An accurate identification of oil spill types is the basis of determining the source of leakage, evaluating the potential damage, and deciding a plan of responses for an oil spill event. Despite sufficient studies that interpreted and analyzed hyperspectral data of oil spills, these studies that identify or classify oil spill types is rather limited. Aiming at identifying different types of oil spills, this article analyses the reflectance spectra obtained from high-resolution hyperspectral sensors using multiple machine learning methods. Four types of machine learning models are applied in this article: random forest; support vector machine (SVM); and deep neural network (DNN); and DNN with differential pooling (DP-DNN). The training and testing data are collected by field experiments under different environmental condition in order to verify the robustness of the machine learning models. The characteristics of reflectance is briefly described, and the results conform with results from previous studies. The performances of the machine learning models are evaluated and compared in terms of both accuracy of prediction and computational complexity. The results indicate that the two DNN models are able to achieve the most accurate prediction among the four machine learning models at the cost of more computation. The SVM model, or the proposed DP-DNN model may be a favorable choice when training time is limited.

Urban commerce and its distribution have always been an important part of urban research. However, most previous studies were based on statistical data and did not reflect real street experience. Thanks to the Street View image and deep learning technology, researchers are able to carry out large scale studies from real human visual experience. In this article, we aim at sensing the commercial spaces in cities. In order to achieve this ultimate goal, deep learning is applied to process the raw data of Street View image. We disassemble the goal into three tasks: firstly, obtaining all the Street View images in a specific area; then classifying the Street View images according to the commercial facilities in it; and finally creating a visualization of the detected data into a map. For the first task, we get the road network coordinate information from the openstreetmap (OSM) website, set the sampling point on the road, and then download the Street View images of the sampling points’ coordinate through the API provided by Baidumap. For the second task, we adopt a two-level learning strategy rather than directly using Deep Convolutional Neural Network for classification. For the final task, we choose the heat map as the expression of the results and draw the map by the existing GIS software. Furthermore, the results from this study can be conveniently combined with other data because of the use of street-network-based data structure. An application of this method combines with street-network data, the calculation of a city’s 15-minute commercial service circle coverage is also shown in this study.

Cyclone detection is a classic yet developing topic. Various methods have been developed for the purpose of cyclone detection based on sea level pressure, cloud imagery, wind field, etc. In this study, a data fusion approach that utilizes the data productions from multiple remote sensors is presented. A deep-learning-based object detection algorithm was adopted to form a global-scale cyclone detection model. Wind field data obtained from Mean Wind Field-Advanced Scatterometer (MWF-ASCAT) was integrated with the rainfall intensity data obtained from Global Precipitation Measurement (GPM) as the dataset for model training and testing. Feature pyramid network (FPN), which was designed for small target detection, was integrated with faster-regions with convolutional neural network (faster-RCNN) to detect the cyclones within the fused dataset. The proposed model consists of two modules: a feature extractor and region proposal network (RPN) based on FPN that searches for the potential areas of cyclones within the fused dataset, and a regions of interests (ROI) processor that calibrate the locations of cyclone regions through a fully-connected neural network and a bounding box regression. An ablation experiment was also designed in the study in order to verify the necessity of data fusion. The results from ablation experiment suggested that the wind field data provided more contribution in the cyclone detection than the precipitation data.