This paper reviews recent advancements in remote sensing image scene classification, proposes a large-scale benchmark dataset named "NWPU-RESISC45," and evaluates several state-of-the-art methods using this dataset. The NWPU-RESISC45 dataset contains 31,500 images, covering 45 scene classes with 700 images per class, addressing limitations of existing datasets such as small scale, lack of image variations, and saturation of accuracy. The dataset is designed to enable the development and evaluation of various data-driven algorithms, particularly deep learning-based methods. The paper also provides a comprehensive review of existing datasets and methods, including handcrafted features, unsupervised feature learning, and deep feature learning. Finally, it evaluates representative methods on the NWPU-RESISC45 dataset, providing a useful performance baseline for future research.This paper reviews recent advancements in remote sensing image scene classification, proposes a large-scale benchmark dataset named "NWPU-RESISC45," and evaluates several state-of-the-art methods using this dataset. The NWPU-RESISC45 dataset contains 31,500 images, covering 45 scene classes with 700 images per class, addressing limitations of existing datasets such as small scale, lack of image variations, and saturation of accuracy. The dataset is designed to enable the development and evaluation of various data-driven algorithms, particularly deep learning-based methods. The paper also provides a comprehensive review of existing datasets and methods, including handcrafted features, unsupervised feature learning, and deep feature learning. Finally, it evaluates representative methods on the NWPU-RESISC45 dataset, providing a useful performance baseline for future research.