Forecasting upper atmospheric scalars advection using deep learning: an $$O_3$$ experiment

Steffenel, Luiz Angelo; Anabor, Vagner; Pinheiro, Damaris Kirsch; Guzman, Lissette; Bittencourt, Gabriela Dornelles; Benchérif, Hassan

doi:10.1007/s10994-020-05944-x

Cited by 3 publications

(1 citation statement)

References 53 publications

(60 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This result was due to the mid-latitudes in the tropical stratosphere air masses displacement onto the ozone lamina, and the DYBAL code was used to identify the dynamic barriers positioning in the MIMOSA model. This has been encouraging new studies that aim to simulate and predict these events [68], using deep learning [90] and a new dataset, ERA-5 reanalysis [91], to investigate the long-term atmospheric dynamics behavior [92]. In October 2015, these events led to a +16.6 ± 54.6% UVI increase, even with a predominance of partly cloudy days [93].…”

Section: Discussionmentioning

confidence: 99%

Observations, Remote Sensing, and Model Simulation to Analyze Southern Brazil Antarctic Ozone Hole Influence

Peres,

Pinheiro,

Bencherif

et al. 2024

Remote Sensing

Self Cite

View full text Add to dashboard Cite

This paper presents the observational, remote sensing, and model simulation used to analyze southern Brazil Antarctic ozone hole influence (SBAOHI) events that occurred between 2005 and 2014. To analyze it, we use total ozone column (TOC) data provided by a Brewer spectrophotometer (BS) and the OMI (Ozone Monitoring Instrument). In addition to the AURA/MLS (Microwave Limb Sounder) instrument, satellite ozone profiles were utilized with DYBAL (Dynamical Barrier Localization) code in the MIMOSA (Modélisation Isentrope du Transport Mésoéchelle de l’Ozone Stratosphérique par Advection) model Potential Vorticity (PV) fields. TOC has 7.0 ± 2.9 DU reductions average in 62 events. October has more events (30.7%). Polar tongue events are 19.3% in total, being more frequently observed in October (50% of cases), with medium intensity (58.2%), and in the stratosphere medium levels (55.0%). Already, polar filament events (80.7%) are more frequent in September (32.0%), with medium intensity (42.0%), and stratosphere medium levels (40.7%).

show abstract

Section: Discussionmentioning

confidence: 99%

Observations, Remote Sensing, and Model Simulation to Analyze Southern Brazil Antarctic Ozone Hole Influence

Peres,

Pinheiro,

Bencherif

et al. 2024

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

Literature Review on Integrating Generalized Space-Time Autoregressive Integrated Moving Average (GSTARIMA) and Deep Neural Networks in Machine Learning for Climate Forecasting

et al. 2023

View full text Add to dashboard Cite

The issue of climate change holds immense significance, affecting various aspects of life, including the environment, the interaction between soil conditions and the atmosphere, and agriculture. Over the past few decades, a range of spatio-temporal and Deep Neural Network (DNN) techniques had been proposed within the field of Machine Learning (ML) for climate forecasting, using spatial and temporal data. The forecasting model in this paper is highly complex, particularly due to the presence of nonlinear data in the residual modeling of General Space-Time Autoregressive Integrated Moving Average (GSTARIMA), which represented nonstationary data with time and location dependencies. This model effectively captured trends and seasonal data with time and location dependencies. On the other hand, DNNs proved reliable for modeling nonlinear data that posed challenges for spatio-temporal approaches. This research presented a comprehensive overview of the integrated approach between the GSTARIMA model and DNNs, following the six-stage Data Analytics Lifecycle methodology. The focus was primarily on previous works conducted between 2013 and 2022. The review showed that the GSTARIMA–DNN integration model was a promising tool for forecasting climate in a specific region in the future. Although spatio-temporal and DNN approaches have been widely employed for predicting the climate and its impact on human life due to their computational efficiency and ability to handle complex problems, the proposed method is expected to be universally accepted for integrating these models, which encompass location and time dependencies. Furthermore, it was found that the GSTARIMA–DNN method, incorporating multivariate variables, locations, and multiple hidden layers, was suitable for short-term climate forecasting. Finally, this paper presented several future directions and recommendations for further research.

show abstract

Representing chemical history in ozone time-series predictions – a model experiment study building on the MLAir (v1.5) deep learning framework

et al. 2022

View full text Add to dashboard Cite

Abstract. Tropospheric ozone is a secondary air pollutant that is harmful to living beings and crops. Predicting ozone concentrations at specific locations is thus important to initiate protection measures, i.e. emission reductions or warnings to the population. Ozone levels at specific locations result from emission and sink processes, mixing and chemical transformation along an air parcel's trajectory. Current ozone forecasting systems generally rely on computationally expensive chemistry transport models (CTMs). However, recently several studies have demonstrated the potential of deep learning for this task. While a few of these studies were trained on gridded model data, most efforts focus on forecasting time series from individual measurement locations. In this study, we present a hybrid approach which is based on time-series forecasting (up to 4 d) but uses spatially aggregated meteorological and chemical data from upstream wind sectors to represent some aspects of the chemical history of air parcels arriving at the measurement location. To demonstrate the value of this additional information, we extracted pseudo-observation data for Germany from a CTM to avoid extra complications with irregularly spaced and missing data. However, our method can be extended so that it can be applied to observational time series. Using one upstream sector alone improves the forecasts by 10 % during all 4 d, while the use of three sectors improves the mean squared error (MSE) skill score by 14 % during the first 2 d of the prediction but depends on the upstream wind direction. Our method shows its best performance in the northern half of Germany for the first 2 prediction days. Based on the data's seasonality and simulation period, we shed some light on our models' open challenges with (i) spatial structures in terms of decreasing skill scores from the northern German plain to the mountainous south and (ii) concept drifts related to an unusually cold winter season. Here we expect that the inclusion of explainable artificial intelligence methods could reveal additional insights in future versions of our model.

show abstract

Forecasting upper atmospheric scalars advection using deep learning: an $$O_3$$ experiment

Cited by 3 publications

References 53 publications

Observations, Remote Sensing, and Model Simulation to Analyze Southern Brazil Antarctic Ozone Hole Influence

Observations, Remote Sensing, and Model Simulation to Analyze Southern Brazil Antarctic Ozone Hole Influence

Literature Review on Integrating Generalized Space-Time Autoregressive Integrated Moving Average (GSTARIMA) and Deep Neural Networks in Machine Learning for Climate Forecasting

Representing chemical history in ozone time-series predictions – a model experiment study building on the MLAir (v1.5) deep learning framework

Contact Info

Product

Resources

About