Tolulope Ale

iHARP Research Assistant | UMBC Ph.D. Candidate

Email: tale2@umbc.edu
See me at Google Scholar Citation Page, LinkedIn

Research Interests

  • Anomaly Detection
  • Multivariate Temporal Data Mining
  • Explainable Machine Learning and Attribution Modeling
  • Climate Informatics
  • Natural Language Processing

Successfully defended the Ph.D. proposal in May 2024

Short Biography

Tolulope Ale, MSc., is a doctoral student in the information systems department. He obtained a master’s degree in physics from the University of Texas at El Paso in 2021 with a focus on computational biophysics. He is interested in applied Data Science and Machine Learning. Tolu is conducting research in the Data Mining/Machine Learning area under Dr. Vandana Janeja. His interest is in identifying anomalous associations in temporal data that can be further used in predictive analytics. Tolu’s research is focused on mining multivariate anomalous temporal events in the Arctic domain.

Research Summary

Tolu’s research introduces a new method for detecting unusual patterns in climate data, focusing on snow and ice melt in the Arctic. The approach helps identify when and why extreme melting events happen, using advanced computer models that group similar climate features and track changes over time. By comparing model results with real-world observations, the study ensures the findings are accurate and trustworthy. It also explains which climate factors are most responsible for unusual melting, helping scientists better understand the causes. Ultimately, this work supports smarter strategies for dealing with climate change by improving how we track and explain extreme weather events.

Publications
  • Tolulope Ale, Vandana P. Janeja, and Nicole-Jeanne Schlegel. 2024. Harnessing Feature Clustering For Enhanced Anomaly Detection With Variational Autoencoder And Dynamic Threshold. In IGARSS 2024 – 2024 IEEE International Geoscience and Remote Sensing Symposium, July 07, 2024. IEEE, Athens, Greece, 8692–8696. https://doi.org/10.1109/IGARSS53475.2024.10640794
Internships/ Fellowships
  • 2025 Summer – Microsoft Corporation
    • Tolu will be working as a Data Science Summer Intern, in which his focus will be on manipulating large volumes of data by leveraging Machine Learning or statistical modeling techniques to develop solutions to problems in computer hardware or software that will contribute to driving innovation.
  • 2024 Summer – Amazon
    • Tolu conducted feature engineering to define new metrics and Key Performance Indicators focused on identifying brand and seller abuse, then implemented statistical analyses to determine the significance and reliability of each metric. Subsequently, he developed a comprehensive data mining framework to uncover various abuse patterns within the brand registry. Lastly, he created an interactive, self-service dashboard enabling stakeholders to proactively monitor and detect emerging abuse trends.
  • 2023 Summer/ Fall – NASA GESTAR
    • Tolu evaluated Global Navigation Satellite Systems-Radio Occultation (GNSS-RO) soundings, particularly the quality of the GeoOptics refractivity profile purchased by NASA, and analyzed variability in Planetary Boundary Layer (PBL) Height, leading to improved data accuracy for atmospheric studies. He then developed a machine learning model to detect atmospheric PBL height from vertical resolution refractivity profiles.
Proposal Defense

Successfully Defended On: May 23, 2024

Abstract

The multivariate time series analysis within climate data represents a crucial yet less explored field. This is particularly relevant when examining extreme climate events, such as snow melting in polar regions, which necessitate the consideration of multiple variables to capture fluctuations accurately. Anomalies in climate data often result from the interplay of several variables, meaning that what appears anomalous under univariate analysis may, in fact, align with expected patterns once contextualized within a multivariate framework. This approach more accurately reflects the interconnected nature of real-world phenomena, where events seldom occur in isolation. The primary challenge in anomaly detection algorithms for multivariate climate time series lies in effectively harnessing the intricate relationships among the multivariate data. Despite the advancements in deep learning for anomaly detection, very few efforts have been directed toward climate data; this could be due to the lack of labeled data and the complexity of climate variables. Additionally, a significant limitation of existing anomaly detection algorithms is their lack of explainability, especially in climate data, where it is crucial to pinpoint which variable most significantly influences an anomaly score. Beyond merely identifying anomalies, it is vital to ascertain the primary variable contributing to the anomaly, facilitating targeted strategies for mitigating such occurrences in climate datasets.

In response, we propose a novel framework incorporated with feature attribution for detecting anomalies within multivariate time series data and then analyzing climate change trends in polar regions. Our methodology employs a Variational Autoencoder (VAE) framework, chosen for its stochastic nature, which we enhanced by incorporating correlation-based feature clustering and dynamic thresholding. These enhancements allow the VAE to focus on localized representations, thereby enriching the latent representation quality and the accuracy of detected anomalies. Given the complex interdependencies among variables and over time within multivariate climate data, we introduce the concepts of temporal overlap and proximity. These concepts allow us to identify how an anomaly in a variable relates to an anomaly in other variables. Through extensive experimentation on three distinct datasets, our research substantiates the efficacy of the proposed framework, marking a significant advancement in anomaly detection within climate data analysis.

Committee

  • Dr. Vandana Janaja – Advisor and Committee Chair (UMBC)
  • Dr. Nicole-Jeanne Schlegel – Committee Member (NOAA)
  • Dr. Jianwu Wang – Committee Member (UMBC)
  • Dr. Patti Ordóñez – Committee Member (UMBC)
  • Dr. Sudip Chakraborty – Committee Member (UMBC)

Last updated 1 May 2025