Accurate classification of Alzheimer's disease (AD) and its prodromal stage, mild cognitive impairment (MCI), plays a critical role in possibly preventing progression of memory impairment and improving quality of life for AD patients. Among many research tasks, it is of a particular interest to identify noninvasive imaging biomarkers for AD diagnosis. In this paper, we present a robust deep learning system to identify different progression stages of AD patients based on MRI and PET scans. We utilized the dropout technique to improve classical deep learning by preventing its weight coadaptation, which is a typical cause of overfitting in deep learning. In addition, we incorporated stability selection, an adaptive learning factor, and a multitask learning strategy into the deep learning framework. We applied the proposed method to the ADNI dataset, and conducted experiments for AD and MCI conversion diagnosis. Experimental results showed that the dropout technique is very effective in AD diagnosis, improving the classification accuracies by 5.9% on average as compared to the classical deep learning methods.

The increasing penetration of renewable energy makes the traditional N-1 contingency screening highly challenging when a large number of uncertain scenarios need to be combined with contingency screening. In this letter, a novel data-driven method, similar to image-processing technique, is proposed for accelerating N-1 contingency screening of power systems based on the deep convolutional neural network (CNN) method for calculating AC power flows under N-1 contingency and uncertain scenarios. Once the deep CNN is well trained, it has high generalization and works in a nearly computation-free fashion for unseen instances such as topological changes in the N-1 cases and uncertain renewable scenarios. The proposed deep CNN is implemented on several standard IEEE test systems to verify its accuracy and computational efficiency. The proposed study constitutes a solid demonstration of the considerable potential of the data-driven deep CNN in future online applications.

Land cover classification with the focus on chlorophyll-rich vegetation detection plays an important role in urban growth monitoring and planning, autonomous navigation, drone mapping, biodiversity conservation, etc. Conventional approaches usually apply the normalized difference vegetation index (NDVI) for vegetation detection. In this paper, we investigate the performance of deep learning and conventional methods for vegetation detection. Two deep learning methods, DeepLabV3+ and our customized convolutional neural network (CNN) were evaluated with respect to their detection performance when training and testing datasets originated from different geographical sites with different image resolutions. A novel object-based vegetation detection approach, which utilizes NDVI, computer vision, and machine learning (ML) techniques, is also proposed. The vegetation detection methods were applied to high-resolution airborne color images which consist of RGB and near-infrared (NIR) bands. RGB color images alone were also used with the two deep learning methods to examine their detection performances without the NIR band. The detection performances of the deep learning methods with respect to the object-based detection approach are discussed and sample images from the datasets are used for demonstrations.

Natural disasters such as flooding can severely affect human life and property. To provide rescue through an emergency response team, we need an accurate flooding assessment of the affected area after the event. Traditionally, it requires a lot of human resources to obtain an accurate estimation of a flooded area. In this paper, we compared several traditional machine-learning approaches for flood detection including multi-layer perceptron (MLP), support vector machine (SVM), deep convolutional neural network (DCNN) with recent domain adaptation-based approaches, based on a multi-modal and multi-temporal image dataset. Specifically, we used SPOT-5 and RADAR images from the flood event that occurred in November 2000 in Gloucester, UK. Experimental results show that the domain adaptation-based approach, semi-supervised domain adaptation (SSDA) with 20 labeled data samples, achieved slightly better values of the area under the precision-recall (PR) curve (AUC) of 0.9173 and F1 score of 0.8846 than those by traditional machine approaches. However, SSDA required much less labor for ground-truth labeling and should be recommended in practice.

There is an emerging interest in using hyperspectral data for land cover classification. The motivation behind using hyperspectral data is the notion that increasing the number of narrowband spectral channels would provide richer spectral information and thus help improve the land cover classification performance. Although hyperspectral data with hundreds of channels provide detailed spectral signatures, the curse of dimensionality might lead to degradation in the land cover classification performance. Moreover, in some practical applications, hyperspectral data may not be available due to cost, data storage, or bandwidth issues, and RGB and near infrared (NIR) could be the only image bands available for land cover classification. Light detection and ranging (LiDAR) data is another type of data to assist land cover classification especially if the land covers of interest have different heights. In this paper, we examined the performance of two Convolutional Neural Network (CNN)-based deep learning algorithms for land cover classification using only four bands (RGB+NIR) and five bands (RGB+NIR+LiDAR), where these limited number of image bands were augmented using Extended Multi-attribute Profiles (EMAP). The deep learning algorithms were applied to a well-known dataset used in the 2013 IEEE Geoscience and Remote Sensing Society (GRSS) Data Fusion Contest. With EMAP augmentation, the two deep learning algorithms were observed to achieve better land cover classification performance using only four bands as compared to that using all 144 hyperspectral bands.

Satellite remote sensing offers an effective remedy to challenges in ground-based and aerial mapping that have previously impeded quantitative assessments of global seagrass extent. Commercial satellite platforms offer fine spatial resolution, an important consideration in patchy seagrass ecosystems. Currently, no consistent protocol exists for image processing of commercial data, limiting reproducibility and comparison across space and time. Additionally, the radiometric performance of commercial satellite sensors has not been assessed against the dark and variable targets characteristic of coastal waters. This study compared data products derived from two commercial satellites: DigitalGlobe's WorldView-2 and Planet's RapidEye. A single scene from each platform was obtained at St. Joseph Bay in Florida, USA, corresponding to a November 2010 field campaign. A reproducible processing regime was developed to transform imagery from basic products, as delivered from each company, into analysis-ready data usable for various scientific applications. Satellite-derived surface reflectances were compared against field measurements. WorldView-2 imagery exhibited high disagreement in the coastal blue and blue spectral bands, chronically overpredicting. RapidEye exhibited better agreement than WorldView-2, but overpredicted slightly across all spectral bands. A deep convolutional neural network was used to classify imagery into deep water, land, submerged sand, seagrass, and intertidal classes. Classification results were compared to seagrass maps derived from photointerpreted aerial imagery. This study offers the first radiometric assessment of WorldView-2 and RapidEye over a coastal system, revealing inherent calibration issues in shorter wavelengths of WorldView-2. Both platforms demonstrated as much as 97% agreement with aerial estimates, despite differing resolutions. Thus, calibration issues in WorldView-2 did not appear to interfere with classification accuracy, but could be problematic if estimating biomass. The image processing routine developed here offers a reproducible workflow for WorldView-2 and RapidEye imagery, which was tested in two additional coastal systems. This approach may become platform independent as more sensors become available.