A Branched Deep Convolutional Network for Forecasting the Occurrence of Hazes in Paris using Meteorological Maps with Different Characteristic Spatial Scales

TL;DR

This paper introduces a deep learning approach with branched convolutional networks to forecast haze events in Paris, leveraging multi-scale meteorological maps to improve spatial feature preservation and prediction accuracy.

Contribution

It presents novel branched deep convolutional architectures tailored for multi-scale meteorological data to enhance haze forecasting performance.

Findings

Improved forecast accuracy over previous models.

Effective preservation of spatial information across scales.

Successful validation on unseen 2021-2022 data.

Abstract

A deep learning platform has been developed to forecast the occurrence of the low visibility events or hazes. It is trained by using multi-decadal daily regional maps of various meteorological and hydrological variables as input features and surface visibility observations as the targets. To better preserve the characteristic spatial information of different input features for training, two branched architectures have recently been developed for the case of Paris hazes. These new architectures have improved the performance of the network, producing reasonable scores in both validation and a blind forecasting evaluation using the data of 2021 and 2022 that have not been used in the training and validation.