Cloud-computing and machine learning in support of country-level land cover and ecosystem extent mapping in Liberia and Gabon
Autoři:
Celio de Sousa aff001; Lola Fatoyinbo aff002; Christopher Neigh aff002; Farrel Boucka aff003; Vanessa Angoue aff003; Trond Larsen aff004
Působiště autorů:
Universities Space Research Association/GESTAR, Columbia, Maryland, United States of America
aff001; Earth Sciences Division, NASA Goddard Space Flight Center, Greenbelt, Maryland, United States of America
aff002; Agence Gabonaise d'Etudes et d'Observations Spatiales (AGEOS), Libreville, Gabon
aff003; Conservation International, Arlington, Virginia, United States of America
aff004
Vyšlo v časopise:
PLoS ONE 15(1)
Kategorie:
Research Article
prolekare.web.journal.doi_sk:
https://doi.org/10.1371/journal.pone.0227438
Souhrn
Liberia and Gabon joined the Gaborone Declaration for Sustainability in Africa (GDSA), established in 2012, with the goal of incorporating the value of nature into national decision making by estimating the multiple services obtained from ecosystems using the natural capital accounting framework. In this study, we produced 30-m resolution 10 classes land cover maps for the 2015 epoch for Liberia and Gabon using the Google Earth Engine (GEE) cloud platform to support the ongoing natural capital accounting efforts in these nations. We propose an integrated method of pixel-based classification using Landsat 8 data, the Random Forest (RF) classifier and ancillary data to produce high quality land cover products to fit a broad range of applications, including natural capital accounting. Our approach focuses on a pre-classification filtering (Masking Phase) based on spectral signature and ancillary data to reduce the number of pixels prone to be misclassified; therefore, increasing the quality of the final product. The proposed approach yields an overall accuracy of 83% and 81% for Liberia and Gabon, respectively, outperforming prior land cover products for these countries in both thematic content and accuracy. Our approach, while relatively simple and highly replicable, was able to produce high quality land cover products to fill an observational gap in up to date land cover data at national scale for Liberia and Gabon.
Klíčová slova:
Ecosystems – Forests – Forest ecology – Crops – Flooding – Liberia – Mangrove swamps – Gabon
Zdroje
1. Ordway EM, Asner GP, Lambin EF. Deforestation risk due to commodity crop expansion in sub-Saharan Africa. Environ Res Lett. 2017;12(4).
2. Christie T, Steininger MK, Juhn D, Peal A. Fragmentation and clearance of Liberia’s forests during 1986–2000. Oryx [Internet]. 2007 Oct 3;41(4):539–43. Available from: http://www.journals.cambridge.org/abstract_S0030605307000609
3. Henders S, Persson UM, Kastner T. Trading forests: land-use change and carbon emissions embodied in production and exports of forest-risk commodities. Environ Res Lett. 2015 Dec;10(12):125012.
4. Kastner T, Erb KH, Haberl H. Rapid growth in agricultural trade: Effects on global area efficiency and the role of management. Environ Res Lett. 2014;9(3). doi: 10.1088/1748-9326/9/3/031002
5. Malhi Y, Adu-bredu S, Asare RA, Lewis SL, Mayaux P. The past, present and future of Africa’ s rainforests. Philos Trans R Soc B Biol Sci. 2013;(September).
6. Mittermeier RA, Gil P, Hoffmann M, Pilgrim J, Brooks T, Mittermeier C, et al. Hotspots Revisited: Earth’s Biologically Richest and Most Endangered Terrestrial Ecoregions. Cemex. 2004 Dec;
7. Sannier C, Mcroberts RE, Fichet L, Massard E, Makaga K. Using the regression estimator with Landsat data to estimate proportion forest cover and net proportion deforestation in Gabon. Remote Sens Environ [Internet]. 2014;151:138–48. Available from: https://doi.org/10.1016/j.rse.2013.09.015
8. Carpenter SR, Mooney HA, Agard J, Capistrano D, Defries RS, Díaz S, et al. Science for managing ecosystem services: Beyond the Millennium Ecosystem Assessment. Proc Natl Acad Sci. 2009;106(5):1305–12. doi: 10.1073/pnas.0808772106 19179280
9. Daily G, Polasky S, Goldstein J, Kareiva P, Mooney H, Pejchar L, et al. Ecosystem services in decision making: time to deliver. Front Ecol Environ. 2009;
10. Bennett EM, Garry P, Gordon L. Understanding relationships among multiple ecosystem services. Ecol Lett. 2009;12:1394–404. doi: 10.1111/j.1461-0248.2009.01387.x 19845725
11. Häyhä T, Franzese P. Ecosystem services assessment: A review under an ecological-economic and systems perspective. Ecol Model. 2014;289:124–32.
12. Friedl MA, Sulla-Menashe D, Tan B, Schneider A, Ramankutty N, Sibley A, et al. MODIS Collection 5 global land cover: Algorithm refinements and characterization of new datasets. Remote Sens Environ. 2010;114(1):168–82.
13. Arino O, Arino O, Gross D, Gross D, Ranera F, Ranera F. GlobCover: ESA service for Global Land Cover from MERIS. Processing. 2000;2412–5.
14. Bontemps S, Defourny P, Bogaert E Van, Kalogirou V, Perez JR. GLOBCOVER 2009 Products Description and Validation Report. ESA Bull. 2011;136(June 2016):53.
15. Fritz S, Belward AS, Hartley A, European Commission. Joint Research Centre. H, H.-j. S, Douglas EH, et al. Harmonisation, Mosaicking and Production of the Global Land Cover 2000 Database (Beta version). 2003;41.
16. Bartholomé E, Belward AS. GLC2000: A new approach to global land cover mapping from earth observation data. Int J Remote Sens. 2005;26(9):1959–77.
17. Loveland TR, Reed BC, Brown JF, Ohlen DO, Zhu Z, Yang L, et al. Development of a global land cover characteristics database and IGBP DISCover from 1 km AVHRR data Development of a global land cover characteristics database and IGBP DISCover from 1 km AVHRR data. Int J Remote Sens. 2000;21(7):6–7.
18. Wickham J, Homer C, Vogelmann J, Mckerrow A, Mueller R, Herold N, et al. The Multi-Resolution Land Characteristics (MRLC) Consortium—20 Years of Development and Integration of USA National Land Cover Data. Remote Sens. 2014;(Cdl):7424–41.
19. Jawarneh RN, Biradar CM. Decadal National Land Cover Database for Jordan at 30 m resolution. Arab J Geosci. 2017;
20. Vittek M, Brink A, Donnay F, Simonetti D, Desclée B. Land cover change monitoring using landsat MSS/TM satellite image data over west Africa between 1975 and 1990. Remote Sens. 2013;6(1):658–76.
21. Laurin GV, Liesenberg V, Chen Q, Guerriero L, Del Frate F, Bartolini A, et al. Optical and SAR sensor synergies for forest and land cover mapping in a tropical site in West Africa. Int J Appl Earth Obs Geoinf [Internet]. 2012;21(1):7–16. Available from: https://doi.org/10.1016/j.jag.2012.08.002
22. Gessner U, Machwitz M, Esch T, Tillack A, Naeimi V, Kuenzer C, et al. Multi-sensor mapping of West African land cover using MODIS, ASAR and TanDEM-X/TerraSAR-X data. Remote Sens Environ [Internet]. 2015;164:282–97. Available from: https://doi.org/10.1016/j.rse.2015.03.029
23. Mayaux P, Bartholome E, Fritz S, Belward A. A New Land Cover Map of Africa for the Year 2000. J Biogeogr. 2004;31:861–77.
24. Gorelick N, Hancher M, Dixon M, Ilyushchenko S, Thau D, Moore R. Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sens Environ [Internet]. 2017;202:18–27. Available from: https://doi.org/10.1016/j.rse.2017.06.031
25. Johansen K, Phinn S, Taylor M. Mapping woody vegetation clearing in Queensland, Australia from Landsat imagery using the Google Earth Engine. Remote Sens Appl Soc Environ [Internet]. 2015;1(July):36–49. Available from: https://doi.org/10.1016/j.rsase.2015.06.002
26. Johnson BA, Iizuka K. Integrating OpenStreetMap crowdsourced data and Landsat time-series imagery for rapid land use/land cover (LULC) mapping: Case study of the Laguna de Bay area of the Philippines. Appl Geogr [Internet]. 2016 Feb;67:140–9. Available from: https://doi.org/10.1016/j.apgeog.2015.12.006
27. Wingate V, Phinn S, Kuhn N, Bloemertz L, Dhanjal-Adams K. Mapping Decadal Land Cover Changes in the Woodlands of North Eastern Namibia from 1975 to 2014 Using the Landsat Satellite Archived Data. Remote Sens [Internet]. 2016 Aug 20;8(8):681. Available from: http://www.mdpi.com/2072-4292/8/8/681
28. Goldblatt R, You W, Hanson G, Khandelwal A. Detecting the Boundaries of Urban Areas in India: A Dataset for Pixel-Based Image Classification in Google Earth Engine. Remote Sens [Internet]. 2016 Aug 1;8(8):634. Available from: http://www.mdpi.com/2072-4292/8/8/634
29. Xiong J, Thenkabail P, Tilton J, Gumma M, Teluguntla P, Oliphant A, et al. Nominal 30-m Cropland Extent Map of Continental Africa by Integrating Pixel-Based and Object-Based Algorithms Using Sentinel-2 and Landsat-8 Data on Google Earth Engine. Remote Sens [Internet]. 2017 Oct 19;9(10):1065. Available from: http://www.mdpi.com/2072-4292/9/10/1065
30. Hansen MCC, Potapov PV, Moore R, Hancher M, Turubanova SA a, Tyukavina A, et al. High-Resolution Global Maps of 21st-Century Forest Cover Change. Science (80-) [Internet]. 2013 Nov 15;342(6160):850–3. Available from: http://www.ncbi.nlm.nih.gov/pubmed/24233722
31. Bunting P, Rosenqvist A, Lucas RM, Rebelo L, Hilarides L, Thomas N, et al. The Global Mangrove Watch—A New 2010 Global Baseline of Mangrove Extent. Remote Sens. 2018;
32. Oliphant AJ, Thenkabail PS, Teluguntla P, Xiong J, Krishna M, Congalton RG, et al. Mapping cropland extent of Southeast and Northeast Asia using multi-year time-series Landsat 30-m data using a random forest classifier on the Google Earth Engine Cloud. Int J Appl Earth Obs Geoinf [Internet]. 2019;81(August 2018):110–24. Available from: https://doi.org/10.1016/j.jag.2018.11.014
33. Simonetti D, Simonetti E, Szantoi Z, Lupi A, Eva HD. First Results from the Phenology-Based Synthesis Classifier Using Landsat 8 Imagery. IEEE Geosci Remote Sens Lett. 2015;12(7):1496–500.
34. Mahdianpari M, Salehi B, Mohammadimanesh F. The First Wetland Inventory Map of Newfoundland at a Spatial Resolution of 10 m Using Sentinel-1 and Sentinel-2 Data on the Google Earth Engine Cloud Computing Platform. Remote Sens. 2018;11(4).
35. Sidhu N, Pebesma E, Câmara G. Using Google Earth Engine to detect land cover change: Singapore as a use case Using Google Earth Engine to detect land cover change: Singapore as a use. Eur J Remote Sens [Internet]. 2018;51(1):486–500. Available from: https://doi.org/10.1080/22797254.2018.1451782
36. Miettinen J, Shi C, Liew SC. Land cover map of Southeast Asia at 250 m spatial resolution. Remote Sens Lett [Internet]. 2016 Jul 2;7(7):701–10. Available from: https://doi.org/10.1080/2150704X.2016.1182659
37. Chen B, Xiao X, Li X, Pan L, Doughty R, Ma J, et al. A mangrove forest map of China in 2015: Analysis of time series Landsat 7/8 and Sentinel-1A imagery in Google Earth Engine cloud computing platform. ISPRS J Photogramm Remote Sens [Internet]. 2017 Sep;131(September):104–20. Available from: https://doi.org/10.1016/j.isprsjprs.2017.07.011
38. Parente L, Ferreira L, Faria A, Nogueira S, Araújo F, Teixeira L, et al. Monitoring the brazilian pasturelands: A new mapping approach based on the landsat 8 spectral and temporal domains. Int J Appl Earth Obs Geoinf [Internet]. 2017 Oct;62(June):135–43. Available from: https://doi.org/10.1016/j.jag.2017.06.003
39. Giri Chandra, Lomg J, Abbas S, Mani R Murali FMQ and DT. Distribution and dynamics of mangrove forests of South Asia. J Environ Manage. 2015;48(v):101–11.
40. Trianni G, Angiuli E, Lisini G, Gamba P. Human settlements from Landsat data using Google Earth Engine. Geosci Remote Sens Symp. 2014;1473–6.
41. Jin Z, Azzari G, You C, Di S, Aston S, Burke M, et al. Smallholder maize area and yield mapping at national scales with Google Earth Engine. Remote Sens Environ [Internet]. 2019;228(September 2018):115–28. Available from: https://doi.org/10.1016/j.rse.2019.04.016
42. Lohou F, Kergoat L, Guichard F, Boone A, Cappelaere B, Cohard J, et al. Surface response to rain events throughout the West African monsoon. 2014;3883–98.
43. Azzari G, Lobell DB. Landsat-based classification in the cloud: An opportunity for a paradigm shift in land cover monitoring. Remote Sens Environ [Internet]. 2016;202:64–74. Available from: https://doi.org/10.1016/j.rse.2017.05.025
44. Midekisa A, Holl F, Savory DJ, Andrade-Pacheco R, Gething PW, Bennett A, et al. Mapping land cover change over continental Africa using Landsat and Google Earth Engine cloud computing. Schumann GJ-P, editor. PLoS One [Internet]. 2017 Sep 27;12(9):e0184926. Available from: https://plos.org/10.1371/journal.pone.0184926 28953943
45. Giri C, Ochieng E, Tieszen LL, Zhu Z, Singh A, Loveland T, et al. Status and distribution of mangrove forests of the world using earth. 2011;154–9.
46. Breiman L. Random Forests. Mach Learn. 2001;45(1):5–32.
47. Bwangoy JB, Hansen MC, Roy DP, Grandi G De, Justice CO. Remote Sensing of Environment Wetland mapping in the Congo Basin using optical and radar remotely sensed data and derived topographical indices. Remote Sens Environ [Internet]. 2010;114(1):73–86. Available from: https://doi.org/10.1016/j.rse.2009.08.004
48. Dinh N, Hazarika M. Remote Sensing of Environment A comparison of forest cover maps in Mainland Southeast Asia from multiple sources: Remote Sens Environ [Internet]. 2012;127:60–73. Available from: https://doi.org/10.1016/j.rse.2012.08.022
49. Hansen MC, Roy DP, Lindquist E, Adusei B, Justice CO, Altstatt A. A method for integrating MODIS and Landsat data for systematic monitoring of forest cover and change in the Congo Basin. Remote Sens Environ. 2008;112:2495–513.
50. Shi T, Liu J, Hu Z, Liu H, Wang J, Wu G. New spectral metrics for mangrove forest identification. Remote Sens Lett [Internet]. 2016;7(9):885–94. Available from: https://doi.org/10.1080/2150704X.2016.1195935
51. Xu H. Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery. Int J Remote Sens. 2007;1161.
52. Zha Y, Gao J, Ni S. Use of normalized di ff erence built-up index in automatically mapping urban areas from TM imagery. Proc 2005 IEEE Int Geosci Remote Sens Symp. 2003;24(3):583–94.
53. Wang Z, Gang C, Li X, Chen Y. Application of a normalized difference impervious index (NDII) to extract urban impervious surface features based on Landsat TM images. Int J Remote Sens. 2015;36(March 2018). doi: 10.1080/01431161.2015.1101505
54. Zhao H, Chen X. Use of Normalized Difference Bareness Index in Quickly Mapping Bare Areas from TM / ETM +. Proceedings 2005 IEEE Int Geosci Remote Sens Symp 2005 IGARSS ‘05. 2005;1666–8.
55. Rikimaru A, Miyatake S. Development of Forest Canopy Density Mapping and Monitoring Model using Indices of Vegetation, Bare soil and Shadow. Proceeding 18th Asian Conf Remote Sens 1997. 1997;
56. Kawamura M, Jayamana S, Tsujiko Y. Relation between social and environmental conditions in Colombo Sri Lanka and the urban index estimated by satellite remote sensing data.pdf. Int Arch Photogramm Remote Sens. 1996;
57. Rouse W, Haas H, Deering W. 20 monitoring vegetation systems in the great plains with ERTS. 3rd ERTS Symp. 1973;
58. Gitelson AA, Vina A, Arkebauer T, Rundquist D, Keydan G, Leavitt B. Remote estimation of leaf area index and green leaf biomass in maize canopies. Geophys Res Lett. 2003;
59. Jordan C. Derivation of leaf-area index from quality of light on the forest floor. Ecology. 1969;50(4):1–4.
60. Townsend PA, Walsh SJ. Modeling floodplain inundation using an integrated GIS with radar and optical remote sensing. Geomorphology. 1998;21:295–312.
61. Townsend PA. Mapping Seasonal Flooding in Forested Wetlands Using Multi-Temporal Radarsat SAR. Photogramm Eng Remote Sens. 1995;
62. Tsyganskaya V, Martinis S, Marzahn P, Ludwig R, Tsyganskaya V, Martinis S, et al. SAR-based detection of flooded vegetation–a review of characteristics and approaches. Int J Remote Sens [Internet]. 2018;39(8):2255–93. Available from: https://doi.org/10.1080/01431161.2017.1420938
63. Hess LL, Melack JM, Filoso S, Wang Y. Delineation of Inundated Area and Vegetation Along the Amazon Floodplain with the SIR-C Synthetic Aperture Radar. IEEE Trans Geosci Remote Sens. 1995;33(4).
64. Wang Y, Hess LL, Filoso S, Melack JM. Understanding the Radar Backscattering from Flooded and Nonflooded Amazonian Forests: Results from Canopy Backscatter Modeling. Remote Sens Environ. 1995;4257(1979).
65. Henderson FM, Lewis AJ. Radar detection of wetland ecosystems: A review. Int J Remote Sens. 2008;1161.
66. Hess LL, Melack JM. Remote sensing of vegetation and flooding on Magela Creek Floodplain (Northern Territory, Australia) with the SIR-C synthetic aperture radar Remote sensing of vegetation and flooding on Magela Creek Floodplain (Northern Territory, Australia) with th. Hydrobiologia. 2015;(January).
67. Olofsson P, Foody GM, Herold M, Stehman SV, Woodcock CE, Wulder MA. Good practices for estimating area and assessing accuracy of land change. Remote Sens Environ [Internet]. 2014;148:42–57. Available from: https://doi.org/10.1016/j.rse.2014.02.015
68. Geoville, Metria. Liberia Land Cover and Forest Mapping for the Readiness Preparation Aactivities of the Forestry Development Authority. 2016.
69. Pekel J-F, Cottam A, Gorelick N, Belward AS. High-resolution mapping of global surface water and its long-term changes. Nature [Internet]. 2016 Dec 7;540(7633):418–22. Available from: http://www.nature.com/doifinder/10.1038/nature20584 27926733
70. Claverie M, Ju J, Masek JG, Dungan JL, Vermote EF, Roger J, et al. The Harmonized Landsat and Sentinel-2 surface reflectance data set. Remote Sens Environ [Internet]. 2018;219(August 2017):145–61. Available from: https://doi.org/10.1016/j.rse.2018.09.002
Článok vyšiel v časopise
PLOS One
2020 Číslo 1
- Metamizol jako analgetikum první volby: kdy, pro koho, jak a proč?
- Nejasný stín na plicích – kazuistika
- Masturbační chování žen v ČR − dotazníková studie
- Těžké menstruační krvácení může značit poruchu krevní srážlivosti. Jaký management vyšetření a léčby je v takovém případě vhodný?
- Fixní kombinace paracetamol/kodein nabízí synergické analgetické účinky
Najčítanejšie v tomto čísle
- Psychometric validation of Czech version of the Sport Motivation Scale
- Comparison of Monocyte Distribution Width (MDW) and Procalcitonin for early recognition of sepsis
- Effects of supplemental creatine and guanidinoacetic acid on spatial memory and the brain of weaned Yucatan miniature pigs
- Accelerated sparsity based reconstruction of compressively sensed multichannel EEG signals