Mapping and Assessing the Dynamics of Shifting Agricultural Landscapes Using Google Earth Engine Cloud Computing, a Case Study in Mozambique
"> Figure 1
<p>Location of Vilankulo district in Mozambique (<b>left</b>) and map of Vilankulo district (<b>right</b>) with location of the training and validation datasets. CCNV—close canopy natural vegetation; OCNV—open canopy natural vegetation; WB—water bodies; AGR—agriculture; BS—bare soils; GR—grassland.</p> "> Figure 2
<p>Land cover maps of Vilankulo for the years 2012 (upper left), 2015 (upper right), and 2018 (lower left). CCNV—close canopy natural vegetation; OCNV—open canopy natural vegetation; WB—water bodies; AGR—agriculture; BS—bare soils; GR—grassland.</p> "> Figure 3
<p>Comparison between cultivated area derived from remote sensing data (classification results) and from ‘Serviços Distritais de Actividades Económicas (SDAE)’ (Local agrarian data). The percentage of overestimation of Google Earth Engine (GEE) classification relative to ground truth data is provided for each year.</p> ">
Abstract
:1. Introduction
2. Materials and Methods
2.1. Study Area Description
2.2. Landsat Image Selection and Pre-Processing
2.3. Texture Features
2.4. Vegetation Indices
2.5. Image Composites
2.6. Training and Validation Samples Collection
2.7. Input Features Selection for Classification
2.8. Classifier Algorithm
2.9. Accuracy Assessment
3. Results
3.1. Input Feature Selection
3.2. Spatial and Temporal Dynamics of Agriculture
3.2.1. Classification Results
3.2.2. Land Cover Statistics and Land Cover Changes
3.3. Comparison between Remote Sensed Classification and Agricultural Statistics
4. Discussion
5. Conclusions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
References
- FAO. FAO, Country Programming Framework for Mozambique 2016–2020; FAO: Maputo, Mozambique, 2016; p. 13. [Google Scholar]
- Fritz, S.; See, L.; McCallum, I.; You, L.; Bun, A.; Moltchanova, E.; Duerauer, M.; Albrecht, F.; Schill, C.; Perger, C.; et al. Mapping global cropland and field size. Glob. Chang. Biol. 2015, 21, 1980–1992. [Google Scholar] [CrossRef]
- Waldner, F.; Fritz, S.; Di Gregorio, A.; Defourny, P. Mapping Priorities to Focus Cropland Mapping Activities: Fitness Assessment of Existing Global, Regional and National Cropland Maps. Remote Sens. 2015, 7, 7959–7986. [Google Scholar] [CrossRef] [Green Version]
- Justice, C.O.; Becker-Reshef, I. Report from the Workshop on Developing a Strategy for Global Agricultural Monitoring in the Framework of Group on Earth Observations (GEO); UN FAO: Rome, Italy, 2007; p. 67. [Google Scholar]
- Hannerz, F.; Lotsch, A. Assessment of remotely sensed and statistical inventories of African agricultural fields. Int. J. Remote Sens. 2008, 29, 3787–3804. [Google Scholar] [CrossRef]
- Vancutsem, C.; Marinho, E.; Kayitakire, F.; See, L.; Fritz, S. Harmonizing and combining existing land cover/land use datasets for cropland area monitoring at the African continental scale. Remote Sens. 2012, 5, 22. [Google Scholar] [CrossRef] [Green Version]
- Lobell, D.B.; Bala, G.; Duffy, P.B. Biogeophysical impacts of cropland management changes on climate. Geophys. Res. Lett. 2006, 33. [Google Scholar] [CrossRef]
- INE. Censo Agro-Pecuário CAP 2009–2010: Resultados preliminares-Moçambique; Instituto Nacional de Estatistcas: Madrid, Spain, 2011; p. 125. [Google Scholar]
- Morris, M.B.H.; Byerlee, D.; Savanti, P.; Staatz, J. Awakening Africa’s Sleeping Giant: Prospects for Commercial Agriculture in the Guinea Savannah Zone and Beyond; The World Bank: Washington, DC, USA, 2009. [Google Scholar]
- United Nations. World Population Prospects: The 2012 Revision, Highlights and Advance Tables; United Nations: New York, NY, USA, 2013. [Google Scholar]
- Brink, A.B.; Eva, H.D. Monitoring 25 years of land cover change dynamics in Africa: A sample based remote sensing approach. Appl. Geogr. 2009, 29, 12. [Google Scholar] [CrossRef]
- Ramankutty, N.; Evan, A.T.; Monfreda, C.; Foley, J.A. Farming the planet: 1. Geographic distribution of global agricultural lands in the year 2000. Glob. Biogeochem. Cycles 2008, 22. [Google Scholar] [CrossRef]
- Azzari, G.; Lobell, D.B. Landsat-based classification in the cloud: An opportunity for a paradigm shift in land cover monitoring. Remote Sens. Environ. 2017, 202, 64–74. [Google Scholar] [CrossRef]
- Bartholomé, E.; Belward, A.S. GLC2000: A new approach to global land cover mapping from Earth observation data. Int. J. Remote Sens. 2005, 26, 1959–1977. [Google Scholar] [CrossRef]
- Fritz, S.; Bartholomé, E.; Belward, A.; Hartley, A.; Stibig, H.J.; Eva, H.; Mayaux, P.; Bartalev, S.; Latifovic, R.; Kolmert, S.; et al. Harmonisation, Mosaicing and Production of the Global Land Cover 2000 Database (Beta Version); EC-JRC: Ispra, Italy, 2003. [Google Scholar]
- Arino, O.; Gross, D.; Ranera, F.; Leroy, M.; Bicheron, P.; Brockman, C.; Defourny, P.; Vancutsem, C.; Achard, F.; Durieux, L.; et al. GlobCover: ESA service for global land cover from MERIS. In Proceedings of the 2007 IEEE International Geoscience and Remote Sensing Symposium, Barcelona, Spain, 23–28 July 2007; pp. 2412–2415. [Google Scholar]
- Friedl, M.A.; Sulla-Menashe, D.; Tan, B.; Schneider, A.; Ramankutty, N.; Sibley, A.; Huang, X. MODIS Collection 5 global land cover: Algorithm refinements and characterization of new datasets. Remote Sens. Environ. 2010, 114, 168–182. [Google Scholar] [CrossRef]
- Loveland, T.R.; Reed, B.C.; Brown, J.F.; Ohlen, D.O.; Zhu, Z.; Yang, L.; Merchant, J.W. Development of a global land cover characteristics database and IGBP DISCover from 1 km AVHRR data. Int. J. Remote Sens. 2000, 21, 1303–1330. [Google Scholar] [CrossRef]
- Thenkabail, P.S.; Knox, J.W.; Ozdogan, M.; Gumma, M.K.; Congalton, R.G.; Wu, Z.; Milesi, C.; Finkral, A.; Marshall, M.; Mariotto, I.; et al. Assessing future risks to agricultural productivity, water resources and food security: How can remote sensing help? Photogramm. Eng. Remote Sens. 2012, 78, 773–782. [Google Scholar]
- Chen, J.; Chen, J.; Liao, A.; Cao, X.; Chen, L.; Chen, X.; He, C.; Han, G.; Peng, S.; Lu, M.; et al. Global land cover mapping at 30m resolution: A POK-based operational approach. ISPRS J. Photogramm. Remote Sens. 2015, 103, 7–27. [Google Scholar] [CrossRef] [Green Version]
- Anderson, W.; You, L.; Wood, S.; Wood-Sichra, U.; Wu, W. An analysis of methodological and spatial differences in global cropping systems models and maps. Glob. Ecol. Biogeogr. 2015, 24, 180–191. [Google Scholar] [CrossRef]
- Fritz, S.; See, L.; McCallum, I.; Schill, C.; Obersteiner, M.; van der Velde, M.; Boettcher, H.; Havlík, P.; Achard, F. Highlighting continued uncertainty in global land cover maps for the user community. Environ. Res. Lett. 2011, 6, 044005. [Google Scholar] [CrossRef]
- Debats, S.R.; Luo, D.; Estes, L.D.; Fuchs, T.J.; Caylor, K.K. A generalized computer vision approach to mapping crop fields in heterogeneous agricultural landscapes. Remote Sens. Environ. 2016, 179, 210–221. [Google Scholar] [CrossRef] [Green Version]
- Delrue, J.; Bydekerke, L.; Eerens, H.; Gilliams, S.; Piccard, I.; Swinnen, E. Crop mapping in countries with small-scale farming: A case study for West Shewa, Ethiopia. Int. J. Remote Sens. 2013, 34, 2566–2582. [Google Scholar] [CrossRef]
- Jain, M.; Mondal, P.; DeFries, R.S.; Small, C.; Galford, G.L. Mapping cropping intensity of smallholder farms: A comparison of methods using multiple sensors. Remote Sens. Environ. 2013, 134, 210–223. [Google Scholar] [CrossRef] [Green Version]
- Jin, Z.; Azzari, G.; You, C.; Di Tommaso, S.; Aston, S.; Burke, M.; Lobell, D.B. Smallholder maize area and yield mapping at national scales with Google Earth Engine. Remote Sens. Environ. 2019, 228, 115–128. [Google Scholar] [CrossRef]
- Lebourgeois, V.; Dupuy, S.; Vintrou, É.; Ameline, M.; Butler, S.; Bégué, A. A Combined Random Forest and OBIA Classification Scheme for Mapping Smallholder Agriculture at Different Nomenclature Levels Using Multisource Data (Simulated Sentinel-2 Time Series, VHRS and DEM). Remote Sens. 2017, 9, 259. [Google Scholar] [CrossRef] [Green Version]
- McCarty, J.L.; Neigh, C.S.R.; Carroll, M.L.; Wooten, M.R. Extracting smallholder cropped area in Tigray, Ethiopia with wall-to-wall sub-meter WorldView and moderate resolution Landsat 8 imagery. Remote Sens. Environ. 2017, 202, 142–151. [Google Scholar] [CrossRef]
- Sweeney, S.; Ruseva, T.; Estes, L.; Evans, T. Mapping Cropland in Smallholder-Dominated Savannas: Integrating Remote Sensing Techniques and Probabilistic Modeling. Remote Sens. 2015, 7, 15295–15317. [Google Scholar] [CrossRef] [Green Version]
- Timmermans, A. Mapping Cropland in Smallholder Farmer Systems in South-Africa Using Sentinel-2 Imagery; Université Catholique de Louvain: Louvain, Belgium, 2018. [Google Scholar]
- Vogels, M.; De Jong, S.; Sterk, G.; Douma, H.; Addink, E. Spatio-Temporal Patterns of Smallholder Irrigated Agriculture in the Horn of Africa Using GEOBIA and Sentinel-2 Imagery. Remote Sens. 2019, 11, 143. [Google Scholar] [CrossRef] [Green Version]
- Lambert, M.-J.; Pierre, T.; Xavier, B.; Philippe, B.; Pierre, D. Estimating smallholder crops production at village level from Sentinel-2 time series in Mali’s cotton belt. Remote Sens. Environ. 2018, 216. [Google Scholar] [CrossRef]
- Räsänen, A.; Virtanen, T. Data and resolution requirements in mapping vegetation in spatially heterogeneous landscapes. Remote Sens. Environ. 2019, 230, 111207. [Google Scholar] [CrossRef]
- Chen, W.; Li, X.; He, H.; Wang, L. Assessing Different Feature Sets’ Effects on Land Cover Classification in Complex Surface-Mined Landscapes by ZiYuan-3 Satellite Imagery. Remote Sensing 2018, 10, 23. [Google Scholar] [CrossRef] [Green Version]
- Coburn, C.A.; Roberts, A.C.B. A multiscale texture analysis procedure for improved forest stand classification. Int. J. Remote Sens. 2004, 25, 4287–4308. [Google Scholar] [CrossRef] [Green Version]
- Khatami, R.; Mountrakis, G.; Stehman, S.V. A meta-analysis of remote sensing research on supervised pixel-based land-cover image classification processes: General guidelines for practitioners and future research. Remote Sens. Environ. 2016, 177, 89–100. [Google Scholar] [CrossRef] [Green Version]
- Rodriguez-Galiano, V.F.; Chica-Olmo, M.; Abarca-Hernandez, F.; Atkinson, P.M.; Jeganathan, C. Random Forest classification of Mediterranean land cover using multi-seasonal imagery and multi-seasonal texture. Remote Sens. Environ. 2012, 121, 93–107. [Google Scholar] [CrossRef]
- Wu, W.; Zucca, C.; Karam, F.; Liu, G. Enhancing the performance of regional land cover mapping. Int. J. Appl. Earth Obs. Geoinf. 2016, 52, 422–432. [Google Scholar] [CrossRef]
- Wulder, M.A.; White, J.C.; Loveland, T.R.; Woodcock, C.E.; Belward, A.S.; Cohen, W.B.; Fosnight, E.A.; Shaw, J.; Masek, J.G.; Roy, D.P. The global Landsat archive: Status, consolidation, and direction. Remote Sens. Environ. 2016, 185, 271–283. [Google Scholar] [CrossRef] [Green Version]
- Kpienbaareh, D.; Kansanga, M.; Luginaah, I. Examining the potential of open source remote sensing for building effective decision support systems for precision agriculture in resource-poor settings. GeoJournal 2018. [Google Scholar] [CrossRef]
- Gorelick, N.; Hancher, M.; Dixon, M.; Ilyushchenko, S.; Thau, D.; Moore, R. Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sens. Environ. 2017, 202, 18–27. [Google Scholar] [CrossRef]
- Dong, J.; Xiao, X.; Menarguez, M.A.; Zhang, G.; Qin, Y.; Thau, D.; Biradar, C.; Moore, B. Mapping paddy rice planting area in northeastern Asia with Landsat 8 images, phenology-based algorithm and Google Earth Engine. Remote Sens. Environ. 2016, 185, 142–154. [Google Scholar] [CrossRef] [Green Version]
- Padarian, J.; Minasny, B.; McBratney, A.B. Using Google’s cloud-based platform for digital soil mapping. Comput. Geosci. 2015, 83, 80–88. [Google Scholar] [CrossRef]
- Patel, N.N.; Angiuli, E.; Gamba, P.; Gaughan, A.; Lisini, G.; Stevens, F.R.; Tatem, A.J.; Trianni, G. Multitemporal settlement and population mapping from Landsat using Google Earth Engine. Int. J. Appl. Earth Obs. Geoinf. 2015, 35, 199–208. [Google Scholar] [CrossRef] [Green Version]
- Simonetti, D.; Simonetti, E.; Szantoi, Z.; Lupi, A.; Eva, H.D. First Results from the Phenology-Based Synthesis Classifier Using Landsat 8 Imagery. IEEE Geosci. Remote Sens. Lett. 2015, 12, 1496–1500. [Google Scholar] [CrossRef]
- Hansen, M.C.; Potapov, P.V.; Moore, R.; Hancher, M.; Turubanova, S.A.; Tyukavina, A.; Thau, D.; Stehman, S.V.; Goetz, S.J.; Loveland, T.R.; et al. High-Resolution Global Maps of 21st-Century Forest Cover Change. Science 2013, 342, 850–853. [Google Scholar] [CrossRef] [Green Version]
- Pekel, J.-F.; Cottam, A.; Gorelick, N.; Belward, A.S. High-resolution mapping of global surface water and its long-term changes. Nature 2016, 540, 418. [Google Scholar] [CrossRef]
- Breiman, L. Random Forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef] [Green Version]
- Cortes, C.; Vapnik, V. Support-vector networks. Mach. Learn. 1995, 20, 273–297. [Google Scholar] [CrossRef]
- Phillips, S.J.; Anderson, R.P.; Schapire, R.E. Maximum entropy modeling of species geographic distributions. Ecol. Model. 2006, 190, 231–259. [Google Scholar] [CrossRef] [Green Version]
- Breiman, L.; Friedman, J.; Stone, C.; Olshen, R. Classification and Regression Trees; Chapman&Hall/CRC: Boca Raton, FL, USA, 1984. [Google Scholar]
- Belgiu, M.; Drăguţ, L. Random forest in remote sensing: A review of applications and future directions. ISPRS J. Photogramm. Remote Sens. 2016, 114, 24–31. [Google Scholar] [CrossRef]
- Gómez, C.; White, J.C.; Wulder, M.A. Optical remotely sensed time series data for land cover classification: A review. ISPRS J. Photogramm. Remote Sens. 2016, 116, 55–72. [Google Scholar] [CrossRef] [Green Version]
- Pretty, J.N.; Noble, A.D.; Bossio, D.; Dixon, J.; Hine, R.E.; Penning de Vries, F.W.T.; Morison, J.I.L. Resource-Conserving Agriculture Increases Yields in Developing Countries. Environ. Sci. Technol. 2006, 40, 1114–1119. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Haralick, R.M.; Shanmugam, K.; Dinstein, I. Textural Features for Image Classification. IEEE Trans. Syst. ManCybern. 1973, SMC-3, 610–621. [Google Scholar] [CrossRef] [Green Version]
- Kuplich, T.M.; Curran, P.J.; Atkinson, P.M. Relating SAR image texture to the biomass of regenerating tropical forests. Int. J. Remote Sens. 2005, 26, 4829–4854. [Google Scholar] [CrossRef]
- Asner, G.P.; Palace, M.; Keller, M.; Pereira, R., Jr.; Silva, J.N.M.; Zweede, J.C. Estimating Canopy Structure in an Amazon Forest from Laser Range Finder and IKONOS Satellite Observations1. Biotropica 2002, 34, 483–492. [Google Scholar] [CrossRef]
- Wright, C.; Gallant, A. Improved wetland remote sensing in Yellowstone National Park using classification trees to combine TM imagery and ancillary environmental data. Remote Sens. Environ. 2007, 107, 582–605. [Google Scholar] [CrossRef]
- Augusteijn, M.F.; Clemens, L.E.; Shaw, K.A. Performance evaluation of texture measures for ground cover identification in satellite images by means of a neural network classifier. IEEE Trans. Geosci. Remote Sens. 1995, 33, 616–626. [Google Scholar] [CrossRef]
- Baraldi, A.; Parmiggiani, F. An investigation of the textural characteristics associated with Gray Level Co-occurrence Matrix statistical parameters. Geosci. Remote Sens. IEEE Trans. 1995, 33, 293–304. [Google Scholar] [CrossRef]
- Castillo-Santiago, M.; Ricker, M.; Jong, B. Estimation of tropical forest structure from SPOT5 satellite images. Int. J. Remote Sens. 2010, 31, 2767–2782. [Google Scholar] [CrossRef]
- Kayitakire, F.; Hamel, C.; Defourny, P. Retrieving forest structure variables based on image texture analysis and IKONOS-2 imagery. Remote Sens. Environ. 2006, 102, 390–401. [Google Scholar] [CrossRef]
- Ozdemir, I.; Karnieli, A. Predicting forest structural parameters using the image texture derived from WorldView-2 multispectral imagery in a dryland forest, Israel. Int. J. Appl. Earth Obs. Geoinf. 2011, 13, 701–710. [Google Scholar] [CrossRef]
- Estes, L.D.; Reillo, P.R.; Mwangi, A.G.; Okin, G.S.; Shugart, H.H. Remote sensing of structural complexity indices for habitat and species distribution modeling. Remote Sens. Environ. 2010, 114, 792–804. [Google Scholar] [CrossRef]
- Beekhuizen, J.; Clarke, K.C. Toward accountable land use mapping: Using geocomputation to improve classification accuracy and reveal uncertainty. Int. J. Appl. Earth Obs. Geoinf. 2010, 12, 127–137. [Google Scholar] [CrossRef]
- Kimothi, M.; Dasari, A. Methodology to map the spread of an invasive plant (Lantana camara L.) in forest ecosystems using Indian remote sensing satellite data. Int. J. Remote Sens. 2010, 31, 3273–3289. [Google Scholar] [CrossRef]
- Pacifici, F.; Chini, M.; Emery, W.J. A neural network approach using multi-scale textural metrics from very high-resolution panchromatic imagery for urban land-use classification. Remote Sens. Environ. 2009, 113, 1276–1292. [Google Scholar] [CrossRef]
- Conners, R.W.; Trivedi, M.M.; Harlow, C.A. Segmentation of a high-resolution urban scene using texture operators. Comput. Vis. Graph. Image Process. 1984, 25, 273–310. [Google Scholar] [CrossRef]
- Rouse, J.W.; Haas, R.H.; Schell, J.A.; Deering, D.W. Monitoring vegetation systems in the Great Plains with ERTS. Proceedings of Third Earth Resources Technology Satellite Symposium, Washington, DC, USA, 10–14 December 1973; p. 9. [Google Scholar]
- Huete, A.R. A soil-adjusted vegetation index (SAVI). Remote Sens. Environ. 1988, 25, 295–309. [Google Scholar] [CrossRef]
- Huete, A.; Didan, K.; Miura, T.; Rodriguez, E.P.; Gao, X.; Ferreira, L.G. Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sens. Environ. 2002, 83, 195–213. [Google Scholar] [CrossRef]
- McFeeters, S.K. The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features. Int. J. Remote Sens. 1996, 17, 1425–1432. [Google Scholar] [CrossRef]
- Mahdianpari, M.; Salehi, B.; Mohammadimanesh, F.; Homayouni, S.; Gill, E. 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, 43. [Google Scholar] [CrossRef] [Green Version]
- De Alban, J.D.; Connette, G.; Oswald, P.; Webb, E. Combined Landsat and L-Band SAR Data Improves Land Cover Classification and Change Detection in Dynamic Tropical Landscapes. Remote Sens. 2018, 10, 306. [Google Scholar] [CrossRef] [Green Version]
- Qadir, A.; Mondal, P. Synergistic Use of Radar and Optical Satellite Data for Improved Monsoon Cropland Mapping in India. Remote Sens. 2020, 12, 522. [Google Scholar] [CrossRef] [Green Version]
- Cossu, R. Segmentation by means of textural analysis. Pixel 1988, 1, 4. [Google Scholar]
- Carr, J.R.; Miranda, F.P.d. The semivariogram in comparison to the co-occurrence matrix for classification of image texture. IEEE Trans. Geosci. Remote Sens. 1998, 36, 1945–1952. [Google Scholar] [CrossRef] [Green Version]
- Rao, P.; Seshasai, M.; Kandrika, S.; Rao, M.; Rao, B.; Dwivedi, R.; Venkataratnam, L. Textural analysis of IRS-1D panchromatic data for land cover classification. Int. J. Remote Sens. 2002, 23, 3327–3345. [Google Scholar] [CrossRef]
- Solberg, A.H.S. Contextual data fusion applied to forest map revision. IEEE Trans. Geosci. Remote Sens. 1999, 37, 1234–1243. [Google Scholar] [CrossRef]
- Mishra, N.B.; Crews, K.A. Mapping vegetation morphology types in a dry savanna ecosystem: Integrating hierarchical object-based image analysis with Random Forest. Int. J. Remote Sens. 2014, 35, 1175–1198. [Google Scholar] [CrossRef]
- Richards, J.A.; Jia, X. Remote Sensing Digital Image Analysis: An Introduction, 4th ed.; Springer: Berlin, Germany, 2006. [Google Scholar]
- Swain, P.H.; King, R.C. Two effective feature selection criteria for multispectral remote sensing. In Proceedings of the International Joint Conference on Pattern Recognition, Washington, DC, USA, 1 January 1973; p. 6. [Google Scholar]
- Swain, H.; Davis, S.M. Remote Sensing: The Quantitative Approach; McGraw-Hill: New York, NY, USA, 1978. [Google Scholar]
- Turner, M.G. Landscape Ecology: The Effect of Pattern on Process. Annu. Rev. Ecol. Syst. 1989, 20, 171–197. [Google Scholar] [CrossRef]
- Breiman, L.; Cutler, A. Random Forests Homepage. Available online: http://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm (accessed on 29 May 2019).
- Akar, Ö.; Güngör, O. Integrating multiple texture methods and NDVI to the Random Forest classification algorithm to detect tea and hazelnut plantation areas in northeast Turkey. Int. J. Remote Sens. 2015, 36, 442–464. [Google Scholar] [CrossRef]
- Congalton, R.G. A review of assessing the accuracy of classifications of remotely sensed data. Remote Sens. Environ. 1991, 37, 35–46. [Google Scholar] [CrossRef]
- Pôças, I.; Cunha, M.; Marçal, A.; Pereira, L. An evaluation of changes in a mountainous rural landscape of Northeast Portugal using remotely sensed data. Landsc. Urban Plan. 2011, 101, 253–261. [Google Scholar] [CrossRef] [Green Version]
- Xu, Y.; Yu, L.; Zhao, F.R.; Cai, X.; Zhao, J.; Lu, H.; Gong, P. Tracking annual cropland changes from 1984 to 2016 using time-series Landsat images with a change-detection and post-classification approach: Experiments from three sites in Africa. Remote Sens. Environ. 2018, 218, 13–31. [Google Scholar] [CrossRef]
- Samanta, A.; Knyazikhin, Y.; Xu, L.; Dickinson, R.E.; Fu, R.; Costa, M.H.; Saatchi, S.S.; Nemani, R.R.; Myneni, R.B. Seasonal changes in leaf area of Amazon forests from leaf flushing and abscission. J. Geophys. Res. Biogeosci. 2012, 117. [Google Scholar] [CrossRef] [Green Version]
- Wu, Q.; Song, C.; Song, J.; Wang, J.; Chen, S.; Yu, B. Impacts of Leaf Age on Canopy Spectral Signature Variation in Evergreen Chinese Fir Forests. Remote Sens. 2018, 10, 262. [Google Scholar] [CrossRef] [Green Version]
- Carrao, H.; Sarmento, P.; Araújo, A.; Caetano, M. Separability Aanalysis of Land Cover Classes at Regional Scale: A Comparative Study of MERIS and MODIS Data; European Space Agency, (Special Publication) ESA SP: Paris, France, 2007. [Google Scholar]
- Nitze, I.; Schulthess, U.; Asche, H. Comparison of machine learning algorithms random forest, artificial neural network and support vector machine to maximum likelihood for supervised crop type classification. Proceedings of 4th Conference on GEographic Object-Based Image Analysis, Rio de Janeiro, Brazil, 7–9 May 2012; p. 35. [Google Scholar]
- Tatsumi, K.; Yamashiki, Y.; Canales Torres, M.A.; Taipe, C.L.R. Crop classification of upland fields using Random forest of time-series Landsat 7 ETM+ data. Comput. Electron. Agric. 2015, 115, 171–179. [Google Scholar] [CrossRef]
- Aguilar, R.; Zurita-Milla, R.; Izquierdo-Verdiguier, E.; de By, R.A. A Cloud-Based Multi-Temporal Ensemble Classifier to Map Smallholder Farming Systems. Remote Sens. 2018, 10, 729. [Google Scholar] [CrossRef] [Green Version]
- Ok, A.O.; Akar, O.; Gungor, O. Evaluation of random forest method for agricultural crop classification. Eur. J. Remote Sens. 2012, 45, 421–432. [Google Scholar] [CrossRef]
- Jacobson, A.; Dhanota, J.; Godfrey, J.; Jacobson, H.; Rossman, Z.; Stanish, A.; Walker, H.; Riggio, J. A novel approach to mapping land conversion using Google Earth with an application to East Africa. Environ. Model. Softw. 2015, 72, 1–9. [Google Scholar] [CrossRef] [Green Version]
- Pimm, S.L.; Jenkins, C.N.; Abell, R.; Brooks, T.M.; Gittleman, J.L.; Joppa, L.N.; Raven, P.H.; Roberts, C.M.; Sexton, J.O. The biodiversity of species and their rates of extinction, distribution, and protection. Science 2014, 344, 1246752. [Google Scholar] [CrossRef] [PubMed]
- De Groote, H.; Traoré, O. The cost of accuracy in crop area estimation. Agric. Syst. 2005, 84, 21–38. [Google Scholar] [CrossRef] [Green Version]
- Dheeravath, V.; Thenkabail, P.; Chandrakantha, G.; Noojipady, P.; Reddy, G.P.O.; Biradar, C.; Gumma, M.; Velpuri, N.M. Irrigated areas of India derived using MODIS 500 m time series for the years 2001–2003. ISPRS J. Photogramm. Remote Sens. 2010, 65, 42–59. [Google Scholar] [CrossRef]
Season | Path/Row | Date |
---|---|---|
2015/2016 | 166/75 | 6 October 2015 |
166/76 | 6 October 2015 | |
23 November 2015 | ||
167/75 | 13 October 2015 | |
14 November 2015 | ||
2018/2019 | 166/75 | 14 October 2018 |
1 December 2018 | ||
17 December 2018 | ||
166/76 | 15 November 2018 | |
1 December 2018 | ||
17 December 2018 | ||
167/75 | 5 October 2018 | |
6 November 2018 | ||
8 December 2018 24 December 2018 |
Season | Path/Row | Date (Fill Scenes) | Date (Source Scenes) |
---|---|---|---|
2012/2013 | 166/75 | 5 October 2012 | 25 January 2013 |
166/76 | 5 October 2012 | 6 November 2012 | |
167/75 | 10 September 2012 | 13 November 2012 |
Cover Class | 2012 | 2015 | 2018 | |||
---|---|---|---|---|---|---|
Training | Validation | Training | Validation | Training | Validation | |
CCNV | 319 | 109 | 331 | 110 | 169 | 88 |
OCNV | 268 | 78 | 205 | 60 | 119 | 93 |
WB | 267 | 82 | 166 | 57 | 67 | 42 |
AGR | 551 | 154 | 606 | 177 | 316 | 185 |
BS | 181 | 40 | 342 | 172 | 138 | 93 |
GR | 330 | 116 | 375 | 108 | 221 | 132 |
# | Feature Combinations | Total Features | Average Separability per Classes | Average | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
Textures | W | VIs | # Bands | CCNV | OCNV | WB | AGR | BS | GR | |||
1 | T1 | 2 | Nil | 3 | 57 | 1.66 | 0.38 | 0.37 | 0.37 | 0.44 | 0.45 | 0.61 |
2 | T1 | 5 | Nil | 3 | 57 | 1.37 | 0.54 | 1.30 | 1.62 | 0.89 | 0.60 | 1.05 |
3 | T1 | 10 | Nil | 3 | 57 | 1.42 | 0.72 | 1.26 | 1.62 | 1.10 | 1.08 | 1.20 |
4 | T1 | 20 | Nil | 3 | 57 | 1.52 | 1.02 | 1.30 | 1.62 | 1.69 | 1.49 | 1.44 |
5 | T1 | 25 | Nil | 3 | 57 | 1.03 | 1.33 | 1.23 | 1.22 | 1.53 | 1.50 | 1.30 |
6 | T1 | 30 | Nil | 3 | 57 | 0.91 | 1.33 | 1.14 | 1.13 | 1.35 | 1.50 | 1.23 |
7 | T2 | 2 | Nil | 3 | 18 | 1.67 | 0.39 | 0.38 | 0.38 | 0.45 | 0.46 | 0.62 |
8 | T2 | 5 | Nil | 3 | 18 | 1.61 | 0.83 | 1.61 | 0.83 | 0.90 | 0.88 | 1.11 |
9 | T2 | 10 | Nil | 3 | 18 | 1.66 | 0.73 | 1.27 | 1.82 | 1.11 | 0.79 | 1.23 |
10 | T2 | 20 | Nil | 3 | 18 | 1.23 | 1.32 | 1.29 | 1.37 | 1.69 | 1.34 | 1.37 |
11 | T2 | 25 | Nil | 3 | 18 | 1.22 | 1.59 | 1.54 | 1.23 | 1.54 | 1.60 | 1.45 |
12 | T2 | 30 | Nil | 3 | 18 | 1.13 | 1.60 | 1.48 | 1.14 | 1.36 | 1.60 | 1.38 |
13 | T3 | 2 | Nil | 3 | 18 | 0.32 | 0.31 | 1.03 | 0.27 | 0.43 | 0.27 | 0.44 |
14 | T3 | 5 | Nil | 3 | 18 | 0.26 | 0.25 | 1.03 | 0.31 | 0.43 | 0.32 | 0.44 |
15 | T3 | 10 | Nil | 3 | 18 | 0.06 | 0.07 | 0.05 | 0.06 | 0.20 | 0.12 | 0.10 |
16 | T3 | 20 | Nil | 3 | 18 | 0.09 | 0.07 | 0.13 | 0.06 | 0.16 | 0.18 | 0.11 |
17 | T3 | 25 | Nil | 3 | 18 | 0.12 | 0.07 | 0.13 | 0.22 | 0.18 | 0.30 | 0.17 |
18 | T3 | 30 | Nil | 3 | 18 | 0.19 | 0.13 | 0.22 | 0.17 | 0.38 | 0.25 | 0.22 |
19 | T4 | 2 | Nil | 3 | 18 | 0.40 | 0.39 | 1.35 | 0.10 | 0.47 | 0.34 | 0.51 |
20 | T4 | 5 | Nil | 3 | 18 | 0.31 | 0.30 | 1.27 | 0.31 | 0.46 | 0.32 | 0.50 |
21 | T4 | 10 | Nil | 3 | 18 | 0.06 | 0.05 | 0.05 | 0.05 | 0.17 | 0.13 | 0.08 |
22 | T4 | 20 | Nil | 3 | 18 | 0.08 | 0.09 | 0.08 | 0.42 | 0.71 | 0.48 | 0.31 |
23 | T4 | 25 | Nil | 3 | 18 | 0.14 | 0.56 | 0.34 | 0.40 | 0.71 | 0.32 | 0.41 |
24 | T4 | 30 | Nil | 3 | 18 | 0.09 | 0.11 | 0.19 | 0.05 | 0.08 | 0.16 | 0.11 |
25 | Nil | 4 | 3 | 7 | 0.21 | 0.20 | 0.05 | 0.22 | 0.40 | 0.23 | 0.22 | |
26 | Nil | Nil | 3 | 3 | 0.43 | 0.39 | 1.56 | 0.42 | 0.71 | 0.48 | 0.66 |
CCNV | OCNV | WB | AGR | BS | GR | CCNV | OCNV | WB | AGR | BS | GR | CCNV | OCNV | WB | AGR | BS | GR | ||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
#2: Bands, T1-W 5 | #4: Bands, T1-W 20 | #6: Bands, T1-W 30 | |||||||||||||||||||
CCNV | #1: Bands, T1-w 2 | 1.97 | 0.17 | 1.97 | 1.96 | 1.98 | #3: Bands, T1-w 10 | 1.98 | 1.09 | 0.03 | 1.47 | 1.99 | #5: Bands, T1-w 25 | 1.98 | 1.03 | 0.04 | 0.57 | 1.99 | |||
OCNV | 1.68 | 1.96 | 0.01 | 0.15 | 0.04 | 1.98 | 1.99 | 1.99 | 1.92 | 0.04 | 1.98 | 1.99 | 1.99 | 1.97 | 0.04 | ||||||
WB | 1.65 | 0.01 | 1.96 | 1.95 | 1.97 | 1 | 1.99 | 0.97 | 1.83 | 1.99 | 1.1 | 1.99 | 0.89 | 1.49 | 1.99 | ||||||
AGR | 1.66 | 0.01 | 0 | 0.09 | 0.08 | 0.69 | 1.97 | 1.52 | 1.53 | 1.99 | 0.07 | 1.99 | 0.92 | 0.75 | 1.99 | ||||||
BS | 1.57 | 0.15 | 0.08 | 0.09 | 0.31 | 1.98 | 0.15 | 1.99 | 1.96 | 1.92 | 0.95 | 1.96 | 1.66 | 1.12 | 1.97 | ||||||
GR | 1.72 | 0.04 | 0.09 | 0.08 | 0.31 | 1.99 | 0.04 | 1.99 | 1.97 | 0.31 | 1.99 | 0.04 | 1.99 | 1.99 | 1.96 | ||||||
#8: Bands, T2-W 5 | #10: Bands, T2-W 20 | #12: Bands, T2-W 30 | |||||||||||||||||||
CCNV | #7: Bands, T2-w 2 | 1.97 | 0.18 | 1.97 | 1.97 | 1.98 | #9: Bands, T2-w 10 | 1.98 | 1.09 | 0.35 | 1.47 | 1.99 | #11: Bands, T2-w 25 | 1.98 | 1.05 | 0.05 | 0.58 | 1.99 | |||
OCNV | 1.69 | 1.97 | 0.01 | 0.16 | 0.05 | 1.98 | 1.99 | 1.99 | 1.91 | 0.05 | 1.98 | 1.99 | 1.99 | 1.97 | 0.05 | ||||||
WB | 1.68 | 0.02 | 1.96 | 1.95 | 1.97 | 1.01 | 1.99 | 0.97 | 1.82 | 1.99 | 1.11 | 1.99 | 0.89 | 1.5 | 1.99 | ||||||
AGR | 1.68 | 0.01 | 0 | 0.1 | 0.09 | 0.69 | 1.97 | 1.53 | 1.54 | 1.99 | 0.07 | 1.99 | 0.93 | 0.77 | 1.99 | ||||||
BS | 1.58 | 0.16 | 0.08 | 0.1 | 0.33 | 1.98 | 0.16 | 1.99 | 1.95 | 1.93 | 0.97 | 1.96 | 1.67 | 1.15 | 1.97 | ||||||
GR | 1.73 | 0.05 | 0.11 | 0.09 | 0.33 | 1.99 | 0.05 | 1.99 | 1.96 | 0.33 | 1.99 | 0.05 | 1.99 | 1.99 | 1.96 | ||||||
#14: Bands, T3-W 5 | #16: Bands, T3-W 20 | #18: Bands, T3-W 30 | |||||||||||||||||||
CCNV | #13: Bands, T3-w 2 | 0.03 | 0.92 | 0.06 | 0.29 | 0.003 | #15: Bands, T3-w 10 | 0.01 | 0.17 | 0.02 | 0.21 | 0.03 | #17: Bands, T3-w 25 | 0.07 | 0.18 | 0.06 | 0.55 | 0.09 | |||
OCNV | 0.03 | 1.02 | 0.01 | 0.16 | 0.05 | 0.01 | 0.13 | 0.01 | 0.16 | 0.05 | 0.02 | 0.18 | 0.08 | 0.25 | 0.07 | ||||||
WB | 0.91 | 1.03 | 1.08 | 1.27 | 0.88 | 0.04 | 0.06 | 0.07 | 0 | 0.29 | 0.01 | 0.05 | 0.4 | 0.07 | 0.29 | ||||||
AGR | 0.06 | 0.01 | 1.08 | 0.11 | 0.09 | 0.02 | 0.21 | 0.004 | 0.12 | 0.09 | 0.04 | 0.11 | 0.07 | 0.27 | 0.04 | ||||||
BS | 0.29 | 0.16 | 1.27 | 0.11 | 0.33 | 0.21 | 0.16 | 0.08 | 0.11 | 0.33 | 0.31 | 0.16 | 0.09 | 0.22 | 0.77 | ||||||
GR | 0.002 | 0.05 | 0.88 | 0.09 | 0.33 | 0.03 | 0.05 | 0.12 | 0.09 | 0.33 | 0.24 | 0.03 | 0.45 | 0.66 | 0.11 | ||||||
#20: Bands, T4-W 5 | #22: Bands, T4-W 20 | #24: Bands, T4-W 30 | |||||||||||||||||||
CCNV | #19: Bands, T4-w 2 | 0.03 | 1.18 | 0.06 | 0.28 | 0.003 | #21: Bands, T4-w 10 | 0.004 | 0.16 | 0.02 | 0.2 | 0.03 | #23: Bands, T4-w 25 | 0.07 | 0.19 | 0.04 | 0.07 | 0.08 | |||
OCNV | 0.03 | 1.26 | 0.01 | 0.16 | 0.05 | 0 | 0.13 | 0.01 | 0.16 | 0.05 | 0.05 | 0.26 | 0.16 | 0.05 | 0.02 | ||||||
WB | 1.23 | 1.32 | 1.3 | 1.45 | 1.14 | 0.04 | 0.02 | 0.07 | 0 | 0.29 | 0.01 | 0.45 | 0.04 | 0.01 | 0.46 | ||||||
AGR | 0.06 | 0.01 | 1.36 | 0.1 | 0.09 | 0.02 | 0.01 | 0.01 | 0.09 | 0.09 | 0.12 | 0.99 | 0.17 | 0.02 | 0.01 | ||||||
BS | 0.29 | 0.16 | 1.49 | 0.1 | 0.33 | 0.2 | 0.16 | 0.07 | 0.1 | 0.33 | 0.5 | 0.78 | 0.85 | 0.66 | 0.24 | ||||||
GR | 0.002 | 0.05 | 1.21 | 0.09 | 0.33 | 0.03 | 0.05 | 0.13 | 0.09 | 0.33 | 0.04 | 0.52 | 0.23 | 0.04 | 0.77 | ||||||
#26: Bands | |||||||||||||||||||||
CCNV | #25: Bands and VIs | 0.04 | 1.43 | 0.09 | 0.53 | 0.05 | |||||||||||||||
OCNV | 0.01 | 1.55 | 0.02 | 0.33 | 0.01 | ||||||||||||||||
WB | 0.68 | 0.75 | 1.57 | 1.78 | 1.49 | ||||||||||||||||
AGR | 0.05 | 0.01 | 0.79 | 0.21 | 0.19 | ||||||||||||||||
BS | 0.28 | 0.19 | 1.03 | 0.12 | 0.68 | ||||||||||||||||
GR | 0.02 | 0.06 | 0.56 | 0.11 | 0.38 |
2012 | CCNV | OCNV | WB | AGR | BS | GR | CA |
CCNV | 102 | 7 | 0 | 0 | 0 | 0 | 0.94 |
OCNV | 2 | 67 | 0 | 2 | 0 | 7 | 0.86 |
WB | 0 | 0 | 82 | 0 | 0 | 0 | 1.0 |
AGR | 0 | 1 | 0 | 153 | 0 | 2 | 0.99 |
BS | 0 | 0 | 0 | 0 | 40 | 0 | 1.0 |
GR | 0 | 3 | 0 | 3 | 0 | 110 | 0.95 |
PA | 0.98 | 0.89 | 1.0 | 0.97 | 1.00 | 0.94 | |
2015 | CCNV | OCNV | WB | AGR | BS | GR | CA |
CCNV | 110 | 0 | 0 | 0 | 0 | 0 | 1 |
OCNV | 0 | 59 | 0 | 1 | 0 | 0 | 0.98 |
WB | 0 | 0 | 57 | 0 | 0 | 0 | 1 |
AGR | 1 | 0 | 0 | 176 | 0 | 0 | 0.99 |
BS | 0 | 0 | 0 | 0 | 172 | 0 | 1 |
GR | 0 | 0 | 0 | 0 | 0 | 108 | 1 |
PA | 0.99 | 1.00 | 1 | 0.99 | 1.00 | 1.00 | |
2018 | CCNV | OCNV | WB | AGR | BS | GR | CA |
CCNV | 64 | 8 | 0 | 4 | 0 | 0 | 0.85 |
OCNV | 2 | 64 | 0 | 5 | 0 | 1 | 0.82 |
WB | 0 | 0 | 66 | 0 | 0 | 0 | 1.0 |
AGR | 6 | 1 | 0 | 170 | 2 | 4 | 0.91 |
BS | 1 | 2 | 0 | 6 | 113 | 7 | 0.92 |
GR | 5 | 4 | 0 | 4 | 0 | 75 | 0.85 |
PA | 0.85 | 0.78 | 1 | 0.89 | 0.98 | 0.79 |
Years | Overall Accuracy | Kappa Coefficient |
---|---|---|
2012 | 0.94 | 0.93 |
2015 | 0.98 | 0.97 |
2018 | 0.89 | 0.87 |
2012/2015 | CCNV | OCNV | WB | AGR | BS | GR | AREA (ha) 2015 |
---|---|---|---|---|---|---|---|
CCNV | 42,053.31 | 20,482.56 | 316.26 | 187.47 | 57.87 | 9113.04 | 72,210.51 |
OCNV | 32,066.91 | 181,246.77 | 460.53 | 34,703.28 | 661.05 | 60,404.49 | 309,543.03 |
WB | 910.44 | 952.56 | 7620.30 | 5.31 | 53.91 | 1506.06 | 11,048.58 |
AGR | 4030.38 | 25,792.65 | 174.42 | 31,350.96 | 1717.83 | 12,498.66 | 75,564.90 |
BS | 185.22 | 203.22 | 410.22 | 902.97 | 4362.48 | 1464.30 | 7528.41 |
GR | 9851.22 | 75,631.50 | 1631.70 | 1267.29 | 142.38 | 57,006.63 | 145,530.72 |
AREA (ha) 2012 | 89,097.48 | 304,309.26 | 10,613.43 | 68,417.28 | 6995.52 | 141,993.18 | 621,426.15 |
Change (2015–2012) | −16,886.97 | 5233.77 | 435.15 | 7147.62 | 532.89 | 3537.54 | |
−18.95% | 1.72% | 4.10% | 10.45% | 7.62% | 2.49% |
2015/2018 | CCNV | OCNV | WB | AGR | BS | GR | AREA (ha) 2018 |
---|---|---|---|---|---|---|---|
CCNV | 46,894.14 | 20,919.24 | 979.92 | 1966.68 | 24.84 | 3295.35 | 74,080.17 |
OCNV | 20,724.75 | 198,877.68 | 518.31 | 26,241.84 | 2151.63 | 69,778.80 | 318,293.01 |
WB | 329.31 | 3091.59 | 8768.97 | 397.80 | 259.56 | 1812.33 | 14,659.56 |
AGR | 1383.84 | 48,959.73 | 64.35 | 35,482.32 | 1251.54 | 2300.94 | 89,442.72 |
BS | 10.62 | 2577.15 | 428.31 | 1355.49 | 3112.65 | 140.67 | 7624.89 |
GR | 2867.85 | 35,117.64 | 288.72 | 10,120.77 | 728.19 | 68,202.63 | 117,325.80 |
AREA (ha) 2015 | 72,210.51 | 309,543.03 | 11,048.58 | 75,564.90 | 7528.41 | 145,530.72 | 621,426.15 |
Change (2018–2015) | 1869.66 | 8749.98 | 3610.98 | 13,877.82 | 96.48 | −28,204.92 | |
2.59% | 2.83% | 32.68% | 18.37% | 1.28% | −19.38% |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Mananze, S.; Pôças, I.; Cunha, M. Mapping and Assessing the Dynamics of Shifting Agricultural Landscapes Using Google Earth Engine Cloud Computing, a Case Study in Mozambique. Remote Sens. 2020, 12, 1279. https://doi.org/10.3390/rs12081279
Mananze S, Pôças I, Cunha M. Mapping and Assessing the Dynamics of Shifting Agricultural Landscapes Using Google Earth Engine Cloud Computing, a Case Study in Mozambique. Remote Sensing. 2020; 12(8):1279. https://doi.org/10.3390/rs12081279
Chicago/Turabian StyleMananze, Sosdito, Isabel Pôças, and Mário Cunha. 2020. "Mapping and Assessing the Dynamics of Shifting Agricultural Landscapes Using Google Earth Engine Cloud Computing, a Case Study in Mozambique" Remote Sensing 12, no. 8: 1279. https://doi.org/10.3390/rs12081279