Search

Long-term trends in groundwater levels over the contiguous United States (CONUS) have been investigated for water resource management. Numerical modeling or remotely sensed data are frequently utilized as analytical tools; however, observational data on the CONUS have rarely been used. This study explored observational groundwater levels at 642 wells across the CONUS from 1990 to 2019. Wells with less than 30% of missing data over 30 years were selected, and trends in their groundwater levels were assessed using a Seasonal Mann-Kendall’s test and Sen’s slope. Trends in three climatic variables (precipitation, maximum temperature, and minimum temperature) were simultaneously analyzed. The results showed that trends and the degree of change in groundwater levels varied spatially across the CONUS and were not correlated with those of the three climatic variables. The degree of change in the groundwater levels was small for the majority of wells (> 85%), with less than the absolute value of one Sen’s slope. Wells with more than the absolute value of one Sen’s slope showed declining trends in groundwater levels, emphasizing the need for groundwater protection. This study was limited in explaining the major drivers of groundwater fluctuations across the CONUS owing to the complexity of natural and anthropogenic drivers. Thus, it was concluded that multiple tools should be concurrently used to interpret groundwater dynamics across the CONUS to secure groundwater resources.

The deep learning technique has recently led to significant improvement in object detection accuracy. In many applications, object detection is performed on video data consisting of a sequence of two-dimensional (2D) image frames. Numerous object detection schemes have been designed to detect objects independently in each video frame. Though temporal information within adjacent image frames can be exploited in subsequent object tracking stage, it has been shown that the object detection accuracy can be significantly improved by exploiting the temporal structure in the image sequence in the object detection stage. In this paper, we propose a novel video object detection method that exploits both the motion context inferred from the adjacent frames and the spatio-temporal features aggregated over the image sequence. First, correlation between the spatial feature maps over two adjacent frames are computed and the embedding vector, representing the motion context, is obtained by encoding the $N$ correlation maps using long short term memory (LSTM). In addition to utilizing the motion context, the spatial feature maps for ( $N+1$ ) consecutive frames are aggregated to boost the quality of the feature map. The gated attention network is employed to selectively combine the temporal feature maps based on their relevance to the feature map in the present image frame. While most video object detectors have been developed for two-stage object detectors, our proposed idea applies to one-stage detectors with the advantage of low computational complexity in practical real-time applications. Our numerical evaluation conducted on the ImageNet object detection from video (VID) dataset demonstrates that our proposed network achieves significant performance gain over the baseline algorithms and outperforms the existing one-stage video object detectors.

Recently, automatic visual data understanding from drone platforms becomes highly demanding. To facilitate the study, the Vision Meets Drone Object Detection in Image Challenge is held the second time in conjunction with the 17-th International Conference on Computer Vision (ICCV 2019), focuses on image object detection on drones. Results of 33 object detection algorithms are presented. For each participating detector, a short description is provided in the appendix. Our goal is to advance the state-of-the-art detection algorithms and provide a comprehensive evaluation platform for them. The evaluation protocol of the VisDrone-DET2019 Challenge and the comparison results of all the submitted detectors on the released dataset are publicly available at the website: http: //www.aiskyeye.com/. The results demonstrate that there still remains a large room for improvement for object detection algorithms on drones.