More Like this

1. Machine Learning Based Algorithms for Global Dust Aerosol Detection from Satellite Images: Inter-Comparisons and Evaluation

   https://doi.org/10.3390/rs13030456  

   Lee, Jangho ; Shi, Yingxi Rona ; Cai, Changjie ; Ciren, Pubu ; Wang, Jianwu ; Gangopadhyay, Aryya ; Zhang, Zhibo ( February 2021 , Remote Sensing)

   null (Ed.)

   Identifying dust aerosols from passive satellite images is of great interest for many applications. In this study, we developed five different machine-learning (ML) based algorithms, including Logistic Regression, K Nearest Neighbor, Random Forest (RF), Feed Forward Neural Network (FFNN), and Convolutional Neural Network (CNN), to identify dust aerosols in the daytime satellite images from the Visible Infrared Imaging Radiometer Suite (VIIRS) under cloud-free conditions on a global scale. In order to train the ML algorithms, we collocated the state-of-the-art dust detection product from the Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) with the VIIRS observations along the CALIOP track. The 16 VIIRS M-band observations with the center wavelength ranging from deep blue to thermal infrared, together with solar-viewing geometries and pixel time and locations, are used as the predictor variables. Four different sets of training input data are constructed based on different combinations of VIIRS pixel and predictor variables. The validation and comparison results based on the collocated CALIOP data indicate that the FFNN method based on all available predictor variables is the best performing one among all methods. It has an averaged dust detection accuracy of about 81%, 89%, and 85% over land, ocean and whole globe, respectively, compared with collocated CALIOP. When applied to off-track VIIRS pixels, the FFNN method retrieves geographical distributions of dust that are in good agreement with on-track results as well as CALIOP statistics. For further evaluation, we compared our results based on the ML algorithms to NOAA’s Aerosol Detection Product (ADP), which is a product that classifies dust, smoke, and ash using physical-based methods. The comparison reveals both similarity and differences. Overall, this study demonstrates the great potential of ML methods for dust detection and proves that these methods can be trained on the CALIOP track and then applied to the whole granule of VIIRS granule. 

   more » « less
2. AutoShare: Virtual community solar and storage for energy sharing

   https://doi.org/10.1186/s42162-021-00144-w  

   Lee, Stephen ; Shenoy, Prashant ; Ramamritham, Krithi ; Irwin, David ( July 2021 , Energy Informatics)

   Residential solar installations are becoming increasingly popular among homeowners. However, renters and homeowners living in shared buildings cannot go solar as they do not own the shared spaces. Community-owned solar arrays and energy storage have emerged as a solution, which enables ownership even when they do not own the property or roof. However, such community-owned systems do not allow individuals to control their share for optimizing a home’s electricity bill. To overcome this limitation, inspired by the concept of virtualization in operating systems, we propose virtual community-owned solar and storage—a logical abstraction to allow individuals to independently control their share of the system. We argue that such individual control can benefit all owners and reduce their reliance on grid power. We present mechanisms and algorithms to provide a virtual solar and battery abstraction to users and understand their cost benefits. In doing so, our comparison with a traditional community-owned system shows that our AutoShare approach can achieve the same global savings of 43% while providing independent control of the virtual system. Further, we show that independent energy sharing through virtualization provides an additional 8% increase in savings to individual owners.

    

   more » « less
3. Virtual cultural landscapes: Geospatial visualizations of past environments

   https://doi.org/10.1002/arp.1830  

   Monteleone, Kelly ; Thompson, Amy E. ; Prufer, Keith M. ( May 2021 , Archaeological Prospection)

   Recent advances in spatial and remote sensing technology have led to new methods in archaeological site identification and reconstruction, allowing archaeologists to investigate landscapes and sites on multiple scales. These remotely conducted surveys create virtual cultural landscapes and seascapes that archaeologists and the public interact with and experience, often better than traditional maps. Our study examines landscape reconstruction and archaeological site classifications from a phenomenological and human behavioural ecology (HBE) perspective. HBE aims to reconstruct how humans interacted with these places as part of their active and passive decision making. Through temporal reconstructions, archaeologists and others can experience and interpret past landscapes and subtle changes in cultural land‐ and seascapes. Here, we evaluate the use of remotely sensed data (lidar, satellite imagery, sonar, radar, etc.) for developing virtual cultural landscapes while also incorporating Indigenous perspectives. Our study compares two vastly different landscapes and perspectives: a seascape in coastal Alaska, USA, and a neotropical jungle in Belize, Central America. By incorporating ethnographic accounts, oral histories, Indigenous traditional knowledge and community engagement, archaeologists can develop new tools to understand decisions made in the past, especially pertaining to settlement selection and resource procurement. These virtual reconstructions become cognitive images of a possible place that the observer experiences. Virtual cultural landscapes allow archaeologists to reproduce landscapes that may otherwise be invisible and present them to different publics. These processes elucidate how landscapes changed over time based on human behaviours while simultaneously allowing archaeologists to engage with Indigenous communities and the public in the protection of prehistoric and historic sites and sacred spaces through cultural heritage management.

    

   more » « less
4. Deep Depth Estimation from Visual-Inertial SLAM

   https://doi.org/10.1109/IROS45743.2020.9341448  

   Sartipi, Kourosh ; Do, Tien ; Ke, Tong ; Vuong, Khiem ; Roumeliotis, Stergios I. ( October 2020 , 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS))

   null (Ed.)

   This paper addresses the problem of learning to complete a scene's depth from sparse depth points and images of indoor scenes. Specifically, we study the case in which the sparse depth is computed from a visual-inertial simultaneous localization and mapping (VI-SLAM) system. The resulting point cloud has low density, it is noisy, and has nonuniform spatial distribution, as compared to the input from active depth sensors, e.g., LiDAR or Kinect. Since the VI-SLAM produces point clouds only over textured areas, we compensate for the missing depth of the low-texture surfaces by leveraging their planar structures and their surface normals which is an important intermediate representation. The pre-trained surface normal network, however, suffers from large performance degradation when there is a significant difference in the viewing direction (especially the roll angle) of the test image as compared to the trained ones. To address this limitation, we use the available gravity estimate from the VI-SLAM to warp the input image to the orientation prevailing in the training dataset. This results in a significant performance gain for the surface normal estimate, and thus the dense depth estimates. Finally, we show that our method outperforms other state-of-the-art approaches both on training (ScanNet [1] and NYUv2 [2]) and testing (collected with Azure Kinect [3]) datasets. 

   more » « less
5. Evaluation of high‐resolution DEMs from satellite imagery for geomorphic applications: A case study using the SETSM algorithm

   https://doi.org/10.1002/esp.5263  

   Atwood, Abra ; West, A. Joshua ( November 2021 , Earth Surface Processes and Landforms)

   High‐resolution digital elevation models (DEMs) have revolutionized research in geomorphology by allowing for detailed quantitative analysis of Earth's surface. Satellite stereo images offer the promise of expanding the availability of high‐resolution DEMs over broad areas, but rigorous evaluation of the scientific application of these datasets remains limited. In this study, we consider DEMs built using stereo pairs of high‐resolution (0.5 m) satellite imagery and the open‐source DEM extraction algorithm, Surface Extraction from TIN Space‐search Minimization (SETSM). We selected locations across a range of landscapes to evaluate the application of these DEMs to geomorphic problems, with particular attention to hillslope analyses where high spatial resolution has been shown to be important for revealing topographic signatures of tectonic and environmental processes. We compared the quality of SETSM 2 m DEMs to LiDAR‐derived DEMs and the widely available SRTM‐30 m and ALOS‐30 m DEMs by comparing the elevation data and derivative products (e.g., slope, aspect, and curvature). We found that SETSM DEMs performed noticeably better than SRTM and ALOS DEMs, but with systematic biases relative to LiDAR DEMs in regions with vegetation. Moreover, noise in the initial SETSM elevation data is amplified with every subsequent derivative, significantly decreasing quality. Finally, we evaluated the potential use of SETSM products for change detection. Applying DEM differencing to a major landslide, we found volume and sediment thickness from SETSM DEMs were similar to volumes and thicknesses from other studies. This example illustrates the capabilities of SETSM and other satellite‐based stereo‐photogrammetry for contributing to rapid response after natural disasters. Overall, we conclude that DEMs derived from satellite image stereo‐photogrammetry can markedly improve on lower resolution global elevation data for terrain analysis and can open possibilities for change detection, but that care needs to be taken in their application especially in regions with significant vegetation.

    

   more » « less