scholarly journals Benefits of stochastic weight averaging in developing neural network radiation scheme for numerical weather prediction

2021 ◽  
Author(s):  
Hwan-Jin Song ◽  
Soonyoung Roh ◽  
Juho Lee ◽  
Giung Nam ◽  
Eunggu Yun ◽  
...  
Author(s):  
Nur Arminarahmah ◽  
Miftahul Munir

Prakiraan hujan bulanan bisa digunakan untuk antisipasi banjir dan manajemen sumber daya air, keselamatan jiwa dan harta benda, serta keberlangsungan aktivitas ekonomi. Penggunaan Jaringan Syaraf Tiruan sebagai bagian dari Machine Learning adalah teknik yang sering digunakan selain numerical weather prediction dan metode statistik. Menggunakan peru-bah data bulan dan data empirical orthogonal function anomali suhu muka laut bulanan pada 12 lokasi menghasilkan nilai korelasi yang baik saat pembuatan model, tetapi hasil verifikasi menunjukkan akurasi yang baik didapatkan saat periode musim kemarau dan skill terjelek saat peralihan musim kemarau ke musim hujan.


2021 ◽  
pp. 068
Author(s):  
Ján Mašek

Cet article résume les activités de Jean-François Geleyn qui ont abouti à un schéma de rayonnement de pointe adapté à la prévision numérique du temps. L'objectif principal - traiter les interactions nuage-rayonnement - a été atteint grâce à une amélioration considérable de l'approche à bandes larges (la vision avec deux seuls intervalles spectraux, l'un pour les courtes longueurs d'onde pour le rayonnement solaire, l'autre pour les grandes longueurs d'onde pour le rayonnement thermique), en ouvrant la voie à un appel intermittent du schéma dans le temps. Le schéma qui en résulte offre une alternative compétitive par rapport aux approches traditionnelles en « k-distribution corrélée » utilisant des méthodes plus précises mais plus coûteuses, méthodes qui ne permettent pas la mise à jour en temps réel des effets radiatifs des nuages. The paper summarizes the activities of Jean-François Geleyn leading to a state-of-the-art radiation scheme tailored for numerical weather prediction. The main goal - dealing with cloud-radiation interactions - was reached thanks to significant improvements to the broadband approach allowing for single shortwave and single longwave intervals, opening a way to selective intermittency. The resulting scheme offers an alternative competitive to the mainstream approach that uses very accurate but expensive correlated k-distribution method, not allowing for timely update of cloud radiative effects.


2016 ◽  
Vol 16 (9) ◽  
pp. 5933-5948 ◽  
Author(s):  
Emily Gleeson ◽  
Velle Toll ◽  
Kristian Pagh Nielsen ◽  
Laura Rontu ◽  
Ján Mašek

Abstract. The direct shortwave radiative effect of aerosols under clear-sky conditions in the Aire Limitee Adaptation dynamique Developpement InterNational – High Resolution Limited Area Model (ALADIN-HIRLAM) numerical weather prediction system was investigated using three shortwave radiation schemes in diagnostic single-column experiments: the Integrated Forecast System (IFS), acraneb2 and the hlradia radiation schemes. The multi-band IFS scheme was formerly used operationally by the European Centre for Medium Range Weather Forecasts (ECMWF) whereas hlradia and acraneb2 are broadband schemes. The former is a new version of the HIRLAM radiation scheme while acraneb2 is the radiation scheme in the ALARO-1 physics package. The aim was to evaluate the strengths and weaknesses of the numerical weather prediction (NWP) system regarding aerosols and to prepare it for use of real-time aerosol information. The experiments were run with particular focus on the August 2010 Russian wildfire case. Each of the three radiation schemes accurately (within ±4 % at midday) simulates the direct shortwave aerosol effect when observed aerosol optical properties are used. When the aerosols were excluded from the simulations, errors of more than +15 % in global shortwave irradiance were found at midday, with the error reduced to +10 % when standard climatological aerosols were used. An error of −11 % was seen at midday if only observed aerosol optical depths at 550 nm, and not observation-based spectral dependence of aerosol optical depth, single scattering albedos and asymmetry factors, were included in the simulations. This demonstrates the importance of using the correct aerosol optical properties. The dependency of the direct radiative effect of aerosols on relative humidity was tested and shown to be within ±6 % in this case. By modifying the assumptions about the shape of the IFS climatological vertical aerosol profile, the inherent uncertainties associated with assuming fixed vertical profiles were investigated. The shortwave heating rates in the boundary layer changed by up to a factor of 2 in response to the aerosol vertical distribution without changing the total aerosol optical depth. Finally, we tested the radiative transfer approximations used in the three radiation schemes for typical aerosol optical properties compared to the accurate DISORT model. These approximations are found to be accurate to within ±13 % even for large aerosol loads.


Sign in / Sign up

Export Citation Format

Share Document