Massively-Parallel Change Detection for Satellite Time Series Data with Missing Values

Gieseke, Fabian; Rosca, Sabina; Henriksen, Troels; Verbesselt, Jan; Oancea, Cosmin E.

doi:10.1109/icde48307.2020.00040

Cited by 8 publications

(8 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We demonstrate the benefits of our approach by applying it to Futhark's incremental flattening analysis and evaluating a number of (i) real-world applications [14,16] from the remote-sensing and financial domains and (ii) benchmarks from standard suites, such as Rodinia [7] and Finpar [3,20]. In comparison with the OpenTuner-based implementation, our method reduces the tuning time by a factor as high as 22.6× and on average 6.4×, and in 5 out of the 11 cases it finds better thresholds that speed-up program execution by as high as 10×.…”

Section: Scope and Contributions Of This Papermentioning

confidence: 99%

“…Heston and BFAST are real-world applications: Heston is a calibration program for the Hybrid Stochastic Local Volatility/Hull-White model [16], for which we use datasets from the futhark-benchmarks repository 10 . BFAST [14] is used to detect landscape changes, such as deforestation, in satellite time series data and is widely used by the remote sensing community. We use the peru and africa datasets from the futhark-kdd19 repository 11 .…”

Section: Experimental Validationmentioning

confidence: 99%

“…To make matters even more difficult, the common wisdom does not always hold: in several important cases [3,14] it has been shown that even when the outer parallelism is large enough, exploiting inner levels of parallelism is more efficient, e.g., when the additional parallelism can be mapped to the threads of a Cuda block, and when the intermediate results fit in shared memory. 2 Finally, the best optimization strategy may not even be portable across different generations of the same type of hardware (GPU) from the same vendor [19].…”

Section: Introductionmentioning

confidence: 99%

“…The proposed autotuner [19] uses a black-box approach that relies heavily on the stochastic heuristics of OpenTuner [4], but is impractical for application development and mainstream use, as demonstrated in Sect. 4 on a number of standard datasets of real-world applications [14,16] and public benchmarks from Rodinia [7] and FinPar [3] suites: -even relatively "simple" programs, i.e., exhibiting a small number of thresholds, may result in unpredictable and suboptimal tuning times; -the approach does not scale well, because the search space grows exponentially with the number of thresholds, 4 and thus an optimal result that perfectly discriminates between code versions may not be found, even if it exists.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Dataset Sensitive Autotuning of Multi-versioned Code Based on Monotonic Properties

Munksgaard

Breddam

Henriksen

et al. 2021

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Functional languages allow rewrite-rule systems that aggressively generate a multitude of semantically-equivalent but differently-optimized code versions. In the context of GPGPU execution, this paper addresses the important question of how to compose these code versions into a single program that (near-)optimally discriminates them across different datasets. Rather than aiming at a general autotuning framework reliant on stochastic search, we argue that in some cases, a more effective solution can be obtained by customizing the tuning strategy for the compiler transformation producing the code versions.We present a simple and highly-composable strategy which requires that the (dynamic) program property used to discriminate between code versions conforms with a certain monotonicity assumption. Assuming the monotonicity assumption holds, our strategy guarantees that if an optimal solution exists it will be found. If an optimal solution doesn’t exist, our strategy produces human tractable and deterministic results that provide insights into what went wrong and how it can be fixed.We apply our tuning strategy to the incremental-flattening transformation supported by the publicly-available Futhark compiler and compare with a previous black-box tuning solution that uses the popular OpenTuner library. We demonstrate the feasibility of our solution on a set of standard datasets of real-world applications and public benchmark suites, such as Rodinia and FinPar. We show that our approach shortens the tuning time by a factor of $$6\times $$ 6 × on average, and more importantly, in five out of eleven cases, it produces programs that are (as high as $$10\times $$ 10 × ) faster than the ones produced by the OpenTuner-based technique.

show abstract

Section: Scope and Contributions Of This Papermentioning

confidence: 99%

Section: Experimental Validationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dataset Sensitive Autotuning of Multi-versioned Code Based on Monotonic Properties

Munksgaard

Breddam

Henriksen

et al. 2021

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Prior to our implementation, the BFASTmonitor algorithm was only available as part of the BFAST R package and as an implementation in python, deployable on the graphics processing unit (GPU) [29]. This implementation supports processing of large amounts of satellite data on local desktop computers that have GPU's available.…”

Section: Introductionmentioning

confidence: 99%

Implementation of BFASTmonitor Algorithm on Google Earth Engine to Support Large-Area and Sub-Annual Change Monitoring Using Earth Observation Data

et al. 2020

Self Cite

View full text Add to dashboard Cite

Monitoring of abnormal changes on the earth’s surface (e.g., forest disturbance) has improved greatly in recent years because of satellite remote sensing. However, high computational costs inherently associated with processing and analysis of satellite data often inhibit large-area and sub-annual monitoring. Normal seasonal variations also complicate the detection of abnormal changes at sub-annual scale in the time series of satellite data. Recently, however, computationally powerful platforms, such as the Google Earth Engine (GEE), have been launched to support large-area analysis of satellite data. Change detection methods with the capability to detect abnormal changes in time series data while accounting for normal seasonal variations have also been developed but are computationally intensive. Here, we report an implementation of BFASTmonitor (Breaks For Additive Season and Trend monitor) on GEE to support large-area and sub-annual change monitoring using satellite data available in GEE. BFASTmonitor is a data-driven unsupervised change monitoring approach that detects abnormal changes in time series data, with near real-time monitoring capabilities. Although BFASTmonitor has been widely used in forest cover loss monitoring, it is a generic change monitoring approach that can be used to monitor changes in a various time series data. Using Landsat time series for normalised difference moisture index (NDMI), we evaluated the performance of our GEE BFASTmonitor implementation (GEE BFASTmonitor) by detecting forest disturbance at three forest areas (humid tropical forest, dry tropical forest, and miombo woodland) while comparing it to the original R-based BFASTmonitor implementation (original BFASTmonitor). A map-to-map comparison showed that the spatial and temporal agreements on forest disturbance between the original and our GEE BFASTmonitor implementations were high. At each site, the spatial agreement was more than 97%, whereas the temporal agreement was over 94%. The high spatial and temporal agreement show that we have properly translated and implemented the BFASTmonitor algorithm on GEE. Naturally, due to different numerical solvers being used for regression model fitting in R and GEE, small differences could be observed in the outputs. These differences were most noticeable at the dry tropical forest and miombo woodland sites, where the forest exhibits strong seasonality. To make GEE BFASTmonitor accessible to non-technical users, we developed a web application with simplified user interface. We also created a JavaScript-based GEE BFASTmonitor package that can be imported as a module. Overall, our GEE BFASTmonitor implementation fills an important gap in large-area environmental change monitoring using earth observation data.

show abstract

BFASTm-L2, an unsupervised LULCC detection based on seasonal change detection – An application to large-scale land acquisitions in Senegal

Ngadi Scarpetta,

Lebourgeois,

Laques

et al. 2023

International Journal of Applied Earth Observation and Geoinfor

View full text Add to dashboard Cite

Massively-Parallel Change Detection for Satellite Time Series Data with Missing Values

Cited by 8 publications

References 34 publications

Dataset Sensitive Autotuning of Multi-versioned Code Based on Monotonic Properties

Dataset Sensitive Autotuning of Multi-versioned Code Based on Monotonic Properties

Implementation of BFASTmonitor Algorithm on Google Earth Engine to Support Large-Area and Sub-Annual Change Monitoring Using Earth Observation Data

BFASTm-L2, an unsupervised LULCC detection based on seasonal change detection – An application to large-scale land acquisitions in Senegal

Contact Info

Product

Resources

About