Efficient Evaluation of NALA in ConvLSTM for High-Dimensional Time-Series Traffic-Flow Forecasting .
Supervisor
Naila Aslam
Programme
MSc in Data Analytics
Subject
Computer Science
Abstract
Accurate traffic congestion prediction is essential for effective urban mobility and energy-efficient transport planning. This study evaluates the impact of optimizers on ConvLSTM models for short-term traffic forecasting using the METR-LA dataset, incorporating weather and event data as exogenous features. Two optimizers—Adam and Nesterov-accelerated Lookahead (NALA)—are compared under a frozen-T evaluation to prevent temporal leakage. Data preprocessing included five-minute alignment of weather data and event integration based on sensor proximity. Results show that the best-performing model (Variant C-2), integrating traffic, weather, and event features with reduced dropout and NALA optimization, achieved an MAE of 5.22 and RMSE of 8.79, outperforming traffic-only and traffic-plus-weather baselines. Findings highlight NALA’s potential for improved convergence and demonstrate the value of exogenous features in enhancing traffic forecasting accuracy.
Date of Award
2025
Full Publication Date
2025
Access Rights
open access
Document Type
Capstone Project
Resource Type
thesis
Recommended Citation
Sisov, S.
(2025) Efficient Evaluation of NALA in ConvLSTM for High-Dimensional Time-Series Traffic-Flow Forecasting . CCT College Dublin.
DOI: https://doi.org/10.63227/652.299.93