Year: 2022
Type: preprint
Abstract: The prediction of the Madden-Julian Oscillation (MJO), a massive tropical weather event with vast global socio-economic impacts, has been infamously difficult with physics-based weather prediction models. Here we construct a machine learning model using reservoir computing technique that forecasts the real-time multivariate MJO index (RMM), a macroscopic variable that represents the state of the MJO. The training data was refined by developing a novel filter that extracts the recurrency of MJO signals from the raw atmospheric data and selecting a suitable time-delay coordinate of the RMM. The model demonstrated the skill to forecast the state of MJO events for a month from the pre-developmental stages. Best-performing cases predicted the RMM sequence over two months, which exceeds the expected inherent predictability limit of the MJO.
Source: arXiv (Cornell University)
Authors: Suematsu, Tamaki, Nakai, Kengo, Yoneda, Tsuyoshi, Takasuka, Daisuke, Jinno, Takuya, Saiki, Yoshitaka, Miura, Hiroaki
Language: English
Subfield: Global and Planetary Change
Field: Environmental Science
Domain: Physical Sciences
Open Access status: green
Awards: Understanding the qualitative change of the MJO over the maritime continents by using the YMC observation and a meteorological model, Intermittency due to hetero-chaotic property and its inference, G2660333490, G276634408, Dynamical system analysis of constructed machine learning model from time-series data, G3586471847, G3691478141, G3750503032, 大気大循環と内部対流システムの変動時空間スケールの研究, コールドプールの力学による雲の自己組織化機構の解明, G8072307327, Expediting and Elaborating Business Forecast Using Machine Learning, G8328952525, New developments in the energy cascade of Navier-Stokes turbulence through the collaboration of physics and mathematics
OpenAlex ID: W4313533607