Bayesian Convolutional Neural Network (BCNN)

Bayesian Convolutional Neural Network (BCNN)

Context: The Hyderabad-based Indian National Centre for Ocean Information Services (INCOIS) has developed a new product, a Bayesian Convolutional Neural Network (BCNN).

• BCNN uses Artificial Intelligence (AI), deep learning, and machine learning (ML) to improve forecasts.
• The model’s prediction relies on the fact that El Niño or La Niña are connected to the slow oceanic variations and their atmospheric coupling, which gives sufficient lead time to issue early forecasts.
• It calculates the Niño3.4 index value — used to determine the different phases of ENSO phases —and makes the forecast.
• The index value is obtained by averaging the sea surface temperature (SST) anomaly in the central equatorial Pacific, extending from 5°N to 5°S and 170°W to 120°W.
• It will predict the emergence of El Niño and La Niña conditions of El Niño Southern Oscillation (ENSO) up to 15 months in advance. Existing models can give a prediction up to six to nine months in advance.
• However, historical weather data is needed to feed into BCNN to generate forecasts. Such data is available for lands but not oceans.

Existing models

• Statistical model: It generates forecasts based on various information sets received from different countries and regions.
• Dynamic model: More accurate than static model, involving 3D mathematical simulation of the atmosphere done using High-Performance Computers (HPC).