Next Article in Journal
Study of the Effect of Temporal Sampling Frequency on DSCOVR Observations Using the GEOS-5 Nature Run Results (Part II): Cloud Coverage
Previous Article in Journal
Advantages of Using Microwave Satellite Soil Moisture over Gridded Precipitation Products and Land Surface Model Output in Assessing Regional Vegetation Water Availability and Growth Dynamics for a Lateral Inflow Receiving Landscape
Article Menu

Export Article

Open AccessArticle
Remote Sens. 2016, 8(5), 429; doi:10.3390/rs8050429

Production of the Japan 30-m Land Cover Map of 2013–2015 Using a Random Forests-Based Feature Optimization Approach

1
Center for Environmental Remote Sensing (CEReS), Chiba University, 1-33 Yayoi-cho, Inage-ku, Chiba 263-8522, Japan
2
Department of Informatics, Tokyo University of Information Sciences, 4-1 Onaridai, Wakaba-ku, Chiba 265-8501, Japan
3
Research Institute for Sustainable Humanosphere, Kyoto University, Gokasho, Uji, Kyoto 611-0011, Japan
*
Author to whom correspondence should be addressed.
Academic Editors: Ioannis Gitas and Prasad S. Thenkabail
Received: 29 February 2016 / Revised: 15 May 2016 / Accepted: 16 May 2016 / Published: 20 May 2016
View Full-Text   |   Download PDF [22323 KB, uploaded 20 May 2016]   |  

Abstract

Achieving more timely, accurate and transparent information on the distribution and dynamics of the world’s land cover is essential to understanding the fundamental characteristics, processes and threats associated with human-nature-climate interactions. Higher resolution (~30–50 m) land cover mapping is expected to advance the understanding of the multi-dimensional interactions of the human-nature-climate system with the potentiality of representing most of the biophysical processes and characteristics of the land surface. However, mapping at 30-m resolution is complicated with existing manual techniques, due to the laborious procedures involved with the analysis and interpretation of huge volumes of satellite data. To cope with this problem, an automated technique was explored for the production of a high resolution land cover map at a national scale. The automated technique consists of the construction of a reference library by the optimum combination of the spectral, textural and topographic features and predicting the results using the optimum random forests model. The feature-rich reference library-driven automated technique was used to produce the Japan 30-m resolution land cover (JpLC-30) map of 2013–2015. The JpLC-30 map consists of seven major land cover types: water bodies, deciduous forests, evergreen forests, croplands, bare lands, built-up areas and herbaceous. The resultant JpLC-30 map was compared to the existing 50-m resolution JAXA High Resolution Land-Use and Land-Cover (JHR LULC) map with reference to Google Earth™ images. The JpLC-30 map provides more accurate and up-to-date land cover information than the JHR LULC map. This research recommends an effective utilization of the spectral, textural and topographic information to increase the accuracy of automated land cover mapping. View Full-Text
Keywords: land cover; random forests; multi-spectral; textures; mapping; high-resolution; Landsat 8; topographic; Japan land cover; random forests; multi-spectral; textures; mapping; high-resolution; Landsat 8; topographic; Japan
Figures

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).

Scifeed alert for new publications

Never miss any articles matching your research from any publisher
  • Get alerts for new papers matching your research
  • Find out the new papers from selected authors
  • Updated daily for 49'000+ journals and 6000+ publishers
  • Define your Scifeed now

SciFeed Share & Cite This Article

MDPI and ACS Style

Sharma, R.C.; Tateishi, R.; Hara, K.; Iizuka, K. Production of the Japan 30-m Land Cover Map of 2013–2015 Using a Random Forests-Based Feature Optimization Approach. Remote Sens. 2016, 8, 429.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Remote Sens. EISSN 2072-4292 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top