scholarly journals Rad-cGAN v1.0: Radar-based precipitation nowcasting model with conditional Generative Adversarial Networks for multiple domains

2021 ◽  
Author(s):  
Suyeon Choi ◽  
Yeonjoo Kim
Keyword(s):  
Machine Learning ◽  
South Korea ◽  
Transfer Learning ◽  
Weather Prediction ◽  
Generative Adversarial Networks ◽  
Lead Times ◽  
Successful Implementation ◽  
Short Term ◽  
Radar Images ◽  
Learning Technique

Abstract. Numerical weather prediction models and probabilistic extrapolation methods using radar images have been widely used for precipitation nowcasting. Recently, machine-learning-based precipitation nowcasting models have also been actively developed for relatively short-term precipitation predictions. This study aimed to develop a radar-based precipitation nowcasting model using an advanced machine learning technique, conditional generative adversarial network (cGAN), which shows high performance in image generation tasks. The cGAN-based precipitation nowcasting model, named Rad-cGAN, developed in this study was trained with a radar reflectivity map of the Soyang-gang Dam region in South Korea with a spatial domain of 128 × 128 km, spatial resolution of 1 km, and temporal resolution of 10 min. The model performance was evaluated using previously developed machine-learning-based precipitation nowcasting models, namely convolutional long short-term memory (ConvLSTM) and U-Net, as well as the baseline Eulerian persistence model. We demonstrated that Rad-cGAN outperformed other models not only for the chosen site but also for the entire domain across the Soyang-gang Dam region. Additionally, the proposed model maintained good performance even with lead times up to 80 min based on the critical success index at the intensity threshold of 0.1 mm h−1, while RainNet and ConvLSTM achieved lead times of 70 and 40 min, respectively. We also demonstrated the successful implementation of the transfer learning technique to efficiently train model with the data from other dam regions in South Korea, such as the Andong and Chungju Dam regions. We used pre-trained model, which was completely trained in the Soyang-gang Dam region. This study confirms that Rad-cGAN can be successfully applied to precipitation nowcasting with longer lead times, and using the transfer learning approach it shows good performance in regions other than the originally trained region.

Nowcasting heavy precipitation over the Netherlands using a 13-year radar archive: a machine learning approach

2021 ◽  
Author(s):  
Eva van der Kooij ◽  
Marc Schleiss ◽  
Riccardo Taormina ◽  
Francesco Fioranelli ◽  
Dorien Lugt ◽  
...  
Keyword(s):  
Machine Learning ◽  
The Netherlands ◽  
Heavy Rainfall ◽  
Predictive Performance ◽  
Heavy Precipitation ◽  
Early Warning Systems ◽  
Training Data ◽  
Short Term ◽  
Data Set ◽  
Radar Images

<p>Accurate short-term forecasts, also known as nowcasts, of heavy precipitation are desirable for creating early warning systems for extreme weather and its consequences, e.g. urban flooding. In this research, we explore the use of machine learning for short-term prediction of heavy rainfall showers in the Netherlands.</p><p>We assess the performance of a recurrent, convolutional neural network (TrajGRU) with lead times of 0 to 2 hours. The network is trained on a 13-year archive of radar images with 5-min temporal and 1-km spatial resolution from the precipitation radars of the Royal Netherlands Meteorological Institute (KNMI). We aim to train the model to predict the formation and dissipation of dynamic, heavy, localized rain events, a task for which traditional Lagrangian nowcasting methods still come up short.</p><p>We report on different ways to optimize predictive performance for heavy rainfall intensities through several experiments. The large dataset available provides many possible configurations for training. To focus on heavy rainfall intensities, we use different subsets of this dataset through using different conditions for event selection and varying the ratio of light and heavy precipitation events present in the training data set and change the loss function used to train the model.</p><p>To assess the performance of the model, we compare our method to current state-of-the-art Lagrangian nowcasting system from the pySTEPS library, like S-PROG, a deterministic approximation of an ensemble mean forecast. The results of the experiments are used to discuss the pros and cons of machine-learning based methods for precipitation nowcasting and possible ways to further increase performance.</p>

Improved Training for Machine Learning: The Additional Potential of Innovative Algorithmic Approaches.

2021 ◽  
Author(s):  
Octavian Dumitru ◽  
Gottfried Schwarz ◽  
Mihai Datcu ◽  
Dongyang Ao ◽  
Zhongling Huang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Test Data ◽  
Satellite Images ◽  
Training Data ◽  
Data Selection ◽  
Generative Adversarial Networks ◽  
Radar Images ◽  
Basic Work ◽  
Selection Of

<p>During the last years, much progress has been reached with machine learning algorithms. Among the typical application fields of machine learning are many technical and commercial applications as well as Earth science analyses, where most often indirect and distorted detector data have to be converted to well-calibrated scientific data that are a prerequisite for a correct understanding of the desired physical quantities and their relationships.</p><p>However, the provision of sufficient calibrated data is not enough for the testing, training, and routine processing of most machine learning applications. In principle, one also needs a clear strategy for the selection of necessary and useful training data and an easily understandable quality control of the finally desired parameters.</p><p>At a first glance, one could guess that this problem could be solved by a careful selection of representative test data covering many typical cases as well as some counterexamples. Then these test data can be used for the training of the internal parameters of a machine learning application. At a second glance, however, many researchers found out that a simple stacking up of plain examples is not the best choice for many scientific applications.</p><p>To get improved machine learning results, we concentrated on the analysis of satellite images depicting the Earth’s surface under various conditions such as the selected instrument type, spectral bands, and spatial resolution. In our case, such data are routinely provided by the freely accessible European Sentinel satellite products (e.g., Sentinel-1, and Sentinel-2). Our basic work then included investigations of how some additional processing steps – to be linked with the selected training data – can provide better machine learning results.</p><p>To this end, we analysed and compared three different approaches to find out machine learning strategies for the joint selection and processing of training data for our Earth observation images:</p><ul><li>One can optimize the training data selection by adapting the data selection to the specific instrument, target, and application characteristics [1].</li> <li>As an alternative, one can dynamically generate new training parameters by Generative Adversarial Networks. This is comparable to the role of a sparring partner in boxing [2].</li> <li>One can also use a hybrid semi-supervised approach for Synthetic Aperture Radar images with limited labelled data. The method is split in: polarimetric scattering classification, topic modelling for scattering labels, unsupervised constraint learning, and supervised label prediction with constraints [3].</li> </ul><p>We applied these strategies in the ExtremeEarth sea-ice monitoring project (http://earthanalytics.eu/). As a result, we can demonstrate for which application cases these three strategies will provide a promising alternative to a simple conventional selection of available training data.</p><p>[1] C.O. Dumitru et. al, “Understanding Satellite Images: A Data Mining Module for Sentinel Images”, Big Earth Data, 2020, 4(4), pp. 367-408.</p><p>[2] D. Ao et. al., “Dialectical GAN for SAR Image Translation: From Sentinel-1 to TerraSAR-X”, Remote Sensing, 2018, 10(10), pp. 1-23.</p><p>[3] Z. Huang, et. al., "HDEC-TFA: An Unsupervised Learning Approach for Discovering Physical Scattering Properties of Single-Polarized SAR Images", IEEE Transactions on Geoscience and Remote Sensing, 2020, pp.1-18.</p>

scholarly journals Applying a Deep Q Network for OpenAIs Car Racing Game

2020 ◽  
Author(s):  
Ali Fakhry
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Transfer Learning ◽  
State Of The Art ◽  
Learning Techniques ◽  
Car Racing ◽  
Custom Made ◽  
Learning Technique ◽  
Reward Threshold

The applications of Deep Q-Networks are seen throughout the field of reinforcement learning, a large subsect of machine learning. Using a classic environment from OpenAI, CarRacing-v0, a 2D car racing environment, alongside a custom based modification of the environment, a DQN, Deep Q-Network, was created to solve both the classic and custom environments. The environments are tested using custom made CNN architectures and applying transfer learning from Resnet18. While DQNs were state of the art years ago, using it for CarRacing-v0 appears somewhat unappealing and not as effective as other reinforcement learning techniques. Overall, while the model did train and the agent learned various parts of the environment, attempting to reach the reward threshold for the environment with this reinforcement learning technique seems problematic and difficult as other techniques would be more useful.

Introduction

2006 ◽  
Author(s):  
Huug van den Dool
Keyword(s):  
Physical System ◽  
Weather Prediction ◽  
Climate Prediction ◽  
Lead Times ◽  
Prediction Methods ◽  
Data Sets ◽  
Short Term ◽  
Global Data Sets ◽  
Geophysical System

This is first and foremost a book about short-term climate prediction. The predictions we have in mind are for weather/climate elements, mainly temperature (T) and precipitation (P), at lead times longer than two weeks, beyond the realm of detailed Numerical Weather Prediction (NWP), i.e. predictions for the next month and the next seasons out to at most a few years. call this short-term climate so as to distinguish it from long-term climate change which is not the main subject of this book. A few decades ago “short-term climate prediction” was known as “longrange weather prediction”. In order to understand short-term climate predictions, their skill and what they reveal about the atmosphere, ocean and land, several chapters are devoted to constructing prediction methods. The approach taken is mainly empirical, which means literally that it is based in experience. We will use global data sets to represent the climate and weather humanity experienced (and measured!) in the past several decades. The idea is to use these existing data sets in order to construct prediction methods. In doing so we want to acknowledge that every measurement (with error bars) is a monument about the workings of Nature. We thought about using the word “statistical” instead of “empirical” in the title of the book. These two notions overlap, obviously, but we prefer the word “empirical” because we are driven more by intuition than by a desire to apply existing or developing new statistical theory. While constructing prediction methods we want to discover to the greatest extent possible how the physical system works from observations. While not mentioned in the title, diagnostics of the physical system will thus be an important part of the book as well. We use a variety of classical tools to diagnose the geophysical system. Some of these tools have been developed further and/or old tools are applied in novel ways. We do not intend to cover all diagnostics methods, only those that relate closely to prediction. There will be an emphasis on methods used in operational prediction. It is quite difficult to gain a comprehensive idea from existing literature about methods used in operational short-term climate prediction.

scholarly journals Deep Convolutional Generative Modeling for Artificial Microstructure Development of Aluminum-Silicon Alloy

2021 ◽  
Vol 1 (1) ◽  
pp. 1-6
Author(s):  
Akshansh Mishra ◽  
Tarushi Pathak
Keyword(s):  
Machine Learning ◽  
Generative Adversarial Networks ◽  
Microstructure Development ◽  
Machine Learning Technique ◽  
Silicon Alloy ◽  
Aluminum Silicon Alloy ◽  
Adversarial Networks ◽  
Generative Modeling ◽  
Learning Technique ◽  
The Given

Machine learning which is a sub-domain of an Artificial Intelligence which is finding various applications in manufacturing and material science sectors. In the present study, Deep Generative Modeling which a type of unsupervised machine learning technique has been adapted for the constructing the artificial microstructure of Aluminium-Silicon alloy. Deep Generative Adversarial Networks has been used for developing the artificial microstructure of the given microstructure image dataset. The results obtained showed that the developed models had learnt to replicate the lining near the certain images of the microstructures.

Robust estimation of outage costs in South Korea using a machine learning technique: Bayesian Tobit quantile regression

2020 ◽  
Vol 278 ◽  
pp. 115702
Author(s):  
Mo Se Kim ◽  
Byung Sung Lee ◽  
Hye Seon Lee ◽  
Seung Ho Lee ◽  
Junseok Lee ◽  
...  
Keyword(s):  
Machine Learning ◽  
South Korea ◽  
Quantile Regression ◽  
Robust Estimation ◽  
Machine Learning Technique ◽  
Learning Technique

scholarly journals Post-processing rainfall forecasts from numerical weather prediction models for short-term streamflow forecasting

2013 ◽  
Vol 17 (9) ◽  
pp. 3587-3603 ◽  
Author(s):  
D. E. Robertson ◽  
D. L. Shrestha ◽  
Q. J. Wang
Keyword(s):  
Numerical Weather Prediction ◽  
Prediction Models ◽  
Probability Distributions ◽  
Weather Prediction ◽  
Lead Times ◽  
Streamflow Forecasting ◽  
Post Processing ◽  
Short Term ◽  
Ensemble Forecasts ◽  
Numerical Weather

Abstract. Sub-daily ensemble rainfall forecasts that are bias free and reliably quantify forecast uncertainty are critical for flood and short-term ensemble streamflow forecasting. Post-processing of rainfall predictions from numerical weather prediction models is typically required to provide rainfall forecasts with these properties. In this paper, a new approach to generate ensemble rainfall forecasts by post-processing raw numerical weather prediction (NWP) rainfall predictions is introduced. The approach uses a simplified version of the Bayesian joint probability modelling approach to produce forecast probability distributions for individual locations and forecast lead times. Ensemble forecasts with appropriate spatial and temporal correlations are then generated by linking samples from the forecast probability distributions using the Schaake shuffle. The new approach is evaluated by applying it to post-process predictions from the ACCESS-R numerical weather prediction model at rain gauge locations in the Ovens catchment in southern Australia. The joint distribution of NWP predicted and observed rainfall is shown to be well described by the assumed log-sinh transformed bivariate normal distribution. Ensemble forecasts produced using the approach are shown to be more skilful than the raw NWP predictions both for individual forecast lead times and for cumulative totals throughout all forecast lead times. Skill increases result from the correction of not only the mean bias, but also biases conditional on the magnitude of the NWP rainfall prediction. The post-processed forecast ensembles are demonstrated to successfully discriminate between events and non-events for both small and large rainfall occurrences, and reliably quantify the forecast uncertainty. Future work will assess the efficacy of the post-processing method for a wider range of climatic conditions and also investigate the benefits of using post-processed rainfall forecasts for flood and short-term streamflow forecasting.

scholarly journals Domain Adversarial Transfer Learning for Generalized Tool Wear Prediction

2020 ◽  
Vol 12 (1) ◽  
pp. 8
Author(s):  
Peng (Edward) Wang ◽  
Matthew Russell
Keyword(s):  
Tool Wear ◽  
Transfer Learning ◽  
Network Performance ◽  
Generative Adversarial Networks ◽  
Smart Manufacturing ◽  
Successful Implementation ◽  
Target Domain ◽  
Source Domain ◽  
Network Training ◽  
And Task

Given its demonstrated ability in analyzing and revealing patterns underlying data, Deep Learning (DL) has been increasingly investigated to complement physics-based models in various aspects of smart manufacturing, such as machine condition monitoring and fault diagnosis, complex manufacturing process modeling, and quality inspection. However, successful implementation of DL techniques relies greatly on the amount, variety, and veracity of data for robust network training. Also, the distributions of data used for network training and application should be identical to avoid the internal covariance shift problem that reduces the network performance applicability. As a promising solution to address these challenges, Transfer Learning (TL) enables DL networks trained on a source domain and task to be applied to a separate target domain and task. This paper presents a domain adversarial TL approach, based upon the concepts of generative adversarial networks. In this method, the optimizer seeks to minimize the loss (i.e., regression or classification accuracy) across the labeled training examples from the source domain while maximizing the loss of the domain classifier across the source and target data sets (i.e., maximizing the similarity of source and target features). The developed domain adversarial TL method has been implemented on a 1-D CNN backbone network and evaluated for prediction of tool wear propagation, using NASA's milling dataset. Performance has been compared to other TL techniques, and the results indicate that domain adversarial TL can successfully allow DL models trained on certain scenarios to be applied to new target tasks.

scholarly journals Evaluation of numerical weather prediction model precipitation forecasts for use in short-term streamflow forecasting

2012 ◽  
Vol 9 (11) ◽  
pp. 12563-12611 ◽  
Author(s):  
D. L. Shrestha ◽  
D. E. Robertson ◽  
Q. J. Wang ◽  
T. C. Pagano ◽  
P. Hapuarachchi
Keyword(s):  
Numerical Weather Prediction ◽  
Weather Prediction ◽  
Lead Times ◽  
Streamflow Forecasting ◽  
Low Resolution ◽  
Short Term ◽  
Catchment Scale ◽  
Numerical Weather ◽  
Skill Scores ◽  
Systematic Biases

Abstract. The quality of precipitation forecasts from four Numerical Weather Prediction (NWP) models is evaluated over the Ovens catchment in southeast Australia. Precipitation forecasts are compared with observed precipitation at point and catchment scales and at different temporal resolutions. The four models evaluated are the Australian Community Climate Earth-System Simulator (ACCESS) including ACCESS-G with a 80 km resolution, ACCESS-R 37.5 km, ACCESS-A 12 km, and ACCESS-VT 5 km. The high spatial resolution NWP models (ACCESS-A and ACCESS-VT) appear to be relatively free of bias (i.e. <30%) for 24 h total precipitation forecasts. The low resolution models (ACCESS-R and ACCESS-G) have widespread systematic biases as large as 70%. When evaluated at finer spatial and temporal resolution (e.g. 5 km, hourly) against station observations, the precipitation forecasts appear to have very little skill. There is moderate skill at short lead times when the forecasts are averaged up to daily and/or catchment scale. The skill decreases with increasing lead times and the global model ACCESS-G does not have significant skill beyond 7 days. The precipitation forecasts fail to produce a diurnal cycle shown in observed precipitation. Significant sampling uncertainty in the skill scores suggests that more data are required to get a reliable evaluation of the forecasts. Future work is planned to assess the benefits of using the NWP rainfall forecasts for short-term streamflow forecasting. Our findings here suggest that it is necessary to remove the systematic biases in rainfall forecasts, particularly those from low resolution models, before the rainfall forecasts can be used for streamflow forecasting.

Sign in / Sign up

Export Citation Format

Share Document