A machine learning approach to identifying climate change drivers in Africa’s bioenergy sector
Abstract This study employed machine learning techniques to analyze the key bioenergy sources related to climate change. By utilizing traditional cross-validation and spatial block cross-validation, significant variables were identified. Shape Additive Explanation (SHAP) analysis further revealed th...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-07-01
|
| Series: | Discover Sustainability |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s43621-025-01475-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract This study employed machine learning techniques to analyze the key bioenergy sources related to climate change. By utilizing traditional cross-validation and spatial block cross-validation, significant variables were identified. Shape Additive Explanation (SHAP) analysis further revealed that bagasse consumption negatively correlates with temperature changes, suggesting its potential as a sustainable energy alternative. Conversely, charcoal consumption, charcoal production, and solid biofuel production exhibited a warming effect, emphasizing their role in exacerbating climate change. This finding underscores the urgent need for sustainable energy policies, including improvements in kiln technology for charcoal production and increased investment in renewable energy sources such as solar, wind, and hydropower. Potential spatial dependencies or geostatistical components were not explicitly modeled in the training phase when identifying key bioenergy indicators driving warming in Africa. Future research will aim to incorporate spatially structured models to capture localized variations within the statistical learning framework. |
|---|---|
| ISSN: | 2662-9984 |