A Geoanalytical and AI-Driven Approach for Optimising Biomass Energy Generation from Key Economic Crops in Northeastern Thailand
The transition toward renewable energy sources has become a global priority to address climate change and energy security concerns. Biomass energy, derived from agricultural crops and residues, has emerged as a promising alternative to fossil fuels due to its sustainability and potential to reduce g...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | E3S Web of Conferences |
| Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/29/e3sconf_icfee2025_05005.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The transition toward renewable energy sources has become a global priority to address climate change and energy security concerns. Biomass energy, derived from agricultural crops and residues, has emerged as a promising alternative to fossil fuels due to its sustainability and potential to reduce greenhouse gas emissions. This research study presents the development of a a digital platform for biomass resource management for sugarcane and other economic crops, including rice, maize, oil palm, and cassava, in Northeastern Thailand to support strategic planning for biomass energy generation. The system is designed to optimise the value chain by analysing the cultivation potential of these five crops and geoanalytics within a 50-kilometer radius around biomass power plants, this research analyses the potential of each biomass crop at three levels—high, medium, and low—reflecting the feasibility of converting agricultural residues into energy. Historical data over the past five years were utilised to assess the potential energy output from these crops. Furthermore, artificial intelligence (AI) technologies were employed to forecast key sugarcane parameters, including cane yield, cane cultivation area, and production output. The research involved evaluating 18 AI models, comparing their performance using metrics such as Mean Absolute Error (MAE), Coefficient of Determination (R2), and Root Mean Square Error (RMSE), to identify the most accurate model for long-term forecasting. A 10-year prediction was conducted to provide actionable insights. The system serves as a valuable tool for government agencies to enhance and promote policies that leverage Northeastern Thailand’s key economic crops as sustainable biomass resources, contributing to clean energy generation and added economic value. |
|---|---|
| ISSN: | 2267-1242 |