Learning and RGB Image

2022

View full text Add to dashboard Cite

The diagnostic horizon in a soil is reflective of the environment in which it developed and the inherent characteristics of the material, therefore quantitative approaches to horizon delineation should focus on the diagnostic horizon. Moreover, it can enable the exchange and transfer of soil information between different taxonomic systems. This study aims to explore the use of deep learning and RGB images to train a soil diagnostic horizon identification model that can help field workers determine soil horizon information quickly, efficiently, easily, and cost-effectively. A total of 331 soil profile images of the main soil categories (five soil orders, including Primosols, Ferrosols, Argosols, Anthrosols, and Cambosols) from Hubei and Jiangxi Provinces were used. Each soil profile image was preprocessed and augmented to 10 images and then inputted into the UNet++ architecture. The mean intersection over union and pixel accuracy of the model were 71.24% and 82.66%, respectively. Results show that the model could accurately identify and delineate the soil diagnostic horizons. Moreover, the model performance varied considerably due to the definition of the horizon and whether the diagnostic conditions applied to a wide range of visual features on RGB images, the number of samples, and the soil characteristics of the study area.

show abstract

“…NWP models may take hours to run and are also less accurate than persistence-based forecasts on less than 4 hour predictions [13,14]. In recent years, the enormous amount of ever-increasing weather data has stimulated research interest in data-driven machine learning techniques for nowcasting tasks [15][16][17][18][19][20]. Unlike the model-driven methods, data-driven models do not base their prediction on the calculations of the underlying physics of the atmosphere.…”

Section: Introductionmentioning

confidence: 99%

WF-UNet: Weather Fusion UNet for Precipitation Nowcasting

Kaparakis¹,

Mehrkanoon²

2023

Preprint

View full text Add to dashboard Cite

Designing early warning systems for harsh weather and its effects, such as urban flooding or landslides, requires accurate short-term forecasts (nowcasts) of precipitation. Nowcasting is a significant task with several environmental applications, such as agricultural management or increasing flight safety. In this study, we investigate the use of a UNet core-model and its extension for precipitation nowcasting in western Europe for up to 3 hours ahead. In particular, we propose the Weather Fusion UNet (WF-UNet) model, which utilizes the Core 3D-UNet model and integrates precipitation and wind speed variables as input in the learning process and analyze its influences on the precipitation target task. We have collected six years of precipitation and wind radar images from Jan 2016 to Dec 2021 of 14 European countries, with 1-hour temporal resolution and 31 square km spatial resolution based on the ERA5 dataset, provided by Copernicus, the European Union's Earth observation programme. We compare the proposed WF-UNet model to persistence model as well as other UNet based architectures that are trained only using precipitation radar input data. The obtained results show that WF-UNet outperforms the other examined best-performing architectures by 22%, 8% and 6% lower MSE at a horizon of 1, 2 and 3 hours respectively.

show abstract

Broad-UNet: Multi-scale feature learning for nowcasting tasks

Cited by 49 publications

References 41 publications

CEMA-LSTM: Enhancing Contextual Feature Correlation for Radar Extrapolation Using Fine-Grained Echo Datasets

CEMA-LSTM: Enhancing Contextual Feature Correlation for Radar Extrapolation Using Fine-Grained Echo Datasets

Toward Field Soil Surveys: Identifying and Delineating Soil Diagnostic Horizons Based on Deep Learning and RGB Image

WF-UNet: Weather Fusion UNet for Precipitation Nowcasting

Contact Info

Product

Resources

About