High-Performance Time-Series Quantitative Retrieval From Satellite Images on a GPU Cluster

Abstract

The quality and accuracy of remote sensing instruments continue to increase, allowing geoscientists to perform various quantitative retrieval applications to observe the geophysical variables of land, atmosphere, ocean etc. The explosive growth of time-series RS data over large-scales poses great challenges on managing, processing and interpreting RS ''Big Data''. To explore these time series RS data efficiently, in this paper, we design and implement a high performance framework to address the time-consuming time-series quantitative retrieval issue on a GPU cluster, taking the aerosol optical depth (AOD) retrieval from satellite images as a study case. The presented framework exploits the multi-level parallelism for time-series quantitative RS retrieval to promote efficiency. At the coarse-grained level of parallelism, the AOD time series retrieval is represented as multi-directed acyclic graph (DAG) workflows and scheduled based on a list-based heuristic algorithm, heterogeneous earliest finish time (HEFT), taking the idle slot and priorities of retrieval jobs into account. At the fine-grained level, the parallel strategies for the major remote sensing image processing algorithms divided into three categories, i.e. the point or pixel-based operations, the local operations and the global or irregular operations have been summarized. The parallel framework was implemented with message passing interface (MPI) and compute unified device architecture (CUDA), and experimental results with the AOD retrieval case verify the effectiveness of presented framework.

Temporal Convolutional Networks for the Advance Prediction of ENSO

“…• The ML-based ENSO prediction methods are realized by learning and mining the historical ENSO index features and establishing a prediction model for ENSO prediction. Commonly used methods include support vector regression (SVR) 18,19 , artificial neural networks (ANNs) 20,21 , long short-term memory (LSTM) 22,23 , and so on 24 . For example, in 2009, Silestre and William used a Bayesian neural network (BNN) and SVR, two non-linear regression methods, to forecast the tropical Pacific SST anomalies at lead times ranging from 3 to 15 months using the sea-level pressure (SLP) and SST as predictors.…”

Multistep Prediction of Land Cover From Dense Time Series Remote Sensing Images With Temporal Convolutional Networks

“…But the pixel-level LULC multi-step prediction is still very computationally demanding. Though eight GPUs of China's Tianhe-2 supercomputing clusters were adopted, the 18-year EVI time series (a total of 162,736 pixels with 414 time points) 23-step prediction in Wuhan city still took more than 24 days [51], [52]. • Since the pMTSP method works on the pixel-level, it is more suitable for performing multi-step land cover prediction from a slightly lower spatial resolution remote sensing images.…”

Prediction model for recurrence of hepatocellular carcinoma after resection by using neighbor2vec based algorithms

“…Due to the high dimensional and diversified characteristics of clinical data, the performance of prognostic prediction model is reduced, that is, the dimensional disaster problem of pattern classification appears. Feature selection is an important and commonly used technique in data mining data preprocessing (Liu et al, 2019; Tang, Liu, et al, 2018a). It reduces the number of features, removes irrelevant, redundant, or noisy data, and has a direct impact on the prediction model: it speeds up the data mining algorithm, improves the prediction accuracy and results comprehensibility mining performance.…”