Applications of machine-learning-based approaches in the geosciences have witnessed a substantial increase over the past few years. Here we present an approach that accounts for spatial autocorrelation by introducing spatial features to the models. In particular, we explore two types of spatial features, namely spatial lag and eigenvector spatial filtering (ESF). These features are used within the widely used random forest (RF) method, and their effect is illustrated on two public datasets of varying sizes (Meuse and California housing datasets). The least absolute shrinkage and selection operator (LASSO) is used to determine the best subset of spatial features, and nested cross-validation is used for hyper-parameter tuning and performance evaluation. We utilize Moran’s I and local indicators of spatial association (LISA) to assess how spatial autocorrelation is captured at both global and local scales. Our results show that RF models combined with either spatial lag or ESF features yield lower errors (up to 33% different) and reduce the global spatial autocorrelation of the residuals (up to 95% decrease in Moran’s I) compared to the RF model with no spatial features. The local autocorrelation patterns of the residuals are weakened as well. Compared to benchmark geographically weighted regression (GWR) models, the RF models with spatial features yielded more accurate models with similar levels of global and local autocorrelation in the prediction residuals. This study reveals the effectiveness of spatial features in capturing spatial autocorrelation and provides a generic machine-learning modelling workflow for spatial prediction.

The goal of the present study is to demonstrate that high-poverty counties and robust classification features can be identified by machine learning approaches using only DMSP/OLS night-time light imagery. To accomplish this goal, a total of 96 high-poverty and 96 non-poverty counties were classified using 15 statistical and spatial features extracted from night-time light imagery in China in 2010 formed a training set for identifying high-poverty counties. Seven machine learning approaches were adopted to classify high-poverty counties, and five feature importance measures were used to select robust features. The resulting metrics, including the user’s (>63%), producer’s (>66%) and overall (>82%) accuracies of the poor county identification (probability of poverty greater than 0.6), show that the seven machine learning approaches used in this paper exhibit good performance, although some differences exist among the approaches. The order of feature importance reveals that the relative importance of each feature differs among the models; however, the important features remain consistent. The nine most important features ranked in each approach are relatively robust for poverty identification at the county level. Both spatial feature and statistical features calculated in part from the central tendency, degree of dispersion, and the distribution of the night-time light data were identified as indispensable robust features in all the approaches, indicating that the complex social phenomenon of poverty requires analysis from different aspects. Previous studies that utilized primarily night-time light imagery applied single features related to the central tendency or the distribution features of the imagery; this study provides a new method and can act as a reference for feature selection and identification of high-poverty counties using night-time light imagery and has potential applications across several scientific domains.

As a leading cause of morbidity and premature mortality, obesity has become a major global public health problem. It is therefore important to investigate the spatial variation of obesity prevalence and its associations with environmental and behavioral factors (e.g., food environment, physical activity), to optimize the targeting of scarce public health resources. In this study, the geographic clustering of obesity in the Netherlands was explored by analyzing the local spatial autocorrelation of municipal-level prevalence rates of adulthood obesity (aged ≥19 years) in 2016. The potential influential factors that may be associated with obesity prevalence were first selected from five categories of healthrelated factors through binary and Least Absolute Shrinkage and Selection Operator (LASSO) regressions. Geographically Weighted Regression (GWR) was then used to investigate the spatial variations of the associations between those selected factors and obesity prevalence. The results revealed marked geographic variations in obesity prevalence, with four clusters of high prevalence in the north, south, east, and west, and three clusters of low prevalence in the north and south of the Netherlands. Lack of sports participation, risk of anxiety, falling short of physical activity guidelines, and the number of restaurants around homes were found to be associated with obesity prevalence across municipalities. Our findings show that effective, region-specific strategies are needed to tackle the increasing obesity in the Netherlands.

Synthetic Aperture Radar (SAR) is the main instrument utilized for the detection of oil slicks on the ocean surface. In SAR images, some areas affected by ocean phenomena, such as rain cells, upwellings, and internal waves, or discharge from oil spills appear as dark spots on images. Dark spot detection is the first step in the detection of oil spills, which then become oil slick candidates. The accuracy of dark spot segmentation ultimately affects the accuracy of oil slick identification. Although some advanced deep learning methods that use pixels as processing units perform well in remote sensing image semantic segmentation, detecting some dark spots with weak boundaries from noisy SAR images remains a huge challenge. We propose a dark spot detection method based on superpixels deeper graph convolutional networks (SGDCN) in this paper, which takes the superpixels as the processing units and extracts features for each superpixel. The features calculated from superpixel regions are more robust than those from fixed pixel neighborhoods. To reduce the difficulty of learning tasks, we discard irrelevant features and obtain an optimal subset of features. After superpixel segmentation, the images are transformed into graphs with superpixels as nodes, which are fed into the deeper graph convolutional neural network for node classification. This graph neural network uses a differentiable aggregation function to aggregate the features of nodes and neighbors to form more advanced features. It is the first time using it for dark spot detection. To validate our method, we mark all dark spots on six SAR images covering the Baltic Sea and construct a dark spots detection dataset, which has been made publicly available (https://drive.google.com/drive/folders/12UavrntkDSPrItISQ8iGefXn2gIZHxJ6?usp=sharing). The experimental results demonstrate that our proposed SGDCN is robust and effective.