Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6949192 | ISPRS Journal of Photogrammetry and Remote Sensing | 2018 | 11 Pages |
Abstract
Nitrogen (N) is the most limiting factor to coffee development and productivity. Therefore, development of rapid, spatially explicit and temporal remote sensing-based approaches to determine spatial variability of coffee foliar N are imperative for increasing yields, reducing production costs and mitigating environmental impacts associated with excessive N applications. This study sought to assess the value of Sentinel-2 MSI spectral bands and vegetation indices in empirical estimation of coffee foliar N content at landscape level. Results showed that coffee foliar N is related to Sentinel-2 MSI B4 (R2â¯=â¯0.32), B6 (R2â¯=â¯0.49), B7 (R2â¯=â¯0.42), B8 (R2â¯=â¯0.57) and B12 (R2â¯=â¯0.24) bands. Vegetation indices were more related to coffee foliar N as shown by the Inverted Red-Edge Chlorophyll Index - IRECI (R2â¯=â¯0.66), Relative Normalized Difference Index - RNDVI (R2â¯=â¯0.48), CIRE1 (R2â¯=â¯0.28), and Normalized Difference Infrared Index - NDII (R2â¯=â¯0.37). These variables were also identified by the random forest variable optimisation as the most valuable in coffee foliar N prediction. Modelling coffee foliar N using vegetation indices produced better accuracy (R2â¯=â¯0.71 with RMSEâ¯=â¯0.27 for all and R2â¯=â¯0.73 with RMSEâ¯=â¯0.25 for optimized variables), compared to using spectral bands (R2â¯=â¯0.57 with RMSEâ¯=â¯0.32 for all and R2â¯=â¯0.58 with RMSEâ¯=â¯0.32 for optimized variables). Combining optimized bands and vegetation indices produced the best results in coffee foliar N modelling (R2â¯=â¯0.78, RMSEâ¯=â¯0.23). All the three best performing models (all vegetation indices, optimized vegetation indices and combining optimal bands and optimal vegetation indices) established that 15.2â¯ha (4.7%) of the total area under investigation had low foliar N levels (<2.5%). This study demonstrates the value of Sentinel-2 MSI data, particularly vegetation indices in modelling coffee foliar N at landscape scale.
Related Topics
Physical Sciences and Engineering
Computer Science
Information Systems
Authors
Abel Chemura, Onisimo Mutanga, John Odindi, Dumisani Kutywayo,