Early Prediction of Coffee Yield in the Central Highlands of Vietnam Using a Statistical Approach and Satellite Remote Sensing Vegetation Biophysical Variables

Abstract

Given the present climate change context, accurate and timely coffee yield prediction is critical to all farmers who work in the coffee industry worldwide. The aim of this study is to develop and assess a coffee yield forecasting method at the regional scale in Dak Lak province in the central highlands of Vietnam using the Crop Growth Monitoring System Statistical Tool (CGMSstatTool—CST) software and vegetation biophysical variables (NDVI, LAI, and FAPAR) derived from satellite remote sensing (SPOT-VEGETATION and PROBA-V). There has been no research to date applying this approach to this specific crop, which is the main contribution of this study. The findings of this research reveal that the elaboration of multiple linear regression models based on a combination of information from satellite-derived vegetation biophysical variables (LAI, NDVI, and FAPAR) corresponding to the first six months of the years 2000–2019 resulted in coffee yield forecast models presenting satisfactory accuracy (Adj.R2 = 64 to 69%, RMSEp = 0.155 to 0.158 ton/ha and MAPE = 3.9 to 4.7%). These results demonstrate that the CST may efficiently predict coffee yields on a regional scale by using only satellite-derived vegetation biophysical variables. This study findings are likely to aid local governments and decision makers in precisely forecasting coffee production early and promptly, as well as in recommending relevant local agricultural policies.

Estimation des rendements fourragers des pâturages dans les espaces climatiques du Burkina Faso à partir de données satellitaires

“…Les plus couramment utilisés portent sur les pluies, l'humidité du sol, la température de surface, l'évapotranspiration et le développement de la végétation (Adole et al, 2016 ;Fritz et al, 2019), comme, par exemple, l'indice de végétation par différence normalisée (NDVI, Normalized Difference Vegetation Index), la fraction absorbée du rayonnement photosynthétiquement actif (FAPAR, Fraction of Absorbed Photosynthetically Active Radiation) et la productivité de la matière sèche (DMP, dry matter productivity) (PRAPS, 2017). Ces derniers sont couramment utilisés pour l'estimation des rendements fourragers au Sahel (Diouf et al, 2015 ;Lo et al, 2022 ;Taugourdeau et al, 2023), ou pour l'estimation des rendements d'autres cultures dans des contextes géographiques différents (Thao et al, 2022). Plus particulièrement, selon différents auteurs (Meroni et al, 2014 ;Diouf et al, 2015 ;Olsen et al, 2015 ;Tian et al, 2016 ;Garba et al, 2017 ;Lo et al, 2022)…”

Remote Sensing Information System in Vietnam and Its Application: A Minireview

“…These findings show that the CST can predict coffee yields on a regional scale using only satellite-derived vegetation biophysical variables. This is likely to help local governments and decision-makers forecast coffee production accurately and quickly, as well as recommend relevant local agricultural policies (Thao et al, 2022). With the continued development and application of remote sensing technology, Vietnam will be better equipped to manage its natural resources, respond to disasters, and improve the lives of its citizens.…”

Feasibility of Early Yield Prediction per Coffee Tree Based on Multispectral Aerial Imagery: Case of Arabica Coffee Crops in Cauca-Colombia

“…This was validated by RMSE with ±13.6% and a MAE with ±7.9%. Similarly, Nguyen et al [15] proposed a statistical model for the early prediction of coffee crop yields based on vegetation indexes at a regional level with Copernicus data for the NDVI, FAPAR, and LAI predictors, obtaining an Adj R 2 from 64 to 69% in regression models using the Crop Growth Monitoring System statistical tool, which allows early prediction of up to 6 months before the harvest.…”