Tobia Lakes

Cropland change in southern Romania: a comparison of logistic regressions and artificial neural networks

Changes in cropland have been the dominating land use changes in Central and Eastern Europe, with cropland abandonment frequently exceeding cropland expansion. However, surprisingly little is known about the rates, spatial patterns, and determinants of cropland change in Eastern Europe. We study cropland changes between 1995 and 2005 in Argeş County in Southern Romania with two distinct modeling techniques. We apply and compare spatially explicit logistic regressions with artificial neural networks (ANN) using an integrated socioeconomic and environmental dataset. The logistic regressions allow identifying the determinants of cropland changes, but cannot deal with non-linear and complex functional relationships nor with collinearity between variables. ANNs relax some of these rigorous assumptions inherent in conventional statistical modeling, but likewise have drawbacks such as the unknown contribution of the parameters to the outcome of interest. We compare the outcomes of both modeling techniques quantitatively using several goodness-of-fit statistics. The resulting spatial predictions serve to delineate hotspots of change that indicate areas that are under more eminent threat of future abandonment. The two modeling techniques address two controversial issues of concern for land-change scientists: (1) to identify the spatial determinants that conditioned the observed changes and (2) to deal with complex functional relationships between influencing variables and land use processes. The spatially explicit insights into patterns of cropland change and in particular into hotspots of change derived from multiple methods provide useful information for decision-makers.

Assessment of land use factors associated with dengue cases in Malaysia using Boosted Regression Trees

The transmission of dengue disease is influenced by complex interactions among vector, host and virus. Land use such as water bodies or certain agricultural practices have been identified as likely risk factors for dengue because of the provision of suitable habitats for the vector. Many studies have focused on the land use factors of dengue vector abundance in small areas but have not yet studied the relationship between land use factors and dengue cases for large regions. This study aims to clarify if land use factors other than human settlements, e.g. different types of agricultural land use, water bodies and forest are associated with reported dengue cases from 2008 to 2010 in the state of Selangor, Malaysia. From the correlative relationship, we aim to generate a prediction risk map. We used Boosted Regression Trees (BRT) to account for nonlinearities and interactions between the factors with high predictive accuracies. Our model with a cross-validated performance score (Area Under the Receiver Operator Characteristic Curve, ROC AUC) of 0.81 showed that the most important land use factors are human settlements (model importance of 39.2%), followed by water bodies (16.1%), mixed horticulture (8.7%), open land (7.5%) and neglected grassland (6.7%). A risk map after 100 model runs with a cross-validated ROC AUC mean of 0.81 (±0.001 s.d.) is presented. Our findings may be an important asset for improving surveillance and control interventions for dengue.

Assessing Weather Effects on Dengue Disease in Malaysia

The number of dengue cases has been increasing on a global level in recent years, and particularly so in Malaysia, yet little is known about the effects of weather for identifying the short-term risk of dengue for the population. The aim of this paper is to estimate the weather effects on dengue disease accounting for non-linear temporal effects in Selangor, Kuala Lumpur and Putrajaya, Malaysia, from 2008 to 2010. We selected the weather parameters with a Poisson generalized additive model, and then assessed the effects of minimum temperature, bi-weekly accumulated rainfall and wind speed on dengue cases using a distributed non-linear lag model while adjusting for trend, day-of-week and week of the year. We found that the relative risk of dengue cases is positively associated with increased minimum temperature at a cumulative percentage change of 11.92% (95% CI: 4.41–32.19), from 25.4 °C to 26.5 °C, with the highest effect delayed by 51 days. Increasing bi-weekly accumulated rainfall had a positively strong effect on dengue cases at a cumulative percentage change of 21.45% (95% CI: 8.96, 51.37), from 215 mm to 302 mm, with the highest effect delayed by 26–28 days. The wind speed is negatively associated with dengue cases. The estimated lagged effects can be adapted in the dengue early warning system to assist in vector control and prevention plan.

Restoration in Urban Spaces Nature Views From Home, Greenways, and Public Parks

Despite promising experimental findings, few studies have addressed the potential long-term health benefits of frequent contact with different kinds of urban nature. We examine the cross-sectional relations between two kinds of urban nature (neighborhood vegetation visible from the home, use of public green spaces) and health outcomes (life satisfaction, perceived general health, 2-months hair cortisol levels) in a sample population from Berlin (N = 32) using a mixed-method approach. Participants whose homes had views of high amounts of diverse kinds of vegetation had significantly lower cortisol levels. Moreover, participants who regularly used a vegetated trail along a canal had significantly lower cortisol levels and reported significantly higher life satisfaction than less frequent users. In addition, vegetated routes or paths played an important role in the restorative activities and daily commutes of participants. We discuss directions for future research and recommend more consideration of greenways in urban development.

A review of multiple natural hazards and risks in Germany

Although Germany is not among the most hazard-prone regions of the world, it does experience various natural hazards that have caused considerable economic and human losses in the past. Moreover, risk due to natural hazards is expected to increase in several regions of Germany if efficient risk management is not able to accommodate global changes. The most important natural hazards, in terms of past human and economic damage they caused, are storms, floods, extreme temperatures and earthquakes. They all show a pronounced spatial and temporal variability. In the present article, a review of these natural hazards, associated risks and their management in Germany is provided. This review reveals that event and risk analyses, as well as risk management, predominantly focus on one single hazard, generally not considering the cascading and conjoint effects in a full multi-hazard and risks approach. However, risk management would need integrated multi-risk analyses to identify, understand, quantify and compare different natural hazards and their impacts, as well as their interactions.

A spatial epidemiological analysis of self-rated mental health in the slums of Dhaka

BackgroundThe deprived physical environments present in slums are well-known to have adverse health effects on their residents. However, little is known about the health effects of the social environments in slums. Moreover, neighbourhood quantitative spatial analyses of the mental health status of slum residents are still rare. The aim of this paper is to study self-rated mental health data in several slums of Dhaka, Bangladesh, by accounting for neighbourhood social and physical associations using spatial statistics. We hypothesised that mental health would show a significant spatial pattern in different population groups, and that the spatial patterns would relate to spatially-correlated health-determining factors (HDF).MethodsWe applied a spatial epidemiological approach, including non-spatial ANOVA/ANCOVA, as well as global and local univariate and bivariate Morans I statistics. The WHO-5 Well-being Index was used as a measure of self-rated mental health.ResultsWe found that poor mental health (WHO-5 scores < 13) among the adult population (age ≥15) was prevalent in all slum settlements. We detected spatially autocorrelated WHO-5 scores (i.e., spatial clusters of poor and good mental health among different population groups). Further, we detected spatial associations between mental health and housing quality, sanitation, income generation, environmental health knowledge, education, age, gender, flood non-affectedness, and selected properties of the natural environment.ConclusionsSpatial patterns of mental health were detected and could be partly explained by spatially correlated HDF. We thereby showed that the socio-physical neighbourhood was significantly associated with health status, i.e., mental health at one location was spatially dependent on the mental health and HDF prevalent at neighbouring locations. Furthermore, the spatial patterns point to severe health disparities both within and between the slums. In addition to examining health outcomes, the methodology used here is also applicable to residuals of regression models, such as helping to avoid violating the assumption of data independence that underlies many statistical approaches. We assume that similar spatial structures can be found in other studies focussing on neighbourhood effects on health, and therefore argue for a more widespread incorporation of spatial statistics in epidemiological studies.

Development of an environmental justice index to determine socio-economic disparities of noise pollution and green space in residential areas in Berlin

The majority of human beings worldwide live in urban areas; hence, methods to assess the quality of the urban environment and its impact on human well-being are of the utmost importance. Particularly relevant are areas with low levels of environmental justice, defined as areas where low biophysical quality meets low socio-economic status, and where resources and strategies for coping are rare. This paper develops and applies an index to assess the patterns of environmental justice in residential areas with a strong focus on stakeholder integration. We concentrate on the relationship between socio-economic disparities of environmental burdens, such as traffic noise, and of environmental benefits, such as vegetation, in residential areas of Berlin, Germany. To develop an environmental justice index, we combined the environmental burdens and benefits with a socio-economic indicator. As a result, we identify city-wide patterns of environmental justice in Berlin. While there was a high positive correlation between vegetation and socio-economic status, the patterns for noise pollution were very heterogeneous. Our approach provides a transparent and modular index allowing an area-wide monitoring of environmental justice in urban areas. Such an analysis is urgently needed to develop adequate decision-making strategies for all inhabitants to make living in a healthier city possible.

Mental health in the slums of Dhaka - a geoepidemiological study

BackgroundUrban health is of global concern because the majority of the worlds population lives in urban areas. Although mental health problems (e.g. depression) in developing countries are highly prevalent, such issues are not yet adequately addressed in the rapidly urbanising megacities of these countries, where a growing number of residents live in slums. Little is known about the spectrum of mental well-being in urban slums and only poor knowledge exists on health promotive socio-physical environments in these areas. Using a geo-epidemiological approach, the present study identified factors that contribute to the mental well-being in the slums of Dhaka, which currently accommodates an estimated population of more than 14 million, including 3.4 million slum dwellers.MethodsThe baseline data of a cohort study conducted in early 2009 in nine slums of Dhaka were used. Data were collected from 1,938 adults (≥ 15 years). All respondents were geographically marked based on their households using global positioning systems (GPS). Very high-resolution land cover information was processed in a Geographic Information System (GIS) to obtain additional exposure information. We used a factor analysis to reduce the socio-physical explanatory variables to a fewer set of uncorrelated linear combinations of variables. We then regressed these factors on the WHO-5 Well-being Index that was used as a proxy for self-rated mental well-being.ResultsMental well-being was significantly associated with various factors such as selected features of the natural environment, flood risk, sanitation, housing quality, sufficiency and durability. We further identified associations with population density, job satisfaction, and income generation while controlling for individual factors such as age, gender, and diseases.ConclusionsFactors determining mental well-being were related to the socio-physical environment and individual level characteristics. Given that mental well-being is associated with physiological well-being, our study may provide crucial information for developing better health care and disease prevention programmes in slums of Dhaka and other comparable settings.

Unsupervised change detection in VHR remote sensing imagery – an object-based clustering approach in a dynamic urban environment

Monitoring of changes is one of the most important inherent capabilities of remote sensing. The steadily increasing amount of available very-high resolution (VHR) remote sensing imagery requires highly automatic methods and thus, largely unsupervised concepts for change detection. In addition, new procedures that address this challenge should be capable of handling remote sensing data acquired by different sensors. Thereby, especially in rapidly changing complex urban environments, the high level of detail present in VHR data indicates the deployment of object-based concepts for change detection. This paper presents a novel object-based approach for unsupervised change detection with focus on individual buildings. First, a principal component analysis together with a unique procedure for determination of the number of relevant principal components is performed as a predecessor for change detection. Second, k-means clustering is applied for discrimination of changed and unchanged buildings. In this manner, several groups of object-based difference features that can be derived from multi-temporal VHR data are evaluated regarding their discriminative properties for change detection. In addition, the influence of deviating viewing geometries when using VHR data acquired by different sensors is quantified. Overall, the proposed workflow returned viable results in the order of κ statistics of 0.8–0.9 and beyond for different groups of features, which demonstrates its suitability for unsupervised change detection in dynamic urban environments. With respect to imagery from different sensors, deviating viewing geometries were found to deteriorate the change detection result only slightly in the order of up to 0.04 according to κ statistics, which underlines the robustness of the proposed approach.

Assessment of Seismic Building Vulnerability from Space

This paper quantitatively evaluates the suitability of multi-sensor remote sensing to assess the seismic vulnerability of buildings for the example city of Padang, Indonesia. Features are derived from remote sensing data to characterize the urban environment and are subsequently combined with in situ observations. Machine learning approaches are deployed in a sequential way to identify meaningful sets of features that are suitable to predict seismic vulnerability levels of buildings. When assessing the vulnerability level according to a scoring method, the overall mean absolute percentage error is 10.6%, if using a supervised support vector regression approach. When predicting EMS-98 classes, the results show an overall accuracy of 65.4% and a kappa statistic of 0.36, if using a naive Bayes learning scheme. This study shows potential for a rapid screening assessment of large areas that should be explored further in the future.