Maloy Kumar Devnath

iHARP Research Assistant | UMBC Ph.D. Candidate

Email: maloyd1@umbc.edu
See me at Google Scholar Citation Page, LinkedIn

Research Interests

  • Big Data
  • Artificial Intelligence
  • Spatiotemporal Data Mining
  • Cybersecurity
  • Edge Computing

Successfully defended the Ph.D. proposal in September 2024

Short Biography

Maloy Kumar Devnath, is a Ph.D. student in the Information Systems Department at the University of Maryland Baltimore County. His current research focuses on comprehending the melting patterns of sea ice and investigating its implications on the melting of land ice, which is a key factor contributing to the rising sea levels. Maloy is conducting his research in the Artificial Intelligence/Machine Learning area under the supervision of Dr. Vandana P. Janeja and Dr. Sudip Chakraborty. His academic journey began with a BSc degree, and he briefly worked as a Software Developer at Code Crafters International Limited. Following his passion for education, he transitioned to an academic role as a Lecturer at Bangabandhu Sheikh Mujibur Rahman Science & Technology University, Gopalganj. He is proud to share that, on June 3, 2022, he was promoted to Assistant Professor, reflecting his dedication to teaching.


Research Summary

Maloy’s research explores the rapid changes happening in Antarctica, where both sea ice and land ice are melting at increasing rates. He studies how the loss of sea ice, which normally protects ice sheets from warmer ocean water, might be contributing to faster land ice melt. Using satellite data and machine learning, Maloy identifies unusual melting events and tracks when they begin, how long they last, and where they occur. He also examines how often sea ice retreat and land ice melt happen together, especially in regions showing early melting and delayed recovery. This work helps improve our understanding of how these changes in Antarctica contribute to rising sea levels around the world.


Publications
  • Sudip Chakraborty, Maloy Kumar Devnath, Atefeh Jabeli, Chhaya Kulkarni, Gehan Boteju, Jianwu Wang, and Vandana P. Janeja. 2025. Impact of increased anthropogenic Amazon wildfires on Antarctic Sea ice melt via albedo reduction. Environmental Data Science 4, (2025), e18. https://doi.org/10.1017/eds.2025.1
  • Maloy Kumar Devnath, Sudip Chakraborty, and Vandana P. Janeja. 2024. Deep Learning for Antarctic Sea Ice Anomaly Detection and Prediction: A Two-Module Framework. In Proceedings of the 1st ACM SIGSPATIAL International Workshop on Geospatial Anomaly Detection, October 29, 2024. ACM, Atlanta GA USA, 90–93. https://doi.org/10.1145/3681765.3698457
  • Maloy Kumar Devnath, Sudip Chakraborty, and Vandana P. Janeja. 2024. CMAD: Advancing Understanding of Geospatial Clusters of Anomalous Melt Events in Sea Ice Extent. In The 32nd ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL ’24), October 29-November 1, 2024, Atlanta, GA, USA. ACM, Atlanta, Georgia, USA, https://doi.org/10.1145/3678717.3691280

Proposal Defense

Successfully Defended On: September 5, 2024

Abstract

The dynamics of the Antarctic region which holds 90% of the Earth’s ice volume, particularly the interplay between sea ice retreat and land ice or ice sheets melting, demand rigorous scientific examination due to the alarming changes observed in recent decades. Antarctica’s ice mass has been diminishing rapidly, with an estimated average loss of approximately ∼ 146 billion tons annually since 2002. The reduction in sea ice extent raises critical questions about its repercussions on ice sheet melting, as sea ice provides a protective barrier separating ice sheets from warm ocean currents and wave action. While Antarctic sea ice was expanding until 2015, recent trends show a dramatic reversal with record low extents in February 2023. Understanding the relationship between sea ice changes and ice sheet dynamics is pivotal for deciphering the broader implications of global sea-level rise, a pressing concern for coastal communities, ecosystems, and policymakers. To address this, this thesis employs machine learning algorithms and remote sensing techniques to analyze temporal and spatial variations in the polar climate system. This research aims to develop innovative machine learning algorithms to detect anomalous melt events, variations in melt onset and duration, and quantify the feature similarity and associations between sea ice retreat and land ice or ice sheet melting, particularly in regions experiencing anomalous melts with earlier retreat and late accumulation periods. This thesis specifically aims to:
  1. Understand how anomalous melt events and variations in melt onset and melting period length impact the dynamics of sea ice retreat.
  2. Assess the significance of anomalous melt events compared to steady-state conditions in influencing sea ice retreat.
  3. Quantify feature similarity and associations (co-occurrence) between sea ice retreat and land ice or ice sheet melting in regions experiencing anomalous melts, with particular attention to earlier retreat and late accumulation periods.

By addressing these questions, this thesis contributes to a comprehensive understanding of the intricate interactions between sea ice retreat and ice sheet melting in the Antarctic region and their broader implications for global sea-level rise.

Committee

  • Dr. Vandana Janaja – Advisor and Committee Chair (UMBC)
  • Dr. Sudip Chakraborty – Co-Advisor (UMBC)
  • Dr. James Foulds – Committee Member (UMBC)
  • Dr. Md Osman Gani – Committee Member (UMBC)
  • Dr. Aneesh Subramanian – Committee Member (University of Colorado Boulder)

Last updated 2 May 2025