Downloads: 10 | Views: 220 | Weekly Hits: ⮙1 | Monthly Hits: ⮙2
Informative Article | Geography | India | Volume 13 Issue 9, September 2024 | Popularity: 5.6 / 10
Deep Learning for Land Use and Land Cover Classification Based on Optical Earth Observation Data: A Comprehensive Review
Dr. Prakash Rajeshyam Konka
Abstract: Land Use and Land Cover (LULC) classification plays a crucial role in understanding and monitoring changes to Earth's landscapes, which are essential for urban planning, environmental management, agriculture, and biodiversity conservation. As human activities such as urbanization and deforestation continue to transform land cover, accurate and timely LULC classification becomes increasingly important. In recent years, optical Earth observation (EO) data from satellite missions like Landsat and Sentinel - 2 have provided high - resolution imagery that captures the dynamic changes in land surfaces. However, traditional methods for LULC classification, such as decision trees or support vector machines (SVMs), require extensive manual feature extraction and tend to struggle with large datasets and complex landscapes. This has led to the adoption of deep learning (DL) approaches, which are more effective at handling the complexities of EO data. Deep learning models, particularly convolutional neural networks (CNNs), have gained prominence in LULC classification because of their ability to automatically learn hierarchical spatial features directly from raw image data. CNNs excel at capturing intricate spatial patterns, allowing them to outperform traditional methods in terms of accuracy and automation. Additionally, other DL architectures, such as recurrent neural networks (RNNs) and hybrid models, have further improved classification performance, particularly for multi - temporal data, which is common in EO datasets. This review examines the current state of DL techniques for LULC classification, focusing on key algorithms, such as CNNs and RNNs, frequently used EO datasets, and the challenges researchers face, such as imbalanced data, high computational costs, and model interpretability. Finally, it highlights future research directions, including unsupervised learning, improving class imbalance, and enhancing the interpretability of DL models, which will further advance the field of LULC classification.
Keywords: Land Use and Land Cover (LULC), optical Earth observation, deep learning, convolutional neural networks (CNNs), recurrent neural networks (RNNs), classification, satellite imagery, urbanization
Edition: Volume 13 Issue 9, September 2024
Pages: 1559 - 1563
DOI: https://www.doi.org/10.21275/SR24926074847
Please Disable the Pop-Up Blocker of Web Browser