Excessive urbanization leads to considerable nature deficiency and abundant artificial infrastructure in urban areas, which triggered intensive discussions on people's exposure green space outdoor light at night (ALAN). Recent academic progress highlights that ALAN may be confounders of each other but lacks systematic investigations. This study investigates the associations between by adopting three most used research paradigms: population-level residence-based, individual-level...

Spatiotemporal association pattern mining can discover interesting interdependent relationships among various types of geospatial data. However, existing methods for spatiotemporal patterns usually model geographic phenomena as simple point events. Therefore, they cannot be applied to complex phenomena, which continuously change their properties, shapes or locations, such storms and air pollution. The most salient feature is the dynamic. To fully reveal dynamic characteristics associated...

Building footprints are among the most predominant features in urban areas, and provide valuable information for planning, solar energy suitability analysis, etc. We aim to automatically rapidly identify building by leveraging deep learning techniques increased availability of remote sensing datasets at high spatial resolution. The task is computationally challenging due use large training number parameters. In related work, You-Only-Look-Once (YOLO) a state-of-the-art framework object...

Water quality prediction is the basis of water environmental planning, evaluation, and management. In this work, a novel intelligent model based on fuzzy wavelet neural network (FWNN) including (NN), logic (FL), transform (WT), genetic algorithm (GA) was proposed to simulate nonlinearity parameters predictions. A self‐adapted c ‐means clustering used determine number rules. hybrid learning gradient descent employed optimize parameters. Comparisons were made between FWNN (FNN), (WNN), (ANN)....

Regional co-location patterns represent subsets of feature types that are frequently located together in sub-regions a study area. These unknown priori, and instances these usually unevenly distributed across remain challenging to discover. This developed multi-level method identify regional two steps. First, global were detected, other non-prevalent identified as candidates for patterns. Second, an adaptive spatial clustering was applied detect the where prevalent. To improve computational...

Multilevel co-location patterns embedded in spatial datasets are difficult to discern due the complexity of neighboring relationships among features. The used determine whether instances different features located close geographic proximity. When distributed unevenly, cannot be constructed appropriately. Correspondingly, generated correctly, and prevalence multilevel measured accurately. To overcome this challenge, study develops a method adaptively detect based on natural neighborhoods....

This paper seeks to evaluate and calibrate data collected by low-cost particulate matter (PM) sensors in different environments using aggregated temporal units (i.e., 5-s, 1-min, 10-min, 30 min intervals). We first PM concentrations PM1, PM2.5, PM10) five indoor outdoor of an office building, a train platform lobby subway station, seaside location) Hong Kong, AirBeam2 as the TSI DustTrak DRX Aerosol Monitor 8533 reference sensor. By comparing concentrations, we found high linearity...

Tailings dams in mining areas frequently experience the phenomenon of haphazard dumping and stacking a large amount tailings waste. Under influence surface runoff groundwater infiltration, heavy metals from waste can migrate to surrounding underground soil, resulting extensive metal pollution. To analyze pollution level ecological risk an abandoned lead–zinc mine dam, this study first employed X-ray fluorescence analysis determine vertical distribution patterns with depth. Then, levels were...

The neighborhood effect averaging problem (NEAP) is a fundamental statistical phenomenon in mobility-dependent environmental exposures. It suggests that individual exposures tend toward the average exposure study area when considering human mobility. However, universality of NEAP across various and mechanisms underlying its occurrence remain unclear. Here, using large mobility data set more than 27 000 individuals Chicago Metropolitan Area, we provide robust evidence existence range...

Spatial flow co-location patterns (FCLPs) are important for understanding the spatial dynamics and associations of movements. However, conventional point-based pattern discovery methods ignore movements between locations thus may generate erroneous findings when applied to flows. Despite recent advances, there is still a lack analyzing multivariate To bridge gap, this paper formulates novel problem FCLP presents an effective detection method based on frequent-pattern mining statistics. We...

Detecting regional co-location patterns on urban road networks is challenging because it computationally prohibitive to search all potential and their localities, effective statistical methods for evaluating the prevalence of are lacking. To overcome these challenges, this study developed an adaptive method detecting network-constrained patterns. Specifically, alternate measure was defined based likelihood ratio statistic. A k-nearest neighbor used construct instances candidate patterns, a...

AbstractUsing individual-level data collected from two communities in Hong Kong, this study proposes a significant association rule mining method to identify the complex associations between individual socioeconomic characteristics and perceived air pollution people's daily life. It defines measure, namely inequality index, assess social exposure both residential visited neighborhoods. The results indicate that are not always consistent over communities, nor value ranges of pollution....

Spatial co‐location patterns are useful for understanding positive spatial interactions among different geographical phenomena. Existing methods detecting mostly developed based on planar space assumption; however, phenomena related to human activities strongly constrained by road networks. Although these can be simply modified consider the constraints of networks using network distance or partitioning scheme, user‐specified parameters priori assumptions determining prevalent still...

Regions of anomalous spatial co-locations (ROASCs) are regions where between two different features significantly stronger or weaker than expected. ROASC discovery can provide useful insights for studying unexpected associations at regional scales. The main challenges that the ROASCs spatially arbitrary in geographic shape and distributions unknown a priori. To avoid restrictive assumptions regarding distribution data, we propose distribution-free method discovering arbitrarily shaped...

Abstract Spatial co‐location pattern mining aims to discover a collection of Boolean spatial features, which are frequently located in close geographic proximity each other. Existing methods for identifying patterns usually require users specify two thresholds, i.e. the prevalence threshold measuring candidate and distance search patterns. However, these thresholds difficult determine practice, improper may lead misidentification useful incorrect reporting meaningless The multi‐scale...