VIETNAM NATIONAL UNIVERSITY, HANOI UNIVERSITY OF ENGINEERING AND TECHNOLOGY MAN DUC CHUC RESEARCH ON LAND-COVER CLASSIFICATION METHODOLOGIES FOR OPTICAL SATELLITE IMAGES MASTER THESIS IN COMPUTER SCIENCE Hanoi – 2017 LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com VIETNAM NATIONAL UNIVERSITY, HANOI UNIVERSITY OF ENGINEERING AND TECHNOLOGY MAN DUC CHUC RESEARCH ON LAND-COVER CLASSIFICATION METHODOLOGIES FOR OPTICAL SATELLITE IMAGES DEPARTMENT: COMPUTER SCIENCE MAJOR: COMPUTER SCIENCE CODE: 60480101 MASTER THESIS IN COMPUTER SCIENCE SUPERVISOR: Dr. NGUYEN THI NHAT THANH Hanoi – 2017 LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com PLEDGE I hereby undertake that the content of the thesis: “Research on Land- Cover classification methodologies for optical satellite images” is the research I have conducted under the supervision of Dr. Nguyen Thi Nhat Thanh. In the whole content of the dissertation, what is presented is what I learned and developed from the previous studies.
All of the references are legible and legally quoted. I am responsible for my assurance. Hanoi, day month year 2017 Thesis’s author Man Duc Chuc LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com ACKNOWLEDGEMENTS I would like to express my deep gratitude to my supervisor, Dr. Nguyen Thi Nhat Thanh.
She has given me the opportunity to pursue research in my favorite field. During the dissertation, she has given me valuable suggestions on the subject, and useful advices so that I could finish my dissertation. I also sincerely thank the lecturers in the Faculty of Information Technology, University of Engineering and Technology - Vietnam National University Hanoi, and FIMO Center for teaching me valuable knowledge and experience during my research. Finally, I would like to thank my family, my friends, and those who have supported and encouraged me.
This work was supported by the Space Technology Program of Vietnam under Grant VT-UD/06/16-20. Hanoi, day month year 2017 Man Duc Chuc LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com Content CHAPTER 1. Objectives, contributions and thesis structure. Remote sensing concepts.
Classification of remote sensing systems. Typical spectrum used in remote sensing systems. Machine learning methods in land cover study. Support Vector Machine.
Artificial Neural Network. eXtreme Gradient Boosting. Other promising methods. PROPOSED LAND COVER CLASSIFICATION METHOD .28 1 LUAN VAN CHAT LUONG download : add luanvanchat@agmail.
Landsat 8 SR data. Generation of composite images. Land cover classification. Metrics for classification assessment.
EXPERIMENTS AND RESULTS. Assessment of land-cover classification based on point validation. Yearly single composite classification versus yearly time-series composite classification. Improvement of ensemble model against single-classifier model.
Assessment of land-cover classification results based on map validation .44 2 LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com LIST OF TABLES Table 1. Description of seven global land-cover datasets. Some featured satellite images. Review of compositing methods for satellite images.
Training and testing data. Summary of Year score, DOY score, Opacity score and Distance to cloud/cloud shadow for L8SR composition. F1 score, F1 score average, OA and kappa coefficient for 7 land cover classes of six classification cases obtained using XGBoost. Best classification cases are written in bold.
OA, kappa coefficient, F1 score average for each single-classifier and ensemble model. Best classification cases are written in bold. Confusion matrix of ensemble model. Error (ha and %) of rice mapped area for different classification scenarios.
43 3 LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com LIST OF FIGURES Figure 1. Rice covers map of Mekong river delta, Vietnam in 2012. The acquisition of data in remote sensing. Introduction of a typical remote sensing system.
Passive (left) and active (right) remote sensing systems. Typical wavelengths used in remote sensing. Landsat 7 and Landsat 8 bands. Comparison of Landsat 8 OLI (left) and SR (right) images.
An example of MLP. Hanoi city, study area of this study. Examples of experimental data shown in Google Earth, sampled points are represented by while-colored squares over the Google Earth base images. Landsat 8 footprints over Hanoi.
Statistics of Landsat 8 SR images over Hanoi, (a) number of images by year and month, (b) cloud coverage percentage per image. Overall flowchart of the method. Clear observation count maps for each image used in the compositing process (DOY 137, 169, 265, 281). NDVI (above) and BSI (below) temporal profile of land-cover class.
(a) Original surface reflectance images, (b) composite images, (c) classification maps for each image, and (d) classified map obtained from time-series composite images. F1 score for land-cover class obtained using multiple classifiers. 2016 Land-cover map for Hanoi based on the most accurate classification using time-series composite imagery and the ensemble of five classifiers.42 4 LUAN VAN CHAT LUONG download : add luanvanchat@agmail. INTRODUCTION In this chapter, I briefly present an introduction to remote sensing images and its applications in different research areas.
Furthermore, the problem of land cover classification is also presented. Current progress and challenges in land cover classification are discussed. Finally, motivations and problem statement of the research are shown in the end of the chapter. Motivation Remotely-sensed images have been used for a long time in both military and civilization applications.
The images could be collected from satellites, airborne platforms or Unmanned Aerial Vehicles (UAVs). Among the three, satellite images have gained popularity due to large coverage, available data and so on. In general, remotely- sensed images store information about Earth object’s reflectance of lights, i. Sun’s light in passive remote sensing [1].
Therefore, the images contain itself lots of valuable information of the Earth’s surface or even under the surface. Applications of remotely-sensed images are diverse. For example, satellite images could be used in agriculture, forestry, geology, hydrology, sea ice, land cover mapping, ocean and coastal [1]. In agriculture, two important tasks are crop type mapping and crop monitoring.
Crop type mapping is the process of identification crops and its distribution over an area. This is the first step to crop monitoring which includes crop yield estimation, crop condition assessment, and so on. To these aims, satellite images are efficient and reliable means to derive the required information [1]. In forestry, potential applications could be deforestation mapping, species identification and forest fire mapping.
In the forest where human access is restricted, satellite imagery is an unique source of information for management and monitoring purposes. In geology, satellite images could be used for structural mapping and terrain analysis. In hydrology, some possible applications cloud be flood delineation and mapping, river change detection, irrigation canal leakage detection, wetlands mapping and monitoring, soil moisture monitoring, and a lot of other researches. Iceberg detection and tracking is also done via satellite data.
Furthermore, air pollution and meteorological monitoring 5 LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com could be possible from satellite perspective. In general, many of the applications more or less relate to land cover mapping, i. agriculture, flood mapping, forest mapping, sea ice mapping, and so on. Land cover (LC) is a term that refers to the material that lies above the surface of the Earth.
Some examples of land covers are: plants, buildings, water and clouds. Land cover is the thing that reflects or radiates the Sun’s lights which then be captured by the satellite’s sensors. Land use and land cover classification (LULCC) has been considering as one of the most traditional and important applications in remote sensing since LULCC products are essential for a variety of environmental applications [2]. Figure 1 shows a land cover map for Mekong river delta, Vietnam in 2012 derived from MODIS images [3].
This map shows distribution of rice lands in the region. Rice covers map of Mekong river delta, Vietnam in 2012. Regarding land cover classification (LCC), there are currently many researches around the world. These researches could be categorized by several criteria such as geographical scale of classification, multiple land covers classification or single land 6 LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com cover classification.
For the former, LCC can be classified into regional or global studies. Regional studies focus on investigating LCC methods for one or more specific regions. Global studies concern classification at global scale. There are currently some already published global land-cover datasets as presented in Table 1.
Description of seven global land-cover datasets. GLCC UMD GLC2000 MODIS GlobCove GLCNM FROM- LC r O GLC Sensor AVHRR AVHRR SPOT-4 MODIS MERIS MODIS LANDSA VEGETATI T ON Acquisitio 04/1992– 04/1992– 11/1999– 01/2001– 12/2004 – 01/2008 – 01/2010 – n time 03/1993 03/1993 12/2000 12/2002 06/2006 12/2008 12/2010 Spatial 1 km 1 km 1 km 500 m 300 m 500 m 30 m resolution Input data IGBP 1-km 41 metrics Daily Monthly MERIS 16-day Landsat AVHRR derived mosaics of 4 MODIS L1B data, composite TM/ETM 10-day from spectral L2/L3 MERIS of MODIS + (30 composite, NDVI and channels and composite, mosaics 2008 Data meter), DEM data, AVHRR NDVI of EOS MOD44W MODIS Ecoregions bands 1–5, SPOT, land/water and EVI time data, EROS JERS-1 and mask, SRTM series Maps data. urban, ERS radar MODIS DEM (250 MODIS data, 16-day meter) water DMSP data, EVI, Bioclimati mask DEM MODIS 8- c variables day DEM (1km) global DEM (1km) Classificat Classificati Decision Unsupervise Decision Unsupervi Combined Maximum ion on with tree d tree, Neural sed method of likelihood method post- classificatio networks classificati supervised (MLC), classificati n on classificati J4.8 on on Decision refinement and tree, Unsupervis individual Random ed mapping forests and Support 7 LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com vector machine LC class 17 classes 14 classes 23 classes 17 classes 22 classes 20 classes 10 classes Validation Landsat Other High High SPOT- Integrated MODIS data TM and digital resolution resolution VEGETA potential vegetatio, SPOT datasets satellite data, land cover TION map, DEM and images and ancillary information NDVI, and Google soil-water information Virtual/Go Earth condition ogle Earth image, maps MODIS images Reported Globally Globally Globally Globally Globally Globally Globally accuracy 66.9% Although there are many efforts to map land covers globally, the LC accuracies are still much lower than regional LC maps. This is understandable as there are many challenges in LCC at global scale including diversity of land-cover types, lack of ground-truth data, and so on [4].
In regional studies, the difficulties are more or less reduced, thus resulting in more accurate LC maps. Some typical regional LC studies could be mentioned, i. Hannes et al. investigated Landsat time series (2009 - 2012) for separating cropland and pasture in a heterogeneous Brazilian savannah landscape using random forest classifier and achieved and overall accuracy of 93% [5].
Xiaoping Zhang et al. used Landsat data to monitor impervious surface dynamics at Zhoushan islands from 2006 to 2011 and achieved overall accuracies of 86-88% [6]. Arvor et al. classified five crops in the state of Mato Grosso, Brazil using MODIS EVI time series and their OAs ranged from 74 – 85.
Although land-cover classification (LCC) mapping at medium to high spatial resolution is now easier due to availability of medium/high spatial resolution imagery such as Landsat 5/7/8 [8], in cloud-prone areas, deriving high resolution LCC maps from optical imagery is challenging because of infrequent satellite revisits and lack of cloud-free data. This is even more pronounced in land cover with high temporal dynamics, i. paddy rice or seasonal crops, which require observation of key growing stages to correctly identify [9], [10]. Vietnam is located in a tropical monsoon climate frequently covered by cloud [11], [12].
Some studies used high temporal resolution but low spatial resolution images (MODIS) [13]. Some studies employed single-image classifications [14]. However, common challenges of mono-temporal approaches include misclassification between bare land or impervious surface and vegetation cover type [15]. Whereas land cover classification using cloud-free Landsat scenes may lack enough observations to capture temporal dynamics of land-cover types.
8 LUAN VAN CHAT LUONG download : add luanvanchat@agmail. Objectives, contributions and thesis structure To date, land cover classification in cloud-prone areas is challenging. Furthermore, efficient LC methods for the regions, especially for areas with high temporal dynamics of land covers, are still limited.