Abstract
Accurate and timely monitoring of crops can help in better agriculture management. Remote sensing-based crop monitoring helps to track the real-time crop condition. Small farm holding, intercropping, multi-cropping, inadequate irrigation infrastructure, and other challenges are quite common to Indian farms. Satellite-based crop monitoring uses pixel-based analysis poses many challenges as the majority of Indian farms are smallholdings. Hence, to overcome these challenges a novel method has been proposed based on image processing, and machine learning (ML) algorithms in this chapter. In the study, Morbi or Morvi district of Gujarat state, India has been selected, where majority of holdings are small and marginal with cultivation of cotton, cumin, wheat, bajra, sesamum, and groundnut as major crops. In the study, optical satellite data from Sentinel-2 was used to delineate farm boundaries using standard deviation and perform crop classification by using Random Forest (RF) algorithm with approximately 85% accuracy and an F1-score of 0.84. Open-source Geographic Information System (GIS) platform QGIS was used to perform post-processing operations to handle raster, and vector data analysis. The proposed method can be applied to other areas where different farm holding sizes and multiple crops are grown.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alemu MM (2016) Automated farm field delineation and crop row detection from satellite images. Master’s thesis, University of Twente, The Netherlands.
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
Crommelinck S, Bennett R, Gerke M, Nex F, Yang MY, Vosselman G (2016) Review of automatic feature extraction from high-resolution optical sensor data for uav-Object Based Crop Classification for Precision Farming 17 based cadastral mapping. Remote Sen 8(8):689
Davidse J (2015) Semi-automatic detection of field boundaries from high-resolution satellite imagery. Wageningen University
Garcia-Pedrero A, Gonzalo-Martin C, Lillo-Saavedra M (2017) A machine learning approach for agricultural parcel delineation through agglomerative segmentation. Int J Remote Sen 38(7):1809–1819
Hakkim VA, Joseph EA, Gokul AA, Mufeedha K et al (2016) Precision farming: the future of indian agriculture. J Appl Biol Biotech 4(06):068–072
Marshall M, Crommelinck S, Kohli D, Perger C, Yang MY, Ghosh A, Fritz S, Bie Kd, Nelson A (2019) Crowd-driven and automated mapping of field boundaries in highly fragmented agricultural landscapes of Ethiopia with very high spatial resolution imagery. Remote Sen 11(18):2082
Maxwell SK (2010) Generating land cover boundaries from remotely sensed data using object-based image analysis: overview and epidemiological application. Spat Spatiotemporal Epidemiol 1(4):231–237
North HC, Pairman D, Belliss SE (2018) Boundary delineation of agricultural fields in multitemporal satellite imagery. IEEE J Sel Top Appl Earth Obs Remote Sen 12(1):237–251
Ok AO, Akar O, Gungor O (2012) Evaluation of random forest method for agricultural crop classification. Eur J Remote Sen 45(1):421–432
Peña JM, Gutiérrez PA, Hervás-MartÃnez C, Six J, Plant RE, López-Granados F (2014) Object-based image classification of summer crops with machine learning methods. Remote Sen 6(6):5019–5041
Team QD et al (2016) QGIS geographic information system. Open-source geospatial foundation project
Verbaeten S, Van Assche A (2003) Ensemble methods for noise elimination in classification problems. In: International workshop on multiple classifier systems, Springer, pp 317–325
Wang Z, Boesch R (2007) Color-and texture-based image segmentation for improved forest delineation. IEEE Trans Geosci Remote Sen 45(10):3055–3062
Wassie Y, Koeva M, Bennett R, Lemmen C (2018) A procedure for semi-automated cadastral boundary feature extraction from high-resolution satellite imagery. J Spatial Sci 63(1):75–92
Watkins B (2019) Agricultural field boundary delineation using earth observation methods and multi-temporal sentinel-2 imagery. PhD thesis, Stellenbosch: Stellenbosch University.
Yan L, Roy D (2015) Improved time series land cover classification by missing-observation-adaptive nonlinear dimensionality reduction. Remote Sen Environ 158:478–491
Acknowledgements
The authors would like to thank the Google Earth Engine (GEE) team for providing cloud-computing resources for data visualization and European Space Agency (ESA) for providing open-access data. The authors thank Amnex Infotechnologies Pvt. Ltd. for providing all the needed support and environment to work on this project. Additionally, the authors would like to thank anonymous reviewers for their helpful comments and suggestions.
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
Kumar, J.P., Singhania, D., Patel, S.N., Dakwala, M. (2022). Crop Classification for Precision Farming Using Machine Learning Algorithms and Sentinel-2 Data. 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_7
Download citation
DOI: https://doi.org/10.1007/978-981-16-5847-1_7
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)