Boosted Regression Tree Models Research Articles

Distribution patterns and influencing factors of population exposure risk to particulate matters based on cell phone signaling data

In this study, spatial-temporal characteristics of particular matter (PM) exposure risk in Shenyang were analyzed with landscape patterns using data from land use, cell phone signaling, and PM mobile monitoring. Pollution surfaces were established with geographically weighted regression models and impact factors analysis was implemented by boosted regression tree models. The results showed that weekdays and weekends had different spatial distributions of PM, and the exposure risk was lower on weekends. High exposure risks of PM10 were concentrated in the first ring zone (76.53 people·m−2·μg·m−3) and residential-commercial land (292.34 people·m−2·μg·m−3). Exposure risks of PM2.5 were most affected by residential-commercial land and fourth-class (relative contribution: 59.69 and 8.88, respectively). However, the exposure risks of PM10 were more influenced by first-class roads (relative contribution: 2.01). The results indicated that independent modeling analysis of different types of PM and periods contribute to more detailed studies of spatial-temporal variation of PM. For human activity studies, cell phone signaling data can effectively distinguish spatial-temporal distribution characteristics of the population on weekdays and weekends. Multi-source big data combined with mobile monitoring and model simulations were used to make population exposure risk studies more accessible, real-time, and cost-effective for sustainable urban planning and development.

Temporal and spatial changes in soil organic carbon and soil inorganic carbon stocks in the semi-arid area of northeast China

Soil organic carbon (SOC) and soil inorganic carbon (SIC) has important effects on soil physical, chemical and biological properties. They play an important role in coordinating the relationship between soil water and air, increasing soil water holding capacity and improving plant productivity. In this study, a boosted regression trees (BRT) model was developed to map the spatial distribution carbon stocks in the semi-arid region of Northeast China in 1990 and 2015. During the two periods, 10-fold cross-validation technology was used to test the performance and uncertainty of BRT model. In order to construct the model, 9 environmental variables (derived from climate, topography and biology) and 173 (1990) and 223 (2015) topsoil (0–30 cm) samples were used. The comparison between estimated and observed data shows that the RMSE of SOC and SIC stocks were 0.53 kgm−2 and 0.19 kgm−2 in 1990, and 0.65 kgm−2 and 0.20 kgm−2 in 2015, respectively. Elevation, normalized difference vegetation index, mean annual precipitation and Landsat band 3 were identifies as critical environmental factors for simulating the spatial distribution of SOC, accounting for 76.6 % and 70.3 % of the total relative importance in 1990 and 2015, respectively. Mean annual precipitation, mean annual temperature and topographic wetness index were the critical environmental factors for simulating the spatial variation of SIC during the two periods. Land use change also played an important role in the spatial variability of SOC and SIC stocks. In the past 25 years, soil carbon stocks decreased from 6.2 kg m−2 in 1990 to 5.9 kg m−2 in 2015. The spatial distribution pattern of SOC was high in northeastern area and low in southwestern area during the two periods, while the spatial distribution pattern of SIC was opposite to that of SOC stocks. The mapped soil carbon stock distribution is fundamental to future study of soil carbon cycle and regional carbon balance in semi-arid regions.

A Novel Hybrid Model Combining the Support Vector Machine (SVM) and Boosted Regression Trees (BRT) Technique in Predicting PM10 Concentration

The PM10 concentration is subject to significant changes brought on by both gaseous and meteorological variables. The aim of this research was to explore the performance of a hybrid model combining the support vector machine (SVM) and the boosted regression trees (BRT) technique in predicting the PM10 concentration for 3 consecutive days. The BRT model was trained by utilizing maximum daily data in the cities of Alor Setar, Klang, and Kuching from the years 2002 to 2017. The SVM–BRT model can optimize the number of predictors and predict PM10 concentration; it was shown to be capable of predicting air pollution based on the models’ performance with NAE (0.15–0.33), RMSE (10.46–32.60), R2 (0.33–0.70), IA (0.59–0.91), and PA (0.50–0.84). This was accomplished while saving training time by reducing the feature size given in the data representation and preventing learning from noise (overfitting) to improve accuracy. This knowledge establishes the foundation for the development of efficient methods to prevent and/or minimize the health effects of PM10 exposure on one’s health.

Multi‐scale drivers of spatial patterns in floodplain sediment and phosphorus deposition

AbstractThe capacity for floodplains to capture sediment and filter pollutants is spatially variable and depends on the complex interactions of geomorphic, geologic, and hydrologic variables that operate at multiple scales. In this study, we integrated watershed‐scale and local assessments to improve our understanding of floodplain depositional patterns. We developed a dataset of event‐scale observations of sediment and phosphorus deposition rates distributed at 129 plots across large environmental gradients of floodplain topography, valley geometry, and watershed characteristics in the Lake Champlain Basin, Vermont. Plot‐scale observations were used to evaluate the cross‐scale influence of environmental factors and were summarized into site‐scale averages to explore regional trends. Consistent with other studies, floodplain deposition generally scaled with drainage area, but trends were longitudinally discontinuous and depended on variations in valley width and slope. While variability in deposition patterns at the watershed‐scale was large (average of 2.0 (0.2–9.8) kg sediment m−2 yr−1; average of 1.4 (0.2–6.5) g phosphorus m−2 yr−1), the range in deposition rates locally across a floodplain was greater (average of 4.6 (0.06–21.7) kg sediment m−2 yr−1; average of 6.4 (0.1–41.1) g phosphorus m−2 yr−1). Local variables that described the proximity to water and sediment sources, and frequency with which the plot was activated by a flood, had the greatest relative contribution to boosted regression tree models of phosphorus deposition rates, highlighting the importance of river–floodplain connectivity for floodplain functioning and the profound impact of human activities that limit such connectivity. Patterns identified in our study may guide prioritization of restoration and conservation practices designed to capture sediment and phosphorus on floodplains.

Effects of Forest Fire Prevention Policies on Probability and Drivers of Forest Fires in the Boreal Forests of China during Different Periods

Fire prevention policies during different periods may lead to changes in the drivers of forest fires. Here, we use historical fire data and apply the boosted regression tree (BRT) model to analyze the spatial patterns and drivers of forest fires in the boreal forests of China from 1981 to 2020 (40 years). We divided the fire data into four periods using the old and new Chinese Forest Fire Regulations as a dividing line. Our objectives here were: to explore the influence of key historical events on the drivers of forest fires in northern China, establish a probability model of forest fire occurrence, and draw a probability map of forest fire occurrence and a fire risk zone map, so as to interpret the differences in the drivers of forest fires and fire risk changes over different periods. The results show that: (1) The model results from 1981 to 2020 (all years) did not improve between 2009 and 2020 (the most recent period), indicating the importance of choosing the appropriate modeling time series length and incorporating key historical events in future forest fire modeling; (2) Climate factors are a dominant factor affecting the occurrence of forest fires during different periods. In contrast with previous research, we found that here, it is particularly important to pay attention to the relevant indicators of the autumn fire prevention period (average surface temperature, sunshine hours) in the year before the fire occurrence. In addition, the altitude and the location of watchtowers were considered to have a significant effect on the occurrence of forest fires in the study area. (3) The medium and high fire risk areas in our three chosen time periods (1981–14 March 1988; 15 March 1988–2008; 2009–2020) have changed significantly. Fire risks were higher in the east and southeast areas of the study area in all periods. The northern primeval forest area had fewer medium-risk areas before the new and old regulations were formulated, but the medium-risk areas increased significantly after the old regulations were revised. Our study will help understand the drivers and fire risk distribution of forest fires in the boreal forests of China under the influence of history and will help decision-makers optimize fire management strategies to reduce potential fire risks.

Increasing the utility of tree regeneration inventories: Linking seedling abundance to sapling recruitment

Tree regeneration surveys provide insight into potential forest change and trajectories of stand development, which can guide management in an era of global change. However, most tree regeneration surveys tend to be coarse and/or rapid assessments which can introduce considerable uncertainty into translating estimates of seedling abundance into models of sapling recruitment and subsequent overstory tree abundance and composition. Observations of seedling abundance changes across size classes may be essential to accurately predicting recruitment from seedling sized trees to advanced size classes, which is fundamental to informing our understanding of future forest composition and dynamics. Using the USDA Forest Service’s Forest Inventory and Analysis (FIA) program’s Regeneration Indicator (RI) dataset, in which seedlings are monitored by six height classes, we developed Boosted Regression Tree models to predict presence of sapling recruitment for five common, north temperate and boreal tree species as a function of seedling abundance by height class and site/stand factors. Models using the six RI seedling height classes were compared to models using the single seedling size class as commonly surveyed by programs such as FIA. Use of seedling height classes improved models for all species. Seedlings > 1.5 m tall were the most influential predictors of recruitment for each species while seedlings in classes < 1.5 m tall were either removed entirely from models or had low relative influence (<8%). Seedlings < 0.3 m tall had both positive and negative relationships with sapling recruitment depending on species, suggesting that abundances of small seedlings should be interpreted cautiously. This approach demonstrates the importance of collecting relatively coarse seedling height data during regeneration surveys with potential application to other regions and scenarios to expand the utility of tree regeneration surveys to predict future forest dynamics.

Potential for redistribution of post-moult habitat for Eudyptes penguins in the Southern Ocean under future climate conditions.

Anthropogenic climate change is resulting in spatial redistributions of many species. We assessed the potential effects of climate change on an abundant and widely distributed group of diving birds, Eudyptes penguins, which are the main avian consumers in the Southern Ocean in terms of biomass consumption. Despite their abundance, several of these species have undergone population declines over the past century, potentially due to changing oceanography and prey availability over the important winter months. We used light-based geolocation tracking data for 485 individuals deployed between 2006 and 2020 across 10 of the major breeding locations for five taxa of Eudyptes penguins. We used boosted regression tree modelling to quantify post-moult habitat preference for southern rockhopper (E. chrysocome), eastern rockhopper (E. filholi), northern rockhopper (E. moseleyi) and macaroni/royal (E. chrysolophus and E. schlegeli) penguins. We then modelled their redistribution under two climate change scenarios, representative concentration pathways RCP4.5 and RCP8.5 (for the end of the century, 2071-2100). As climate forcings differ regionally, we quantified redistribution in the Atlantic, Central Indian, East Indian, West Pacific and East Pacific regions. We found sea surface temperature and sea surface height to be the most important predictors of current habitat for these penguins; physical features that are changing rapidly in the Southern Ocean. Our results indicated that the less severe RCP4.5 would lead to less habitat loss than the more severe RCP8.5. The five taxa of penguin may experience a general poleward redistribution of their preferred habitat, but with contrasting effects in the (i) change in total area of preferred habitat under climate change (ii) according to geographic region and (iii) the species (macaroni/royal vs. rockhopper populations). Our results provide further understanding on the regional impacts and vulnerability of species to climate change.

Landscape‐scale drivers of liana load across a Southeast Asian forest canopy differ to the Neotropics

Abstract Lianas (woody vines) are a key component of tropical forests, known to reduce forest carbon storage and sequestration and to be increasing in abundance. Analysing how and why lianas are distributed in forest canopies at landscape scales will help us determine the mechanisms driving changes in lianas over time. This will improve our understanding of liana ecology and projections of tropical forest carbon storage now and into the future. Despite competing hypotheses on the mechanisms driving spatial patterning of lianas, few studies have integrated multiple tree‐level biotic and abiotic factors in an analytical framework. None have done so in the Palaeotropics, which are biogeographically and evolutionarily distinct from the Neotropics, where most research on lianas has been conducted. We used an unoccupied aerial system (UAS; drone) to assess liana load in 50‐ha of Palaeotropical forest canopy in Southeast Asia. We obtained data on hypothesised drivers of liana spatial distribution in the forest canopy, including disturbance, tree characteristics, soil chemistry and topography, from the UAS, from airborne LiDAR and from ground surveys. We integrated these in a comprehensive analytical framework to extract variables at an individual‐tree level and evaluated the relative strengths of the hypothesised drivers and their ability to predict liana distributions through boosted regression tree (BRT) modelling. Tree height and distance to canopy gaps were the two most important predictors of liana load, with relative contribution values in BRT models of 34.60%–45.39% and 7.93%–10.19%, respectively. Our results suggest that taller trees were less often and less heavily infested by lianas than shorter trees, opposite to Neotropical findings. Lianas also occurred more often, and to a greater extent, in tree crowns close to canopy gaps and to neighbouring trees with lianas in their crown. Synthesis. Despite their known importance and prevalence in tropical forests, lianas are not well understood, particularly in the Palaeotropics. Examining 2428 trees across 50‐ha of Palaeotropical forest canopy in Southeast Asia, we find support for the hypothesis that canopy gaps promote liana infestation. However, we also found that liana presence and load declined with tree height, which is opposite to well‐established Neotropical findings. This suggests a fundamental difference between Neotropical and Southeast Asian forests. Considering that most liana literature has focused on the Neotropics, this highlights the need for additional studies in other biogeographic regions to clarify potential differences and enable us to better understand liana impacts on tropical forest ecology, carbon storage and sequestration.

Predicted uranium and radon concentrations in New Hampshire (USA) groundwater—Using Multi Order Hydrologic Position as predictors

AbstractTwo radioactive elements, uranium (U) and radon (Rn), which are of potential concern in New Hampshire (NH) groundwater, are investigated. Exceedance probability maps are tools to highlight locations where the concentrations of undesirable substances in the groundwater may be elevated. Two forms of statistical analysis are used to create exceedance probability maps for U and Rn in NH groundwater. The first, Boosted Regression Tree (BRT), was selected for estimating U exceedance values. It computes exceedance values directly using the Bernoulli distribution function. The second method of statistical analysis used for Rn to determine exceedance probabilities is ordinary least squares (OLS) regression. In the process of determining exceedance probabilities for U and Rn, the utility of a new dataset is investigated. That new predictor dataset is the Multi‐Order Hydrologic Position (MOHP) dataset. MOHP raster datasets have been produced nationally for the conterminous United States at a 30‐m resolution. The concept behind MOHP is that, for any given point on the earth's surface, there is the potential for a longer groundwater flow path as one goes deeper beneath the land surface. MOHP predictors were tested in both models. Three MOHP predictors were found useful in the BRT model and two in the OLS model. MOHP data were found useful as predictors along with other site characteristics in predicting U and Rn exceedance probabilities in New Hampshire groundwater.

Global and regional drivers of abundance patterns in the hart's tongue fern complex (Aspleniaceae).

The hart's tongue fern (HTF) complex is a monophyletic group composed of five geographically segregated members with divergent abundance patterns across its broad geographic range. We postulated hierarchical systems of environmental controls in which climatic and land-use change drive abundance patterns at the global scale, while various ecological conditions function as finer scale determinants that further increase geographic disparities at regional to local scales. After quantifying the abundance patterns of the HTF complex, we estimated their correlations with global climate and land-use dynamics. Regional determinants were assessed using boosted regression tree models with 18 potential ecological variables. Moreover, we investigated long-term population trends in the USA to understand the interplay of climate change and anthropogenic activities on a temporal scale. Latitudinal climate shifts drove latitudinal abundance gradients, and regionally different levels of land-use change resulted in global geographic disparities in population abundance. At a regional scale, population isolation, which accounts for rescue effects, played an important role, particularly in Europe and East Asia where several hot spots occurred. Furthermore, the variables most strongly influencing abundance patterns greatly differed by region: precipitation seasonality in Europe; spatial heterogeneity of temperature and precipitation in East Asia; and magnitudes of past climate change, temperature seasonality and edaphic conditions in North America. In the USA, protected populations showed increasing trends compared with unprotected populations at the same latitude, highlighting the critical role of habitat protection in conservation measures. Geographic disparities in the abundance patterns of the HTF complex were determined by hierarchical systems of environmental controls, wherein climatic and land-use dynamics act globally but are modulated by various regional and local determinants operating at increasingly finer scales. We highlighted that fern conservation must be tailored to particular geographic contexts and environmental conditions by incorporating a better understanding of the dynamics acting at different spatiotemporal scales.

Identifying the determinants of crop yields in China since 1952 and its policy implications

Food security is one of the main challenges facing humanity, and increasing crop yields is critical to meet the growing global food demand. Grain production in China has remarkably improved since its founding in 1949, but the growth remains uneven across regions. The goal of this research was to assess the determinants of the yields of three major food crops (maize, rice, and wheat) in China and the mechanism of their responses to increased crop yields. Boosted regression tree models were created to capture the linked complex predictor-response relationships between crop yields and individual explanatory variables using prefecture-level agricultural statistics in China coupled with geographic data during the period from 1952 to 2017. The results showed that technological inputs (e.g., fertilizers, electricity consumption, and power of agricultural machinery) played a key role in the increase of crop yields, which explained 47%, 39%, and 62% of the variances in the yields of maize, rice, and wheat during the period 1952–2017, respectively. However, the contribution of technology became weaker over time, while the contribution of agro-environmental conditions and structural characteristics of administrative regions became stronger. Partial dependence plots indicated that encouraging higher technological inputs, accelerating large-scale grain production, shortening the urban-rural income gap, and improving the education of farmers were conductive to increasing crop yields. Overall, our results suggest that grain production policies aimed at increasing crop yields should better reflect the spatial heterogeneity of yield gaps; low-yield-gap regions should improve the utilization efficiency of water and fertilizer and formulate measures to inhibit non-grain production on cultivated land, while high-yield-gap regions should focus on improving technological inputs and promoting agricultural restructuring. This study provides deep insights into the processes of how individual explanatory variables affect crop yields, which is essential to develop differentiated grain production policies and provide valuable references for shortening yield gaps in high-yield-gap regions.

Nonlinear relationships of runoff and sediment yield with natural and anthropogenic factors at event scale

AbstractUnderstanding how natural and anthropogenic factors affects the watershed runoff and sediment yield at event scale can provide useful insights into watershed hydrological processes to guide watershed management. This article investigates the nonlinear relationships between natural and anthropogenic factors and event runoff and sediment yield with a boosted regression tree (BRT) model for 38 watersheds within the Loess Plateau in China during 2006 to 2016. The BRT model captures the relative importance of each natural and anthropogenic factors to the variability in runoff and sediment yield. The results show that these relationships are complex and highly nonlinear. The event runoff was most related to NDVI in the grass land (NDVI_g), with a 21.3% contribution, followed by 3‐day antecedent precipitation index (AP3), 10‐day antecedent precipitation index (AP10), precipitation (P), and 7‐day antecedent precipitation index (AP7). For event sediment yield, the strongest factor is AP3, with contribution of 33.3%, followed by P, NDVI in the forest land (NDVI_f), AP7, and NDVI in the crop land (NDVI_c). The marginal effect curves produced by the BRT are often characterized by thresholds. For instance, NDVI_f has the greatest effect on event sediment yield reduction when NDVI_f = 0.42, suggesting that a very intense green coverage is not necessary to achieve maximal soil erosion control. Vegetation coverage and meteorological factors can explain 54.7% of event runoff variation and 55.6% of event sediment yield variation. Our study identify the nonlinear relationships between runoff and sediment yield with vegetation cover and meteorological factors and provide scientific support for the planning of subsequent reforestation projects in the Loess Plateau.

Planted seedling survival in a post-wildfire landscape: From experimental planting to predictive probabilistic surfaces

Across the southwestern United States, high-severity wildfire is causing increasingly large areas of tree mortality and removing the seed sources required for the natural regeneration of these formerly conifer-dominated landscapes. Planting tree seedlings can accelerate reforestation, but in the semi-arid southwestern US, the survival of planted conifer seedlings is typically low. Our research examined how post-fire planting success is influenced by climate, topographic, biotic, and microclimate factors. We present data on a seedling planting experiment within the footprint of the 2011 Las Conchas Fire in northern New Mexico. We planted 768 tree seedlings of four species: ponderosa pine (Pinus ponderosa), piñon (P. edulis), southwestern white pine (P. strobiformis), and Douglas-fir (Pseudotsuga menziesii) in an area burned at high-severity and densely populated by New Mexico locust (Robinia neomexicana) and other shrub species. We established experimental plots stratified by aspect, either northerly or southerly, and cover, either planted under New Mexico locust or in the open, and collected topographical and microclimate measurements over three years. Mean survival over the 3-year period for all species in all treatments was 20%. Using microclimate variables and site-level topographical indices in a piecewise exponential model, we first determined how these factors influenced seedling survival of four conifer tree species, finding that topographical indices describing incoming solar radiation, variables related to vapor pressure deficit, i.e., seasonal maximums, and presence of New Mexico locust increased hazard for all species while variables related to shade, moisture availability, and slope reduced hazard. Following our planting experiment, an additional 1145 ponderosa pine seedlings, planted by USFS, were surveyed for survival and the topographical indices at their locations were recorded. Adding these seedlings' survival data to our experimentally planted ponderosa pine seedlings, we used boosted regression tree models to determine survival probability for ponderosa pine as a product of topographical indices, then extrapolated these findings to the wider landscape, producing a spatial projection of probabilistic seedling survival as a function of readily available topographical data, with a mean AUC value of 0.63. Both sets of analyses highlight the importance of landscape heterogeneity in shaping microclimatic environments and affecting seedling survival in a predictable manner, with areas receiving less solar radiation and more moisture promoting seedling survival. Our results demonstrate that by using fine-scale microtopography that shapes microclimatic environments, future plantings can increase conifer tree seedling survival in high-severity post-wildfire landscapes.

Widespread exposure to Crimean-Congo haemorrhagic fever in Uganda might be driven by transmission from Rhipicephalus ticks: Evidence from cross-sectional and modelling studies

Crimean-Congo haemorrhagic fever (CCHF) is a widespread tick-borne viral infection, present across Africa and Eurasia, which might pose a cryptic public health problem in Uganda. We aimed to understand the magnitude and distribution of CCHF risk in humans, livestock and ticks across Uganda by synthesising epidemiological (cross-sectional) and ecological (modelling) studies. We conducted a cross-sectional study at three urban abattoirs receiving cattle from across Uganda. We sampled humans (n=478), livestock (n=419) and ticks (n=1065) and used commercially-available kits to detect human and livestock CCHF virus (CCHFV) antibodies and antigen in tick pools. We developed boosted regression tree models to evaluate the correlates and geographical distribution of expected tick and wildlife hosts, and of human CCHF exposures, drawing on continent-wide data. The cross-sectional study found CCHFV IgG/IgM seroprevalence in humans of 10·3% (7·8-13·3), with antibody detection positively associated with reported history of tick bite (age-adjusted odds ratio=2·09 (1·09-3·98)). Cattle had a seroprevalence of 69·7% (65·1-73·4). Only one Hyalomma tick (CCHFV-negative) was found. However, CCHFV antigen was detected in Rhipicephalus (5·9% of 304 pools) and Amblyomma (2·9% of 34 pools) species. Modelling predicted high human CCHF risk across much of Uganda, low environmental suitability for Hyalomma, and high suitability for Rhipicephalus and Amblyomma. Our epidemiological and ecological studies provide complementary evidence that CCHF exposure risk is widespread across Uganda. We challenge the idea that Hyalomma ticks are consistently the principal reservoir and vector for CCHFV, and postulate that Rhipicephalus might be important for CCHFV transmission in Uganda, due to high frequency of infected ticks and predicted environmental suitability. UCL Global Challenges Research Fund (GCRF) and Pan-African Network on Emerging and Re-Emerging Infections (PANDORA-ID-NET) funded by the European and Developing Countries Clinical Trials Partnership (EDCTP) under the EU Horizon 2020 Framework Programme for Research and Innovation.

Landscape Ecological Risk Assessment and Impact Factor Analysis of the Qinghai–Tibetan Plateau

The Qinghai–Tibetan Plateau (QTP) is one of the most vulnerable ecosystems worldwide. Over the last few decades, the QTP has been subjected to increasing external pressures, such as climate change, human activity, and natural hazards. Therefore, ecological risk assessment is vital for the environmental protection and sustainable development of the QTP. A landscape ecological risk (LER) assessment based on landscape disturbance and vulnerability was performed to explore the spatiotemporal characteristics associated with LER in the QTP from 1990 to 2020. Furthermore, the impact of LER was quantitatively evaluated with a boosted regression tree model. Results showed that more than 70% of the locations in the QTP exhibited below-medium LER. The LER for the QTP demonstrated downward trends from 1990 to 2020. The LER presented downward trends during the periods from 1990 to 2001 and from 2012 to 2020 and no significant trend during the period from 2002 to 2011. Additionally, high-LER areas were concentrated in the northwestern QTP, whereas low-LER areas were mainly in the southeastern QTP. The LER displayed clustering characteristics across the QTP. Changes in climate, topographic distribution, and human activity influenced the ecological stability of the study area. Precipitation and temperature had the strongest effects on the LER, followed by elevation and grazing intensity. Lower precipitation and temperatures were associated with higher LER. Our results provide precise and specific support for the environmental protection and ecological management of the QTP and other ecologically fragile areas.

Spatial characteristics and driving factors of urban flooding in Chinese megacities

Changes in hydrological processes caused by rapid urbanization lead to the growing incidence of urban flooding, which is a major challenge to urban sustainability. Urban floods have seriously threatened the natural environment and human life. Understanding the spatial patterns and influencing factors of urban flooding has important implications for mitigating urban flood hazards. Previous studies have demonstrated the impact of natural and human factors on urban flooding, but a comprehensive understanding of the mechanisms of urban flooding requires appropriate scales and evidence from multiple cities. In this study, 1201 flood records from 2015 to 2020 in 9 megacities (including Beijing, Tianjin, Shanghai, Xi’an, Nanjing, Wuhan, Guangzhou, Shenzhen, Shenyang) in China were used to investigate the spatial characteristics and driving factors of urban flooding. A combination of multiple stepwise regression and boosted regression tree (BRT) models was used to reveal the flood driving mechanism in megacities. The results indicated that flood events in 9 cities presented an aggregation effect, but the spatial characteristics and kernel density were different between coastal and inland cities. At all scales (1 km, 3 km, 5 km), physical geomorphic features (2D and 3D landscapes) have a high contribution to urban flooding, especially patch density, density of buildings and building shape coefficients. The relative contributions of the 2D and 3D landscape pattern factors increased by 43.8 % and 36.2 % as the grid scale increased from 1 km to 5 km, respectively. However, the relative contributions of topography, meteorology and drainage capacity factors decreased by 47.6 %, 39.0 % and 33.2 %, respectively. At a large scale (5 km), the correlation of driving factors for urban flooding was stronger, and the dominant factors were more obvious. At a small scale (1 km), the contribution of driving factors is relatively average. The scale effect significantly affects urban flooding. which suggests that an appropriate scale can more accurately capture the dominant drivers of urban flooding. Therefore, a novel method that integrates the stepwise regression model and BRT model were presented to quantify the complex relationship between urban flooding and driving factors under various analysis scales. The methods and results proposed by our study provided important insights and perspectives for urban flood risk mitigation and urban planning through multiscale analysis of flood driving mechanisms.

Evaluating Occupational Noise Exposure as a Contributor to Injury Risk among Miners.

This study: (i) assessed the relationship between noise exposure and injury risk, comprehensively adjusting for individual factors, psychosocial stressors, and organizational influences; (ii) determined the relative importance of noise on injuries; (iii) estimated the lowest observed adverse effect level (LOAEL) of noise on injury risk to determine the threshold of noise considered hazardous to injuries; and (iv) quantified the fraction of injuries that could be attributed to hazardous noise exposure. In this cross-sectional study at 10 US surface mine sites, traditional mixed effects, Poisson regression, and boosted regression tree (BRT) models were run on the number of reported work-related injuries in the last year. The LOAEL of noise on injuries was identified by estimating the percent increase in work-related injuries at different thresholds of noise exposure using a counterfactual estimator through the BRT model. A population attributable fraction (PAF) was quantified with this counterfactual estimator to predict reductions in injuries at the LOAEL. Among 18 predictors of work-related injuries, mine site, perceived job safety, age, and sleepiness were the most important predictors. Occupational noise exposure was the seventh most important predictor. The LOAEL of noise for work-related injuries was a full-shift exposure of 88 dBA. Exposure ≥88 dBA was attributed to 20.3% (95% CI: 11.2%, 29.3%) of reported work-related injuries in the last year among the participants. This study further supports hypotheses of a dose-response relationship between occupational noise exposure and work-related injuries, and suggests that exposures ≥88 dBA may increase injury risk in mining.

Global potential distribution of Oryctes rhinoceros, as predicted by Boosted Regression Tree model

Climate change is expected to have a significant influence on species range expansion, habitat shifts, and risk of biological invasion due to changes in survival rates, and rapid reproduction. This will tend to affect their geographical distribution and dispersal patterns, thereby threatening agriculture production and food security. Therefore, it is essential to understand the impact of climate change on the range shifts of an invasive species like the Asiatic rhinoceros beetle, Oryctes rhinoceros Linnaeus (Coleoptera: Dynastinae: Scarabaeidae), to inform policy formulation and preventive measures. To achieve this, we used environmental variables and occurrence records of O. rhinoceros to predict the current and future potential distribution of the pest under two representative concentration pathways (RCPs 4.5 and 8.5) for three time periods (2030, 2050, and 2080). We employed Boosted Regression Tree (BRT) and ArcGIS to create risk maps for the pest. The BRT model predicts an expansion of O. rhinoceros outside the current known distribution. The environmental variables which contributed the most to the geographical distribution of the pest were minimum temperature of coldest month (26.81 %), followed by precipitation of wettest month (20.61 %), temperature annual range (11.34 %), mean diurnal range (11.33 %), and elevation (4.49 %). Under the different climate change scenarios, O. rhinoceros will continue to threaten the economically important host plants until 2080. As a result, there will be a need for effective strategies to prevent its spread. Our predictions are reliable and have the potential to estimate the global distribution of the pest, as well as provide suggestions for prompt of O. rhinoceros prevention and management.

Fire Dynamics of the Bolivian Amazon

This study identifies the spatial and temporal trends, as well as the drivers, of fire dynamics in the Bolivian Amazon basin. Bolivia ranks in the top ten countries in terms of total annual burnt, with fires affecting an estimated 2.3 million hectares of forest in 2020. However, in comparison to the Brazilian Amazon, there has been little research into the fire regime in Bolivia. The sparse research and the limited literature on the subject indicate that fire activity is higher in the Bolivian Amazon basin’s dry forests and flooded savanna zones, and that agriculture and drought are the primary causes of fire activity. In this study, trend analysis and emerging hotspot analysis are deployed to identify the spatial and temporal patterns of fire activity and boosted regression tree models to identify the drivers of forest fire within each ecoregion of the Bolivian Amazon basin. Comparable to most of the Brazilian literature, this study finds that fire activity and fire season length is higher in the flooded Beni Savanna, and Chiquitano seasonally dry tropical forests than in the Bolivian Amazon ecoregion. This study also identifies moisture stress and human activity as the main drivers of fire dynamics within the region. It is intended that this research will offer a foundation for future research and conservation activities aimed at better understanding the fire regime of the Bolivian Amazon basin.

Towards a better understanding of linear species distribution in river valleys: The abundance of river corridor plants is linked to soil exchangeable potassium and pH

The phenomenon that some vascular plant species grow mainly or exclusively in the large river valleys of Central Europe constitutes a long-standing distribution puzzle. In our study, we focused on determining which physicochemical properties of soil affect the distribution of river corridor plant (RCP) species. Research that included RCP coverage, the physicochemical properties of soil as well as several topographic and spatial variables were conducted in 10 transects perpendicular to the San River (SE Poland). The sampled plots were located both in close proximity to the river, where the greatest number of RCP populations are concentrated, and along anthropogenic linear landscape elements which have proven to be important for RCP occurrence in areas located away from the riverbed. Spearman rank correlation matrices were constructed to observe the general relationships between particular variables and Boosted Regression Tree models were used for explaining RCP coverage. Our study indicated that in the case of plots located in proximity to the river, the expected coverage of RCP species was highest in plots characterized by a higher soil exchangeable potassium (K) content, as well as in those located closer to the San River and at lower altitudes. In plots situated along anthropogenic linear landscape elements, the expected coverage of RCPs was highest in plots with a high soil exchangeable K content and in those with a high soil pH. The analyses clearly showed that the physicochemical properties of soils indeed affect RCP species occurrence and they require soils with a high exchangeable K content and a high pH. Since these two soil parameters are closely related to soil fertility, and additionally K enhances root development, we suppose that both factors strengthen the competitiveness of RCPs in floodplain ecosystems.