The Advances, Challenges, and Perspectives in the field of vegetation Classification with emphasis on Horticultural Species Using machine learning Methods
2
Assistant Professor of Department of Geomatics Engineering, Faculty of Civil Engineering, Babol Noshirvani University of Technology
3
3 Ph.D Student
10.22059/eoge.2026.392478.1172
Abstract
This research examines vegetation classification, with a specific focus on mapping agricultural and horticultural crops. It explores topics such as land use changes, plant diversity, and the distribution of horticultural crops. The study highlights the role of satellite data in enabling farmers and natural resource managers to make informed decisions for sustainable agriculture and improved food security. Its findings can also help agricultural policymakers, environmental organizations, and territorial planners make informed decisions at the macro level for land management and ensuring food security. Machine learning techniques are widely used for classifying remote sensing data due to their ability to handle large, complex datasets. These methods enable the creation of accurate and efficient predictive models for vegetation and land image classification, significantly improving the speed and accuracy of data analysis. Research findings suggest that classification accuracy is influenced by factors such as image type, study area, and the specific algorithm employed. In general, it can be stated that 30% of the reviewed studies in vegetation cover classification are based on features, including indices, textures, and elevation data. At the same time, the remainder utilize various classification methods. Among these, 6% employ unsupervised methods, and 94% use supervised methods, including hierarchical (46%), mathematical (24%), and layer models (24%). In terms of vegetation cover studies, 31% focus on horticultural products, 27% on agricultural products, and 42% on other vegetation types. These findings underscore the importance of integrating diverse methods, features, and satellite data to achieve accurate and scalable vegetation classification. In addition to providing a comprehensive review, with temporal and graphical analyses and examining methods and data from different perspectives, this article provides a new classification and overview of studies in this field that can guide decision-makers and researchers in the field of resource management and food security.
Hosseinnasab Bisheh, S. M. , kiani, A. and Mohammadi, M. (2026). The Advances, Challenges, and Perspectives in the field of vegetation Classification with emphasis on Horticultural Species Using machine learning Methods. Earth Observation and Geomatics Engineering, 9(1), -. doi: 10.22059/eoge.2026.392478.1172
MLA
Hosseinnasab Bisheh, S. M. , , kiani, A. , and Mohammadi, M. . "The Advances, Challenges, and Perspectives in the field of vegetation Classification with emphasis on Horticultural Species Using machine learning Methods", Earth Observation and Geomatics Engineering, 9, 1, 2026, -. doi: 10.22059/eoge.2026.392478.1172
HARVARD
Hosseinnasab Bisheh, S. M., kiani, A., Mohammadi, M. (2026). 'The Advances, Challenges, and Perspectives in the field of vegetation Classification with emphasis on Horticultural Species Using machine learning Methods', Earth Observation and Geomatics Engineering, 9(1), pp. -. doi: 10.22059/eoge.2026.392478.1172
CHICAGO
S. M. Hosseinnasab Bisheh , A. kiani and M. Mohammadi, "The Advances, Challenges, and Perspectives in the field of vegetation Classification with emphasis on Horticultural Species Using machine learning Methods," Earth Observation and Geomatics Engineering, 9 1 (2026): -, doi: 10.22059/eoge.2026.392478.1172
VANCOUVER
Hosseinnasab Bisheh, S. M., kiani, A., Mohammadi, M. The Advances, Challenges, and Perspectives in the field of vegetation Classification with emphasis on Horticultural Species Using machine learning Methods. Earth Observation and Geomatics Engineering, 2026; 9(1): -. doi: 10.22059/eoge.2026.392478.1172
)