• Corpus ID: 220665816

Statistical Downscaling of Temperature Distributions from the Synoptic Scale to the Mesoscale Using Deep Convolutional Neural Networks

  title={Statistical Downscaling of Temperature Distributions from the Synoptic Scale to the Mesoscale Using Deep Convolutional Neural Networks},
  author={Tsuyoshi Thomas Sekiyama},
  • T. Sekiyama
  • Published 20 July 2020
  • Environmental Science, Physics, Computer Science
  • ArXiv
Deep learning, particularly convolutional neural networks for image recognition, has been recently used in meteorology. One of the promising applications is developing a statistical surrogate model that converts the output images of low-resolution dynamic models to high-resolution images. Our study exhibits a preliminary experiment that evaluates the performance of a model that downscales synoptic temperature fields to mesoscale temperature fields every 6 hours. The deep learning model was… 
2 Citations
MSG-GAN-SD: A Multi-Scale Gradients GAN for Statistical Downscaling of 2-Meter Temperature over the EURO-CORDEX Domain
One of the most important open challenges in climate science is downscaling. It is a procedure that allows making predictions at local scales, starting from climatic field information available at
Artificial Intelligence Revolutionises Weather Forecast, Climate Monitoring and Decadal Prediction
Artificial Intelligence should become a cornerstone of future weather and climate observation and modelling systems and a new generation of scientists combining atmospheric science domain knowledge and state-of-the-art AI skills needs to be trained.


Technical Note: Deep Learning for Creating Surrogate Models of Precipitation in Earth System Models
Abstract. We investigate techniques for using deep neural networks to produce surrogate models for short term climate forecasts. A convolutional neural network is trained on 97 years of monthly
Configuration and Intercomparison of Deep Learning Neural Models for Statistical Downscaling
Abstract. Deep learning techniques (in particular convolutional neural networks, CNNs) have recently emerged as a promising approach for statistical downscaling due to their ability to learn spatial
Configuration and intercomparison of deep learning neural models for statistical downscaling
A comprehensive assessment of deep learning techniques for continental-scale statistical downscaling, building on the VALUE validation framework, shows that, while the added value of CNNs is mostly limited to the reproduction of extremes for temperature, these techniques do outperform the classic ones in the case of precipitation for most aspects considered.
Towards Operational Downscaling of Low Resolution Wind Fields using Neural Networks
Instead, we propose using neural networks to downscale low-resolution wind-field simulations (input) to high-resolution fields (targets) to try to match a high-resolution simulation. Based on
Deep learning and process understanding for data-driven Earth system science
It is argued that contextual cues should be used as part of deep learning to gain further process understanding of Earth system science problems, improving the predictive ability of seasonal forecasting and modelling of long-range spatial connections across multiple timescales.
The Impact of Surface Wind Data Assimilation on the Predictability of Near-Surface Plume Advection in the Case of the Fukushima Nuclear Accident
We investigated the predictability of plume advection in the lower troposphere and the impact of AMeDAS surface wind data assimilation by using radioactive cesium emitted by the Fukushima nuclear
A pre-operational variational data assimilation system for a non-hydrostatic model at the Japan Meteorological Agency: formulation and preliminary results
A new variational data assimilation system for a non-hydrostatic model is being developed at the Japan Meteorological Agency (JMA) for operational use. Known as the JMA non-hydrostatic model
Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge
It is shown how general background knowledge gained from physics could be used as a guideline for designing efficient Deep Learning models and a formal link between the solution of a class of differential equations underlying a large family of physical phenomena and the proposed model is demonstrated.
Horizontal Resolution Dependence of Atmospheric Simulations of the Fukushima Nuclear Accident Using 15-km, 3-km, and 500-m Grid Models
We investigated the horizontal resolution dependence of atmospheric radionuclide (Cs-137) simulations of the Fukushima nuclear accident on March 15, 2011. We used Eulerian and Lagrangian transport
Very Deep Convolutional Networks for Large-Scale Image Recognition
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.