Lightweight, Embeddings Based Storage and Model Construction Over Satellite Data Collections
Lightweight, Embeddings Based Storage and Model Construction Over Satellite Data Collections
复制标题
DOI：
10.1109/bigdata50022.2020.9377764
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
Kevin Bruhwiler;Paahuni Khandelwal;Daniel Rammer;Samuel Armstrong;S. Pallickara;S. Pallickara
中科院分区：
文献类型：
--
作者：
Kevin Bruhwiler;Paahuni Khandelwal;Daniel Rammer;Samuel Armstrong;S. Pallickara;S. Pallickara
遥感超光谱卫星图像有了大幅度增长。这些数据为理解现象和决策提供了机会。这些收藏品的性质带来了来自其数量，种类和时空分辨率的挑战。这项研究的关键是促进深度学习模型在卫星数据收集上的有效训练。我们描述了我们的新的嵌入（多维潜在空间表示）为基础的方法，以有效地支持模型训练，细化和推理。我们严格探索与嵌入相关的几个方面，包括它们的维度，单波段与多波段，以及波段间度量的保留。我们还纳入了对时空范围内迁移学习的支持，以解决与冷启动相关的问题并缓解资源压力。我们的方法解决了磁盘，网络，CPU/GPU，以及与模型构建相关的几个方面的准确性影响。我们的经验基准评估我们的方法使用MODIS和哨兵-2卫星数据的适用性。我们证明了我们的方法将存储需求减少了10，000倍以上，并将模型构建时间减少了75%。
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%.