Undelivered risk: A counter-factual analysis of the biosecurity risk avoided by inspecting international mail articles

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

International mail articles present an important potential vector for biosecurity and other regulatory risk. Border intervention is a key element in Australia’s biosecurity strategy. Arriving international mail articles are inspected and those that are intercepted with biosecurity risk material are documented, including the address to which the article was to be delivered. Knowledge about patterns in the intended destinations of mail article permits more detailed biosecurity intervention. We used geo-location software to identify the delivery address of mail articles intercepted with biosecurity risk material from 2008–2011. We matched these addresses with demographic data that were recorded at a regional level from the Australian Bureau of Statistics 2011 Census and used random forest statistical analyses to correlate various demographic fields at the regional level with the counts of seized mail articles. The analysis of the seizure counts against demographic characteristics suggests a high correlation between having higher numbers of university students that speak a particular language in a region and higher quantities of intercepted mail articles destined for that region. We also explore metropolitan and regional patterns in the destinations of seized materials. These results can be used to provide information on policy and operational actions to try to reduce the rate at which mail articles that contain biosecurity risk material are sent to Australia.

Related collections

Most cited references 2

Record: found
Abstract: found
Article: found

Is Open Access

A Tale of Two “Forests”: Random Forest Machine Learning Aids Tropical Forest Carbon Mapping

Joseph Mascaro, Gregory Asner, David E. Knapp … (2014)

Accurate and spatially-explicit maps of tropical forest carbon stocks are needed to implement carbon offset mechanisms such as REDD+ (Reduced Deforestation and Degradation Plus). The Random Forest machine learning algorithm may aid carbon mapping applications using remotely-sensed data. However, Random Forest has never been compared to traditional and potentially more reliable techniques such as regionally stratified sampling and upscaling, and it has rarely been employed with spatial data. Here, we evaluated the performance of Random Forest in upscaling airborne LiDAR (Light Detection and Ranging)-based carbon estimates compared to the stratification approach over a 16-million hectare focal area of the Western Amazon. We considered two runs of Random Forest, both with and without spatial contextual modeling by including—in the latter case—x, and y position directly in the model. In each case, we set aside 8 million hectares (i.e., half of the focal area) for validation; this rigorous test of Random Forest went above and beyond the internal validation normally compiled by the algorithm (i.e., called “out-of-bag”), which proved insufficient for this spatial application. In this heterogeneous region of Northern Peru, the model with spatial context was the best preforming run of Random Forest, and explained 59% of LiDAR-based carbon estimates within the validation area, compared to 37% for stratification or 43% by Random Forest without spatial context. With the 60% improvement in explained variation, RMSE against validation LiDAR samples improved from 33 to 26 Mg C ha−1 when using Random Forest with spatial context. Our results suggest that spatial context should be considered when using Random Forest, and that doing so may result in substantially improved carbon stock modeling for purposes of climate change mitigation.