Related Experiment Videos
Explainable deep learning for multi-country energy forecasting and sustainability analysis using climate and
Sajjad Ahmad1, Turke Althobaiti2, Muhammad Shoaib Saleem1
1Department of Mathematics, University of Okara, Okara, 56300, Pakistan.
Scientific Reports
|July 15, 2026
Summary
This study introduces an AI framework for multi-country energy forecasting and sustainability assessment. The Wide & Deep MLP model achieved superior accuracy, identifying temporal, climate, and socio-economic factors as key predictors for energy demand.
Area of Science:
- Energy Systems Analysis
- Artificial Intelligence
- Climate Science
Background:
- Predicting energy demand and assessing sustainability are critical due to climate change and socio-economic shifts.
- Current energy systems require advanced tools for accurate forecasting and evaluation.
Purpose of the Study:
- To develop an integrated framework for multi-country energy forecasting and sustainability assessment.
- To compare the performance of various deep learning models for energy demand prediction.
- To enhance the interpretability of forecasting models using explainable artificial intelligence (XAI).
Main Methods:
- Utilized a multi-country dataset (2020-2024) encompassing climate, socio-economic, environmental, and energy variables.
- Implemented and compared deep learning models: Feedforward Neural Network (FNN), Wide & Deep Multi-Layer Perceptron (MLP), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Deep Autoregressive (DeepAR).
- Applied explainable AI techniques, including SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME), for model interpretability.
Main Results:
- The Wide & Deep MLP model demonstrated superior performance with R²=0.9927, MAE=0.0158, RMSE=0.0228, MAPE=3.3%, and WI=0.9918.
- Statistical significance (p < 0.05) confirmed the performance improvements of the best model over others.
- XAI analysis identified temporal features as primary predictors, with climate and socio-economic factors providing significant additional insights.
Conclusions:
- The proposed integrated framework offers accurate, interpretable, and scalable solutions for energy forecasting and sustainable energy planning.
- The study highlights the importance of temporal, climate, and socio-economic data in energy demand prediction.
- The developed sustainability assessment component aids in evaluating national transition readiness and decarbonization efforts.
Related Concept Videos
01:22Multi-input and Multi-variable systems
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
In the absence of...
01:50Global Climate Change
Throughout its ~4.5 billion year history, the Earth has experienced periods of warming and cooling. However, the current drastic increase in global temperatures is well outside of the Earth’s cyclic norms, and evidence for human-caused global climate change is compelling. Paleoclimatology, the study of ancient climate conditions, provides ample evidence for human-caused global climate change by comparing recent conditions with those in the past.
01:16What is Climate?
Climate refers to the prevailing weather conditions in a specific area over an extended period. As the saying goes, “Climate is what you expect. Weather is what you get.” Climate is influenced by geographic factors, such as latitude, terrain, and proximity to bodies of water.