arrow
返回

A probabilistic forecast for multi-year ENSO using Bayesian convolutional neural network

delete2024-11-05
delete0
delete
OA
AI
P
P. Sreeraj
B
Balaji, B.
A
Arya Paul *
P
P. A. Francis
DOI:10.1088/1748-9326/ad8be1delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
A robust El Ni & ntilde;o Southern Oscillation (ENSO) prediction is essential for monitoring the global climate, regional monsoons, and weather extremes. Despite dedicated efforts spanning decades, the precise prediction of ENSO events through numerical modeling beyond a couple of seasonal lead times remains a daunting challenge. The advent of deep learning-based approaches marks a transformative era in climate and weather prediction. However, many machine learning-based studies attempting ENSO prediction are confined to singular estimates, lacking adequate quantification of uncertainty in learned parameters and overlooking the crucial need for a nuanced understanding of ENSO prediction confidence. Here, we introduce a deep learning-based Bayesian convolutional neural network model that provides robust probabilistic predictions for ENSO with a lead time of up to 9-10 months across all seasons. The Bayesian layers within the convolutional neural network maintain the capability to predict a distribution of learned parameters. Augmented with bias correction, our model reproduces the amplitude of the Ni & ntilde;o 3.4 index with fidelity for lead up to 9-10 months. The inherent capacity for uncertainty modeling enhances the reliability of bayesian neural networks (BNNs), making them particularly valuable in operational services. This research holds substantial socio-economic implications as it enhances our forecasting capabilities and rigorously quantifies forecast uncertainties, providing valuable insights for planning and policymaking.
Keyword:
Bayesian convolutional neural network
ENSO forecast
uncertainty estimation
seasonal predictions

期刊

Environmental Research Letters 封面图
Environmental Research Letters
IF:
5.6
论文数:
9.5K
被引数:
5.0W

机构

M
ministry of earth sciences (moes) - india
学者数:
3.2K
论文数: 2.5K
被引数: 0
引用论文

引用论文

A Vector Autoregressive ENSO Prediction Model
err2015-10-30
err23
errOAAI
errChapman, David; Cane, Mark A.; Henderson, Naomi; Lee, Dong Eun; Chen, Chen
err分享
err收藏
Deep learning for skillful long-lead ENSO forecasts深度学习用于熟练的长期领先ENSO预测
err2023-01-04
err17
errOAAI
errPatil, Kalpesh Ravindra; Doi, Takeshi; Jayanthi, Venkata Ratnam; Behera, Swadhin
err分享
err收藏
Biochar increased photosynthetic and accessory pigments in tomato (Solanum lycopersicum L.) plants by reducing cadmium concentration under various irrigation waters
err2017-08-08
err0
PREAI
errMuhammad Abid; Subhan Danish; Muhammad Zafar-ul-Hye; Muhammad Shaaban; Muhammad Mutahir Iqbal; Abdur Rehim; Muhammad Farooq Qayyum; Muhammad Nadir Naqqash
err分享
err收藏
New EUV selected flare stars
err2024-09-05
err0
PREAI
errBill Ball; Gordon Bromage
err分享
err收藏
All flavours of El Nino have similar early subsurface origins
err2012-06-24
err63
PREAI
errRamesh, Nandini; Murtugudde, Raghu
err分享
err收藏
学者 查看更多内容