A deep learning based approach with adversarial regularization for Doppler weather radar ECHO prediction

Singh, Sonam; Sarkar, Sudeshna; Mitra, Pabitra

doi:10.1109/igarss.2017.8128174

Cited by 16 publications

(11 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using this design, Shi et al [6] was able to use five input steps and predict fifteen consecutive steps ahead. These ConvRNN-based models have been applied successfully in other precipitation nowcasting tasks [1,2,16,23] and other weather forecasts, such as storm tracking [24]. For an REE task, Sato et al [16] modified ConvGRU network to overcome TrajGRU in [6], but that structure is significantly more complex, and we would leave it for future applications.…”

Section: Convolutional Rnn-based Modelsmentioning

confidence: 99%

“…However, we argued that such combination is tricky and still not enough to overcome the issue because it still bases on L1 and L2 only. Singh et al [23] proposed to use Generative Adversarial Networks and showed promising results. However, this technique is not easy to train and require significant more computing resources.…”

Section: Loss Functions For Training Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Computer Vision in Precipitation Nowcasting: Applying Image Quality Assessment Metrics for Training Deep Neural Networks

Tran

Song

2019

Atmosphere

View full text Add to dashboard Cite

This paper presents a viewpoint from computer vision to the radar echo extrapolation task in the precipitation nowcasting domain. Inspired by the success of some convolutional recurrent neural network models in this domain, including convolutional LSTM, convolutional GRU and trajectory GRU, we designed a new sequence-to-sequence neural network structure to leverage these models in a realistic data context. In this design, we decreased the numbers of channels in high abstract recurrent layers rather than increasing them. We formulated the task as a problem of encoding five radar images and predicting 10 steps ahead at the pixel level, and found that using only the common mean squared error can misguide the training and mislead the testing. Especially, the image quality of last predictions usually degraded rapidly. As a solution, we employed some visual image quality assessment techniques including Structural Similarity (SSIM) and multi-scale SSIM to train our models. Experimental results show that our structure was more tolerant to increasing uncertainty in the data, and the use of image quality metrics can significantly reduce the blurry image issue. Moreover, we found that using SSIM was very effective and a combination of SSIM with mean squared error and mean absolute error yielded the best prediction quality.

show abstract

Section: Convolutional Rnn-based Modelsmentioning

confidence: 99%

Section: Loss Functions For Training Neural Networkmentioning

confidence: 99%

Computer Vision in Precipitation Nowcasting: Applying Image Quality Assessment Metrics for Training Deep Neural Networks

Tran

Song

2019

Atmosphere

View full text Add to dashboard Cite

show abstract

“…However these models require very large datasets with tens of thousands of images, due the data-intensive training process. For this reason, CNNs and ConvLSTMs are mainly applied to data sets with short time intervals of no more than a few minutes between data points, which are typically much larger than data sets with longer time intervals [29][30][31][32][33][34][35][36][37][38][39][40]. For single-output prediction, a wider range of ML tools and time frames have been used, from linear methods in [17,21,41,42], to ensemble methods in [43][44][45], to hybrid methods in [28,[46][47][48], to deep models in [49][50][51][52][53][54][55][56] covering time scales from minutes to years.…”

Section: Literature Review and Scope Of The Researchmentioning

confidence: 99%

Basic Statistical Estimation Outperforms Machine Learning in Monthly Prediction of Seasonal Climatic Parameters

et al. 2021

View full text Add to dashboard Cite

Machine learning (ML) has been utilized to predict climatic parameters, and many successes have been reported in the literature. In this paper, we scrutinize the effectiveness of five widely used ML algorithms in the monthly prediction of seasonal climatic parameters using monthly image data. Specifically, we quantify the predictive performance of these algorithms applied to five climatic parameters using various combinations of features. We compare the predictive accuracy of the resulting trained ML models to that of basic statistical estimators that are computed directly from the training data. Our results show that ML never significantly outperforms the statistical baseline, and underperforms for most feature sets. Unlike previous similar studies, we provide error bars for the relative performance of different predictors based on jackknife estimates applied to differences in predictive error magnitudes. We also show that the practice of shuffling data sequences which was employed in some previous references leads to data leakage, resulting in over-estimated performance. Ultimately, the paper demonstrates the importance of using well-grounded statistical techniques when producing and analyzing the results of ML predictive models.

show abstract

“…In our point of view, ConvLSTM, ConvGRU and TrajGRU can be considered as the fundamental methods of this family. In radar-based precipitation nowcasting, they are applied successfully in many tasks [3][4][5]8,11,13,23,24]. Among them, TrajGRU is shown to be better than ConvLSTM, ConvGRU and other only Convolutional Neural Network (CNN)-based models including 2D-CNN and 3D-CNN [4,8].…”

Section: Convolutional Recurrent Neural Network For Radar Echo Extramentioning

confidence: 99%

“…Among them, TrajGRU is shown to be better than ConvLSTM, ConvGRU and other only Convolutional Neural Network (CNN)-based models including 2D-CNN and 3D-CNN [4,8]. In particular, the prediction quality of these Deep Learning models can be enhanced by using different types of loss functions rather than the common Mean Squared Error (MSE) and Mean Absolute Error (MAE) in the training process, such as balanced MSE and balanced MAE [4], discriminator's loss of the Generative Adversarial Network (GAN) method [23], or composite of IQA metrics [8]. In our previous work, a combination of MSE, MAE and Structural SIMilarity (SSIM) is shown to be a very efficient and effective solution to reduce the blurry image issue for these models [8].…”

Section: Convolutional Recurrent Neural Network For Radar Echo Extramentioning

confidence: 99%

Multi-ChannelWeather Radar Echo Extrapolation with Convolutional Recurrent Neural Networks

Tran

Song

2019

Remote Sensing

View full text Add to dashboard Cite

This article presents an investigation into the problem of 3D radar echo extrapolationin precipitation nowcasting, using recent AI advances, together with a viewpoint from ComputerVision. While Deep Learning methods, especially convolutional recurrent neural networks, havebeen developed to perform extrapolation, most works use 2D radar images rather than 3D images.In addition, the very few ones which try 3D data do not show a clear picture of results. Throughthis study, we found a potential problem in the convolution-based prediction of 3D data, which issimilar to the cross-talk effect in multi-channel radar processing but has not been documented well inthe literature, and discovered the root cause. The problem was that, when we generated differentchannels using one receptive field, some information in a channel, especially observation errors,might affect other channels unexpectedly. We found that, when using the early-stopping technique toavoid over-fitting, the receptive field did not learn enough to cancel unnecessary information. If weincreased the number of training iterations, this effect could be reduced but that might worsen theover-fitting situation. We therefore proposed a new output generation block which generates eachchannel separately and showed the improvement. Moreover, we also found that common imageaugmentation techniques in Computer Vision can be helpful for radar echo extrapolation, improvingtesting mean squared error of employed models at least 20% in our experiments.

show abstract

A deep learning based approach with adversarial regularization for Doppler weather radar ECHO prediction

Cited by 16 publications

References 3 publications

Computer Vision in Precipitation Nowcasting: Applying Image Quality Assessment Metrics for Training Deep Neural Networks

Computer Vision in Precipitation Nowcasting: Applying Image Quality Assessment Metrics for Training Deep Neural Networks

Basic Statistical Estimation Outperforms Machine Learning in Monthly Prediction of Seasonal Climatic Parameters

Multi-ChannelWeather Radar Echo Extrapolation with Convolutional Recurrent Neural Networks

Contact Info

Product

Resources

About