|
Assessment of machine learning on sugarcane classification using Landsat-8 and Sentinel-2 satellite imagery |
|---|---|
| รหัสดีโอไอ | |
| Creator | Pipat Reungsang |
| Title | Assessment of machine learning on sugarcane classification using Landsat-8 and Sentinel-2 satellite imagery |
| Contributor | Teerapat Butkhot |
| Publisher | Asia-Pacific Journal of Science and Technology |
| Publication Year | 2564 |
| Journal Title | Asia-Pacific Journal of Science and Technology |
| Journal Vol. | 26 |
| Journal No. | 4 |
| Page no. | 11-Jan |
| Keyword | Sugarcane, Machine learning, Support vector machine, Random forest, Maximum likelihood |
| URL Website | https://www.tci-thaijo.org/index.php/APST |
| Website title | https://so01.tci-thaijo.org/index.php/APST/article/view/249466 |
| ISSN | 2539-6293 |
| Abstract | Agriculture and agricultural product development are important aspects of a country's economic development. Sugarcane is one of the key industrial crops in Thailand, Brazil, China, and India. Therefore, monitoring sugarcane growth and harvest is important for evaluating yield, optimizing logistic operations, and forecasting crop productivity. To monitor sugarcane growth more effectively and efficiently, this study aimed to classify the sugarcane cultivation regions in Chuenchom District, Maha Sarakham Province, Thailand, using Landsat-8 and Sentinel-2 satellite images. To this end, three algorithms were used for classification: support vector machine (SVM), random forest (RF), and maximum likelihood (ML). A combination of parameter sets using four bands (red, green, blue, and NIR) and two vegetation indices: normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI) was set up for the classification. The overall accuracy and kappa coefficient values were computed to validate the classification results with visual interpretation of high-resolution images. Results from the study showed that RF outperformed the SVM and ML classification techniques with overall accuracy and kappa coefficient values of 75.93 and 0.616, respectively, for Landsat-8 images and 78.60 and 0.656, respectively, for Sentinel-2 images. Specifically, RF classification with red, green, blue, and NIR provided the highest accuracy for the Landsat-8 images, while RF classification with red, green, blue, and NDVI proved to be the most accurate for the Sentinel-2 images. In summary, both Landsat-8 and Sentinel-2 satellite images have great potential for sugarcane mapping using remote sensing. |
