مجاميع المعرفة
Volume 11, Numéro 1, Pages 218-236
2025-06-06

Forecasting Of Co2 Emissions In Algeria (2000-2030): A Hybrid Arima-lstm



Authors : Toul Hamza . Sahed Abdelkader .

Abstract

The study analyzed Algeria's CO₂ emissions from 2000 to 2030 by integrating the ARIMA model, which captures linear trends, with the LSTM network, known for detecting complex nonlinear patterns. This hybrid approach significantly outperformed traditional models by delivering highly accurate predictions, as evidenced by substantial reductions in error metrics—including a 58.2% decrease in MAE, a 58.7% drop in MAPE, a 71.4% reduction in MSE, and a 46.5% decline in RMSE. While emissions are projected to continue rising until 2030, the study anticipates a potential slight decline due to the adoption of renewable energy policies and the indirect effects of global crises. Overall, the findings underscore the effectiveness of combining artificial intelligence techniques with traditional statistical methods for enhancing environmental forecasting accuracy, particularly in fossil fuel-dependent nations, and emphasize the urgent need to transition towards cleaner energy sources amid evolving economic and political challenges.

Keywords

Carbon dioxide emissions ; hybrid approach ; ARIMA ; LSTM ; Algeria

Les articles similaires

A Structural Var Analysis Of Energy Consumption, Economic Growth And Co2 Emissions: Evidence From Algeria. تحليل هيكلي باستعمال نموذجvar لاستهلاك الطاقة، النمو الاقتصادي وانبعاثات ثاني أكسيد الكربون. دراسة حالة الجزائر. Analyse Par Le Modèle Svar De La Consommation D'énergie, De La Croissance économique Et Des émissions De Co2. Le Cas De L'algérie.

Hicham Ayad .  Moussa Chenini . 
pages 101-114.

الكفاءة التنبؤية للنماذج الهجينة في أسواق المال الناشئة: نموذج Garch-lstm وتطبيقه على بيانات عائدات الاسواق الخليجية للفترة 2020-2024؛ The Predictive Efficiency Of Hybrid Models In Emerging Financial Markets: A Garch–lstm Model And Its Application To Gulf Market Return Data For The Period 2020–2024

معروف جيلالي . 
ص 198-214.

Forecasting Government Final Consumption Expenditure In Algeria: Comparative Performance Of The Arima (box-jenkins) Model And Artificial Neural Networks (mlp & Lstm) Up To 2034

Lagoune Salim . 
pages 13-27.

Forecasting Of Co2 Emissions In Algeria Using Discrete Wavelet Transform –based Autoregressive Integrated Moving Average Models

Sahed Abdelkader .  Mékidiche Mohammed .  Kahoui Hacene . 
pages 443-449.

The Impact Of Monetary And Fiscal Policies On Co2 Emissions In Algeria During The Period (1990-2025)

Lachi Oualid .  Bechir Sabiha . 
pages 335-349.

Formats de citation