Redirigiendo al acceso original de articulo en 15 segundos...
ARTÍCULO
TITULO

Enhancing Crop Classification Accuracy through Synthetic SAR-Optical Data Generation Using Deep Learning

Ali Mirzaei    
Hossein Bagheri and Iman Khosravi    

Resumen

Crop classification using remote sensing data has emerged as a prominent research area in recent decades. Studies have demonstrated that fusing synthetic aperture radar (SAR) and optical images can significantly enhance the accuracy of classification. However, a major challenge in this field is the limited availability of training data, which adversely affects the performance of classifiers. In agricultural regions, the dominant crops typically consist of one or two specific types, while other crops are scarce. Consequently, when collecting training samples to create a map of agricultural products, there is an abundance of samples from the dominant crops, forming the majority classes. Conversely, samples from other crops are scarce, representing the minority classes. Addressing this issue requires overcoming several challenges and weaknesses associated with the traditional data generation methods. These methods have been employed to tackle the imbalanced nature of training data. Nevertheless, they still face limitations in effectively handling minority classes. Overall, the issue of inadequate training data, particularly for minority classes, remains a hurdle that the traditional methods struggle to overcome. In this research, we explore the effectiveness of a conditional tabular generative adversarial network (CTGAN) as a synthetic data generation method based on a deep learning network, for addressing the challenge of limited training data for minority classes in crop classification using the fusion of SAR-optical data. Our findings demonstrate that the proposed method generates synthetic data with a higher quality, which can significantly increase the number of samples for minority classes, leading to a better performance of crop classifiers. For instance, according to the G-mean metric, we observed notable improvements in the performance of the XGBoost classifier of up to 5% for minority classes. Furthermore, the statistical characteristics of the synthetic data were similar to real data, demonstrating the fidelity of the generated samples. Thus, CTGAN can be employed as a solution for addressing the scarcity of training data for minority classes in crop classification using SAR?optical data.

 Artículos similares

       
 
Clinton Beckford, Donovan Campbell and David Barker    
Members of the genus Dioscorea, food yams, were introduced to Jamaica from Africa during the slave era and have remained a staple in local diets and national cuisine. Yam cultivation has also been an important economic activity providing employm... ver más
Revista: Sustainability

 
David E. Ervin, Leland L. Glenna and Raymond A. Jussaume, Jr.    
The development of genetically engineered (GE) crops has focused predominantly on enhancing conventional pest control approaches. Scientific assessments show that these GE crops generally deliver significant economic and some environmental benefits over ... ver más
Revista: Sustainability

 
Emile A. Frison, Jeremy Cherfas and ToHodgkin    
Agricultural biodiversity has hitherto been valued almost exclusively as a source of traits that can be used in scientific breeding programs to improve the productivity of crop varieties and livestock breeds. We argue that it can make a far greater contr... ver más
Revista: Sustainability

 
Frederick A. Armah, David O. Yawson, Genesis T. Yengoh, Justice O. Odoi and Ernest K. A. Afrifa    
Sub-Sahara Africa is considered to be most vulnerable to climate variability including flooding. The frequency and severity of floods in Northern Ghana over the last decade has increased considerably. Through qualitative modelling the paper explores the ... ver más
Revista: Water