Paper Info
Title
Lightweight, Embeddings Based Storage and Model Construction Over Satellite Data Collections
Abstract
There has been a substantial growth in remotely sensed hyperspectral satellite imagery. These data offer opportunities to understand phenomena and inform decision making. The nature of these collections introduces challenges stemming from their volumes, variety, and spatiotemporal resolutions. The crux of this study is to facilitate effective training of deep learning models over satellite data collections. We describe our novel embeddings (multidimensional latent space representations) based approach to effectively support model training, refinement, and inferences. We rigorously explore several aspects relating to embeddings, including their dimensionality, single vs multiple bands, and preservation of inter-band metrics. We also incorporate support for transfer learning over spatiotemporal scopes to address issues relating to cold start and alleviate resource pressure. Our methodology addresses disk, network, CPU/GPU, and accuracy implications of several aspects relating to model construction. Our empirical benchmarks assess the suitability of our methodology using the MODIS and Sentinel-2 satellite data. We demonstrate that our methodology reduces storage requirements by more than 10,000x and reduces model construction times by 75%.
Year
DOI
Venue
2020
10.1109/BigData50022.2020.9377764
2020 IEEE International Conference on Big Data (Big Data)
Keywords
DocType
ISBN
hyperspectral satellite imagery,deep learning models,spatial computing,storage systems,spatiotemporal transfer learning
Conference
978-1-7281-6252-2
Citations 
PageRank 
References 
1
0.36
0
Authors
6
Name
Order
Citations
PageRank
Kevin Bruhwiler131.74
Paahuni Khandelwal221.73
Daniel Rammer373.16
Samuel Armstrong411.37
Sangmi Lee Pallickara517024.46
Shrideep Pallickara683792.72