Applications of remote sensing and GIS to mapping land cover change in son la province

MINISTRY OF TRAINING MINISTRY OF AGRICULTURE AND AND EDUCATION RURAL DEVELOPMENT THUY LOI UNIVERSITY Nguyen Thi Lien APPLICATIONS OF REMOTE SENSING AND GIS TO MAPPING LAND COVER CHANGE IN SON LA PROVINCE Master Thesis Hanoi, May 2007 MINISTRY OF TRAINING MINISTRY OF AGRICULTURE AND AND EDUCATION RURAL DEVELOPMENT THUY LOI UNIVERSITY Nguyen Thi Lien APPLICATIONS OF REMOTE SENSING AND GIS TO MAPPING LAND COVER CHANGE IN SON LA PROVINCE Field of study: Disaster Mitigation Master Thesis Advisors: Assoc Prof Hoang Thanh Tung Dr Vu Thanh Tu Hanoi, May 2017 ACKNOWLEDGEMENT I am indebted to my respected Assoc Prof Hoang Thanh Tung and Dr Vu Thanh Tu who work as lecturers in Department of Hydrology and Water resources in Thuy Loi University for their continuous guidance, advice and expedience from the proposal preparation to thesis finalization Their constructive comments, untiring help, guidance and practical suggestions inspired me to accomplish this work successfully Besides, I am especially grateful to Dr Nguyen Quoc Khanh and members in the Department of Geologycal and Remote Sensing in Vietnam Institute of Geosciences and Mineral Resources (VIGMR) who supported me in terms of the data collection and gave me useful advices for my thesis I remember all those who have contributed directly or indirectly to successfully completing my study Finally, I must express my very profound gratitude to my family for providing me with unfailing support and continuous encouragement throughout my years of study and through the process of researching and writing this thesis This accomplishment would not have been possible without them Thank you Hanoi, May 11th 2017 Nguyen Thi Lien i DECLRATION I hereby certify the work which is being presented in this thesis entitled, “APPLICATIONS OF REMOTE SENSING AND GIS TO MAPPING LAND COVER CHANGE IN SON LA PROVINCE” in partial fulfillment of the requirement for the award of the Master of Disaster Management, is an authentic record of my own work carried out under supervision of Assoc Prof Hoang Thanh Tung and Dr Vu Thanh Tu The matter embodied in this thesis has not been submitted by me for the award of any other degree or diploma Date: Nguyen Thi Lien ii ABSTRACT The thesis "Application of remote sensing and GIS to mapping of land cover changes in Son La province" was carried out and finished in May 2017 Purpose of the thesis is to study and apply remote sensing technology and GIS in mapping changes of land cover in Son La Province To meet the thesis requirements, the following tasks have been implemented: - Study of land cover, remote sensing and GIS theories - Collection of satellite imagery data and statistical data for classification, intepretation of land cover maps over years Implementation of sptial analisis in GIS for evaluation of land cover change map - Conclusions about the results achieved and the assessment methodology After the implementation process, the subject has obtained some results: - Land cover map of Son La province in 1999 and 2015 with types of land cover: bush, lake-river, natural forest, planted forest, bare soil, agricultural land, specialized land - Land cover changes map in Son La province during 1999-2015 With the results achieved, remote sensing technology and GIS can be seen as effective methods with relatively high accuracy, cost savings in classification and catalytic activity iii Abbreviation GIS Geographic Information System TM Thematic mapper ETM Enhanced Thematic Mapper MLC Maximum Like hood classifer method ROI Region Of Interest K Kapa CB Bush SH Lake – river RTN Natural forest RT Planted forest ĐT Bare soil ĐNN Agricultural ĐCD Specialized land iv TABLE OF CONTENTS INTRODUCTION Research rationale Main objective of the research Subject and scope of the research Structure of the research CHAPTER I: LITERATURE REVIEWS 1.1 Overall study on applications of Remote Sensing and GIS in mapping land cover changes in the World 1.2 Overall study on applications of Remote Sensing and GIS in mapping land cover changes in Vietnam 1.3 Approach of the research 1.3.1 The remote sensing is used for monitoring land cover changes 10 1.3.2 GIS spatial analysis is used for evaluation of land cover changes 14 CHAPTER II: RESEARCH ON THE APPLICATION OF REMOSTE SENSING AND GIS IN ESTABLISHMENT OF LAND COVER CHANGE MAP OF SON LA PROVINCE 17 2.1 Overview of study area 17 2.1.1 Natural and socio-economic conditions 17 2.1.2 Characteristics of land cover in the study area 18 2.2 Data collection and analysis 19 2.2.1 Remote sensing data 19 2.2.2 Land use status 21 2.2.3 Field survey 25 2.3 Preprocess of remote sensing image 26 2.3.1 Radiant calibration 26 v 2.3.2 Enhance image visibility 26 2.3.3 Geometric correction 28 2.4 Image classification method 30 2.4.1 Unsupervised classification method 30 2.4.2 Supervised classification method 31 2.5 Evaluate accuracy and image processing after classification 36 2.5.1 Evaluate the accuracy after classification 36 2.5.2 Image processing after classification 37 2.6 Establish land cover map and land cover change map 37 2.6.1 Establish land cover map 37 2.6.2.Establish land cover change map 38 CHAPTER III: RESULTS AND DISCUSSIONS 40 3.1 Image classification results in 1999 40 3.2 Image classification results in 2015 44 3.3 Established results of land cover change map 46 CONCLUSIONS AND RECOMMENDATIONS 51 Conclusions 51 Recommendations 51 REFERENCES 53 vi LIST OF FIGURES Figure Overview of research Figure Remote sensing image processing Figure 3.Spectral reflective characteristics of some of the main natural objects 10 Figure Scene P128-R45 covers 90% area of Son La province 21 Figure Land use map in Son La province in 2005 24 Figure Field survey of sample points 25 Figure Enhance image visibility 27 Figure Image before and after being enhanced image quality 28 Figure Landsat image in 1999 after geometric grafting and correction 29 Figure 10 Landsat image in 2015 after geometric grafting and correction 30 Figure 11 Select the sample area 34 Figure 12 Check the difference between the samples 36 Figure 13.Use the Crosstab tool in the IDRISI software to calculate sub-carpets fluctuations 39 Figure 14.Photo classification result in 1999 41 Figure 15 Image classification results in 2015 44 Figure 16 Land cover change map in Son La province 50 vii LIST OF TABLES Table 1.Some interpretation signs on the fake color combination of SPOT satellite images 14 Table Distribution of vegetation cover and current land use status in 2011 18 Table Remote sensing image data 20 Table Land use status of Son La province in 2005 as follows: 22 Table Statistics of sample scores for each type of cover 25 Table Some interpretive patterns used in the topic Error! Bookmark not defined Table Assessment accuracy according to Kappa coefficientand overall accuracy for 1999 image classification results in Son La province 42 Table Statistics of area covered by each type of cover in Son La province in 1999 42 Table Statistics of area covered by each type of cover in districts of Son La province in 1999 43 Table 10 Assessment of accuracy according to Kappa coefficientand overall accuracy for image classification in 2015 in Son La province 45 Table 11 Statistics of cover area of each type of cover in Son La province in 1999 45 Table 12 Statistics of area covered by each kind of cover in districts of Son La province in 2015 46 Table 13 The number of pixel land cover change between 1999 and 20015 in Son La province 47 Table 14 Pixel ratio changes in two periods 1999 and 2015 in Son La province 47 Table 15 Evaluate the maturation variation in stage 1999-2015 49 viii CHAPTER III RESULTS AND DISCUSSIONS Using the Supervised classification method and applying the Maximum Likelihood algorithm, on the selected training samples for classification results Continuing to use the Majority Analysis method to group sparse pixels to smooth the classification results The 1999 and 2015 vegetation cover map of Son La province was established mainly based on the Landsat ETM (taken in 1999) and Landsat (taken in 2015) with scene images (P127R45, P126R46, P128R45, P128R46), with the image information as shown in Table1 Other satellite images, such as Landsat TM and ETM taken years ago, are also used for additional analysis of cloud cover in key images; Or used to refer to information on subjects in the period near 1999 and 2015 when classifying over Using the Supervised classification method, the author has identified seven groups of samples with the same spectral value, corresponding to seven groups of objects commonly found in Son La province These sample groups are tested on the basis of the high-resolution stereotypes of Google Earth and the 2005 and 2010 land use maps Seven groups of mottled objects were classified from remote sensing images The areas of Son La province include: bush (CB), lake – river (SH), natural forest (RTN), planted forest (RT), bare soil (ĐT), agricultural land (ĐNN) and specialized land (ĐCD) Based on the Kappa coefficient and the global precision of the categorized work, the Landsat images of the two periods of 2001 and 2015 in the ENVI software are as follows: 3.1 Image classification results in 1999 According to photo classification results, in 1999, the natural forest class occupying the largest area with 6432,097 km2 (accounting for over 45% of the total area of the province), followed by planted forest with 4689,678 km2 (accounting for over 33% Total area of the province) The lowest land cover types are agricultural land and bare soil, occupying respectivelyarea of 64,676 km2 and 110,343 km2 40 Figure 1: Photo classification result in 1999 The author used the Kappa coefficient in ENVI to evaluate the accuracy of classification results 41 Table Assessment accuracy according to Kappa coefficientand overall accuracy for 1999 image classification results in Son La province Kappa Coefficient Overall Accuracy 0,812 93,21 Độ xác cao Độ xác cao Table Statistics of area covered by each type of cover in Son La province in 1999 No Sum Type of land River-lake Natural forest Planted forest Agricultural land Specialized land Bare soil Bush Area (km2) 160.377 6432.097 4689.678 64.676 1749.663 110.343 902.465 14109.299 Percent (%) 1.137 45.588 33.238 0.458 12.401 0.782 6.396 100 In which, the area of natural forest is concentrated mainly in Moc Chau, Muong La, Ma and Thuan Chau districts with area in turn as 1050.9km2, 710.928km2, 705.069km2, 707.244km2, Son La city is the area with the lowest natural forest area is 115,444 km2 Specialized land is distributed mainly in Moc Chau, Phu Yen and Mai Son districts, with an area in turn as 227,109km2, 209,508km2 and 254,567km2 Son La city is the lowest specialized land area with 64,697km2 Bare soil is type of land cover with the smallest area in the whole province with the total bare soil area of 110,343 km2, distributed mainly in Mai Son and Sop Cop districts with area in turn as 23.984 km2, 17.627 km2 Bush occupies 8% of the total area of Son La province, including mangroves, scrublands, and grasslands This type of forest is due to deforestation, degraded forest degraded by human impact The bush are distributed mainly in Mai Son, Song Ma and Moc Chau districts with the area in turn as 164.74km2, 123.8km2, 140.28km2 Son La is a potential province for water resources with 35 large streams; the two large rivers, Da River in length of 280km long with 32 tributaries and Ma River in length of 90 km with 17 tributaries; 7,900 hectares of water surface of Hoa Binh lake and 1,400 hectares of water surface of 42 ponds and lakes River density is 1.8 km / km2, but unevenly distributed, rivers with heavy gradient, many waterfalls and rapids due to high mountainous terrain, deep divisions Flow varies on season, amplitude fluctuations between rainy season and dry season is quite large The area of rivers and lakes in Son La province is concentrated mainly in Phu Yen and Bac Yen districts with area in turn as 42,698 km2 and 35,214 km2 Because topographic features is low mountains, more than 87% of the natural land area of the province has a slope of 250 or more, this makes the fields are narrow, mainly terraced fields The area of agricultural land is concentrated mainly in Quynh Nhai, Sop Cop, Song Ma, Thuan Chau districts with area in turrn as 9,651 km2, 6,667 km2, 10,413 km2, 8,244 km2 Table 3 Statistics of area covered by each type of cover in districts of Son La province in 1999 Land cover District Natural forest Bắc Yên 448.324 141.137 10.877 60.879 404.933 35.214 1.091 Mai Sơn 521.944 254.567 23.984 164.744 433.827 9.728 17.5 Mộc Châu 1050.90 227.109 4.769 48.196 684.788 29.142 0.397 Mường La 710.928 143.479 8.989 65.382 477.831 16.519 4.192 Phù Yên 586.911 209.508 6.339 43.794 342.381 42.698 2.746 Quỳnh Nhai 535.020 116.571 1.308 41.836 338.081 13.239 9.651 Sốp Cộp 688.067 74.445 17.627 96.189 589.067 1.288 6.667 Sông Mã 705.069 170.561 10.484 123.799 606.719 5.632 10.413 Thuận 707.244 175.729 10.842 140.283 488.705 4.383 8.224 No Specialized land Bare soil Bush Planted forest River, lake Agricultural land Châu 10 Yên Châu 362.244 171.858 7.80 71.428 236.018 1.67 2.249 11 TP.Sơn La 115.444 64.697 7.322 45.932 87.322 0.859 1.994 43 3.2 Image classification results in 2015 According to image classification results in 2015, specialized land occupies the largest area with 6402.223 km2 (occupies more than 45% of the total area of the province), next up is natural forest with 2318.99 km2 (occupies over 16% % of the total area of the province) The lowest land cover types are rivers and lakes and planted forest occupying an area in turn as 253,711 km2and 201,546 km2 Figure Image classification results in 2015 44 The authors used the Kappa coefficient in ENVI to evaluate the accuracy of classification results Table Assessment of accuracy according to Kappa coefficientand overall accuracy for image classification in 2015 in Son La province Kappa Coefficient Overall Accuracy 0,836 94,25 Độ xác cao Độ xác cao Table Statistics of cover area of each type of cover in Son La province in 1999 No Type of land Area (km2) Percent (%) Sum River-lake Natural forest Planted forest Agricultural land Specialized land Bare soil Bush 253.711 2318.99 201.546 2233.61 6402.223 2026.769 672.424 14109.299 1.798186 16.43593 1.428465 15.83079 45.37599 14.3648 4.76583 100 The distribution of cover in districts is also uneven Natural forests are distributed mainly in Muong La, Bac Yen, Thuan Chau and Moc Chau districts with the area in turn as 396,834 km2, 258,408km2, 255,485km2, 341,6043km2 Specialized land is distributed mainly in Moc Chau, Sop Cop, Thuan Chau districts with the area in turn as 920,162 km2, 916,612km2, 748,027km2 The area of bare soil is distributed mainly in Moc Chau and Ma River districts, with an area of 434.410989 km2, 384.6101248km2 Bush areas are concentrated in Phu Yen, Mai Son and Moc Chau districts, with the distribution area in turn as 79.5941km2, 94.4611km2, 72.1922 km2 Mai Son, Phu Yen, Song Ma and Thuan Chau districts have the largest planted area in the province in turn as 23.5798 km2, 38.6470 km2, 34.6936 km2, 23.7570 km2 The area of lakes and rivers in 2015 has large fluctuations and distributes mainly in Muong La and Quynh Nhai districts Mai Son, Muong La and Thuan Chau districts are the largest agricultural land districts in the province 45 Table Statistics of area covered by each kind of cover in districts of Son La province in 2015 Land cover land Bare soil Bush Planted forest River, lake Agricultural land 258.409 437.796 151.410 18.681 9.123 26.451 199.512 Mộc Châu 341.604 920.162 434.411 72.192 6.525 24.795 248.819 Mai Sơn 238.188 563.384 228.495 94.461 23.580 3.502 276.267 Mường La 396.834 610.449 106.733 49.022 19.176 37.137 204.020 Phù Yên 253.654 514.339 144.657 79.594 38.647 28.706 174.459 Quỳnh Nhai 107.211 629.173 34.574 29.397 8.571 99.637 137.276 Sốp Cộp 163.178 916.612 166.743 62.106 15.747 24.992 143.288 TP.Sơn La 26.492 175.460 38.461 47.068 6.323 0.210 29.961 Sông Mã 118.152 628.075 384.610 59.950 34.694 0.001 403.346 10 Thuận Châu 255.429 748.027 181.807 95.917 23.757 8.199 214.799 11 Yên Châu 159.840 258.746 154.868 64.036 15.403 0.082 201.863 Specialized District Natural forest Bắc Yên No 3.3 Established results of land cover change map Land cover change two period (1999 and 2015) calculated using CROSSTAB tool (Cross-Classification) in IDRISI 17software 46 Table The number of pixel land cover change between 1999 and 20015 in Son La province Yea r 1999 Type of land cover Natural forest Planted forest Bush Bare soil Agrland Specland Sum 106824 31782 41217 422 5582 5582 35624 227033 Natural forest 234 1855523 613172 79829 19829 19829 19722 2608138 Planted forest 6766 31797 32738 5096 13784 56100 77452 223733 Bush 6565 153643 243458 48313 42200 34667 219081 747927 Bare soil 2446 607082 931633 180596 143465 13927 371939 2251088 Agr-land 13318 603877 1005046 155653 123501 31073 547246 2479714 Spec-land 16431 2946698 3127048 339080 166488 34495 4999757 11629997 152584 6230402 5994312 808989 514849 195673 6270821 152584 River, lake 2015 River, lake Sum Analysis of the central summary table to compare the elements on the diagonal, which shows no change in the type of land cover between the two periods Here, columns represent land cover in 1999 and rows represent land cover in 2015 For example, in 6230402 pixel classified natural forests in 1999, there were 31782 pixels transformed into Lake-river, with 31797 pixels transforming into Planted Forests, 153643 pixels transformed into Shrubs; 607082 pixel transforms into bare land; 603877 pixel transformed into agricultural land; 2946698 pixel transformed into a Dedicated Land in 2015 The same is true for other types of land cover Table Pixel ratio changes in two periods 1999 and 2015 in Son La province 1999 2015 Year Type of land cover River, lake Natural forest Planted forest Bush Bare soil Agrland Specland Sum River, lake 0.0031 0.0009 0.0012 0.0000 0.0002 0.0010 0.0010 0.0074 0.000 0.0546 0.0180 0.0023 0.0006 0.0000 0.0006 0.0761 Natural 47 1999 Year Type of land cover River, lake Natural forest Planted forest Bush Bare soil Agrland Specland Planted forest 0.0002 0.0009 0.0010 0.0001 0.0004 0.0017 0.0023 Bush 0.0002 0.0045 0.0072 0.0014 0.0012 0.0010 0.0064 0.0219 Bare soil 0.0001 0.0179 0.0274 0.0053 0.0042 0.0004 0.0109 0.0662 Agr-land 0.0004 0.0178 0.0296 0.0046 0.0036 0.0009 0.0161 0.073 Spec-land 0.0005 0.0867 0.0920 0.0100 0.0049 0.0010 0.0147 0.2098 Sum 0.0045 0.1833 0.1764 0.0237 0.0151 0.006 0.052 0.0045 Sum forest 0.0066 Statistical results of land cover change Table 14, shows that type of cover which has the most fluctuation are natural forests, planted forests, Specialized land, agricultural land, bare soil In particular, there is a significant reduction in the area of natural forest and planted forest with the change area in turn as -4113.11km2 and 4488.13km2 These areas have been replaced by the development of some specialized land (residential areas, production areas, commercial areas ), next is expansion of agriculture and bare land area Specialized land, bare land, agricultural land has a noticeable expansion, with variable area in turn as 4652.56km2, 1916.426 km2, 2168934km2 Specialized land is increased by sharply decreasing in area of shrub, bare land, agricultural land Bare soil is increased by sharply decreasing in area of agricultural land, specialized land Agricultural land in 2015 has been significantly increased by the variation of the types of vegetation cover of natural forest, planted forests and bush Based on the results of the analysis, Table 12 shows that type of cover has strong fluctuations This depends on the terrain conditions and economic development strategy of Son La province 48 Table Evaluate the maturation variation in stage 1999-2015 Are of Land cover in 1999 (km2) Are of land Are of Land % Are of cover in 1999 cover change Land cover (km2) (km2) change) No Type of land cover River-lake 160.377 253.711 93.334 0.661507 Natural forest 6432.097 2318.99 -4113.11 -29.1517 Planted forest 4689.678 201.546 -4488.13 -31.8097 Agricultural land 64.676 2233.61 2168.934 15.37237 Specialized land 1749.663 6402.223 4652.56 32.97513 Bare soil 110.343 2026.769 1916.426 13.58272 Bush 902.465 672.424 -230.041 -1.63042 14109.3 14109.3 Sum (Note: The area of change receives value + When the area of that type of cover increase The area of fluctuation receives negative value when the area of the type of cover decrease) KIA index in total: 0.4386 In order to characterize the change between the two periods, the Kappa index in total is 0.4386 used The KIA index shows that despite the change in coverage between the two periods, 43.86% of pixels in 1999 did not change to another maturity calculated in 2015 49 Figure 3 Land cover change map in Son La province 50 CONCLUSIONS AND RECOMMENDATIONS Conclusions Through the research process the author finds that: - There are currently many methods to establish the map of ground cover status, but the application of remote sensing technology in the study of land cover change is a method to bring about high efficiency, shorten time, save effort, meet the requirements in the current period - The accuracy of monitoring ground cover changes in Son La province depends mainly on spatial resolution and classification methods on satellite imagery Spatial resolution plays an important role in monitoring maneuverability Spatial resolution of LANDSAT (30m) so the level of detail is not good, the classification results are not high So in the future, if there are higher resolution sources, the classification results will be more accurate - GIS technology plays an important role in integrating information and computational fluctuations for monitoring ground cover changes - The classification results show that Son La province is the place where the variation in the area of land use is strong In which the most disturbing type of cover is natural forest, barren hills and scrub In particular, there is a significant reduction in the area of natural forests and planted forests These areas have been replaced by the development of specialized areas (residential areas, production areas, commercial areas ) or the development of natural forests Next is the variation of lakes and rivers, specialized land, grasslands and crop structure fluctuation calculations on IDRISI software, 58.49% of cover types are unchanged Recommendations Due to budget constraints, the subject has used free images with medium resolution and high quality Therefore, the results have not reached the highest accuracy For higher accuracy, other high resolution images should be used Due to the limited time and source of image data, the topic only establish map of vegetation cover in 1999 and 2015, and land cover change map in 16 years period from 1999-2015 In order to achieve results with high value and as a source of data for policy planners, it should be used many images at more time and narrow the amplitude of time fluctuation assessment 51 However, in order to create the map according to method used remote sensing data, image sources must be current, high image quality and reliable accuracy plays a very important role But at whatever resolution, the field is still an important job to put more information into classification process - Son La province is a place with high level of changes in land cover, changes in natural and planted forests to other areas of lakes and other specialized land have had major impacts on the economy, environment and many other social issues Therefore, it need to strengthen the use of remote sensing and GIS in monitoring and managing the rapid fluctuation of these soils Remote sensing technology has been growing rapidly over the last few decades Information collected from earth observation satellites is becoming increasingly accurate, with increasing frequency Combining remote sensing technology with traditional technology in environmental monitoring allows for improved monitoring information accuracy Although the introduction of remote sensing technology into the monitoring and monitoring of the environment is still difficult, but with the trend of the times, the application of remote sensing has become increasingly widespread There are some applications of remote sensing in Vietnam: In 2008, with the help of foreign experts Remote Sensing Center (now as National Remote Sensing Bureau), has been successful in using Multi-temporal radar image in the monitoring and identification of oil pollution in the South China Sea The National Remote Sensing Bureau has also applied remote sensing technology in environmental sensitization mapping for environmental impact assessment, wetland monitoring mapping The National Remote Sensing Bureau has also been assigned to build a database, set up a map of the development of polluted areas of waste water from industrial and urban areas In the future, the use of remote sensing in mineral exploration, monitoring of geological hazards is entirely possible 52 REFERENCES Aguirre, M.C.G., Alvarez, R., Dirzo, R., & Bernal, A (2005) Post-classification digital change detection analysis of a temperate forest in the southwest basin of Mexico City, in a 16-year span IEEE, 7803-9119 Alphan, H., & Tuluhan K.Y (2005) Monitoring Environmental Changes in the Mediterranean Coastal Landscape: The Case of Environmental management, Vol 35, No, 5, pp 607-619 Cukurova, Turkey Berry, C (1998) Multitemporal Land Cover Classification of the Little Washita Watershed Using the Kauth-Thomas Greenness Vegetation Index In, Geography (p 71) Stillwater: Oklahoma State University Chen, C H., (2007) Signal and Image Processing For Remote Sensing Taylor and Francis Group, LLC Civco, L D., Hurd, J D., Wilson, E H., Song, M., & Zhenkui, Z., (2002) A Comparison of Land Use and land Cover Change Detection Methods ASPRSACSM Annual Conferenceand XXII Congress Congalton, R G., & Green, K (1999) Assessing the Accuracy of Remotely Sensed Data: Principles and Practices Lewis Press, Boca Raton, Florida Cserhalmi, D., & Kristof, D (2007) Vegetation Change Detection of Mires with Digital Aerial Photographs Alps- Adria Scientific Workshop Obervellach, Austria Bjorn Prenzel, 2003, Remote sensing-based quantification of land-cover and land-use change for planning, Department of Geography, York University, Canada Carlos M.Jarque, Anil K.Bera, 1980, Efficient tests for normality, homoscedasticity and serial independence of regression residuals, Australian National University, Australia 10 James R.Anderson et al., 1976, A Land use and land cover classification system for use with remote sensor data 11 M Harika et al., 2012, Land use/land cover changes detection and urban sprawl 53 analysis 12 Robert A., Schowengerdt, 2007, Remote Sensing: Models and Methods for Image rd Processing, Edition, Oxford University, UK 13 Selcuk Reis, 2008, Analyzing Land Use/Land Cover Chang Using Remote Sensing and GIS in Rize, North-East Turkey, Aksaray University, Turkey 14 Tayyebi et al 2008, Monitoring land use change by multi-temporal landsat remote sensing imager, University of Tehran, Iran 15 Waldo Tobler, 1987, Measuring Spatial Resolution, Proceedings, Land Resources Information Systems Conferences 16 Xiaoning Gong, Lars Gunnar Marklund, Sachiko Tsuji, 2009, Land Use Classification, FAO 17 Nguyen Dinh Duong (2005) "Remote Sensing Techniques and Methods" Graduate lectures 18 Phan Van Loc, Truong Anh Kiet, Nguyen Truong Xuan (2005) "Geodesic Survey" –Ha Noi Transportation Publishing House 19 Dinh Thi Bao Hoa (2007) "Study on the rational use of suburban land in Thanh Tri district, Hanoi with the support of remote sensing technology and geographic information system" 20 Phan Van Loc, Truong Anh Kiet, Nguyen Truong Xuan (2005) "Geodesic Survey" - Hanoi Transportation Publishing House 21 Pham Vong Thanh (2000) "Management of land resources by remote sensing data" - Graduate lecture 22 Nguyen Ngoc Thach (2004) "Remote sensing basis" 23 Nguyen Ngoc Thanh (editors), Nguyen Dinh Hoe, Tran Van Thuy, Uong Dinh Khanh, Lai Vinh Cam (1997) "Remote Sensing in Natural Resources and Environmental Studies" - Hanoi Science and Technology Publishing House 24 U.S Fish & Wildlife Service (2006), “Object Based Image Classification Using SPRING Software” 25 Rajesh Bahadur Thapa, M A., M.Sc "Spatial Decision Support Model for Peri - Urban Agriculture Case Study of Ha Noi Province, Viet Nam" 54 ... analysis and role of remote sensing – GIS in research of land cover convulsion Chapter II: Research of remote sensing and GIS application in establishment of land cover changes map of Son La province. .. applications of Remote Sensing and GIS in mapping land cover changes in the World 1.2 Overall study on applications of Remote Sensing and GIS in mapping land cover changes in Vietnam ... - Land cover map of Son La province in 1999 and 2015 with types of land cover: bush, lake-river, natural forest, planted forest, bare soil, agricultural land, specialized land - Land cover changes