Sebastian Brinkmann
Sebastian Brinkmann

Data Scientist

GfK - An NIQ Company

Hi đź‘‹

I’m a Data Scientist at GfK Geomarketing, specializing in developing methodologies for international market analysis. Previously, I explored the intersection of machine learning, natural environments, and human behavior as part of the Digital Health Geography research group.
This site showcases my personal projects, where I tackle geo-spatial challenges using R.

View CV

Interests
  • Data Science
  • Spatial Analysis
  • Urban Forestry
  • Remote Sensing
  • Epidemiology
Education

  • B.Sc. in Physical Geography

    FAU Erlangen-NĂĽrnberg

  • B.Sc. in Applied mathematics and physics

    TH Ohm NĂĽrnberg



đź“š Recent Posts

NĂĽrnberg - 3. Greenness Accessibility Index (GACI)

By integrating realistic walking routes and park size weighting, the Greenspace Accessibility Index (GACI) offers a more practical and community-focused measure of how easily residents can reach quality public parks.

NĂĽrnberg - 2. Greenspace Availability Index (GAVI)

By combining NDVI, LAI, and LULC data at multiple scales with lacunarity-based weights, the Greenspace Availability Index (GAVI) captures both the quantity and arrangement of urban vegetation - providing a more accurate and nuanced measure of greenspace.

NĂĽrnberg - 1. Viewshed Greenness Visibility Index (VGVI)

By combining binary greenspace data with DSM/DTM viewshed analysis, the Visibility-based Greenspace Index (VGVI) captures how much vegetation is actually seen from a ground-level perspective—offering a more user-centered and comprehensive measure of urban greenery.

See all
đź“š Featured Publications

SEE ALL PUBLICATIONS

Räumliche Erreichbarkeit von Gedächtnisambulanzen – Eine geographische Analyse im Rahmen von digiDEM Bayern
Urban Health

Räumliche Erreichbarkeit von Gedächtnisambulanzen – Eine geographische Analyse im Rahmen von digiDEM Bayern

Memory clinics play a crucial role in the qualified diagnosis of dementia. This study aimed to assess the accessibility of memory clinics for people with dementia in Bavaria by utilizing a Geographic Information System (GIS) to calculate travel times from all Bavarian municipalities to the nearest memory clinic using OpenStreetMap data. It was found that the majority (40%; n = 93,950) of modeled individuals with dementia live in communities with an average travel time of 20 to 40 minutes to the nearest clinic, while approximately 7,000 (3%) face a travel time of more than one hour, particularly in rural areas. In light of demographic trends, improving accessibility to memory clinics across all locations is imperative. The expansion of memory clinics in areas with lengthy travel times or the introduction of mobile diagnostic services could enhance care for people with dementia.

Modelling eye-level visibility of urban green space: Optimising city-wide point-based viewshed computations through prototyping
Neighborhood Greenspace and Socioeconomic Risk are Associated with Diabetes Risk at the Sub-neighborhood Scale: Results from the Prospective Urban and Rural Epidemiology (PURE) Study
Diabetes

Neighborhood Greenspace and Socioeconomic Risk are Associated with Diabetes Risk at the Sub-neighborhood Scale: Results from the Prospective Urban and Rural Epidemiology (PURE) Study

We propose a novel diabetes risk index (DRI-GLUCoSE) derived from socioeconomic status and satellite data based greenspace. We mapped index scores in two Canadian cities (Vancouver and Hamilton) and validated the index using fully adjusted logistic regression models to predict individual diabetes status. The final models achieved a predictive accuracy of 75%, the highest among environmental risk models to date. Our combined index of local greenspace and socioeconomic factors demonstrates that the environmental component of diabetes risk is not sufficiently explained by diet and physical activity, and that increasing urban greenspace may be a suitable means of reducing the burden of diabetes at the community scale.

A multimethod approach for county-scale geospatial analysis of emerging infectious diseases. A cross-sectional case study of COVID-19 incidence in Germany
COVID-19

A multimethod approach for county-scale geospatial analysis of emerging infectious diseases. A cross-sectional case study of COVID-19 incidence in Germany

As of 13 July 2020, 12.9 million COVID-19 cases have been reported worldwide. Prior studies have demonstrated that local socioeconomic and built environment characteristics may significantly contribute to viral transmission and incidence rates, thereby accounting for some of the spatial variation observed. Due to uncertainties, non-linearities, and multiple interaction effects observed in the associations between COVID-19 incidence and socioeconomic, infrastructural, and built environment characteristics, we present a structured multimethod approach for analysing cross-sectional incidence data within in an Exploratory Spatial Data Analysis (ESDA) framework at the NUTS3 (county) scale.

Contact