Using Google Earth Engine to Map Complex Shade-Grown Coffee Landscapes in Northern Nicaragua

Abstract

Shade-grown coffee (shade coffee) is an important component of the forested tropics, and is essential to the conservation of forest-dependent biodiversity. Despite its importance, shade coffee is challenging to map using remotely sensed data given its spectral similarity to forested land. This paper addresses this challenge in three districts of northern Nicaragua, here leveraging cloud-based computing techniques within Google Earth Engine (GEE) to integrate multi-seasonal Landsat 8 satellite imagery (30 m), and physiographic variables (temperature, topography, and precipitation). Applying a random forest machine learning algorithm using reference data from two field surveys produced a 90.5% accuracy across ten classes of land cover, with an 82.1% and 80.0% user's and producer's accuracy respectively for shade-grown coffee. Comparing classification accuracies obtained from five datasets exploring different combinations of non-seasonal and seasonal spectral data as well as physiographic data also revealed a trend of increasing accuracy when seasonal data were included in the model and a significant improvement (7.8-20.1%) when topographical data were integrated with spectral data. These results are significant in piloting an open-access and user-friendly approach to mapping heterogeneous shade coffee landscapes with high overall accuracy, even in locations with persistent cloud cover.

The First Wetland Inventory Map of Newfoundland at a Spatial Resolution of 10 m Using Sentinel-1 and Sentinel-2 Data on the Google Earth Engine Cloud Computing Platform

“…As noted in a previous study [83], the image mosaicking technique over a long time-period may increase classification errors in areas of high inter-annual change, causing a signal of seasonality to be overlooked. Although this image mosaicking technique is essential for addressing the limitation of frequent cloud cover for land cover mapping using optical remote sensing data across a broad spatial scale, this was mitigated in this study to a feasible extent.…”

Assessing the Transferability of Machine Learning Algorithms Using Cloud Computing and Earth Observation Datasets for Agricultural Land Use/Cover Mapping

“…In this study, pre-processing includes subsetting, mosaicking and enhancement of the satellite imageries, preparation of training and test samples. Of course, atmospheric and geometric corrections are one of the important steps of preprocessing (Mustak, 2013) but google earth engine has a capability to download radiometrically and geometrically calibrated satellite imagery (Kelley et al, 2018). In addition, mosaic and stacking of images bands during both Kharif and Rabi season were done using median algorithms.…”

“…In addition, mosaic and stacking of images bands during both Kharif and Rabi season were done using median algorithms. The median algorithms (Reducer function) widely used in google earth engine for mosaicking and stacking satellite image bands because it has better capability to represent the central tendency of the variables (e.g., DN values) as compared to other methods e.g., mean, mode (Kelley et al, 2018).…”

“…Google earth engine (GEE) is a cloud computing API which has a better capability to fast access and high computation of large volume of openly accessible satellite imageries (big data) at no cost (Jacobson et al, 2015;Kelley et al, 2018;Tsai et al, 2018). Integration of machine learning algorithms with GEE is an added advantage over advanced machine learning for different application like land use/cover mapping (Tsai et al, 2018).…”

“…Normalized Difference Vegetation Index: Normalized Difference Vegetation Index (NDVI) commonly used in land use/cover classification for discrimination of vegetated area from the non-vegetated area (Kelley et al, 2018). NDVI was calculated using following equation 1:…”