A geographically weighted random forest approach for evaluate forest change drivers in the Northern Ecuadorian Amazon

Abstract

The Tropical Andes region includes biodiversity hotspots of high conservation priority whose management strategies depend on the analysis of forest dynamics drivers (FDDs). These depend on complex social and ecological interactions that manifest on different space–time scales and are commonly evaluated through regression analysis of multivariate datasets. However, processing such datasets is challenging, especially when time series are used and inconsistencies in data collection complicate their integration. Moreover, regression analysis in FDD characterization has been criticized for failing to capture spatial variability; therefore, alternatives such as geographically weighted regression (GWR) have been proposed, but their sensitivity to multicollinearity has not yet been solved. In this scenario, we present an innovative methodology that combines techniques to: 1) derive remote sensing time series products; 2) improve census processing with dasymetric mapping; 3) combine GWR and random forest (RF) to derive local variables importance; and 4) report results based in a clustering and hypothesis testing. We applied this methodology in the northwestern Ecuadorian Amazon, a highly heterogeneous region characterized by different active fronts of deforestation and reforestation, within the time period 2000–2010. Our objective was to identify linkages between these processes and validate the potential of the proposed methodology. Our findings indicate that land-use intensity proxies can be extracted from remote sensing time series, while intercensal analysis can be facilitated by calculating population density maps. Moreover, our implementation of GWR with RF achieved accurate predictions above the 74% using the out-of-bag samples, demonstrating that derived RF features can be used to construct hypothesis and discuss forest change drivers with more detailed information. In the other hand, our analysis revealed contrasting effects between deforestation and reforestation for variables related to suitability to agriculture and accessibility to its facilities, which is also reflected according patch size, land cover and population dynamics patterns. This approach demonstrates the benefits of integrating remote sensing–derived products and socioeconomic data to understand coupled socioecological systems more from a local than a global scale.

Geographically weighted machine learning model for untangling spatial heterogeneity of type 2 diabetes mellitus (T2D) prevalence in the USA

“…Although the GW-RF model in this study used only six well-known risk factors for exploring spatial heterogeneity of T2D prevalence, the focus of this study is not understanding the causation of T2D prevalence across US counties. Instead, this study is intended as a demonstration of how the recently developed GW-RF model 23 , 24 , 76 , 77 can be used as both a predictive and exploratory tool to explore spatial heterogeneity of T2D considering the non-linear relationship between risk factors and T2D prevalence. Thus, this method is applicable in many instances where there is an issue about selecting significantly correlated variables at various geographical locations.…”

Understanding the Drivers of Mobility during the COVID-19 Pandemic in Florida, USA Using a Machine Learning Approach

“…Machine learning algorithms [9], and random forest models in particular [10], are widely used in geospatial modeling by providing determinant-specific spatial contexts. These models have been especially useful for identifying explanatory variables and assessing the importance of these variables with respect to dependent variables, such as transport mode choice decision prediction, transportation mode recognition, travel demand system prediction, and explanation of drivers for forest change [11][12][13][14]. A random forest regression model is a meta-estimator that fits a number of decision trees to various subsamples of the dataset, and uses averaging to improve the predictive accuracy and control over-fitting [15,16].…”

Spatial Modeling of Sociodemographic Risk for COVID-19 Mortality

“…Overall, spatial lag variations between independent variables is reflective of local socioeconomic and cultural views which can dampen (or exacerbate) the effects of COVID-19 associated factors (e.g. deaths) [55].…”