https://doi.org/10.1007/978-981-99-9521-9_1 is the doi and The sugarcane classification can further be used to find dense and sparse vegetation after the classification is done with deep learning models. The outcomes of this study will help to improve sugarcane categorization techniques and will help farmers, researchers, and agricultural stakeholders make better crop management, yield estimation, and resource optimization decisions in sugarcane farming.By considering variables such as distinct spectral bands, temporal fluctuations, and potential difficulties in separating sugarcane from other land cover types, the objective is to construct and check working of deep learning models for categorizing sugarcane locations using Sentinel-2 data. These findings illustrate the feature extraction utilizing deep learning models with an SVM classifier for sugarcane. . A dataset made from multispectral Sentinel imagery is used for the classification of sugarcane. This approach seeks to separate sugarcane-growing regions from other regions in Sentinel-2 images using VGG19, MobileNetV2, and CNN as feature extractors. Traditional crop categorization methods based on manual inspection or restricted ground-based data gathering are time consuming and frequently inaccurate. As a result, an automated and efficient strategy is suggested that requires the use of remote sensing data and the sugarcane  categorisation for agricultural management and monitoring. capabilities of deep learning algorithms is important.According to the findings, the CNN model with network layers achieves an accuracy of 83.40%. Despite the challenges posed by a limited sugarcane sample size, the 
average overall accuracy of VGG19 as feature extractor is 79.24% and MobileNetV2 
is 72.25%. MobileNetV2 (70.85 and 72.25%) is marginally less competent than every 
other model. Overall VGG19 model as feature extractor (FE) gives better result than 
that of CNN and MobileNetV2 model as there is difference in its precision and 
recall when compared with other model’s precision and recall. The future scope can 
be increased dataset of sugarcane or hyperspectral imagery dataset to increase the 
accuracy when used with deep learning models. Further, the classified sugarcane 
crop can be used for dense and sparse vegetation analysis or variety of sugarcane can 
be found from it.

These findings illustrate the feature extraction utilizing 
deep learning models with an SVM classifier for sugarcane. By considering vari
ables such as distinct spectral bands, temporal fluctuations, and potential difficulties 
in separating sugarcane from other land cover types, the objective is to construct 
and check working of deep learning models for categorizing sugarcane locations 
using Sentinel-2 data. The sugarcane classification can further be used to find dense 
and sparse vegetation after the classification is done with deep learning models. The 
outcomes of this study will help to improve sugarcane categorization techniques 
and will help farmers, researchers, and agricultural stakeholders make better crop 
management, yield estimation, and resource optimization decisions in sugarcane 
farming.This approach seeks to separate sugarcane-growing 
regions from other regions in Sentinel-2 images using VGG19, MobileNetV2, and 
CNN as feature extractors.