When Simpler Wins: Facebooks Prophet vs LSTM for Air Pollution Forecasting in Data-Constrained Northern Nigeria

TL;DR

This study compares Facebook Prophet and LSTM models for air pollution forecasting in Northern Nigeria, finding that simpler models like Prophet can outperform LSTM in data-scarce, trend-driven environments, guiding resource-efficient decision-making.

Contribution

It provides a systematic comparison of Prophet and LSTM in low-resource settings, highlighting the effectiveness of simpler models for air pollution forecasting.

Findings

Prophet matches or exceeds LSTM accuracy in trend-dominated data.

LSTM performs better with abrupt structural changes.

Simpler models are effective in data-constrained environments.

Abstract

Air pollution forecasting is critical for proactive environmental management, yet data irregularities and scarcity remain major challenges in low-resource regions. Northern Nigeria faces high levels of air pollutants, but few studies have systematically compared the performance of advanced machine learning models under such constraints. This study evaluates Long Short-Term Memory (LSTM) networks and the Facebook Prophet model for forecasting multiple pollutants (CO, SO2, SO4) using monthly observational data from 2018 to 2023 across 19 states. Results show that Prophet often matches or exceeds LSTM's accuracy, particularly in series dominated by seasonal and long-term trends, while LSTM performs better in datasets with abrupt structural changes. These findings challenge the assumption that deep learning models inherently outperform simpler approaches, highlighting the importance of model-data alignment. For policymakers and practitioners in resource-constrained settings, this work supports adopting context-sensitive, computationally efficient forecasting methods over complexity for its own sake.