Abstract
Crop monitoring becomes essential in attaining food security for implementation of various agricultural serving programs. So, fast and reliable crop monitoring is must. Using traditional methods, crop monitoring maps need high amount of satellite data downloading and processing time. Google Earth Engine (GEE) cloud platform enables us to save time in downloading and processing of time series satellite data, the every satellite imagery is converted into Normalized Difference Vegetation Index (NDVI) image and stacked monthly wise maximum images. The stacked image was used for conducting supervised classification. The main objective of this study is to evaluate the performance of different supervised machine learning (ML) classifiers in GEE platform and Spectral Matching Technique (SMT) using Sentinel-2 10 m satellite imagery in specific crop type classification. The crop classification for the year 2018–19 (rabi season) was carried for Jhansi District using supervised classifiers like Random Forest (RF), Support Vector Machine (SVM) and Classification and Regression Trees (CART) in GEE platform and also with SMT with the help of ground data. It was attained nearly 81.8% accuracy for RF, 68.8% for SVM, 64.9% for CART and 88% for SMT. The results obtained using RF classifier were nearly relative to SMT classification map. The study indicates that classifier’s performance depends on the quality of ground data used, RF can reduce the error samples in ground samples and produce satisfactory results. This study compared results obtained from all the above classifiers with agricultural statistics and also compared crop-wise accuracies. In the study, it was observed that RF classification is outperformed when compared with other classifiers considered in the study.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Anderson MC, Allen RG, Morse A, Kustas WP (2012) Use of Landsat thermal imagery in monitoring evapotranspiration and managing water resources. Remote Sens Environ 122:50–65
Belgiu M, Csillik O (2018) Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis. Remote Sens Environ 204:509–523
Bicheron P, Huc M, Henry C, Bontemps S, Lacaux J (2008) GlobCover products description manual, Issue 2, Revision 2. European Space Agency (ESA)
Boche H, Mönich UJ (2020) Turing computability of Fourier transforms of bandlimited and discrete signals. IEEE Trans Signal Process 68:532–547
Brown JC. Jepson WE. Kastens JH. Wardlow BD. Lomas JM. Price K. (2007) Multitemporal, moderate-spatial-resolution remote sensing of modern agricultural production and land modification in the Brazilian Amazon. GISci. Remote Sens. 44: 117–148
Breiman L (2001) Random forests. Mach Learn 45(1):5–32
Coltin B, McMichael S., Smith T, Fong T (2016) Automatic boosted flood mapping from satellite data. Int J Remote Sens 37:993–1015
Cortes C, Vladimir V (1995) Support-vector networks. Mach Learn 20(3):273–297
Deng C, Wu C (2013) The use of single-date MODIS imagery for estimating large-scale urban impervious surface fraction with spectral mixture analysis and machine learning techniques. ISPRS J Photogramm Remote Sens 86:100–110
Dong J, Xiao X, Kou W, Qin Y, Zhang G, Li L, Jin C, Zhou Y, Wang J, Biradar C (2015) Tracking the dynamics of paddy rice planting area in 1986–2010 through time series Landsat images and phenology-based algorithms. Remote Sens Environ 160:99–113
Dong J, Xiao X, Menarguez MA, Zhang G, Qin Y, Thau D, Biradar C, Moore III B (2016) Mapping paddy rice planting area in northeastern Asia with Landsat 8 images, phenology-based algorithm and Google Earth Engine. Remote Sens Environ 185:142–154
Egorov A, Hansen M, Roy DP, Kommareddy A, Potapov P (2015) Image interpretation-guided supervised classification using nested segmentation. Remote Sens Environ 165:135–147
Feyisa GL, Palao LK, Nelson A, Gumma MK, Paliwal A, Win KT, Nge KH, Johnson DE (2020) Characterizing and mapping cropping patterns in a complex agro-ecosystem: an iterative participatory mapping procedure using machine learning algorithms and MODIS vegetation indices. Comput Electron Agr 175:105595
Friedl MA, Brodley CE (1997) Decision tree classification of land cover from remotely sensed data. Remote Sens Environ 61:399–409
Gómez C, White JC, Wulder MA (2016) Optical remotely sensed time series data for land cover classification: A review. ISPRS J Photogramm Remote Sens 116:55–72
Gorelick N, Hancher M, Dixon M, Ilyushchenko S, Thau D, Moore R (2017) Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sens Environ 202:18–27
Griffiths P, Nendel C, Hostert P (2019) Intra-annual reflectance composites from Sentinel-2 and Landsat for national-scale crop and land cover mapping. Remote Sens Environ 220:135–151
Gumma MK, Thenkabail PS, Deevi KC, Mohammed IA, Teluguntla P, Oliphant A, Xiong J, Aye T, Whitbread AM (2018) Mapping cropland fallow areas in myanmar to scale up sustainable intensification of pulse crops in the farming system. GISci Remote Sens 55:926–949
Gumma MK, Thenkabail PS, Maunahan A, Islam S, Nelson A (2014) Mapping seasonal rice cropland extent and area in the high cropping intensity environment of Bangladesh using MODIS 500 m data for the year 2010. ISPRS J Photogramm Remote Sens 91:98–113
Gumma MK, Thenkabail PS, Teluguntla PG, Oliphant A, Xiong J, Giri C, Pyla V, Dixit S, Whitbread AM (2020) Agricultural cropland extent and areas of South Asia derived using Landsat satellite 30-m time-series big-data using random forest machine learning algorithms on the Google Earth Engine cloud. GISci Remote Sens 57:302–322
Gumma MK, Thenkabail PS, Teluguntla P, Rao MN, Mohammed IA, Whitbread AM (2016) Mapping rice-fallow cropland areas for short-season grain legumes intensification in South Asia using MODIS 250 m time-series data. Int J Digital Earth 9(10):981–1003
Hansen MC, Potapov PV, Moore R, Hancher M, Turubanova S, Tyukavina A, Thau D, Stehman S, Goetz SJ, Loveland TR (2013) High-resolution global maps of 21st-century forest cover change. Science 342:850–853
Harris FJ (1978) On the use of windows for harmonic analysis with the discrete Fourier transform. Proc IEEE 66:51–83
Im J (2020) Earth observations and geographic information science for sustainable development goals. GISci Remote Sens 57:591–592
Jeganathan C, Dash J, Atkinson P (2014) Remotely sensed trends in the phenology of northern high latitude terrestrial vegetation, controlling for land cover change and vegetation type. Remote Sens Environ 143:154–170
Lambert M-J, Traoré PCS, Blaes X, Baret P, Defourny P (2018) Estimating smallholder crops production at village level from Sentinel-2 time series in Mali’s cotton belt. Remote Sens Environ 216:647–657
Liu X, Hu G, Chen Y, Li X, Xu X, Li S, Pei F, Wang S (2018) High-resolution multi-temporal mapping of global urban land using Landsat images based on the Google Earth Engine Platform. Remote Sens Environ 209:227–239
Lobell DB, Thau D, Seifert C, Engle E, Little B (2015) A scalable satellite-based crop yield mapper. Remote Sens Environ 164:324–333
Long JA, Lawrence RL, Greenwood MC, Marshall L, Miller PR (2013) Object-oriented crop classification using multitemporal ETM+SLC-off imagery and random forest. GISci Remote Sens 50:418–436
McCarthy MJ, Radabaugh KR, Moyer RP, Muller-Karger FE (2018) Enabling efficient, large-scale high-spatial resolution wetland mapping using satellites. Remote Sens Environ 208:189–201
Meier J, Zabel F, Mauser W (2018) A global approach to estimate irrigated areas–a comparison between different data and statistics. Hydrol Earth Syst Sci 22:1119
Millard K, Richardson M (2015) On the importance of training data sample selection in random forest image classification: a case study in peatland ecosystem mapping. Remote Sens 7:8489–8515
Oliphant AJ, Thenkabail PS, Teluguntla P, Xiong J, Gumma MK, Congalton RG, Yadav K (2019) 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 Obser Geoinf 81:110–124
Ozdogan M, Gutman G (2008) A new methodology to map irrigated areas using multi-temporal MODIS and ancillary data: an application example in the continental US. Remote Sens Environ 112:3520–3537
Pan Z, Huang J, Zhou Q, Wang L, Cheng Y, Zhang H, Blackburn GA, Yan J, Liu J (2015) Mapping crop phenology using NDVI time-series derived from HJ-1 A/B data. Int J Appl Earth Obser Geoinf 34:188–197
Patel NN, Angiuli E, Gamba P, Gaughan A, Lisini G, Stevens FR, Tatem AJ, Trianni G (2015) Multitemporal settlement and population mapping from Landsat using Google Earth Engine. Int J Appl Earth Obser Geoinf 35:199–208
Pekel J-F, Cottam A, Gorelick N, Belward AS (2016) High-resolution mapping of global surface water and its long-term changes. Nature 540:418–422
Pittman K, Hansen MC, Becker-Reshef I, Potapov PV, Justice CO (2010) Estimating global cropland extent with multi-year MODIS data. Remote Sens 2:1844–1863
Platas-Garza MA, de la O Serna JA (2010) Dynamic harmonic analysis through Taylor–Fourier transform. IEEE Trans Instrum Meas 60:804–813
Sidhu N, Pebesma E, Câmara G (2018) Using Google Earth Engine to detect land cover change: Singapore as a use case. Eur J Remote Sens 51:486–500
Tateishi R, Hoan NT, Kobayashi T, Alsaaideh B, Tana G, Phong DX (2014) Production of global land cover data-GLCNMO2008. J Geog Geol 6:99
Teluguntla P, Thenkabail PS, Oliphant A, Xiong J, Gumma MK, Congalton RG, Yadav K, Huete A (2018) A 30-m landsat-derived cropland extent product of Australia and China using random forest machine learning algorithm on Google Earth Engine cloud computing platform. ISPRS J Photogramm Remote Sens 144:325–340
Thenkabail P, GangadharaRao P, Biggs T, Krishna M, Turral H (2007) Spectral matching techniques to determine historical land-use/land-cover (LULC) and irrigated areas using time-series 0.1-degree AVHRR pathfinder datasets. Photogramm Eng Remote Sens 73:1029–1040
Thenkabail PS, Biradar CM, Noojipady P, Dheeravath V, Li Y, Velpuri M, Gumma M, Gangalakunta ORP, Turral H, Cai X (2009). Global irrigated area map (GIAM), derived from remote sensing, for the end of the last millennium. Int J Remote Sens 30:3679–3733
Thenkabail PS, Knox JW, Ozdogan M, Gumma MK, Congalton RG, Wu Z, Milesi C, Finkral A, Marshall M, Mariotto I (2012) Assessing future risks to agricultural productivity, water resources and food security: how can remote sensing help? PE&RS, Photogramm Eng Remote Sens 78:773–782
Veloso A, Mermoz S, Bouvet A, Le Toan T, Planells M, Dejoux J-F, Ceschia E (2017) Understanding the temporal behavior of crops using Sentinel-1 and Sentinel-2-like data for agricultural applications. Remote Sens Environ 199:415–426
Xie Y, Lark TJ, Brown JF, Gibbs HK (2019) Mapping irrigated cropland extent across the conterminous United States at 30 m resolution using a semi-automatic training approach on Google Earth Engine. ISPRS J Photogramm Remote Sens 155:136–149
Xiong J, Thenkabail PS, Gumma MK, Teluguntla P, Poehnelt J, Congalton RG, Yadav K, Thau D (2017a) Automated cropland mapping of continental Africa using Google Earth Engine cloud computing. ISPRS J Photogramm Remote Sens 126:225–244
Xiong J, Thenkabail PS, Tilton JC, Gumma MK, Teluguntla P, Oliphant A, Congalton RG, Yadav K, Gorelick N (2017b). 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 9:1065
Acknowledgements
This research was supported by the RIICE III project funded by the Swiss Agency for Development Cooperation (SDC), the Government of Uttar Pradesh, India, through its ‘Doubling Farmers Income’ in Bundelkhand, and the CGIAR Research Program on Water, Land and Ecosystems (WLE). The authors are grateful to Divya Kashyap, Arindom Baidya, and other team members for their suggestions and recommendations. We also thank Jameeruddin A and Ismail for their support during ground data collection.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Panjala, P., Gumma, M.K., Teluguntla, P. (2022). Machine Learning Approaches and Sentinel-2 Data in Crop Type Mapping. In: Reddy, G.P.O., Raval, M.S., Adinarayana, J., Chaudhary, S. (eds) Data Science in Agriculture and Natural Resource Management. Studies in Big Data, vol 96. Springer, Singapore. https://doi.org/10.1007/978-981-16-5847-1_8
Download citation
DOI: https://doi.org/10.1007/978-981-16-5847-1_8
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-5846-4
Online ISBN: 978-981-16-5847-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)