Toward Operational Mapping of Woody Canopy Cover in Tropical Savannas Using Google Earth Engine

Abstract

Savanna woody plants can store significant amounts of carbon while also providing numerous other ecological and socio-economic benefits. However, they are significantly under-represented in widely used tree cover datasets, due to mapping challenges presented by their complex landscapes, and the underestimation of woody plants by methods that exclude short stature trees and shrubs. In this study, we describe a Google Earth Engine (GEE) application and present test case results for mapping percent woody canopy cover (%WCC) over a large savanna area. Relevant predictors of %WCC include information derived from radar backscatter (Sentinel-1) and optical reflectance (Sentinel-2), which are used in conjunction with plot level %WCC measurements to train and evaluate random forest models. We can predict %WCC at 40 m pixel resolution for the full extent of Senegal with a root mean square error of ∼8% (based on independent sample evaluation). Further examination of model results provides insights into method stability and potential generalizability. Annual median radar backscatter intensity is determined to be the most important satellite-based predictor of %WCC in savannas, likely due to its relatively strong response to non-leaf structural components of small woody plants which remain mostly constant across the wet and dry season. However, the best performing model combines radar backscatter metrics with optical reflectance indices that serve as proxies for greenness, dry biomass, burn incidence, plant water content, chlorophyll content, and seasonality. The primary use of GEE in the methodology makes it scalable and replicable by end-users with limited infrastructure for processing large remote sensing data.

How Do Climate and Catchment Attributes Influence Flood Generating Processes? A Large‐Sample Study for 671 Catchments Across the Contiguous USA

“…We provide a brief introduction into interpretable machine learning and a more in depth introduction into ALE in the supporting information. ALE plots improve the application of more commonly used partial dependence plots (Anchang et al., 2020; Friedman, 2001; Molnar, 2019). After a model was fit to the data, ALE plots evaluate the change in model prediction over a small interval of an input variable (Apley & Zhu, 2016).…”

“…ALE are a relatively new method. They have proven their applicability in several fields (e.g., Anchang et al., 2020; Brown et al., 2020; Konapala et al., 2020). One limitation is that ALE evaluate the reaction of a model to changes in an attribute.…”

Eleven Years of Mangrove–Mudflat Dynamics on the Mud Volcano-Induced Prograding Delta in East Java, Indonesia: Integrating UAV and Satellite Imagery

“…A composite from one-month scenes of the particular month was created with the median value of the selected bands and indices for mangrove classification for optical sensor (S2, L7, L8). A mean function was applied for the satellite with SAR instrument (S1) [76,77]. The median value was chosen because it is less affected by outlier values that arise, for instance, from pixels affected by clouds or snow during the masking procedures [75].…”

“…Lastly, the mean value of all S1 images was employed. This mean function makes the S1 composite less susceptible to variation in image acquisition [76,77]. With this additional dataset, each S1 mosaic had two bands and one index, while S2, L7, and L8 had 10, 6, and 7 spectral bands, respectively, and each was composed of four vegetation indices (Table 1).…”

Migratory Birds Monitoring of India’s Largest Shallow Saline Ramsar Site with Big Geospatial Data Using Google Earth Engine for Restoration

“…This enables minimum dependence on special remote sensing software such as Earth Resources Data Analysis System (ERDAS) Imagine and Environment for Visualizing Images (ENVI), nevertheless, they are still needed for special functions that are not offered on GEE (like object-based image assessment) [16]. GEE has been widely explored for vegetation mapping and monitoring such as global estimation of Fraction of Absorbed Photosynthetically Active Radiation (FAPAR) [20], Leaf Area Index (LAI) [21], Canopy water content (CWC) [22], and Fraction Vegetation Cover (FVC) [23], for agricultural applications like crop area mapping [24], crop yield estimation [25] and pests and diseases vulnerability [16].…”