DEVELOPMENT OF THE SUITABILITY OF SOLAR AND WIND ENERGY POTENTIAL AREAS IN THE SOUTHEAST ASIA REGION BASED ON MACHINE LEARNING AND REMOTE SENSING
<p align="justify"> The increase in population in Southeast Asia has led to a doubling of energy needs in 2040. If the use of non-renewable energy is still massively used to meet this need, it will have a dangerous negative impact globally. Therefore, there is a need for an energy tr...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Project |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/73465 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | <p align="justify"> The increase in population in Southeast Asia has led to a doubling of energy needs in 2040. If the use of non-renewable energy is still massively used to meet this need, it will have a dangerous negative impact globally. Therefore, there is a need for an energy transition to renewable energy to meet energy needs in Southeast Asia. This requires data and information regarding the distribution of potential areas of solar energy and wind energy in Southeast Asia. This final project was made with the aim of getting results in the form of point distribution and potential areas of solar energy and wind energy using machine learning and remote sensing methods. It is hoped that the results of this final project can become input for the government in designing policies to meet energy needs through the renewable energy transition. The methodology used is literature study, data processing, and analysis. Data processing that will be carried out for processing the distribution of potential points, and potential areas of renewable energy uses machine learning algorithms considering various criteria or parameters. The results of the data processing are 256 potential solar energy points, 90 wind energy potential points, machine learning results of solar energy potential points with Area Under Curve (AUC) values in the excellent classification class, results machine learning of wind energy potential points with AUC in the good to excellent classification class, machine learning results of existing solar energy points with AUC values in the fair classification class, machine learning results of existing wind energy points with AUC in the poor to fair classification class. This shows that the resulting potential points are able to identify and estimate the distribution of potential areas better than the existing points.
|
|---|