Autoencoder-Driven Weather Clustering for Source Estimation during Nuclear Events

  title={Autoencoder-Driven Weather Clustering for Source Estimation during Nuclear Events},
  author={Iraklis A. Klampanos and Athanasios Davvetas and Spyros Andronopoulos and Charalambos Pappas and Andreas Ikonomopoulos and Vangelis Karkaletsis},
Abstract Emergency response applications for nuclear or radiological events can be significantly improved via deep feature learning due its ability to capture the inherent complexity of the data involved. In this paper we present a novel methodology for rapid source estimation during radiological releases based on deep feature extraction and weather clustering. Atmospheric dispersions are then calculated based on identified predominant weather patterns and are matched against simulated… 
Unsupervised Severe Weather Detection Via Joint Representation Learning Over Textual and Weather Data
It is posited that incorporating external or auxiliary information, such as the outcome of an external task or an observation, can improve the decision boundaries of an unsupervised detection algorithm.
A Comprehensive Review of Deep Learning Applications in Hydrology and Water Resources
This study provides a comprehensive review of state-of-the-art deep learning approaches used in the water industry for generation, prediction, enhancement, and classification tasks, and serves as a guide for how to utilize available deep learning methods for future water resources challenges.
A comprehensive review of deep learning applications in hydrology and water resources.
This study provides a comprehensive review of state-of-the-art deep learning approaches used in the water industry for generation, prediction, enhancement, and classification tasks, and serves as a guide for how to utilize available deep learning methods for future water resources challenges.
Stochastic perturbations and dimension reduction for modelling uncertainty of atmospheric dispersion simulations
A generic mathematical formulation for time dependent perturbation of both amplitude and dynamics of the inputs of the numerical dispersion model is devised, which allows a more thorough exploration of possible outcomes than simpler perturbations found in the literature.
Denoising stacked autoencoders for transient electromagnetic signal denoising
The noise reduction method can effectively reduce the noise of the SFS in contrast with the Kalman, principal component analysis (PCA) and wavelet transform methods and strongly support the speculation of deeper underground features.
A denoising stacked autoencoders for transient electromagnetic signal denoising
Abstract. Transient electromagnetic method (TEM) is extremely important in geophysics. However, the secondary field signal(SFS) in TEM received by coil is easily disturbed by random noise, sensor
Spatial-Temporal Features Based Sensor Network Partition in Dam Safety Monitoring System
Experimental results on the public datasets and a real dataset from an arch dam demonstrate that the proposed network partition algorithm NPA can achieve better partition performance than TSDA+K-Means and TSDA+, and introduce the auxiliary objective variable to optimize the network partition objective function.
An assessment of climate change impact on air masses arriving in Athens, Greece
Climate change is inherently linked to long-term non-stationary changes in the characteristics and frequency of weather patterns. The present study attempts to identify the statistical changes of
Selection methodology of representative meteorological days for assessment of renewable energy systems
The analysis showed that increasing the number of RDs indeed improves the representativeness of the reconstructed year with disagreement indices as low as 1.041, and the proposed autoencoder feature extraction approach outperformed the conventional statistical approach.
TS-PADM: Anomaly Detection Model of Wireless Sensors Based on Spatial-Temporal Feature Points
This paper first defines the temporal and spatial feature of data flows; then, a time series denoising autoencoder is proposed to extract the discriminative high-dimensional characteristics to represent the data points, and a probability statistics-based anomaly detection model (PADM) was proposed for identifying the abnormal data.


A new classification approach for detecting severe weather patterns
An innovative approach for the classification of meteorological data based on the frequency of occurrence of the values of different variables provided by a weather forecast model is proposed and it is expected that the screening of the outputs of the meteorological model Eta by the proposed classifier could serve as a support tool for meteorologists in order to identify in advance patterns associated to severe convective events.
Using Self-Organizing Maps to Investigate Extreme Climate Events: An Application to Wintertime Precipitation in the Balkans
Abstract This paper examines some of the physical mechanisms and remote linkages associated with extreme wintertime precipitation in the Balkans. The analysis is assessed on daily timescales to
Weather Pattern Classification to Represent the Urban Heat Island in Present and Future Climate
AbstractA classification of weather patterns (WP) is derived that is tailored to best represent situations relevant for the urban heat island (UHI). Three different types of k-means-based cluster
Weather analogue: A tool for real-time prediction of daily weather data realizations based on a modified k-nearest neighbor approach
The results from this study showed that this weather analogue modeling tool could be a valuable tool for realization of any weather dependent function and there is also scope for incorporation of this tool with application of agricultural, ecological, and hydrological process-based simulation models.
RODOS meteorological pre-processor and atmospheric dispersion model DIPCOT: a model suite for radionuclides dispersion in complex terrain
The Meteorological Pre-Processor (MPP) of the Decision Support System RODOS acts as interface between the incoming meteorological data from stations and/or prognostic models and the Atmospheric
Combining principal component regression and artificial neural networks for more accurate predictions of ground-level ozone
It was found that combining the predictions from the PCR and ANN models reduced the root mean square errors of ozone concentrations and it is clear that combining predictions generated by different methods could improve the accuracy and provide a prediction that is superior to a single model prediction.
The ERA-Interim reanalysis: configuration and performance of the data assimilation system
ERA-Interim is the latest global atmospheric reanalysis produced by the European Centre for Medium-Range Weather Forecasts (ECMWF). The ERA-Interim project was conducted in part to prepare for a new
Extracting and composing robust features with denoising autoencoders
This work introduces and motivate a new training principle for unsupervised learning of a representation based on the idea of making the learned representations robust to partial corruption of the input pattern.
Self-organizing maps: applications to synoptic climatology
Self organizing maps (SOMs) are used to locate archetypal points that describe the multi-dimensional distribution function of a gridded sea level pressure data set for the northeast United States.
NOAA’s HYSPLIT Atmospheric Transport and Dispersion Modeling System
AbstractThe Hybrid Single-Particle Lagrangian Integrated Trajectory model (HYSPLIT), developed by NOAA’s Air Resources Laboratory, is one of the most widely used models for atmospheric trajectory and