Spectral characteristics play an important role in the classification of oil film, but the presence of too many bands can lead to information redundancy and reduced classification accuracy. In this study, a classification model that combines spectral indices-based band selection (SIs) and one-dimensional convolutional neural networks was proposed to realize automatic oil films classification using hyperspectral remote sensing images. Additionally, for comparison, the minimum Redundancy Maximum Relevance (mRMR) was tested for reducing the number of bands. The support vector machine (SVM), random forest (RF), and Hu’s convolutional neural networks (CNN) were trained and tested. The results show that the accuracy of classifications through the one dimensional convolutional neural network (1D CNN) models surpassed the accuracy of other machine learning algorithms such as SVM and RF. The model of SIs+1D CNN could produce a relatively higher accuracy oil film distribution map within less time than other models.

The Local Climate Zone (LCZ) scheme provides researchers with a standard method to monitor the Urban Heat Island (UHI) effect and conduct temperature studies. How to generate reliable LCZ maps has therefore become a research focus. In recent years, researchers have attempted to use Landsat imagery to delineate LCZs and generate maps worldwide based on the World Urban Database and Access Portal Tools (WUDAPT). However, the mapping results obtained by the WUDAPT method are not satisfactory. In this paper, to generate more accurate LCZ maps, we propose a novel Convolutional Neural Network (CNN) model (namely, LCZ-CNN), which is designed to cope with the issues of LCZ classification using Landsat imagery. Furthermore, in this study, we applied the LCZ-CNN model to generate LCZ mapping results for China's 32 major cities distributed in various climatic zones, achieving a significantly better accuracy than the traditional classification strategies and a satisfactory computational efficiency. The proposed LCZ-CNN model achieved satisfactory classification accuracies in all 32 cities, and the Overall Accuracies (OAs) of more than half of the cities were higher than 80%. We also designed a series of experiments to comprehensively analyze the proposed LCZ-CNN model, with regard to the transferability of the network and the effectiveness of multiseasonal information. It was found that the first convolutional stage, corresponding to low-level features, shows better transferability than the second and third convolutional stages, which extract high-level and more image-or task-oriented features. It was also confirmed that the multi-seasonal information can improve the accuracy of LCZ classification. The thermal characteristics of the different LCZ classes were also analyzed based on the mapping results for China's 32 major cities, and the experimental results confirmed the close relationship between the LCZ classes and the magnitude of the Land Surface Temperature (LST).

No abstract