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

@article{Sekiyama2020StatisticalDO, title={Statistical Downscaling of Temperature Distributions from the Synoptic Scale to the Mesoscale Using Deep Convolutional Neural Networks}, author={Tsuyoshi Thomas Sekiyama}, journal={ArXiv}, year={2020}, volume={abs/2007.10839} }

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…

## Figures, Tables, and Topics from this paper

## 2 Citations

MSG-GAN-SD: A Multi-Scale Gradients GAN for Statistical Downscaling of 2-Meter Temperature over the EURO-CORDEX Domain

- AI
- 2021

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

- Computer ScienceRemote. Sens.
- 2021

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.

## References

SHOWING 1-10 OF 23 REFERENCES

Technical Note: Deep Learning for Creating Surrogate Models of Precipitation in Earth System Models

- 2019

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

- 2019

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

- Computer Science
- 2020

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

- Computer Science
- 2020

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

- Computer Science, MedicineNature
- 2019

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

- Environmental Science
- 2017

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

- 2005

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

- Computer Science, MathematicsICLR
- 2018

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

- Environmental Science
- 2015

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

- Computer ScienceICLR
- 2015

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.