Geospatial Health: achievements, innovations, priorities DOI Creative Commons

Sherif Amer,

Ellen-Wien Augustijn,

Carmen Anthonj

et al.

Geospatial health, Journal Year: 2024, Volume and Issue: 19(2)

Published: Oct. 25, 2024

An expert panel discussion on achievements, current areas of rapid scientific progress, prospects, and critical gaps in geospatial health was organized as part the 16thsymposium global network public earth scientists dedicated to development (GnosisGIS), held at Faculty Geo-Information Science Earth Observation (ITC) University Twente The Netherlands November 2023. symposium consisted a three-day event that brought together an interdisciplinary group researchers professionals from across globe. aim session threefold: firstly, reflect main achievements discipline past decade; secondly, identify key innovation where progress is currently made thirdly, associated research education priorities move forward. [...]

Language: Английский

Auditing Flood Vulnerability Geo-Intelligence Workflow for Biases DOI Creative Commons
Brian K. Masinde, Caroline Gevaert, Michael Nagenborg

et al.

ISPRS International Journal of Geo-Information, Journal Year: 2024, Volume and Issue: 13(12), P. 419 - 419

Published: Nov. 21, 2024

Geodata, geographical information science (GISc), and GeoAI (geo-intelligence workflows) play an increasingly important role in predictive disaster risk reduction management (DRRM), aiding decision-makers determining where when to allocate resources. There have been discussions on the ethical pitfalls of these systems context DRRM because documented cases biases AI other socio-technical systems. However, none expound how audit geo-intelligence workflows for from data collection, processing, model development. This paper considers a case study that uses characterize housing stock vulnerability flooding Karonga district, Malawi. We use Friedman Nissenbaum’s definition categorization emphasize as negative undesirable outcome. limit scope affect visibility different typologies workflow. The results show introduces amplifies against houses certain materials. Hence, group within population area living would potentially miss out interventions. Based this example, we urge community researchers practitioners normalize auditing prevent disasters biases.

Language: Английский

Citations

8
Assessing the impact of building footprint dataset choice for health programme planning: a case study of indoor residual spraying (IRS) in Zambia DOI Creative Commons
Heather Chamberlain,

Derek Pollard,

Anna Winters

et al.

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 19, 2025

Abstract Background The increasing availability globally of building footprint datasets has brought new opportunities to support a geographic approach health programme planning. This is particularly acute in settings with high disease burdens but limited geospatial data available targeted comparability recently started be explored, the impact utilising particular dataset analyses decision making for planning not been studied. Here, we quantify four different planning, an example malaria vector control initiatives Zambia. Methods Using indoor residual spraying (IRS) campaigns Zambia, identify priority locations deployment this intervention based on criteria related area, proximity and counts footprints per settlement. We apply same count variability settlements that are identified. Results show nationally potential IRS varies by over 230% datasets, considering minimum threshold 25 sprayable buildings Differences most pronounced rural settlements, indicating choice may bias selection include or exclude consequently population groups, some areas. Conclusions results study can have considerable identified IRS, terms (i) their location count, (ii) within settlements. potentially substantial implications campaign implementation coverage assessment. Given magnitude differences observed, further work should more broadly assess sensitivity metrics across range contexts types.

Language: Английский

Citations

0
Artificial intelligence and machine learning-powered GIS for proactive disaster resilience in a changing climate DOI Creative Commons

Justin Diehr,

Ayorinde Ogunyiola, Oluwabunmi Dada

et al.

Annals of GIS, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 14

Published: March 7, 2025

Language: Английский

Citations

0
AI-generated buildings in OpenStreetMap: frequency of use and differences from non-AI-generated buildings DOI Creative Commons
Milan Fila, Radim Štampach, Benjamin Herfort

et al.

International Journal of Digital Earth, Journal Year: 2025, Volume and Issue: 18(1)

Published: March 5, 2025

AI-assisted mapping is an innovative approach to data production in OpenStreetMap (OSM), designed add new buildings maps using advanced editing tools based on deep learning techniques and recently released global-scale building datasets derived from satellite imagery. However, the identification of OSM AI-generated remains challenging without a comprehensive global overview scale, magnitude, impact OSM. The present study examines evolution spatiotemporal OSM, applying ohsome framework, high-performance analysis platform for full-history analysis. study's findings indicate that tags recommended by providers are effective identifying buildings, spatial distribution highly uneven, with over 50 percent all located United States 75 concentrated just five countries. A positive correlation observed between prevalence both population size natural disaster mortality rates per 100,000 people. In most countries, modified less frequently than non-AI-generated buildings. case selected location verify quality also presented.

Language: Английский

Citations

0
Mapping Lifecycle Building Material Embodied Carbon Emissions for Beijing-Tianjin-Hebei Urban Agglomeration DOI
Xiaoyu Zheng, Bowen Cai, Jooyoung Park

et al.

Sustainable Cities and Society, Journal Year: 2024, Volume and Issue: unknown, P. 106058 - 106058

Published: Dec. 1, 2024

Language: Английский

Citations

3
Open Data-Driven 3D Building Models for Micro-Population Mapping in a Data-Limited Setting DOI Creative Commons
Kittisak Maneepong,

Ryota Yamanotera,

Yuki Akiyama

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(21), P. 3922 - 3922

Published: Oct. 22, 2024

Urban planning and management increasingly depend on accurate building population data. However, many regions lack sufficient resources to acquire maintain these data, creating challenges in data availability. Our methodology integrates multiple sources, including aerial imagery, Points of Interest (POIs), digital elevation models, employing Light Gradient Boosting Machine (LightGBM) Decision Tree (GBDT) classify uses morphological filtration estimate heights. This research contributes bridging the gap between needs availability resource-constrained urban environments, offering a scalable solution for global application mapping.

Language: Английский

Citations

1
Geospatial Health: achievements, innovations, priorities DOI Creative Commons

Sherif Amer,

Ellen-Wien Augustijn,

Carmen Anthonj

et al.

Geospatial health, Journal Year: 2024, Volume and Issue: 19(2)

Published: Oct. 25, 2024

An expert panel discussion on achievements, current areas of rapid scientific progress, prospects, and critical gaps in geospatial health was organized as part the 16thsymposium global network public earth scientists dedicated to development (GnosisGIS), held at Faculty Geo-Information Science Earth Observation (ITC) University Twente The Netherlands November 2023. symposium consisted a three-day event that brought together an interdisciplinary group researchers professionals from across globe. aim session threefold: firstly, reflect main achievements discipline past decade; secondly, identify key innovation where progress is currently made thirdly, associated research education priorities move forward. [...]

Language: Английский

Citations

0