本文へ移動

サイトナビゲーションへ移動

検索ボックスへ移動

サイドバーへ移動

ここは、本文エリアの先頭です。

PALSAR-2 Global Land Cover Classification

JAXA Supercomputer System Annual Report February 2022-January 2023

Report Number: R22EER40100

Subject Category: Space Technology

PDF available here

  • Responsible Representative: Shinichi Sobue
  • Contact Information: Sota Hirayama(hirayama.sota@jaxa.jp)
  • Members: Naoyoshi Hirade, Sota Hirayama, Koichi Imamura

Abstract

Focusing on the Asian region where ALOS-2/PALSAR-2 ScanSAR data is abundant, we have developed a prototype high-resolution land-cover classification map for the Asian region. The classification is based on convolutional neural networks and uses the SACLASS2 method, which specializes in processing time-series data, and utilizes not only ALOS-2/PALSAR-2 data but also JAXA earth observation satellite data such as GCOM-C/SGLI and GsMaP. The overall accuracy of 86% was achieved.

Reference URL

Please refer to ‘Dataset | ALOS@EORC‘.

Reasons and benefits of using JAXA Supercomputer System

Accelerate machine learning use and large-scale data processing

Achievements of the Year

The use of JSS3 enabled the classification process, which originally took several days to several months, to be performed in about one day. This enabled us to conduct many classification trials, and led to the improvement of the accuracy of the land cover map.

Annual Reoprt Figures for 2022

Fig.1: Data used for classification

 

Annual Reoprt Figures for 2022

Fig.2: Prototype land-cover classification map in Asia

 

Publications

N/A

Usage of JSS

Computational Information

  • Process Parallelization Methods: Parallel execution of shell script with xargs
  • Thread Parallelization Methods: N/A
  • Number of Processes: 5 – 6
  • Elapsed Time per Case: 35.8 Hour(s)

JSS3 Resources Used

 

Fraction of Usage in Total Resources*1(%): 0.01

 

Details

Please refer to System Configuration of JSS3 for the system configuration and major specifications of JSS3.

Computational Resources
System Name CPU Resources Used
(Core x Hours)
Fraction of Usage*2(%)
TOKI-SORA 0.00 0.00
TOKI-ST 423.93 0.00
TOKI-GP 22437.62 0.95
TOKI-XM 0.00 0.00
TOKI-LM 675.41 0.05
TOKI-TST 0.00 0.00
TOKI-TGP 0.00 0.00
TOKI-TLM 0.00 0.00

 

File System Resources
File System Name Storage Assigned
(GiB)
Fraction of Usage*2(%)
/home 25.00 0.02
/data and /data2 51450.00 0.40
/ssd 5370.00 0.74

 

Archiver Resources
Archiver Name Storage Used
(TiB)
Fraction of Usage*2(%)
J-SPACE 0.00 0.00

*1: Fraction of Usage in Total Resources: Weighted average of three resource types (Computing, File System, and Archiver).

*2: Fraction of Usage:Percentage of usage relative to each resource used in one year.

 

ISV Software Licenses Used

ISV Software Licenses Resources
ISV Software Licenses Used
(Hours)
Fraction of Usage*2(%)
ISV Software Licenses
(Total)
0.00 0.00

*2: Fraction of Usage:Percentage of usage relative to each resource used in one year.

JAXA Supercomputer System Annual Report February 2022-January 2023