GENERATION OF THE HIGH-RESOLUTION LAND-USE AND LAND-COVER MAP IN JAPAN VERSION 21.11

被引：3

作者：

Hirayama, Sota ^{[1
]}

Tadono, Takeo ^{[1
]}

Mizukami, Yousei ^{[1
]}

Ohki, Masato ^{[1
]}

Imamura, Koichi ^{[2
]}

Hirade, Naoyoshi ^{[2
]}

Ohgushi, Fumi ^{[2
]}

Dotsu, Masanori ^{[2
]}

Yamanokuchi, Tsutomu ^{[2
]}

Nasahara, Kenlo Nishida ^{[3
]}

机构：

[1] Japan Aerosp Explorat Agcy JAXA, Tokyo, Japan

[2] Remote Sensing Technol Ctr Japan RESTEC, Tokyo, Japan

[3] Univ Tsukuba, Tsukuba, Ibaraki, Japan

来源：

2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022) | 2022年

关键词：

land-use; land-cover; CNN; Sentinel-2; ALOS-2/PALSAR-2;

D O I：

10.1109/IGARSS46834.2022.9884315

中图分类号：

P [天文学、地球科学];

学科分类号：

07 ;

摘要：

Japan Aerospace Exploration Agency (JAXA) Earth Observation Research Center (EORC) has produced a high-resolution land-use and land-cover classification map for Japan indicating the average cover in 2018-2020. The classification accuracy was improved by using a combination of Sentinel-2 and ALOS-2/PALSAR-2 data. We developed a convolutional neural network-based algorithm specialized for pattern recognition in multispectral and time-series feature spaces, and achieved an overall accuracy of 88.85% in 12 classifications. This is the most accurate high-resolution land-cover map ever produced by JAXA. This highly accurate product is being used for the calculation of SDGs global indicators such as 15.4.2 "Mountain Green Cover Index".

引用

页码：4339 / 4342

页数：4