A comparison of two adaptive multivariate analysis methods (PLSR and ANN) for winter wheat yield forecasting using Landsat-8 OLI images. Issue 4 (15th February 2017)

• Record Type: Journal Article
• Authors: Chen, Pengfei; Jing, Qi
• Is Part Of: Advances in space research. Volume 59:Issue 4(2017)
• Page Start: 987
• Page End: 995
• Publication Date: 2017-02-15
• Subjects: Winter wheat -- Yield forecast -- Partial least squares regression -- Artificial neural networks; Space sciences -- Periodicals; Astronautics -- Periodicals; Geophysics -- Periodicals; 500.505
• DOI: 10.1016/j.asr.2016.11.029
• Languages: English
• ISSNs: 0273-1177

Abstract

Abstract: An assumption that the non-linear method is more reasonable than the linear method when canopy reflectance is used to establish the yield prediction model was proposed and tested in this study. For this purpose, partial least squares regression (PLSR) and artificial neural networks (ANN), represented linear and non-linear analysis method, were applied and compared for wheat yield prediction. Multi-period Landsat-8 OLI images were collected at two different wheat growth stages, and a field campaign was conducted to obtain grain yields at selected sampling sites in 2014. The field data were divided into a calibration database and a testing database. Using calibration data, a cross-validation concept was introduced for the PLSR and ANN model construction to prevent over-fitting. All models were tested using the test data. The ANN yield-prediction model produced R 2, RMSE and RMSE % values of 0.61, 979 kg ha −1, and 10.38%, respectively, in the testing phase, performing better than the PLSR yield-prediction model, which produced R 2, RMSE, and RMSE % values of 0.39, 1211 kg ha −1, and 12.84%, respectively. Non-linear method was suggested as a better method for yield prediction.