Remotely-sensed satellite image fusion is indispensable for the generation of long-term gap-free Earth observation data. While cloud computing (CC) provides the big picture for RS big data (RSBD), the fundamental question of the efficient fusion of RSBD on CC platforms has not yet been settled. To this end, we propose a lightweight cloud-native framework for the elastic processing of RSBD in this study. With the scaling mechanisms provided by both the Infrastructure as a Service (IaaS) and Platform as a Services (PaaS) of CC, the Spark-on-Kubernetes operator model running in the framework can enhance the efficiency of Spark-based algorithms without considering bottlenecks such as task latency caused by an unbalanced workload, and can ease the burden to tune the performance parameters for their parallel algorithms. Internally, we propose a task scheduling mechanism (TSM) to dynamically change the Spark executor pods’ affinities to the computing hosts. The TSM learns the workload of a computing host. Learning from the ratio between the number of completed and failed tasks on a computing host, the TSM dispatches Spark executor pods to newer and less-overwhelmed computing hosts. In order to illustrate the advantage, we implement a parallel enhanced spatial and temporal adaptive reflectance fusion model (PESTARFM) to enable the efficient fusion of big RS images with a Spark aggregation function. We construct an OpenStack cloud computing environment to test the usability of the framework. According to the experiments, TSM can improve the performance of the PESTARFM using only PaaS scaling to about 11.7%. When using both the IaaS and PaaS scaling, the maximum performance gain with the TSM can be even greater than 13.6%. The fusion of such big Sentinel and PlanetScope images requires less than 4 min in the experimental environment.
Due to the inconsistent spatiotemporal spectral scales, a remote sensing dataset over a large-scale area and over long-term time series will have large variations and large statistical distribution features, which will lead to a performance drop of the deep learning model that is only trained on the source domain. For building an extraction task, deep learning methods perform weak generalization from the source domain to the other domain. To solve the problem, we propose a Capsule–Encoder–Decoder model. We use a vector named capsule to store the characteristics of the building and its parts. In our work, the encoder extracts capsules from remote sensing images. Capsules contain the information of the buildings’ parts. Additionally, the decoder calculates the relationship between the target building and its parts. The decoder corrects the buildings’ distribution and up-samples them to extract target buildings. Using remote sensing images in the lower Yellow River as the source dataset, building extraction experiments were trained on both our method and the mainstream methods. Compared with the mainstream methods on the source dataset, our method achieves convergence faster, and our method shows higher accuracy. Significantly, without fine tuning, our method can reduce the error rates of building extraction results on an almost unfamiliar dataset. The building parts’ distribution in capsules has high-level semantic information, and capsules can describe the characteristics of buildings more comprehensively, which are more explanatory. The results prove that our method can not only effectively extract buildings but also perform great generalization from the source remote sensing dataset to another.
The Three Georges Dam (TGD) has brought many benefits to the society by periodically changing the water level of its reservoir (TGR). Water discharging regularly takes places in the falling season when the downstream of the Yangtze River is drying. The TGD, the world’s largest hydroelectric project, can greatly mitigate the risk of flood caused by extreme precipitation with the prior discharging policy applied in the preflood season. At the end of flood season, water impounding in the storage season can help resist a drought the next year. However, owing to the difficulty in mining causality, the considerable debate about its environmental and climatic impacts have emerged in much of the empirical and modeling studies. We used causal generative neural networks (CGNN) to construct the linkage of water level–climate–vegetation across the TGD areas with a ten-year daily remotely sensed normalized difference vegetation index (NDVI), gauge-based precipitation, temperature observations, water level and streamflow. By quantifying the causality linkages with a non-linear Granger-causality framework, we find that the 30-days accumulated change of water level of the TGR significantly affects the vegetation growth with a median factor of 31.5% in the 100 km buffer region. The result showed that the vegetation dynamics linked to the water level regulation policy were at the regional scale rather than the local scale. Further, the water level regulation in the flood stage can greatly improve the vegetation growth in the buffer regions of the TGR area. Specifically, the explainable Granger causalities of the 25 km, 50 km, 75 km and 100 km buffer regions were 21.72%, 19.24%, 17.31% and 16.03%, respectively. In the falling and impounding stages, the functionality of the TGR that boosts the vegetation growth were not obvious (ranging from 6.1% to 8.3%). Overall, the results demonstrated that the regional vegetation dynamics were driven not only by the factor of climate variations but also by the TGR operation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.