Forecasting corn yield at the farm level in Brazil based on the FAO-66 approach and soil-adjusted vegetation index (SAVI)
2019
Venancio, Luan Peroni | Mantovani, Everardo Chartuni | do Amaral, Cibele Hummel | Usher Neale, Christopher Michael | Gonçalves, Ivo Zution | Filgueiras, Roberto | Campos, Isidro
Crop yield forecasting at the field level is essential for decision-making and the prediction of agricultural economic returns for farmers. Thus, this study evaluated the performance of a methodology for corn yield prediction in irrigated fields in the western region of the state of Bahia, Brazil. This methodology integrates a time series of the basal crop coefficient (Kcb) estimated from the soil-adjusted vegetation index (SAVI) into a simple model based on the water productivity as presented in the FAO-66 manual. In this context, an extensive field-level dataset of 52 center pivot fields of cultivated with corn was used for four consecutive growing seasons (2013 to 2016). Surface reflectance images from the Landsat series were used to calculate the SAVI. The methodology performance was assessed through RMSE, RRMSE, MBE, MAE, and r². The results revealed that the difference between the predicted and actual yield values ranged between -12.2% and 18.8% but that the majority of the estimates remained between -10% and 10%, considering that a single harvest index (HI) was used for the hybrids cultivated in the growing seasons of 2014, 2015 and 2016. After a new reanalysis (by grouping the similar hybrids and using specific HIs), the performance of the predictions increased, especially for the Pioneer hybrids; the majority of the differences between the predicted yield values and the measured yield values remained between -5% and 5%. The results of this research showed that it is essential to work with different HIs when considering different hybrids and years under different weather conditions.
اظهر المزيد [+] اقل [-]الكلمات المفتاحية الخاصة بالمكنز الزراعي (أجروفوك)
المعلومات البيبليوغرافية
تم تزويد هذا السجل من قبل National Agricultural Library