|
|
|
 |
Search published articles |
 |
|
Showing 2 results for Ebrahimzadeh
Mahsa Tekyeh-Nejad, - Ata Allah Ebrahimzadeh, - Maliheh Ahmadi,
Volume 11, Issue 1 (6-2023)
Abstract
Hyperspectral image classification is a crucial aspect of remote sensing image analysis. Deep learning methods have been successfully used to classify remote sensing data. In recent years, convolutional neural networks (CNNs) have been significantly used in hyperspectral image classification, which has tried to overcome the computational and processing challenges of hyperspectral data. By increasing the number of parameters and layers of convolutional neural networks, their efficiency in solving complex problems decreases. For this reason, in this article, a new architecture of convolutional neural networks has been introduced, this network has a good performance and reduces the computing time.
In this paper, we introduce a novel CNN that utilizes spectral-spatial information as input and employs principal component analysis (PCA) to reduce spectral bands. To prevent overfitting, we combine batch normalization and dropout techniques. Our two-dimensional CNN includes convolutional layers, pooling layers, and fully connected layers. We also incorporate PCA and patch selection to enhance the accuracy of our model.
To evaluate the effectiveness of our proposed model, we conducted experiments on three datasets: Indian Pines, Pavia University, and Salinas. Our simulation results demonstrate that our model achieves a classification accuracy of 100%, with less training time and complexity than existing models.
Somayeh Ebrahimzadeh, Masoud Soleimani, Sara Atarchi, Mehdi Saadat Novin, Seyed Hassan Shabanian,
Volume 11, Issue 3 (12-2023)
Abstract
Abstract
Soil erosion has devastating and irreversible consequences for human life. Hence, supportive measures are necessary to reduce and control soil erosion in the most affected areas. Achieving this goal requires detecting severely soil-eroded areas (SSEA), because it is not possible to implement supportive measures throughout the area. Detection of SSEA using field-based methods is very difficult, costly, and faces various limitations. To deal with it, taking advantage of remote sensing data capabilities has been widely attention today. The interaction of the radar signal with the surface roughness changes can be evaluated through Interferometric Synthetic Aperture Radar (InSAR) coherence changes. In fact, soil erosion causes the movement of soil particles and decreases InSAR coherence. Accordingly, the aim of this study is to detect SSEA in Khuzestan province as one of the areas with high soil erosion rates using a processed time series of Sentinel-1 InSAR coherence from 2018 to 2020. The map of SSEA was obtained by detecting and excluding other effective factors causing InSAR coherence reduction, such as water, vegetation, and topography. Validation of the results based on comparison with the valid soil erosion map of the study area revealed that 86% of SSEA detected by the proposed method are consistent with the ground reality. Also, the compatibility of SSEA with the genus and resistance of different geological formations in the region emphasizes the validity of the results.
|
|
