Early Within-Season Yield Prediction and Disease Detection Using Sentinel Satellite Imageries and Machine Learning Technologies in Biomass Sorghum
- 394 Downloads
Sorghum is grown for several purposes including biomass for producing energy and fodder, and grain for producing health-promoting foods. Sorghum is a drought resistant cereal with low input requirements, making it one of the most promising crops under the world’s tropics and higher latitudes. Crop monitoring, one of the leading activities in smart farming, can help cut production costs and more so under climate change. In this study, Sentinel 2A and 2B-derived fAPAR and NDVI data were used to monitor sorghum phenology, foliar diseases, and to predict aboveground biomass yields months before harvest, using machine learning approaches including Bayesian methods and region-convolutional neural network. The results obtained in this work were encouraging. We were able to predict biomass yields up to 6 months before harvest with mean absolute percentage error (MAPE) < 0.2, while diseases were detected with accuracy up to 90%. The best machine learning algorithm was Bayesian additive regression trees (bartMachine method), while the best biomass yields prediction regressors were the days of year 150 and 165. These results were achieved at a Pilot level and the technologies showed industrial scale implementation potentials with tremendous benefits for the farmer, extension services, policy makers, and other parties at interest.
KeywordsSorghum biomass Sorghum diseases Prediction modeling Machine learning Bayesian learning NDVI and fAPAR Satellite imagery Sentinel-2
Part of this work was supported (beneficiary: first author) by the project Data-driven Bioeconomy (www.databio.eu), GA number: 732064 (H2020-ICT-2016-1—innovation action), and the project Risorse GeneticheVegetali (RGV/FAO) 2014e2016 of the Ministero delle PoliticheAgricole, Alimentari e Forestali, Rome.
- 1.Habyarimana, E., Lorenzoni, C., Redaelli, R., Alfieri, M., Amaducci, S., Cox, S.: Towards a perennial biomass sorghum crop: a comparative investigation of biomass yields and overwintering of Sorghum bicolorx S. halepense lines relative to long term S. bicolor trials in northern Italy. Biomass Bioenergy 111, 187–195 (2018)CrossRefGoogle Scholar
- 10.Kussul, N., Kolotii, A., Skakun, S., Shelestov, A., Kussul, O., Oliynuk, T.: Efficiency estimation of different satellite data usage for winter wheat yield forecasting in Ukraine. In: Proceedings of the 2014 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Quebec City, Canada (2014)Google Scholar
- 13.Habyarimana, E., Piccard, I., Catellani, M., De Franceschi, P., Dall’Agata, M.: Towards predictive modeling of sorghum biomass yields using fraction of absorbed photosynthetically active radiation derived from Sentinel-2 satellite imagery and supervised machine learning techniques. Agronomy 9, 203 (2019)CrossRefGoogle Scholar
- 14.Rumpf, T., Mahlein, A.-K., Steiner, U., Oerke, E.-C., Dehne, H.-W., Plümer, L.: Early detection and classification of plant diseases with Support Vector Machines based on hyperspectral reflectance. Comput. Electron. Agric. 74(1), 91–99 (2010). https://doi.org/10.1016/j.compag.2010.12.012CrossRefGoogle Scholar
- 17.Weiss, M., Baret, F.: ATBD S2ToolBox Level 2 Products: LAI, FAPAR, FCOVER (Version 1.1). http://step.esa.int/docs/extra/ATBD_S2ToolBox_L2B_V1.1.pdf. Accessed 04 May 2019
- 19.R Core Team: R: A Language and Environment for Statistical Computing; R Foundation for Statistical Computing, Vienna, Austria (2013)Google Scholar
- 20.Jost, Z.: “Bayesian Additive Regression Trees” paper summary. https://towardsdatascience.com/bayesian-additive-regression-trees-paper-summary-9da19708fa71. Accessed 04 May 2019