【摘 要】
：
Although deep learning has achieved a milestone in forecasting the El Nino-Southern Oscillation(ENSO),the current models are insufficient to simulate diverse characteristics of the ENSO,which depends on the calendar season.Consequently,a model was generat
【机 构】
：
Department of Oceanography,Chonnam National University,Gwangju 61186,South Korea;Kakao Brain,Bundang
论文部分内容阅读
Although deep learning has achieved a milestone in forecasting the El Nino-Southern Oscillation(ENSO),the current models are insufficient to simulate diverse characteristics of the ENSO,which depends on the calendar season.Consequently,a model was generated for specific seasons which indicates these models did not consider physical constraints between different target seasons and forecast lead times,thereby leading to arbitrary fluctuations in the predicted time series.To overcome this problem and account for ENSO seasonality,we developed an all-season convolutional neural network(A_CNN)model.The cor-relation skill of the ENSO index was particularly improved for forecasts of the boreal spring,which is the most challenging season to predict.Moreover,activation map values indicated a clear time evolution with increasing forecast lead time.The study findings reveal the comprehensive role of various climate precursors of ENSO events that act differently over time,thus indicating the potential of the A_CNN model as a diagnostic tool.
其他文献
Determination and conceptualization of atomic structures of metallic glasses or amorphous alloys remain a grand challenge.Structural models proposed for bulk metallic glasses are still controversial owing to experimental difficulties in directly imaging t
Schottky-contacted sensors have been demonstrated to show high sensitivity and fast response time in various sensing systems.In order to improve their sensing performance,the Schottky barriers height(SBH)at the interface of semiconductor and metal electro
To satisfy the current global energy demand,the development and practical applications of designing and constructing high-energy cathodes for Li-ion batteries(LIBs)are necessitated[1].In particular,layered oxide cathode materials,especially lithium-mangan
Face masks contribute greatly to the protection of human health in the epidemic of corona virus disease 2019(COVID-19).However,the extensive use of masks has brought new challenges to the environment and human health,such as vast plastic and plastic parti
Enhanced glycolysis is a distinct feature associated with numerous stem cells and cancer cells.However,little is known about its regulatory roles in gene expression and cell fate determination.Here,we confirm that glycolytic metabolism and lactate product
Single-atom catalysts(SACs)have emerged as one of the most competitive catalysts toward a variety of important electrochemical reactions,thanks to their maximum atom economy,unique electronic and geometric structures.However,the role of SACs supports on t
Spiking neural network,inspired by the human brain,consisting of spiking neurons and plastic synapses,is a promising solution for highly efficient data processing in neuromorphic computing.Recently,memristor-based neurons and synapses are becoming intrigu
Organic photovoltaic(OPV)cells have found their potential applications in the harvest of indoor light photons.However,the output power of such indoor devices is usually far from the demand of the internet of things.Therefore,it is essential to boost the o
Ion mobility analysis is a well-known analytical technique for identifying gas-phase compounds in fast-response gas-monitoring systems.However,the conventional plasma discharge system is bulky,operates at a high temperature,and inappropriate for volatile
Photocatalytic reduction of carbon monoxide (CO) is a promising route to the production of high-value chemicals and fuels,as a supplement to high energy-input Fischer-Tropsch synthesis (FTS) and a key step in direct photo/electro-reduction CO2 to multi-ca