Skip to main content

Developing Maize Yield Predictive Models from Sentinel-2 MSI Derived Vegetation Indices: An Approach to an Early Warning System on Yield Fluctuation and Food Security

Abstract

Annual crop yield fluctuation due to natural and anthropogenic factors is a major concern of the Ethiopian Government. For an immediate response to drastically changing crop yields and resulting harvest failures and to enhance the country’s food security in general, extensive area crop growth monitoring and early prediction of production are needed. In this study, we developed an early maize (Zea mays) yield forecasting model using Sentinel-2 MSI (Multispectral Instrument); the study was carried out in the Abaya district of the Oromia Regional State in Ethiopia. The model consists of the following components: (1) Sentinel-2 image-based cropland identification for different crop development stages, (2) extraction of time series Sentinel-2 vegetation indices for crop growth monitoring, and (3) a simple linear stepwise forward regression approach for yield prediction. We tested different spectral indices regarding their performance in describing the crop development and eventually predicting the expected yield. The result showed that (1) the linear Red-Edge Enhanced Vegetation Index (Red-Edge EVI), (2) the combination of the Enhanced Vegetation Index (EVI) and the Green Vegetation Index (GVI), (3) the combination of the Red-Edge EVI and Soil Adjusted Vegetation Index (SAVI), and (4) the combination of the Normalized Difference Vegetation Index (NDVI), Red-Edge EVI and SAVI offer the best predictive model about 2 months before harvesting with the highest coefficients of determination (R2) of 0.73, 0.80, 0.84, and 0.88, respectively. The correlation for the GVI was generally lowest compared to established models, and no evidence of a peak correlation for NDVI was observed. Our approach showed a high accuracy of detecting maize fields, detecting crop phenology, and early predicting of grain yield for the study year 2018. Our simple model may generate early warning information, which may support in-time decision-making regarding food supply when critical yield fluctuations are to be expected.

Zusammenfassung

Jährliche Schwankungen der Ernteerträge aufgrund natürlicher und anthropogener Faktoren sind ein Hauptanliegen der äthiopischen Regierung. Für eine sofortige Reaktion auf sich drastisch verändernde Ernteerträge und daraus resultierende Ernteausfälle sowie zur Verbesserung der Ernährungssicherheit des Landes im Allgemeinen sind eine großflächige Überwachung des Pflanzenwachstums und eine frühzeitige Vorhersage der Produktion erforderlich. In dieser Studie haben wir ein Modell zur frühzeitigen Vorhersage des Maisertrags (Zea mays) unter Verwendung des Sentinel-2 MSI (Multispectral Instrument) entwickelt; die Studie wurde im Bezirk Abaya im Regionalstaat Oromia in Äthiopien durchgeführt. Das Modell besteht aus den folgenden Komponenten: (1) Sentinel-2-Bild-basierte Ackerland-Identifikation für verschiedene Pflanzenentwicklungsstadien, (2) Extraktion von Zeitreihen von Sentinel-2-Vegetationsindizes (VIs) für die Überwachung des Pflanzenwachstums und (3) ein einfacher linearer schrittweiser Vorwärtsregressionsansatz für die Ertragsvorhersage. Wir testeten verschiedene Spektralindizes hinsichtlich ihrer Leistung bei der Beschreibung der Pflanzenentwicklung und schließlich der Vorhersage des erwarteten Ertrags. Das Ergebnis zeigte, dass: (i) der lineare Red-Edge Enhanced Vegetation Index (Red-Edge EVI), (ii) die Kombination aus dem Enhanced Vegetation Index (EVI) und dem Green Vegetation Index (GVI), (iii) die Kombination aus dem Red-Edge EVI und dem Soil Adjusted Vegetation Index (SAVI), und (iv) die Kombination aus dem Normalized Difference Vegetation Index (NDVI), Red-Edge EVI und SAVI das beste Vorhersagemodell etwa zwei Monate vor der Ernte mit den höchsten Bestimmtheitsmaßen (R2) von 0,73, 0,80, 0,84 bzw. 0,88, bieten. Die Korrelation für den GVI war im Vergleich zu den etablierten Modellen generell am niedrigsten, und für den NDVI wurde kein Hinweis auf eine Spitzenkorrelation beobachtet. Unser Ansatz zeigte eine hohe Genauigkeit bei der Erkennung von Maisfeldern, der Erkennung der Pflanzenphänologie und der frühzeitigen Vorhersage des Kornertrags für das Studienjahr 2018. Unser einfaches Modell kann Frühwarninformationen generieren, die eine rechtzeitige Entscheidungsfindung bezüglich der Nahrungsmittelversorgung unterstützen können, wenn kritische Ertragsschwankungen zu erwarten sind.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

References

  1. Balaghi R, Tychon B, Eerens H, Jlibene M (2008) Empirical regression models using NDVI, rainfall and temperature data for the early prediction of wheat grain yields in Morocco. Int J Appl Earth Obs Geoinf 10(4):438–452. https://doi.org/10.1016/j.jag.2006.12.001

    Article  Google Scholar 

  2. Ban H, Kim KS, Park N, Lee B (2016) Using MODIS data to predict regional corn yields. Remote Sens 16(9):1–19. https://doi.org/10.3390/rs9010016

    Article  Google Scholar 

  3. Baret F, Guyot G, Major DJ (1989) TSAVI: a vegetation index which minimizes soil brightness effects on LAI and APAR estimation. In: 12th Canadian symposium on remote sensing geoscience and remote sensing symposium 3. pp 1355–1358. https://doi.org/10.1109/IGARSS.1989.576128

  4. 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. https://doi.org/10.1016/j.rse.2017.10.005

    Article  Google Scholar 

  5. Belgiu M, Drăguţ L (2016) Random forest in remote sensing: a review of applications and future directions. ISPRS J Photogramm Remote Sens 114:24–31. https://doi.org/10.1016/j.isprsjprs.2016.01.011

    Article  Google Scholar 

  6. Bolton DK, Friedl MA (2013) Forecasting crop yield using remotely sensed vegetation indices and crop phenology metrics. Agric for Meteorol 173:74–84. https://doi.org/10.1016/j.agrformet.2013.01.007

    Article  Google Scholar 

  7. Boschetti M, Nutini F, Manfron G, Brivio PA, Nelson A (2014) Comparative analysis of normalised difference spectral indices derived from MODIS for detecting surface water in flooded rice cropping systems. PLoS One 9(2):1–21. https://doi.org/10.1371/journal.pone.0088741

    Article  Google Scholar 

  8. Breiman L (2001) Random forests. Mach Learn 45:5–32. https://doi.org/10.1023/A:1010933404324

    Article  Google Scholar 

  9. Bussay A, Velde MVD, Fumagalli D, Seguini L (2015) Improving operational maize yield forecasting in Hungary. AGSY 141:94–106. https://doi.org/10.1016/j.agsy.2015.10.001

    Article  Google Scholar 

  10. Casanova D, Epema GF, Goudriaan J (1998) Monitoring rice reflectance at field level for estimating biomass and LAI. Field Crop Res 55(1):83–92. https://doi.org/10.1016/S0378-4290(97)00064-6

    Article  Google Scholar 

  11. Chipanshi A, Zhang Y, Kouadio L, Newlands N, Davidson A, Hill H, Warren R, Qian B, Daneshfar B, Bedard F, Reichert G (2015) Agricultural and forest meteorology evaluation of the integrated canadian crop yield forecaster ( ICCYF) model for in-season prediction of crop yield across the Canadian agricultural landscape. Agric for Meteorol 206:137–150. https://doi.org/10.1016/j.agrformet.2015.03.007

    Article  Google Scholar 

  12. Chivasa W, Mutanga O, Biradar C (2017) Application of remote sensing in estimating maize grain yield in heterogeneous African agricultural landscapes: a review. Int J Remote Sens 38(23):6816–6845. https://doi.org/10.1080/01431161.2017.1365390

    Article  Google Scholar 

  13. Cian F, Marconcini M, Ceccato P (2018) Normalized Difference Flood Index for rapid flood mapping: taking advantage of EO big data. Remote Sens Environ 209:712–730. https://doi.org/10.1016/j.rse.2018.03.006

    Article  Google Scholar 

  14. Clevers JGP, Gitelson AA (2013) Remote estimation of crop and grass chlorophyll and nitrogen content using red-edge bands on Sentinel-2 and -3. Int J Appl Earth Obs Geoinf 23:344–351. https://doi.org/10.1016/j.jag.2012.10.008

    Article  Google Scholar 

  15. Cochrane L, Bekele YW (2018) Average crop yield (2001–2017) in Ethiopia: trends at national, regional and zonal levels. Data Brief 16:1025–1033. https://doi.org/10.1016/j.dib.2017.12.039

    Article  Google Scholar 

  16. Congalton RG (1991) A review of assessing the accuracy of classifications of remotely sensed data. Remote Sens Environ 37(1):35–46. https://doi.org/10.1016/0034-4257(91)90048-B

    Article  Google Scholar 

  17. CSA (Central Statistical Agency of Ethiopia) (2018) Farm management statistics of Ethiopia. Available at https://knoema.com/EFMS2020/farm-management-statistics-of-ethiopia. Accessed 16 Sept 2021.

  18. da Silva EE, Rojo Baio FH, Ribeiro TLP, da Silva Junior CA, Borges RS, Teodoro PE (2020) UAV-multispectral and vegetation indices in soybean grain yield prediction based on in situ observation. Remote Sens Appl Soc Environ 18:100318. https://doi.org/10.1016/j.rsase.2020.100318

    Article  Google Scholar 

  19. Darvishzadeh R, Atzberger C, Skidmore AK, Abkar AA (2009) Leaf Area Index derivation from hyperspectral vegetation indicesand the red edge position. Int J Remote Sens 30(23):6199–6218. https://doi.org/10.1080/01431160902842342

    Article  Google Scholar 

  20. Dong T, Meng J, Shang J, Liu J, Wu B (2015) Evaluation of chlorophyll-related vegetation indices using simulated Sentinel-2 data for estimation of crop fraction of absorbed photosynthetically active radiation. IEEE J Sel Top Appl Earth Obs Remote Sens 8(8):4049–4059. https://doi.org/10.1109/JSTARS.2015.2400134

    Article  Google Scholar 

  21. Eddy PR, Smith AM, Hill BD, Peddle DR, Coburn CA, Blackshaw RE (2014) Weed and crop discrimination using hyperspectral image data and reduced bandsets. Can J Remote Sens 39(6):481–490. https://doi.org/10.5589/m14-001

    Article  Google Scholar 

  22. ESA (European Space Agency) (2016) Copernicus Sentinel-2 mission. Available at https://www.esa.int/Applications/Observing_the_Earth/Copernicus/Sentinel-2. Accessed 01 Jan 2020

  23. FAO (2015) Analysis of price incentives for maize in Ethiopia for the time period 2005–2012. Available at http://www.fao.org/in-action/mafap/resources/detail/en/c/394285/. Accessed 01 Sept 2021

  24. Forkuor G, Conrad C, Thiel M, Ullmann T, Zoungrana E (2014) Integration of optical and synthetic aperture radar imagery for improving crop mapping in Northwestern Benin, West Africa. Remote Sens 6(7):6472–6499. https://doi.org/10.3390/rs6076472

    Article  Google Scholar 

  25. Forkuor G, Dimobe K, Serme I, Tondoh JE (2017) Landsat-8 vs. Sentinel-2: examining the added value of sentinel-2 ’ s red-edge bands to land-use and land-cover mapping in Burkina Faso. Gisci Remote Sens 55(3):331–354. https://doi.org/10.1080/15481603.2017.1370169

    Article  Google Scholar 

  26. Gislason PO, Benediktsson JA, Sveinsson JR (2006) Random forests for land cover classification. Pattern Recogn Lett 27(4):294–300. https://doi.org/10.1016/j.patrec.2005.08.011

    Article  Google Scholar 

  27. Gitelson A, Merzlyak MN (1994) Spectral reflectance changes associated with autumn senescence of Aesculus hippocastanum L. and Acer platanoides L. leaves. Spectral features and relation to chlorophyll estimation. J Plant Physiol 143(3):286–292. https://doi.org/10.1016/S0176-1617(11)81633-0

    Article  Google Scholar 

  28. González-Gómez L, Campos I, Calera A (2018) Use of different temporal scales to monitor phenology and its relationship with temporal evolution of normalized difference vegetation index in wheat. J Appl Remote Sens 12(2):1–18. https://doi.org/10.1117/1.JRS.12.026010

    Article  Google Scholar 

  29. Guo BB, Qi SL, Heng YR, Duan JZ, Zhang HY, Wu YP, Feng W, Xie YX, Zhu YJ (2017) Remotely assessing leaf N uptake in winter wheat based on canopy hyperspectral red-edge absorption. Eur J Agron 82:113–124. https://doi.org/10.1016/j.eja.2016.10.009

    Article  Google Scholar 

  30. Haerani H, Apan A, Basnet B (2018) Mapping of peanut crops in Queensland, Australia, using time-series PROBA-V 100-m normalized difference vegetation index imagery. J Appl Remote Sens 12(3):1–22. https://doi.org/10.1117/1.JRS.12.036005

    Article  Google Scholar 

  31. Hu Q, Sulla-Menashe D, Xu B, Yin H, Tang H, Yang P, Wu W (2019) A phenology-based spectral and temporal feature selection method for crop mapping from satellite time series. Int J Appl Earth Obs Geoinf 80:218–229. https://doi.org/10.1016/j.jag.2019.04.014

    Article  Google Scholar 

  32. Huete AR, Jackson RD (1987) Suitability of spectral indices for evaluating vegetation characteristics on arid rangelands. Remote Sens Environ 23(2):213–232. https://doi.org/10.1016/0034-4257(87)90038-1

    Article  Google Scholar 

  33. Huete AR, Liu H, van Leeuwen WJD (1997) The use of vegetation indices in forested regions: issues of linearity and saturation. IEEE Int Geosci Remote Sens 1(1):1966–1968. https://doi.org/10.1109/IGARSS.1997.609169

    Article  Google Scholar 

  34. Huete A, Didan K, Miura T, Rodriguez EP, Gao X, Ferreira LG (2002) Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sens Environ 83(1):195–213. https://doi.org/10.1016/S0034-4257(02)00096-2

    Article  Google Scholar 

  35. Kamal J, Bhatia KJ (2010) Review of rice crop identification and classification using hyper-spectral image processing system. Int J Comput Sci Commun 1(1): 253–258. http://www.csjournals.com/IJCSC/PDF1-1/54.pdf

  36. Khaliq A, Peroni L, Chiaberge M (2018) Land cover and crop classification using multitemporal sentinel-2 images based on crops phenological cycle. 2018 IEEE Workshop on Environmental, Energy, and Structural Monitoring Systems (EESMS). https://doi.org/10.1109/EESMS.2018.8405830

  37. Kussul N, Lavreniuk M, Shelestov A, Yailymov B (2016) Along the season crop classification in Ukraine based on time series of optical and SAR images using ensemble of neural network classifiers. 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). pp 7145–7148. https://doi.org/10.1109/IGARSS.2016.7730864

  38. Lambert M, Sibiry PC, 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. https://doi.org/10.1016/j.rse.2018.06.036

    Article  Google Scholar 

  39. Lebourgeois V, Dupuy S, Vintrou É, Ameline M, Butler S, Bégué A (2017) 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. https://doi.org/10.3390/rs9030259

    Article  Google Scholar 

  40. Liao C, Wang J, Dong T, Shang J, Liu J, Song Y (2019) Using spatio-temporal fusion of Landsat-8 and MODIS data to derive phenology, biomass and yield estimates for corn and soybean. Sci Total Environ 650:1707–1721. https://doi.org/10.1016/j.scitotenv.2018.09.308

    Article  Google Scholar 

  41. Liu WT, Kogan F (2002) Monitoring Brazilian soybean production using NOAA/AVHRR based vegetation condition indices. Int J Remote Sens 23(6):1161–1179. https://doi.org/10.1080/01431160110076126

    Article  Google Scholar 

  42. Lobell DB, Asner GP, Ortiz-Monasterio JI, Benning TL (2003) Remote sensing of regional crop production in the Yaqui Valley, Mexico: estimates and uncertainties. Agric Ecosyst Environ 94(2):205–220. https://doi.org/10.1016/S0167-8809(02)00021-X

    Article  Google Scholar 

  43. Maresma Á, Ariza M, Martínez E, Lloveras J, Martínez-Casasnovas JA (2016) Analysis of Vegetation Indices to Determine Nitrogen Application and Yield Prediction in Maize (Zea mays L.) from a Standard UAV Service. Remote Sens 8(12):1–15. https://doi.org/10.3390/rs8120973

    Article  Google Scholar 

  44. Mazzia V, Khaliq A, Chiaberge M (2020) Improvement in land cover and crop classification based on temporal features learning from Sentinel-2 data using recurrent-convolutional neural network (R-CNN). Appl Sci 10(1):1–23. https://doi.org/10.3390/app10010238

    Article  Google Scholar 

  45. Meng W, Fu-lu TAO, Wen-jiao SHI (2014) Corn yield forecasting in northeast china using remotely Se n sed spectral indices and crop phenology metrics. J Integr Agric 13:1538–1545. https://doi.org/10.1016/S2095-3119(14)60817-0

    Article  Google Scholar 

  46. Mkhabela MS, Bullock P, Raj S, Wang S, Yang Y (2011) Crop yield forecasting on the Canadian Prairies using MODIS NDVI data. Agric for Meteorol 151(3):385–393. https://doi.org/10.1016/j.agrformet.2010.11.012

    Article  Google Scholar 

  47. MOA (Ministry of Agriculture) (2015) Ethiopian agriculture: production and market development. http://www.moa.gov.et/agricultural-development-sector. Accessed 01 Nov 2018

  48. MOA (Ministry of Agriculture) (2019) Ethiopian agriculture: annual production and factors affecting this sector. http://www.moa.gov.et/web/guest/about-the-ministry. Accessed 2019 Feb

  49. Mutanga O, Skidmore AK (2004) Narrow band vegetation indices overcome the saturation problem in biomass estimation. Int J Remote Sens 25(19):3999–4014. https://doi.org/10.1080/01431160310001654923

    Article  Google Scholar 

  50. Nasrallah A, Baghdadi N, Mhawej M, Faour G, Darwish T, Belhouchette H, Darwich S (2018) A novel approach for mapping wheat areas using high resolution Sentinel-2 images. Sensors. https://doi.org/10.3390/s18072089

    Article  Google Scholar 

  51. Noureldin NA, Aboelghar MA, Saudy HS, Ali AM (2013) Rice yield forecasting models using satellite imagery in Egypt. Egypt J Remote Sens Space Sci 16(1):125–131. https://doi.org/10.1016/j.ejrs.2013.04.005

    Article  Google Scholar 

  52. Palchowdhuri Y, Valcarce-Diñeiro R, King P, Sanabria-Soto M (2018) Classification of multi-temporal spectral indices for crop type mapping: a case study in Coalville, UK. J Agric Sci 156(1):24–36. https://doi.org/10.1017/S0021859617000879

    Article  Google Scholar 

  53. Panda SS, Ames DP, Panigrahi S (2010) Application of vegetation indices for agricultural crop yield prediction using neural network techniques. Remote Sens 2(3):673–696. https://doi.org/10.3390/rs2030673

    Article  Google Scholar 

  54. Park SK, Schowengerdt RA (1983) Image reconstruction by parametric cubic convolution. Comput vis Graph Image Process 23(3):258–272. https://doi.org/10.1016/0734-189X(83)90026-9

    Article  Google Scholar 

  55. Peng Y, Gitelson AA (2011) Application of chlorophyll-related vegetation indices for remote estimation of maize productivity. Agric for Meteorol 151(9):1267–1276. https://doi.org/10.1016/j.agrformet.2011.05.005

    Article  Google Scholar 

  56. Prabhakara K, Hively WD, Mccarty GW (2015) Evaluating the relationship between biomass, percent groundcover and remote sensing indices across six winter cover crop fields in Maryland, United States. Int J Appl Earth Obs Geoinf 39(3):88–102. https://doi.org/10.1016/j.jag.2015.03.002

    Article  Google Scholar 

  57. Ramirez-Villegas J, Challinor A (2012) Assessing relevant climate data for agricultural applications. Agric for Meteorol 161:26–45. https://doi.org/10.1016/j.agrformet.2012.03.015

    Article  Google Scholar 

  58. Rodriguez-Galiano VF, Ghimire B, Rogan J, Chica-Olmo M, Rigol-Sanchez JP (2012) An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS J Photogramm Remote Sens 67:93–104. https://doi.org/10.1016/j.isprsjprs.2011.11.002

    Article  Google Scholar 

  59. Rossini M, Panigada C, Meroni M, Busetto L, Castrovinci R, Colombo R (2007) Pedunculate oak forests (Quercus robur L.) survey in the Ticino Regional Park (Italy) by remote sensing. J Silvic for Ecol 4(2):194–203. https://doi.org/10.3832/efor0450-0040194

    Article  Google Scholar 

  60. Rouse JW, Haas RH, Schell JA, Deering DW, Harlan JC (1973) Monitoring the vernal advancement of retrogradation of natural vegetation (vols. E73–10303). Available via NTRS - NASA. https://ntrs.nasa.gov/citations/19740008955. Accessed 01 June 2021

  61. Rouse JW, Haas RH, Schell JA, Deering DW, Harlan JC (1974) Monitoring vegetation systems in the great plains with ERTS. Proceedings, Third Earth Resources Technology Satellite-1 Symposium, Greenbelt 1974. pp 3010–3017. Available via CiNii Research. http://ci.nii.ac.jp/naid/10025572118/en/. Accessed 05 Oct 2021

  62. RStudio Team (2018) RStudio: Integrated Development for R. RStudio, PBC, Boston, MA. Available at http://www.rstudio.com/. Accessed 01 Aug 2021

  63. Ruml M, Vulic T (2005) Importance of phenological observations and predictions in agriculture. J Agric Sci 50(2):217–225. https://doi.org/10.2298/jas0502217r

    Article  Google Scholar 

  64. Running SW, Loveland TR, Pierce LL, Nemani RR, Hunt ER (1995) A remote sensing based vegetation classification logic for global land cover analysis. Remote Sens Environ 51(1):39–48. https://doi.org/10.1016/0034-4257(94)00063-S

    Article  Google Scholar 

  65. Sacks WJ, Kucharik CJ (2011) Crop management and phenology trends in the US Corn Belt: impacts on yields, evapotranspiration and energy balance. Agric for Meteorol 151(7):882–894. https://doi.org/10.1016/j.agrformet.2011.02.010

    Article  Google Scholar 

  66. Sakamoto T, Yokozawa M, Toritani H, Shibayama M, Ishitsuka N, Ohno H (2005) A crop phenology detection method using time-series MODIS data. Remote Sens Environ 96(3):366–374. https://doi.org/10.1016/j.rse.2005.03.008

    Article  Google Scholar 

  67. Sakamoto T, Wardlow BD, Gitelson AA, Verma SB, Suyker AE, Arkebauer TJ (2014) Remote sensing of environment a two-step filtering approach for detecting maize and soybean phenology with time-series MODIS data. Remote Sens Environ 114(10):2146–2159. https://doi.org/10.1016/j.rse.2010.04.019

    Article  Google Scholar 

  68. Sharma LK, Bu H, Denton A, Franzen DW (2015) Active-optical sensors using red NDVI compared to red edge NDVI for prediction of corn grain yield in North Dakota, USA. Remote Sens 15(11):27832–27853. https://doi.org/10.3390/s151127832

    Article  Google Scholar 

  69. Smethurst PJ, Huth NI, Masikati P, Sileshi GW, Akinnifesi FK, Wilson J, Sinclair F (2017) Accurate crop yield predictions from modelling tree-crop interactions in gliricidia-maize agroforestry. Agric Syst 155:70–77. https://doi.org/10.1016/j.agsy.2017.04.008

    Article  Google Scholar 

  70. Sonobe R, Yamaya Y, Tani H, Wang X, Kobayashi N, Mochizuki K (2018) Crop classification from Sentinel-2-derived vegetation indices using ensemble learning. J Appl Remote Sens 12(2):1–16. https://doi.org/10.1117/1.JRS.12.026019

    Article  Google Scholar 

  71. Tian H, Huang N, Niu Z, Qin Y, Pei J, Wang J (2019) Mapping winter crops in china with multi-source satellite imagery and phenology-based algorithm. Remote Sens 11(7):1–23. https://doi.org/10.3390/rs11070820

    Article  Google Scholar 

  72. UNDP (2000) The Agricultural Weredas of Borena Zone, Oromiya Region. Available at https://www.africa.upenn.edu/eue_web/borena0600.htm. Accessed 20 Dec 2018

  73. Vuolo F, Neuwirth M, Immitzer M, Atzberger C, Ng WT (2018) How much does multi-temporal Sentinel-2 data improve crop type classification? Int J Appl Earth Obs Geoinf 72:122–130. https://doi.org/10.1016/j.jag.2018.06.007

    Article  Google Scholar 

  74. Waldhoff G, Lussem U, Bareth G (2017) Multi-data approach for remote sensing-based regional crop rotation mapping: a case study for the Rur catchment, Germany. Int J Appl Earth Obs Geoinf 61:55–69. https://doi.org/10.1016/j.jag.2017.04.009

    Article  Google Scholar 

  75. Xue J, Su B (2017) Significant remote sensing vegetation indices: a review of developments and applications. J Sens 2017:1353691. https://doi.org/10.1155/2017/1353691

    Article  Google Scholar 

  76. Zheng H, Du P, Chen J, Xia J, Li E, Xu Z, Li X, Yokoya N (2017) Performance evaluation of downscaling Sentinel-2 imagery for land use and land cover classification by spectral-spatial features. Remote Sens. https://doi.org/10.3390/rs9121274

    Article  Google Scholar 

  77. Zhou X, Zheng HB, Xu XQ, He JY, Ge XK, Yao X, Cheng T, Zhu Y, Cao WX, Tian YC (2017) Predicting grain yield in rice using multi-temporal vegetation indices from UAV-based multispectral and digital imagery. ISPRS J Photogramm Remote Sens 130:246–255. https://doi.org/10.1016/j.isprsjprs.2017.05.003

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by Dilla University, Ethiopia, under-funds for medium and large-scale research projects. Field maize yield data and phenological stages were collected at small-scale farmlands in collaboration with local farmers. We thank ESA for the availability of Sentinel-2 MSI at Copernicus Open Access Hub. We would also like to thank the anonymous reviewers for their insightful comments.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Muluken N. Bazezew.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Bazezew, M.N., Belay, A.T., Guda, S.T. et al. Developing Maize Yield Predictive Models from Sentinel-2 MSI Derived Vegetation Indices: An Approach to an Early Warning System on Yield Fluctuation and Food Security. PFG (2021). https://doi.org/10.1007/s41064-021-00178-5

Download citation

Keywords

  • Crop phenology
  • GVI
  • Red-Edge EVI
  • SAVI
  • Spectral indices
  • Zea mays