Arjun Babu Nellikkattil

Arjun Babu Nellikkattil

he/him

I am a climate scientist passionate about developing advanced mathematical and machine learning tools to improve our understanding of the climate system and predict future changes. My current research focuses on refining climate risk assessments and informing policy decisions by providing precise, data-driven insights into future precipitation trends.

Posts by Collection

portfolio

publications

Prediction of daily sea surface temperature using artificial neural networks

Published in International Journal of Remote Sensing, 2018

This manuscript presents an artificial neural network model to predict the sea surface temperature (SST) and delineate SST fronts in the northeastern Arabian Sea.

Recommended citation: Aparna, S. G., Selrina D’souza, and N. B. Arjun. "Prediction of daily sea surface temperature using artificial neural networks." International Journal of Remote Sensing 39, no. 12 (2018): 4214-4231.
Download Paper

Aiding the Earth System Models with Super Resolution Deep Learning

Published in 한국정보과학회, 2021

Two state-of-the-art deep learning approaches to upscale computationally cheaper low-resolution simulation data into high resolution.

Recommended citation: Mai, Tung-Duong, et al. "Aiding the Earth System Models with Super Resolution Deep Learning." 2021 한국소프트웨어종합학술대회. 한국정보과학회, 2021.
Download Paper

Downscaling earth system models with deep learning

Published in Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining, 2022

We introduce GINE, a new statistical downscaling method that uses computer vision to enhance climate model resolution while preserving key spatial features. This approach improves the accuracy and visual quality of downscaled data, making high-resolution climate projections more accessible for policymakers.

Recommended citation: Park, Sungwon, Karandeep Singh, Arjun Nellikkattil, Elke Zeller, Tung Duong Mai, and Meeyoung Cha. "Downscaling earth system models with deep learning." In Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining, pp. 3733-3742. 2022.
Download Paper

Future sea-level projections with a coupled atmosphere-ocean-ice-sheet model

Published in Nature Communications, 2023

Traditional ice-sheet models often ignore interactions between ice, ocean, and atmosphere, which can influence future sea-level rise. Using a coupled climate-ice-sheet model, we find that Antarctic feedbacks enhance basal melting but also reduce surface melting and calving, moderating the overall contribution to sea-level rise. These results highlight the need to account for complex climate-ice interactions for more accurate sea-level rise projections.

Recommended citation: Park, Jun-Young, Fabian Schloesser, Axel Timmermann, Dipayan Choudhury, June-Yi Lee, and Arjun Babu Nellikkattil. "Future sea-level projections with a coupled atmosphere-ocean-ice-sheet model." Nature Communications 14, no. 1 (2023): 636.
Download Paper

Increased amplitude of atmospheric rivers and associated extreme precipitation in ultra-high-resolution greenhouse warming simulations

Published in Communications Earth & Environment, 2023

Atmospheric rivers are expected to become more frequent and intense with rising CO₂ levels, contributing more to global precipitation and extreme rainfall events. These changes have significant implications for future water management and adaptation strategies.

Recommended citation: Nellikkattil, Arjun Babu, June-Yi Lee, Bin Guan, Axel Timmermann, Sun-Seon Lee, Jung-Eun Chu, and Danielle Lemmon. "Increased amplitude of atmospheric rivers and associated extreme precipitation in ultra-high-resolution greenhouse warming simulations." Communications Earth & Environment 4, no. 1 (2023): 313.
Download Paper

Scalable Feature Extraction and Tracking (SCAFET): a general framework for feature extraction from large climate data sets

Published in Geoscientific Model Development, 2024

SCAFET is a generalized computational framework that extracts and tracks climate features using shape-based metrics, allowing for consistent comparisons across different models and datasets. Unlike traditional methods, it does not rely on prior model assumptions, making it adaptable for detecting atmospheric rivers, cyclones, jet streams, and other climate phenomena across various scales and dimensions.

Recommended citation: Nellikkattil, Arjun Babu, Danielle Lemmon, Travis Allen O`Brien, June-Yi Lee, and Jung-Eun Chu. "Scalable Feature Extraction and Tracking (SCAFET): a general framework for feature extraction from large climate data sets." Geoscientific Model Development 17, no. 1 (2024): 301-320.
Download Paper

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.