Abstract
Mapping the spatial distribution of crops and predicting yields are crucial for food security measures and management. Remote sensing imagery obtained from different satellite sensors has different crop identification capability owing to the different spatial and spectral resolutions. This study aims to discriminate the major crop types and to estimate the corresponding acreage in Hazaribagh district during Rabi season 2018–2019 using a multispectral satellite image of Sentinel-2B with 10 m of spatial resolution. Support Vector Machine (SVM) classification algorithm was deployed for land use land cover classification and crop types mapping. The accuracy assessment for crop types showed a satisfactory overall accuracy and kappa coefficient as ~ 87.36% and 0.81, respectively. Three crops were broadly identified, namely wheat, mustard, and other Rabi crops, and their corresponding acreages were estimated as ~ 39.8, 10.7, and 70.5 km2, respectively. Furthermore, wheat and mustard yields were predicted as ~ 1.75 and 0.74 ton/ha, respectively using a regression-based yield model. These estimated yields were quite close to reported crop statistics with a mean yield of 1.7 (for wheat) and 0.6 (for mustard) ton/ha. AquaCrop model was also used to simulate the wheat yield during the Rabi season 2018–2019, and the mean yield was simulated as ~ 1.92 ton/ha. The simulated yield from the AquaCrop model was comparable with the regression-based estimates (i.e., 1.75 ton/ha) and also with the historical crop statistics (i.e., 1.70 ton/ha) of the Hazaribagh district. This comprehensive study concluded that the Sentinel-2B satellite data have the capabilities to discriminate the heterogeneous land cover features and crop types with considerable classification accuracy. The AquaCrop model is also beneficial for predicting yields and this information can be useful for agriculture policymakers.
Zusammenfassung
Die Kartierung der räumlichen Verteilung von Kulturpflanzen sowie die Vorhersage von Erträgen sind für Maßnahmen und das Management der Ernährungssicherheit von entscheidender Bedeutung. Fernerkundlich generierte Aufnahmen, die auf verschiedenen Satellitensensoren basieren, ermöglichen aufgrund der unterschiedlichen räumlichen und zeitlichen Auflösung differenzierte Aussagen zu Erntemöglichkeiten. Diese Studie zielt darauf ab, die wichtigsten Anbautypen zu identifizieren und die entsprechende Anbaufläche im Distrikt Hazaribagh während der Rabi-Saison 2018–2019 mithilfe eines multispektralen Satellitenbilds von Sentinel-2B (mit einer räumlichen Auflösung von 10 m) abzuschätzen. Dabei wurde der SVM-Klassifizierungsalgorithmus (Support Vector Machine) für die Landnutzungs-Landbedeckungsklassifizierung sowie für die Kartierung von Erntetypen eingesetzt. Die Genauigkeitsbewertung ergab eine zufriedenstellende Gesamtgenauigkeit sowie einen zufriedenstellenden Kappa-Koeffizienten von ~ 87,36% bzw. 0,81. Drei Kulturen wurden identifiziert, nämlich Weizen, Senf und Gemüse, und ihre entsprechenden Anbauflächen wurden auf ~ 39,8, 10,7 bzw. 70,5 km2 geschätzt. Darüber hinaus wurden die Weizen- und Senferträge unter Verwendung eines auf einer Regression basierenden Ertragsmodells auf ~ 1,75 bzw. 0,74 t/ha geschätzt. Diese geschätzten Erträge lagen ziemlich nahe an den offiziell gemeldeten Erntestatistiken. Das AquaCrop-Modell wurde auch verwendet, um den Weizenertrag während der Rabi-Saison 2018–2019 zu simulieren, und der mittlere Ertrag wurde mit ~ 1,92 t/ha geschätzt. Der simulierte Ertrag des Modells hatte eine gute Beziehung zu den beobachteten und historischen Daten des Hazaribagh-Distrikts. Diese umfassende Studie besagt, dass die Sentinel-2B-Satellitendaten die heterogenen Landbedeckungsmerkmale mit beträchtlicher Klassifizierungsgenauigkeit unterscheiden können. Das Sentinel-2B- und das AquaCrop-Modell können für die Vorhersage von Erträgen von Vorteil sein, und diese Informationen können für Entscheidungsträger in der Agrarpolitik hilfreich sein.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Availability of data and materials
Not applicable.
Code availability
Not applicable.
References
Alexandratos N, Bruinsma J (2012) World agriculture towards 2030/2050: the 2012 revision. ESA Working paper No. 12–03. Rome, FAO
Aneece I, Thenkabail PS (2018) Accuracies achieved in classifying five leading world crop types and their growth stages using optimal earth observing-1 hyperion hyperspectral narrow bands on Google earth engine. Remote Sens 10(12):2027. http://www.mdpi.com/2072-4292/10/12/2027
Baby A, Shekh AM (2005) Field calibration and evaluation of crop simulation model InfoCrop to estimate wheat yields. J Agrometeorol 7:199–207
Bar S, Parida BR, Pandey AC (2020) Landsat-8 and Sentinel-2 based Forest fire burn area mapping using machine learning algorithms on GEE cloud platform over Uttarakhand, Western Himalaya. Remote Sens Appl Soc Environ 18:100324. https://doi.org/10.1016/j.rsase.2020.100324
Boyle SA, Kennedy CM, Torres J, Colman K, Pérez-Estigarribia PE, de la Sancha NU (2014) High-resolution satellite imagery is an important yet underutilized resource in conservation biology. PLoS ONE 9:e86908. https://doi.org/10.1371/journal.pone.0086908
CGWB (2013) Central Ground water Board report on ground water information booklet for Hazaribagh District, Jharkhand State. Ministry of Water Resources, Govt. of India. Available online: http://cgwb.gov.in/district_profile/jharkhand/hazaribagh.pdf. Accessed on 27 Nov 2020
Chandra A, Mitra P, Dubey SK, Ray SS (2019) Machine learning approach for kharif rice yield prediction integrating multi-temporal vegetation indices and weather and non-weather variables. ISPRS Int Arch Photogramm Remote Sens Spat Inf Sci. https://doi.org/10.5194/isprs-archives-XLII-3-W6-187-2019
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297
DES (2019) Directorate of Economics and Statistics, DAC&FW (DES). 2019. Agricultural statistics at a glance. Ministry of Agriculture, Government of India. Available online: https://eands.dacnet.nic.in. Accessed on 27 Nov 2020.
Devadas R (2012) Support vector machine classification of object-based data for crop mapping, using multi-temporal landsat imagery. In: International archives of the photogrammetry, remote sensing and spatial information sciences, vol XXXIX-B7, 2012 XXII ISPRS Congress, 25 August–1 September 2012, Melbourne, Australia
Doraiswamy P (2004) Crop condition and yield simulations using Landsat and MODIS. Remote Sens Environ 92(4):548–559. https://doi.org/10.1016/j.rse.2004.05.017
Fisher JRB, Acosta EA, Dennedy-Frank PJ, Kroeger T, Boucher TM (2018) Impact of satellite imagery spatial resolution on land use classification accuracy and modeled water quality. Remote Sens Ecol Conserv 4:137–149. https://doi.org/10.1002/rse2.61
Foody GM (1992) On the compensation for chance agreement in image classification accuracy assessment. Photogramm Eng Remote Sens 58(10):1459–1460
Geza M, McCray JE (2008) Effects of soil data resolution on SWAT model stream flow and water quality predictions. J Environ Manag 88:393–406. https://doi.org/10.1016/j.jenvman.2007.03.016
Greaves G, Wang YM (2016) Assessment of FAO AquaCrop model for simulating maize growth and productivity under deficit irrigation in a tropical environment. Water 8(12):557. https://doi.org/10.3390/w8120557
Htitiou A, Boudhar A, Lebrini Y, Hadria R, Lionboui H, Elmansouri L, Tychon B, Benabdelouahab T (2019) The performance of random forest classification based on phenological metrics derived from Sentinel-2 and Landsat 8 to Map Crop Cover in an irrigated Semi-Arid Region. Remote Sens Earth Syst Sci 2(4):208–224. https://doi.org/10.1007/s41976-019-00023-9
Huang Z, Chen H, Hsu CJ, Chen W-H, Wu S (2004) Credit rating analysis with support vector machines and neural networks: a market comparative study. Decis Support Syst 37(4):543–558. https://doi.org/10.1016/S0167-9236(03)00086-1
Kalra N, Aggarwal PK, Singh AK et al (2006) Methodology for national wheat yield forecast using wheat growth model, WTGROWS, and remote sensing inputs. In: Kuligowski RJ, Parihar JS, Saito G (eds) Proc. SPIE 6411, agriculture and hydrology applications of remote sensing, p 641106. https://doi.org/10.1117/12.697698.
Karakizi C, Antoniou G, Karantzalos K (2018) Towards joint land cover and crop type mapping with numerous classes. In: IGARSS 2018–2018 IEEE international geoscience and remote sensing symposium, pp 2980–2983. https://doi.org/10.1109/IGARSS.2018.8517473
Ladli D, Lal K, Jalem K, Ranjan AK (2020) Synergy of satellite-derived drought indices for agricultural drought quantification and yield prediction. In: Spatial information science for natural resource management, pp 122–148. IGI Global. https://doi.org/10.4018/978-1-7998-5027-4.ch007
Lopresti MF, Di Bella CM, Degioanni AJ (2015) Relationship between MODIS-NDVI data and wheat yield: a case study in Northern Buenos Aires province, Argentina. Inf Process Agric 2(2):73–84. https://doi.org/10.1016/j.inpa.2015.06.001
Löw F, Michel U, Dech S, Conrad C (2013) Impact of feature selection on the accuracy and spatial uncertainty of per-field crop classification using support vector machines. ISPRS J Photogramm Remote Sens 85:102–119. https://doi.org/10.1016/j.isprsjprs.2013.08.007
Mansaray LR, Huang W, Zhang D, Huang J, Jun L (2017) Mapping rice fields in urban Shanghai, Southeast China, using Sentinel-1A and Landsat 8 Datasets. Remote Sens 9(3):257. https://doi.org/10.3390/rs9030257
Mather P, Tso B (2016) Classification Methods For Remotely Sensed Data. CRC Press, Boca Raton. https://doi.org/10.1201/9781420090741
Mishra VN, Kumar P, Gupta DK, Prasad R (2014) Classification of various land features using RISAT-1 dual polarimetric data. ISPRS Int Arch Photogramm Remote Sens Spat Inf Sci. https://doi.org/10.5194/isprsarchives-XL-8-833-2014
Nagy A, Fehér J, Tamás J (2018) Wheat and maize yield forecasting for the Tisza river catchment using MODIS NDVI time series and reported crop statistics. Comput Electron Agric 151:41–49. https://doi.org/10.1016/j.compag.2018.05.035
Neetu, Ray SS (2019) Exploring machine learning classification algorithms for crop classification using Sentinel 2 data. ISPRS Int Arch Photogramm Remote Sens Spat Inf Sci. https://doi.org/10.5194/isprs-archives-XLII-3-W6-573-2019
NRSC (2014) Land use/land cover database on 1:50,000 scale, Natural Resources Census Project, LUCMD, LRUMG, RSAA. National Remote Sensing Centre, ISRO, Hyderabad
Pal M, Mather PM (2005) Support vector machines for classification in remote sensing. Int J Remote Sens 26(5):1007–1011. https://doi.org/10.1080/01431160512331314083
Parida BR (2006) Analysing the effect of severity and duration of agricultural drought on crop performance using terra-MODIS satellite data and meteorological data. Dissertation, The Int. Institute for Geo-Information Science and Earth Observation. Available online: https://webapps.itc.utwente.nl/librarywww/papers_2006/msc/iirs/bikash.pdf. Accessed on 13 Oct 2020
Parida BR, Mandal SP (2020) Polarimetric decomposition methods for LULC mapping using ALOS L-band PolSAR data in Western parts of Mizoram, Northeast India. SN Appl Sci 2(6):1049. https://doi.org/10.1007/s42452-020-2866-1
Parida BR, Ranjan AK (2019a) Up-scaling paddy yield at satellite-footprint scale using satellite data in conjunction with CCE data in Sahibganj district. ISPRS Int Arch Photogramm Remote Sens Spat Inf Sci, Jharkhand. https://doi.org/10.5194/isprs-archives-XLII-3-W6-235-2019
Parida BR, Ranjan AK (2019b) Wheat acreage mapping and yield prediction using Landsat-8 OLI Satellite Data: a case study in Sahibganj Province, Jharkhand (India). Remote Sens Earth Syst Sci 2(2–3):96–107. https://doi.org/10.1007/s41976-019-00015-9
Parida BR, Pandey AC, Patel NR (2020) Greening and browning trends of vegetation in India and their responses to climatic and non-climatic drivers. Climate 8(8):92. https://doi.org/10.3390/cli8080092
Prasad NR, Patel NR, Danodia A (2020) Crop yield prediction in cotton for regional level using random forest approach. Spat Inf Res. https://doi.org/10.1007/s41324-020-00346-6
Raes D, Steduto P, Hsiao TC, Fereres E (2009) AquaCrop—the FAO Crop Model to simulate yield response to water: II. Main algorithms and software description. Agron J 101(3):438–447. https://doi.org/10.2134/agronj2008.0140s
Ranjan AK, Parida BR (2019) Paddy acreage mapping and yield prediction using sentinel-based optical and SAR data in Sahibganj district, Jharkhand (India). Spat Inf Res 27(4):399–410. https://doi.org/10.1007/s41324-019-00246-4
Ranjan AK, Parida BR (2020a) Predicting paddy yield at spatial scale using optical and synthetic aperture radar (SAR) based satellite data in conjunction with field-based crop cutting experiment (CCE) data. Int J Remote Sens 42(6):2046–2071. https://doi.org/10.1080/01431161.2020.1851063
Ranjan AK, Parida BR (2020b) Estimating biochemical parameters of paddy using satellite and near-proximal sensor data in Sahibganj Province, Jharkhand (India). Remote Sens Appl Soc Environ 18:100293. https://doi.org/10.1016/j.rsase.2020.100293
Ranjan AK, Sahoo D, Gorai AK (2020) Quantitative assessment of landscape transformation due to coal mining activity using earth observation satellite data in Jharsuguda coal mining region, Odisha, India. Environ Dev Sustain. https://doi.org/10.1007/s10668-020-00784-0
Sambodo KA, Indriasari N (2014) Land cover classification of ALOS PALSAR data using support vector machine. Int J Remote Sens Earth Sci (IJReSES). https://doi.org/10.30536/j.ijreses.2013.v10.a1836
Saxena R, Bhardwaj V, Kalra N (2006) Simulation of wheat yield using WTGROWS in northern India. J Agrometeorol 8(1):87–90
Saxena DS, Dubey SK, Choudhary K, Sehgal S, Neetu, Ray SS (2019) An analysis of national-state-district level acreage and production estimates of Rabi sorghum under FASAL project. ISPRS Int Arch Photogramm Remote Sens Spat Inf Sci. https://doi.org/10.5194/isprs-archives-XLII-3-W6-79-2019
Shao Y, Lunetta RS (2012) Comparison of support vector machine, neural network, and CART algorithms for the land-cover classification using limited training data points. ISPRS J Photogramm Remote Sens 70:78–87. https://doi.org/10.1016/j.isprsjprs.2012.04.001
Sharma A, Mukherjee J, Sehgal VK, Chakraborty D, Das D (2019) Rice acreage estimation of Ludhiana District using Sentinel-1A time series data. J Agric Phys 18(2)
Singh PK, Singh KK, Baxla AK, Rathore LS (2015) Impact of climatic variability on wheat yield predication using DSSAT v 4.5 (CERES-wheat) model for the different agroclimatic zones in India. In: Singh AK, Dagar JC, Arunachalam A et al (eds) Climate change modelling, planning and policy for agriculture. Springer, New Delhi, pp 45–55
Son NT, Chen CF, Chen CR, Minh VQ, Trung NH (2014) A comparative analysis of multitemporal MODIS EVI and NDVI data for large-scale rice yield estimation. Agric For Meteorol 197:52–64. https://doi.org/10.1016/j.agrformet.2014.06.007
Teodoro AC, Araujo R (2016) Comparison of performance of object-based image analysis techniques available in open source software (Spring and Orfeo Toolbox/Monteverdi) considering very high spatial resolution data. J Appl Remote Sens 10(1):016011. https://doi.org/10.1117/1.JRS.10.016011
Thenkabail PS, Biradar CM, Noojipady P, Dheeravath V, Li Y, Velpuri M, Gumma M, Gangalakunta ORP, Turral H, Cai X, Vithanage J, Schull MA, Dutta R (2009) Global irrigated area map (GIAM), derived from remote sensing, for the end of the last millennium. Int J Remote Sens 30(14):3679–3733. https://doi.org/10.1080/01431160802698919
United Nations (2019) World population prospects 2019: data booklet. UN. https://doi.org/10.18356/3e9d869f-en
Varghese AO, Suryavanshi A, Joshi AK (2016) Analysis of different polarimetric target decomposition methods in forest density classification using C band SAR data. Int J Remote Sens 37(3):694–709. https://doi.org/10.1080/01431161.2015.1136448
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. https://doi.org/10.1016/j.rse.2017.07.015
Verma AK, Garg PK, Hari Prasad KS (2017) Sugarcane crop identification from LISS IV data using ISODATA, MLC, and indices-based decision tree approach. Arab J Geosci 10(1):16. https://doi.org/10.1007/s12517-016-2815-x
Wardlow B, Egbert S, Kastens J (2007) Analysis of time-series MODIS 250 m vegetation index data for crop classification in the US Central Great Plains. Remote Sens Environ 108(3):290–310. https://doi.org/10.1016/j.rse.2006.11.021
Watson JEM, Iwamura T, Butt N (2013) Mapping vulnerability and conservation adaptation strategies under climate change. Nat Clim Change 3(11):989–994. https://doi.org/10.1038/nclimate2007
Xavier AC, Rudorff BFT, Shimabukuro YE, Berka LMS, Moreira MA (2006) Multi-temporal analysis of MODIS data to classify sugarcane crop. Int J Remote Sens 27(4):755–768. https://doi.org/10.1080/01431160500296735
Zheng B, Myint SW, Thenkabail PS, Aggarwal RM (2015) A support vector machine to identify irrigated crop types using time-series Landsat NDVI data. Int J Appl Earth Obs Geoinf 34:103–112. https://doi.org/10.1016/j.jag.2014.07.002
Acknowledgements
Authors thanks Copernicus for providing access to Sentinel-2B satellite data and thanks to Directorate of Economics and Statistics, DAC&FW (DES) for providing the agriculture statistics. BRP received funding from the University Grants Commission (UGC) under the start-up Grant.
Funding
This research was supported by the University Grants Commission (UGC) under the start-up Grant number F.4-5(209-FRP)/2015/BSR.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Ethical approval
All ethical standards was followed during the research.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Parida, B.R., Kumar, A. & Ranjan, A.K. Crop Types Discrimination and Yield Prediction Using Sentinel-2 Data and AquaCrop Model in Hazaribagh District, Jharkhand. KN J. Cartogr. Geogr. Inf. 73, 77–89 (2023). https://doi.org/10.1007/s42489-021-00073-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42489-021-00073-4