Dataset Information

Using Random Forest to Improve the Downscaling of Global Livestock Census Data.

ABSTRACT: Large scale, high-resolution global data on farm animal distributions are essential for spatially explicit assessments of the epidemiological, environmental and socio-economic impacts of the livestock sector. This has been the major motivation behind the development of the Gridded Livestock of the World (GLW) database, which has been extensively used since its first publication in 2007. The database relies on a downscaling methodology whereby census counts of animals in sub-national administrative units are redistributed at the level of grid cells as a function of a series of spatial covariates. The recent upgrade of GLW1 to GLW2 involved automating the processing, improvement of input data, and downscaling at a spatial resolution of 1 km per cell (5 km per cell in the earlier version). The underlying statistical methodology, however, remained unchanged. In this paper, we evaluate new methods to downscale census data with a higher accuracy and increased processing efficiency. Two main factors were evaluated, based on sample census datasets of cattle in Africa and chickens in Asia. First, we implemented and evaluated Random Forest models (RF) instead of stratified regressions. Second, we investigated whether models that predicted the number of animals per rural person (per capita) could provide better downscaled estimates than the previous approach that predicted absolute densities (animals per km2). RF models consistently provided better predictions than the stratified regressions for both continents and species. The benefit of per capita over absolute density models varied according to the species and continent. In addition, different technical options were evaluated to reduce the processing time while maintaining their predictive power. Future GLW runs (GLW 3.0) will apply the new RF methodology with optimized modelling options. The potential benefit of per capita models will need to be further investigated with a better distinction between rural and agricultural populations.

SUBMITTER: Nicolas G

PROVIDER: S-EPMC4792414 | biostudies-literature | 2016

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using Random Forest to Improve the Downscaling of Global Livestock Census Data.

Nicolas Gaëlle G Robinson Timothy P TP Wint G R William GR Conchedda Giulia G Cinardi Giuseppina G Gilbert Marius M

PloS one 20160315 3

Large scale, high-resolution global data on farm animal distributions are essential for spatially explicit assessments of the epidemiological, environmental and socio-economic impacts of the livestock sector. This has been the major motivation behind the development of the Gridded Livestock of the World (GLW) database, which has been extensively used since its first publication in 2007. The database relies on a downscaling methodology whereby census counts of animals in sub-national administrati ...[more]

PMID: 26977807

Similar Datasets

Project description:BACKGROUND:Clostridiales and Bacteroidales are uniquely adapted to the gut environment and have co-evolved with their hosts resulting in convergent microbiome patterns within mammalian species. As a result, members of Clostridiales and Bacteroidales are particularly suitable for identifying sources of fecal contamination in environmental samples. However, a comprehensive evaluation of their predictive power and development of computational approaches is lacking. Given the global public health concern for waterborne disease, accurate identification of fecal pollution sources is essential for effective risk assessment and management. Here, we use random forest algorithm and 16S rRNA gene amplicon sequences assigned to Clostridiales and Bacteroidales to identify common fecal pollution sources. We benchmarked the accuracy, consistency, and sensitivity of our classification approach using fecal, environmental, and artificial in silico generated samples. RESULTS:Clostridiales and Bacteroidales classifiers were composed mainly of sequences that displayed differential distributions (host-preferred) among sewage, cow, deer, pig, cat, and dog sources. Each classifier correctly identified human and individual animal sources in approximately 90% of the fecal and environmental samples tested. Misclassifications resulted mostly from false-positive identification of cat and dog fecal signatures in host animals not used to build the classifiers, suggesting characterization of additional animals would improve accuracy. Random forest predictions were highly reproducible, reflecting the consistency of the bacterial signatures within each of the animal and sewage sources. Using in silico generated samples, we could detect fecal bacterial signatures when the source dataset accounted for as little as ~?0.5% of the assemblage, with ~?0.04% of the sequences matching the classifiers. Finally, we developed a proxy to estimate proportions among sources, which allowed us to determine which sources contribute the most to observed fecal pollution. CONCLUSION:Random forest classification with 16S rRNA gene amplicons offers a rapid, sensitive, and accurate solution for identifying host microbial signatures to detect human and animal fecal contamination in environmental samples.

Project description:For community ecologists, "neutral or not?" is a fundamental question, and thus, rejecting neutrality is an important first step before investigating the deterministic processes underlying community dynamics. Hubbell's neutral model is an important contribution to the exploration of community dynamics, both technically and philosophically. However, the neutrality tests for this model are limited by a lack of statistical power, partly because the zero-sum assumption of the model is unrealistic. In this study, we developed a neutrality test for local communities that implements non-zero-sum community dynamics and determines the number of new species (N sp) between observations. For the non-zero-sum neutrality test, the model distributed the expected N sp, as calculated by extensive simulations, which allowed us to investigate the neutrality of the observed community by comparing the observed N sp with distributions of the expected N sp derived from the simulations. For this comparison, we developed a new "non-zero-sum N sp test," which we validated by running multiple neutral simulations using different parameter settings. We found that the non-zero-sum N sp test rejected neutrality at a near-significance level, which justified the validity of our approach. For an empirical test, the non-zero-sum N sp test was applied to real tropical tree communities in Panama and Malaysia. The non-zero-sum N sp test rejected neutrality in both communities when the observation interval was long and N sp was large. Hence, the non-zero-sum N sp test is an effective way to examine neutrality and has reasonable statistical power to reject the neutral model, especially when the observed N sp is large. This unique and simple approach is statistically powerful, even though it only employs two temporal sequences of community data. Thus, this test can be easily applied to existing datasets. In addition, application of the test will provide significant benefits for detecting changing biodiversity under climate change and anthropogenic disturbance.

Dataset Information

Using Random Forest to Improve the Downscaling of Global Livestock Census Data.

Publications

Using Random Forest to Improve the Downscaling of Global Livestock Census Data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets