Determination of the nighttime light imagery for urban city population using DMSP-OLS methods in Istanbul

DF-DM: A foundational process model for multimodal data fusion in the artificial intelligence era

In the big data era, integrating diverse data modalities poses significant challenges, particularly in complex fields like healthcare. This paper introduces a new process model for multimodal Data Fusion for Data Mining, integrating embeddings and the Cross-Industry Standard Process for Data Mining with the existing Data Fusion Information Group model. Our model aims to decrease computational costs, complexity, and bias while improving efficiency and reliability. We also propose "disentangled dense fusion," a novel embedding fusion method designed to optimize mutual information and facilitate dense inter-modality feature interaction, thereby minimizing redundant information. We demonstrate the model's efficacy through three use cases: predicting diabetic retinopathy using retinal images and patient metadata, domestic violence prediction employing satellite imagery, internet, and census data, and identifying clinical and demographic features from radiography images and clinical notes. The model achieved a Macro F1 score of 0.92 in diabetic retinopathy prediction, an R-squared of 0.854 and sMAPE of 24.868 in domestic violence prediction, and a macro AUC of 0.92 and 0.99 for disease prediction and sex classification, respectively, in radiological analysis. These results underscore the Data Fusion for Data Mining model's potential to significantly impact multimodal data processing, promoting its adoption in diverse, resource-constrained settings.

Association between light at night and the risk of child death in sub-saharan Africa: a cross-sectional analysis based on DHS data

BACKGROUND

The high under-five mortality rate (U5MR) in Africa is a significant public health concern. Previous studies have found that satellite retrieved light at night (LAN) data with long-term and global coverage can be used as a proxy for socio-economic development and urbanization. Currently, few studies on the effects of LAN on child mortality have been conducted in Africa, a region with varying levels of urbanization between countries.

OBJECTIVE

To quantify the correlation between risk of child mortality and LAN as an indicator of urbanization and economic development in Africa.

METHODS

Using data from the Demographic and Health Survey (DHS) database conducted in 15 African countries out of 46 countries from 2005 to 2013, this study estimated LAN levels for children based on their year of birth and residential addresses. This study used Cox proportional hazards models to assess the association between LAN and the risk of child mortality in Africa.

RESULTS

The mean U5MR was 95 per 1,000 livebirths among the 15 African countries during 2005-2013. After adjusting for covariates, each 10-unit increment in LAN was associated with a 5.3% reduction in the risk of U5MR. The effect estimates were more pronounced in areas with lower LAN.

CONCLUSION

In Africa, the risk of U5MR decreased with increasing LAN, especially in areas with lower LAN. The results suggest that the development of urbanization and socio-economic conditions may be beneficial to child health, especially in regions with low LAN. The use of LAN as a proxy may offer an intriguing approach for identifying areas requiring targeted development in urbanization and socio-economic conditions.

A geographic information systems and remote sensing-based approach to assess urban micro-climate change and its impact on human health in Bartin, Turkey

Increasing land surface temperature (LST) is one of the major urban climatology problems arising in urban development. In this paper, the impact of vegetation and built-up areas on the LST and impact of LST on human health are assessed using the Landsat thermal data in Bartin, Turkey. The results show that there is a constant change in the share of vegetation and built-up areas due to rapid urbanization in Bartin. Strong positive correlation has been found between NDBI and LST while strong negative correlation has been found between NDVI and LST, suggesting their strong impacts on land surface temperatures. Similarly, a strong positive correlation has been observed between LST, sleep deprivation, and heat stress. This study provides precise information on effects of urbanization and man-made activities, which cause major changes in micro-climate and human health in the city. This study can assist decision-makers or planners to plan future developments sustainably.

Economic effects of conversion from county (or county-level city) to municipal district in China

Administrative division is an important resource to promote the urbanization process and economic growth in China. As an important way of urban spatial expansion, the effect of the removal of counties (county-level cities) into municipal districts(RCD) on economic growth remains to be empirically tested. In this paper, the panel data at the county level from 1998 to 2016 and the differential method were selected to study this problem. The results show that, during the study period, the RCD significantly promoted the economic growth of Chinese cities. The effect of removing counties (county-level cities) from large cities and megacities to set up districts is obviously better than that of small and medium-sized cities. In small and medium-sized cities with small urban permanent population, the RCD has obvious negative impact on economic development. The effect of county (county-level city) reform in eastern and central regions is more significant, while the effect of policy in western and northeast regions is not significant. When the development intensity of the municipal district is between 15%-20%, the effect of the RCD is relatively good, and the administrative division adjustment of the municipal district has a certain optimal window period.

Extraction of Urban Built-Up Area Based on Deep Learning and Multi-Sources Data Fusion—The Application of an Emerging Technology in Urban Planning

With the rapid expansion of urban built-up areas in recent years, it has become particularly urgent to develop a fast, accurate and popularized urban built-up area extraction method system. As the direct carrier of urban regional relationship, urban built-up area is an important reference to judge the level of urban development. The accurate extraction of urban built-up area plays an important role in formulating scientific planning thus to promote the healthy development of both urban area and rural area. Although nighttime light (NTL) data are used to extract urban built-up areas in previous studies, there are certain shortcomings in using NTL data to extract urban built-up areas. On the other hand, point of interest (POI) data and population migration data represent different attributes in urban space, which can both assist in modifying the deficiencies of NTL data from both static and dynamic spatial elements, respectively, so as to improve the extraction accuracy of urban built-up areas. Therefore, this study attempts to propose a feasible method to modify NTL data by fusing Baidu migration (BM) data and POI data thus accurately extracting urban built-up areas in Guangzhou. More accurate urban built-up areas are extracted using the method of U-net deep learning network. The maximum built-up area extracted from the study is 1103.45 km2, accounting for 95.21% of the total built-up area, and the recall rate is 0.8905, the precision rate is 0.8121, and the F1 score is 0.8321. The results of using POI data and BM data to modify NTL data to extract built-up areas have not been significantly improved due to the fact that the more data get fused, the more noise there would be, which would ultimately affect the results. This study analyzes the feasibility and insufficiency of using big data to modify NTL data through data fusion and feature extraction system, which has important theoretical and practical significance for future studies on urban built-up areas and urban development.

Urban greenery for air pollution control: a meta-analysis of current practice, progress, and challenges

Most governmental initiatives in India, to leash down urban air pollution, have yielded little results till date, largely due to purely technocratic vision, which is shrouded by technological, economic, social, institutional, and political hardships. We present this reflective article on urban greenery, as a proposition to urban authorities (e.g., pollution regulators, environmental systems' managers, urban landscape planners, environmental policy makers), shift from purely technocratic way of thinking to thinking with nature, by strategic greening of urban spaces, for long-term air pollution prevention and control measures. To that end, we offer a meta-analysis of recent (post 2005) global literature using four-stage PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) approach. We open the narrative by briefing about main pollutant filtration mechanisms by trees, followed by cognitive aspects of species selection (e.g., deciduous vs. evergreen, air pollution tolerance index, environmental stressors). Till date, most Indian studies on urban greenery mostly but focused on physiological aspects of trees. Here, we draw attention of urban authorities to an equally compelling, but yet less explored, aspect: design criteria, with reference to two most common urban configurations, namely, street canyon and open road. With pictorial depictions, we enumerate various categories of street canyons and discuss aspect ratio (building height to street width) and various wind flow regimes (isolated roughness, wake interface, and skimming), that the urban authorities should be cognizant about to maximize pollutant removal efficiency. For open road, we discuss vegetation barriers, with special emphasis on canopy porosity/density functions. In the final sections, we reflect on a potential systems' thinking approach for on-ground implementation, comprising of revamping of urban forestry programs, research and development, community mobilization and stakeholder engagement, and strategic outreach. In addition, we emphasize on means to harness co-benefits of urban greenery, beyond mere pollutant removal, to garner support from urban residents' communities. Last but not the least, we also caution the urban authorities about the undesirable outcomes of urban greenery that will require more process-level research.

Artificial illumination influences niche segregation in bats

Artificial light at night (ALAN) is a pervasive form of pollution largely affecting wildlife, from individual behaviour to community structure and dynamics. As nocturnal mammals, bats are often adversely affected by ALAN, yet some "light-opportunistic" species exploit it by hunting insects swarming near lights. Here we used two potentially competing pipistrelle species as models, Kuhl's (Pipistrellus kuhlii) and common (Pipistrellus pipistrellus) pipistrelles, both known to forage in artificially illuminated areas. We set our study in a mountainous area of central Italy, where only recently did the two species become syntopic. We applied spatial modelling and radiotracking to contrast potential vs. actual environmental preferences by the two pipistrelles. Species distribution models and niche analysis showed a large interspecific niche overlap, including a preference for illuminated areas, presenting a potential competition scenario. Pipistrellus pipistrellus association with ALAN, however, was weakened by adding P. kuhlii as a biotic variable to the model. Radiotracking showed that the two species segregated habitats at a small spatial scale and that P. kuhlii used artificially illuminated sites much more frequently than P. pipistrellus, despite both species potentially being streetlamp foragers. We demonstrate that ALAN influences niche segregation between two potentially competing species, confirming its pervasive effects on species and community dynamics, and provide an example of how light pollution and species' habitat preferences may weave a tapestry of complex ecological interactions.