Developing detailed age-specific thematic maps for coffee (Coffea arabica L.) in heterogeneous agricultural landscapes using random forests applied on Landsat 8 multispectral sensor

Abstract

Coffee is a commodity of international trade significance, and its value chain can benefit from age-specific thematic maps. This study aimed to assess the potential of Landsat 8 OLI to develop these maps. Using field-collected samples with the random forest classifier, splitting coffee into three age classes (Scheme A) was compared with running the classification with one compound coffee class (Scheme B). Higher overall classification accuracy was obtained in Scheme B (90.3% for OLI and 86.8% for ETM+) than in Scheme A (86.2% for OLI and 81.0% for ETM+). The NIR band of OLI was the most important band in intra-class discrimination of coffee. Landsat 8 OLI mapped area closely matched farm records (R 2 = 0.88) compared to that of Landsat 7 ETM+ (R 2 = 0.78). It was concluded that Landsat 8 OLI data can be used to produce age-specific thematic maps in coffee production areas although disaggregating coffee classes reduces overall accuracy.

Dynamics of Land Use and Land Cover Changes in Harare, Zimbabwe: A Case Study on the Linkage between Drivers and the Axis of Urban Expansion

“…However, possible sources of error in the calculations may have emerged from geometric rectification, accuracy in digitizing topographic maps and combining different data sources. The spectral differences and characteristics between Landsat 5 TM and Landsat 8 OLI sensors may have affected the accuracy of the thematic maps [23]. Despite these potential discrepancies, the classification and results obtained in the current study have relatively high accuracy considering urban area spectral heterogeneity characteristics and spectral confusion from land cover classes, and the results agree with other published scientific studies carried out at the national and regional level (Supplementary Materials Table S1) [6,24,26,27].…”

“…The points were randomly split into two sets: 80% of the data for training and 20% of the data for accuracy assessment and validation [30]. Polygons (regions of interest (ROIs)) were digitized and used for both LULC classification and accuracy assessment to improve classification and validation range [23]. Statistical testing of spectral separability of the desired classes was verified using the transformed divergence separability index (TD) to ensure classification [40].…”

“…An accuracy assessment was computed for the Kappa coefficient (Kc), overall accuracy (OA), producer's accuracy (PA) and user's accuracy (UA), applying "ground truth regions of interests" [23,43]. Accuracy assessment is a probabilistic approach that computes the association between remotely sensed and referenced data.…”

“…Accurate observation of LULC changes by remote sensing is a vital component of promoting sustainability. Enhancement of land cover class delineation using remote sensing indices and machine learning algorithms such as random forest (RF) and support vector machines (SVMs) have the relatively desirable characteristic of improving multispectral classification [20][21][22][23][24]. The effectiveness of mapping land-cover types using spectral indices is primarily the result of their ability to characterize relative features of interest over a wide range of the spectrum [25].…”

Integration of Sentinel optical and radar data for mapping smallholder coffee production systems in Vietnam

“…Only a handful of studies have distinguished shade (closed-canopy or mixed) coffee from sun coffee (open-canopy or production) at mid-resolutions, such as Landsat (Cordero-Sancho and Sader, 2007;Kawakubo and Pérez Machado, 2016;Ortega-Huerta et al, 2012). Even fewer works distinguish coffee age classes (Chemura et al,2017;Chemura and Mutanga, 2016). And a single work classifies multiple production systems: closed canopy, shade polyculture, sun monoculture and newly planted (sparse cover), using high resolution IKONOS imagery (Widayati et al, 2003).…”