Guiding Responses to Climate Change: Integrating Fourier Transformation and Residual Learning for Arctic Sea Ice Forecasting
Overview
Arctic sea ice plays integral roles in both polar and global environmental systems, notably ecosystems, communities, and economies. As sea ice diminishes due to climate change, it has become imperative to accurately predict sea ice extent (SIE). Using a dataset of Arctic oceanic and atmospheric variables spanning 1979 to 2021, a preliminary exploratory analysis guided the development of pipelines for predicting SIE one month in advance. After a conditional detrender removed long-term linear trends from all variables, grid search tuned a novel composite Fourier Transform model that iteratively removed oscillation. Using grid search to optimize lags and hyperparameters, Gradient Boosting regressors were trained on baseline, detrended, and de-oscillated data, each achieving successively superior performance. Next, a novel framework for visualizing SIE was proposed, utilizing the same Fourier transform process. A dataset of Arctic SIE images was decomposed into constituent pixels. Then, Fourier transform models were applied to each pixel independently and recombined into images. Though no comparable model exists, the high pixel accuracy holds promising results for visualizing SIE. By outperforming current state-of-the-art and deep learning models and proposing a novel image framework, this study demonstrates the potential for employing Fourier transform-based pipelines in predicting Arctic SIE numerically and visually. Moreover, the extensive flexibility of this methodology has bolstered the performance of existing models, suggesting its broad applicability in time series prediction. Furthermore, this study may contribute to prediction tasks of related research and advise future adaptation, resilience, and mitigation efforts in response to Arctic sea ice decline.
Competition history
- ISEF 2023
Resources
Related projects
ISEF · 2024
Deep Learning on a Novel Ising Model To Study Arctic Sea Ice Dynamics
ISEF · 2025
CryoStrat-RL: A Dynamic Graph-Game Framework for Arctic Conservation Using Reinforcement Learning
ISEF · 2025
Hybrid Incremental Learning: A Novel Approach to Time Series Forecasting
ISEF · 2025
Wavelet-Based Hybrid Deep Learning Model for Forecasting El Niño-Southern Oscillation Cycles
ISEF · 2024
Advancing El Niño-Southern Oscillation ("ENSO") Ensemble Forecasting With Distillation-Based Learning
ISEF · 2023
Short Range Hourly Temperature Forecasting in Relation to National Weather Prediction Models: A Breakthrough
ISEF · 2026
Machine Learning for Coral Bleaching Diagnosis and Forecasting Using Images and Environmental Data
JSHS · 2020
Glacier Melting Risk: A predictive model of glacial melting by correlating timeseries geoglacial data with fractal- analysis of remote-sensed images
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: Regeneron International Science and Engineering Fair