We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Estimation of spatio-temporal source of microplastics using Bayesian Neural networks
AI summary Read the abstract
Researchers applied a spatial Bayesian neural network to solve the ill-posed inverse problem of estimating spatio-temporal sources of airborne microplastics, combining Western USA deposition measurements with the FLEXPART dispersion model to improve source estimation compared to conventional Bayesian methods.
Estimation of the source of airborne microplastics is a challenging inverse problem since the number of measurements is very small compared to the number of potential sources. The source is spatio-temporal and thus its estimation from a few measurements is severely ill-posed. Recent studies [1] solve this issue using Bayesian methods that introduce prior on the source term using additional assumptions of sparsity and smoothness. Here, deposition measurements of airborne microplastics and microfibers from the Western USA are combined with the FLEXPART atmospheric dispersion model to construct and solve the linear inverse problem. However, the posterior is obtained only approximately, with an underestimated variance of the estimate.In this contribution, we solve the same inverse problem as in [1] using a source term estimator in the form of a spatial Bayesian neural network [2]. We compare the obtained results with those obtained by the conventional methods. Since the ground truth for the microplastics is not available, the accuracy of the estimation cannot be assessed quantitatively. Therefore, we focus on qualitative comparison and sensitivity study with respect to initial conditions and hyper-parameters of the methods.Acknowledgment:This research has been supported by the Czech Science Foundation (grant no. GA24-10400S).References:[1] Evangeliou, N., Tichý, O., Eckhardt, S., Zwaaftink, C.G. and Brahney, J., 2022. Sources and fate of atmospheric microplastics revealed from inverse and dispersion modelling: From global emissions to deposition. Journal of Hazardous Materials, 432, p.128585.[2] Zammit-Mangion, A., Kaminski, M.D., Tran, B.H., Filippone, M. and Cressie, N., 2023. Spatial Bayesian Neural Networks. arXiv preprint arXiv:2311.09491.
More Papers Like This
Spatio-temporal inversion of atmospheric microplastics emmisions using block-coordinate descent method
AI summary Read the abstract
Researchers developed an inversion modeling method to estimate where airborne microplastics originate based on deposition measurements collected across the western United States. The spatial optimization approach identified likely emission hotspots over broad geographic areas. Better source attribution of atmospheric microplastics can guide pollution reduction strategies for wind-transported plastic particles.
Two stage inversion method for microplastics emission estimation
AI summary Read the abstract
This study applied a two-stage inversion algorithm to estimate the spatial and temporal emission patterns of microplastics and microfibers across the western United States, using deposition measurements and atmospheric transport modeling. The approach successfully reconstructed emission source patterns from sparse measurement data. This kind of inverse modeling is useful for identifying major microplastic emission hotspots from limited monitoring networks.
Atmospheric microplastics emissions estimation and uncertainty quantification using Gibbs sampler
AI summary Read the abstract
Researchers developed a Bayesian inverse modeling approach using a Gibbs sampler to estimate spatiotemporal atmospheric microplastic emissions from concentration measurements, finding that incorporating agricultural, road dust, and ocean emission patterns as regularization priors substantially reduces uncertainty in emission estimates.
Source identification and apportionment of ambient air microplastics: a systematic review
AI summary Read the abstract
Researchers reviewed 26 studies on how scientists identify where airborne microplastics come from, finding that methods fall into three categories: statistical receptor models, air trajectory analysis, and machine learning approaches like support vector machines. The review maps the strengths and limitations of each approach, highlighting that source attribution for atmospheric microplastics remains an evolving and incomplete science.
Sources and fate of atmospheric microplastics revealed from inverse and dispersion modelling: From global emissions to deposition
AI summary Read the abstract
Researchers combined atmospheric observations and inverse modeling to estimate global microplastic emissions at 9.6 megatons per year, then used dispersion modeling to trace sources and deposition patterns from emissions to atmospheric fallout worldwide.
Research digests by email
When a large batch of papers lands in the Atlas, we read through it and send a short write-up of what stood out.