Search Results
Supervised Machine Learning to Assess Methane Emissions of a Dairy Building with Natural Ventilation
A reliable quantification of greenhouse gas emissions is a basis for the development of adequate mitigation measures. Protocols for emission measurements and data analysis approaches to extrapolate to accurate annual emission values are a substantial prerequisite in this context. We systematically analyzed the benefit of supervised machine learning methods to project methane emissions from a naturally ventilated cattle building with a concrete solid floor and manure scraper located in Northern Germany. We took into account approximately 40 weeks of hourly emission measurements and compared model predictions using eight regression approaches, 27 different sampling scenarios and four measures of model accuracy. Data normalization was applied based on median and quartile range. A correlation analysis was performed to evaluate the influence of individual features. This indicated only a very weak linear relation between the methane emission and features that are typically used to predict methane emission values of naturally ventilated barns. It further highlighted the added value of including day-time and squared ambient temperature as features. The error of the predicted emission values was in general below 10%. The results from Gaussian processes, ordinary multilinear regression and neural networks were least robust. More robust results were obtained with multilinear regression with regularization, support vector machines and particularly the ensemble methods gradient boosting and random forest. The latter had the added value to be rather insensitive against the normalization procedure. In the case of multilinear regression, also the removal of not significantly linearly related variables (i.e., keeping only the day-time component) led to robust modeling results. We concluded that measurement protocols with 7 days and six measurement periods can be considered sufficient to model methane emissions from the dairy barn with solid floor with manure scraper, particularly when periods are distributed over the year with a preference for transition periods. Features should be normalized according to median and quartile range and must be carefully selected depending on the modeling approach.
On the feasibility of using open source solvers for the simulation of a turbulent air flow in a dairy barn
Two transient open source solvers, OpenFOAM and ParMooN, and the commercial solver Ansys Fluent are assessed with respect to the simulation of the turbulent air flow inside and around a dairy barn. For this purpose, data were obtained in an experimental campaign at a 1:100 scaled wind tunnel model. All solvers used different meshes, discretization schemes, and turbulence models. The experimental data and numerical results agree well for time-averaged stream-wise and vertical-wise velocities. In particular, the air exchange was predicted with high accuracy by both open source solvers with relative differences less than 4% and by the commercial solver with a relative difference of 9% compared to the experimental results. With respect to the turbulent quantities, good agreements at the second (downwind) half of the barn inside and especially outside the barn could be achieved, where all codes accurately predicted the flow separation and, in many cases, the root-mean-square velocities. Deviations between simulations and experimental results regarding turbulent quantities could be observed in the first part of the barn. These deviations can be attributed to the utilization of roughness elements between inlet and barn in the experiment that were not modeled in the numerical simulations. Both open source solvers proved to be promising tools for the accurate prediction of time-dependent phenomena in an agricultural context, e.g., like the transport of particulate matter or pathogen-laden aerosols in and around agricultural buildings. © 2020 The Authors
On the feasibility of using open source solvers for the simulation of a turbulent air flow in a dairy barn
Two transient open source solvers, OpenFOAM and ParMooN, are assessed with respect to the simulation of the turbulent air flow inside and around a dairy barn. For this purpose, data were obtained in an experimental campaign at a 1:100 scaled wind tunnel model. Both solvers used different meshes, discretization schemes, and turbulence models. The experimental data and numerical results agree well for time-averaged stream-wise and vertical-wise velocities. In particular, the air exchange was predicted with high accuracy by both solvers with relative errors less than 5 % compared to the experimental results. With respect to the turbulent quantities, good agreements at the second (downwind) half of the barn inside and especially outside the barn could be achieved, where both codes accurately predicted the flow separation and the root-mean-square velocities. Deviations between simulations and experimental results regarding turbulent quantities could be observed in the first part of the barn, due to different inlet conditions between the experimental setup and the numerical simulations. Both solvers proved to be promising tools for the accurate prediction of time-dependent phenomena in an agricultural context, e.g., like the transport of particulate matter or pathogen-laden aerosols in and around agricultural buildings.