Anomaly detection for volunteered geographic information: a case study of Safecast data

Xin, Yanan

doi:10.1080/13658816.2021.1981333

Cited by 5 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their study emphasises how important spatial data is for improving the efficacy of disaster risk reduction tactics. Xin (2022) explored anomaly detection for VGI, using Safecast data as a case study. This research demonstrates the potential of VGI in monitoring and responding to environmental hazards.…”

Section: Related Workmentioning

confidence: 99%

Process Analysis in Humanitarian Voluntary Geographic Information: the case of the HOT Tasking Manager

Herrera-Murillo,

Ochoa-Ortiz,

Ahmed

et al. 2024

AGILE GIScience Ser.

View full text Add to dashboard Cite

Abstract. Geographic information is vital for organising humanitarian campaigns and helping those in need. The leading Humanitarian OpenStreetMap Team (HOT) organises projects to create the necessary geographical information and connect to the organisations that need to make decisions on the ground. This work provides insights into project management dynamics and volunteers’ interaction with user interfaces in Volunteered Geographic Information (VGI) in a humanitarian context. We do so by conducting a process analysis of 746 completed, fully validated, and archived projects in the HOT Tasking Manager (HOT-TM) over the past two years. The analysis encompasses a process discovery stage from the perspectives of control flow, time, organisation, and outcome of the mapping tasks that comprise a project. The findings offer valuable implications for future project planning and execution in similar contexts. Our process mining exploration of the task states found a clear path that involves mapping and validation operations with minor deviations. However, we did find a major bottleneck from the mapping to the validation phase, which could reflect that validation capabilities are a scarce resource. Proactive notification for validators, artificial intelligence adoption for task planning, user interface redesign, and strategies for better harnessing the collective intelligence of volunteers could improve the process.

show abstract

Section: Related Workmentioning

confidence: 99%

Process Analysis in Humanitarian Voluntary Geographic Information: the case of the HOT Tasking Manager

Herrera-Murillo,

Ochoa-Ortiz,

Ahmed

et al. 2024

AGILE GIScience Ser.

View full text Add to dashboard Cite

show abstract

“…Another study recommends an approach of cross-comparison with a comparable data source [27]. Concurrent work notes that Safecast flags anomalous data for the manual verification of moderators and that study, which compares Safecast to KURAMA, approaches extreme values as anomalies [28]. However, how extreme values should be treated is complex, as the variance of observations in relation to measurement error related uncertainty can be difficult to assess for spatiotemporally varying phenomena.…”

Section: Introductionmentioning

confidence: 99%

A Bayesian Approach to Estimate the Spatial Distribution of Crowdsourced Radiation Measurements around Fukushima

Hultquist

Oravecz

Cervone

2021

IJGI

View full text Add to dashboard Cite

Citizen-led movements producing spatio-temporal big data are potential sources of useful information during hazards. Yet, the sampling of crowdsourced data is often opportunistic and the statistical variations in the datasets are not typically assessed. There is a scientific need to understand the characteristics and geostatistical variability of big spatial data from these diverse sources if they are to be used for decision making. Crowdsourced radiation measurements can be visualized as raw, often overlapping, points or processed for an aggregated comparison with traditional sources to confirm patterns of elevated radiation levels. However, crowdsourced data from citizen-led projects do not typically use a spatial sampling method so classical geostatistical techniques may not seamlessly be applied. Standard aggregation and interpolation methods were adapted to represent variance, sampling patterns, and the reliability of modeled trends. Finally, a Bayesian approach was used to model the spatial distribution of crowdsourced radiation measurements around Fukushima and quantify uncertainty introduced by the spatial data characteristics. Bayesian kriging of the crowdsourced data captures hotspots and the probabilistic approach could provide timely contextualized information that can improve situational awareness during hazards. This paper calls for the development of methods and metrics to clearly communicate spatial uncertainty by evaluating data characteristics, representing observational gaps and model error, and providing probabilistic outputs for decision making.

show abstract

Robust deep auto-encoding network for real-time anomaly detection at nuclear power plants

Shi

Zhang

2022

Process Safety and Environmental Protection

View full text Add to dashboard Cite

Anomaly detection for volunteered geographic information: a case study of Safecast data

Cited by 5 publications

References 36 publications

Process Analysis in Humanitarian Voluntary Geographic Information: the case of the HOT Tasking Manager

Process Analysis in Humanitarian Voluntary Geographic Information: the case of the HOT Tasking Manager

A Bayesian Approach to Estimate the Spatial Distribution of Crowdsourced Radiation Measurements around Fukushima

Robust deep auto-encoding network for real-time anomaly detection at nuclear power plants

Contact Info

Product

Resources

About