Dataset

We do not recommend the use of the following data (old version) to our users, as improved versions (the newest version) have been released separately. However, we will continue to provide these data on this page, as we believe that some users may need these data for retrospective or revalidation of researches that have already been conducted.The newest version is here.

High-Resolution Land-Use and Land-Cover Map of the Central Region of Vietnam
(Released in July 2018 / Version 18.07) 
Downloads

 You can switch layers with check boxes.

Download product

User registration is required to download the data. Please click here about download and user registration details.

https://www.eorc.jaxa.jp/ALOS/en/dataset/lulc_e.htm

1. Summary

Anthropogenic pressures on land cover system over central Vietnam are growing because of the socio-economic development. In order to highlight the land cover change, we created maps for the year 2007 and 2015, making use of satellite datasets such as Sentinel, Landsat, ALOS-AVNIR-2, PALSAR, PALSAR-2 mosaic etc.

2. Data used for creating the map

  • Data 1: Sentinel 2 10 m resolution, 183 scenes (2017).
  • Data 2: Landsat 8 OLI 30 m resolution, 87 scenes (2017).
  • Data 3: Landsat 7 ETM+ 30 m resolution, 126 scenes (2007).
  • Data 4: Landsat 5 TM 30 m resolution, 85 scenes (2007).
  • Data 5: ALOS AVNIR 2 10 m resolution, 203 scenes (2007).
  • Data 6: ALOS-2 PALSAR-2 25 m resolution mosaic dataset (2017).
  • Data 7: ALOS PALSAR 25 m resolution mosaic dataset (2007).
  • Data 8: SRTM-1 30 m resolution and the map of its slope.
  • Data 9: The map of distances from roads (Roadmap ©OpenStreetMap contributors).

3. Classification algorithm

Bayesian classifier with kernel density estimation (Hashimoto et al., 2014)

4. Data format

  • Coordinate system: Latitude and longitude coordinate system with ITRF-94 on GRS-80 ellipsoid.
  • Tile unit: 1 degree x 1 degree, (10,581 pixels x 10,581 lines)
  • Mesh size: (1 / 10,581) degree × (1 / 10,581) degree (corresponding to approximate 10 m × 10 m)
  • File naming convention: For example, LC_N18E106.tif indicates 18 to 19 degrees north latitude and 106 to 107 degrees east longitude.
  • Format: GeoTIFF format
  • Period of coverage: Year 2007 and 2017 (two different maps)

The value of each pixel is ID number of the category for classification as follows:

  • #0: Unclassified
  • #1: Water
  • #2: Urban and built-up
  • #3: Rice paddy
  • #4: Crops
  • #5: Grassland
  • #6: Orchards
  • #7: Bare land
  • #8: Forest
  • #9: Mangrove
  • #255: No data

5. Accuracy verification

Tables 1 and 2 present the accuracy of central Vietnam maps for producers, users and overall accuracy based on a confusion matrix. The overall accuracy of central Vietnam land cover/land use maps for the year 2007 and 2017 are 90.5 % (kappa coefficient of 90 %) and 90.6 % (kappa coefficient of 90 %) respectively. Figures 1a and 1b show the results of 10-m spatial resolution land cover maps of the central Vietnam for the year 2007 and 2017 respectively.
Table 1: Confusion matrix showing producer's, user's and overall accuracies of the central Vietnam land cover map in 2007.
  Classified Producer's
accuracy (%)
1 2 3 4 5 6 7 8 9 TOTAL
Validation 1 644 0 4 0 0 0 0 0 11 659 97.8
2 0 1,005 3 64 31 76 2 0 0 1,181 85.1
3 0 6 1,138 12 3 2 15 2 58 1,236 92.1
4 0 12 8 1,123 73 105 6 6 2 1,335 84.2
5 0 6 0 4 377 5 1 0 0 393 96.0
6 0 8 2 34 11 637 0 45 0 737 86.5
7 0 7 0 1 1 1 496 0 0 506 98.1
8 1 0 1 0 1 60 0 986 0 1,049 94.0
9 23 0 16 0 2 0 0 0 495 536 92.4
TOTAL 668 1044 1172 1238 499 886 520 1039 566 7632 91.8
User's
accuracy (%)		 96.5 96.3 97.1 90.8 75.6 71.9 95.4 94.9 87.5 89.6 90.5%
Kappa
coefficient		 0.9
Table2: Confusion matrix showing producer’s, user’s and overall accuracies of the central Vietnam land cover map in 2017.
  Classified Producer's
accuracy (%)
1 2 3 4 5 6 7 8 9 TOTAL
Validation 1 2,636 2 1 0 4 0 0 0 2 2,645 99.7
2 0 1,799 1 70 58 75 17 0 0 2,020 89.1
3 5 0 2,971 17 0 11 0 28 19 3,051 97.4
4 2 33 157 2,454 181 171 0 28 48 3,074 79.9
5 84 74 7 107 1,821 135 0 46 7 2,281 79.9
6 1 12 4 153 72 765 0 54 8 1,069 71.6
7 12 60 5 16 7 3 1,264 0 0 1,367 92.5
8 0 0 8 3 1 10 1 3,291 0 3,314 99.4
9 7 3 5 2 2 1 1 22 781 824 94.8
TOTAL 2,747 1,983 3,159 2,822 2,146 1,171 1,283 3,469 865 19,645 89.4
User's
accuracy (%)		 96.0 90.8 94.1 87.0 84.9 65.4 98.6 94.9 90.3 89.1 90.6
Kappa
coefficient		 0.9
Figure 1: The 2007 land cover map (a) and the 2017 land cover map (b).
Figure 1: The 2007 land cover map (a) and the 2017 land cover map (b).

6. References

  • "A New Method to Derive Precise Land-use and Land-cover Maps Using Multi-temporal Optical Data", Shutaro Hashimoto, Takeo Tadono, Masahiko Onosato, Masahiro Hori and Kei Shiomi (2014) Journal of The Remote Sensing Sociery of Japan, 34 (2), 102-112.
  • "Analysis of Land Cover Changes in Central Vietnam Using High Resolution Multi-spectral-temporal Remotely Sensed Data", Phan Cao Duong, Master’s thesis, University of Tsukuba, 2018.
  • "JAXA High-Resolution Land Use/Land Cover Map for Central Vietnam in 2007 and 2017", Phan Cao Duong, Ta Hoang Trung, Kenlo Nishida Nasahara and Takeo Tadono (2018) Remote Sensing, 10(9), 1406.

Acknowledgements