Search Results
How the Selection of Training Data and Modeling Approach Affects the Estimation of Ammonia Emissions from a Naturally Ventilated Dairy Barn—Classical Statistics versus Machine Learning
Environmental protection efforts can only be effective in the long term with a reliable quantification of pollutant gas emissions as a first step to mitigation. Measurement and analysis strategies must permit the accurate extrapolation of emission values. We systematically analyzed the added value of applying modern machine learning methods in the process of monitoring emissions from naturally ventilated livestock buildings to the atmosphere. We considered almost 40 weeks of hourly emission values from a naturally ventilated dairy cattle barn in Northern Germany. We compared model predictions using 27 different scenarios of temporal sampling, multiple measures of model accuracy, and eight different regression approaches. The error of the predicted emission values with the tested measurement protocols was, on average, well below 20%. The sensitivity of the prediction to the selected training dataset was worse for the ordinary multilinear regression. Gradient boosting and random forests provided the most accurate and robust emission value predictions, accompanied by the second-smallest model errors. Most of the highly ranked scenarios involved six measurement periods, while the scenario with the best overall performance was: One measurement period in summer and three in the transition periods, each lasting for 14 days.
Methane Emission Characteristics of Naturally Ventilated Cattle Buildings
The mandate to limit global temperature rise calls for a reliable quantification of gaseous pollutant emissions as a basis for effective mitigation. Methane emissions from ruminant fermentation are of particular relevance in the context of greenhouse gas mitigation. The emission dynamics are so far insufficiently understood. We analyzed hourly methane emission data collected during contrasting seasons from two naturally ventilated dairy cattle buildings with concrete floor and performed a second order polynomial regression. We found a parabolic temperature dependence of the methane emissions irrespective of the measurement site and setup. The position of the parabola vertex varied when considering different hours of the day. The circadian rhythm of methane emissions was represented by the pattern of the fitted values of the constant term of the polynomial and could be well explained by feeding management and air flow conditions. We found barn specific emission minima at ambient temperatures around 10 °C to 15 °C. As this identified temperature optimum coincides with the welfare temperature of dairy cows, we concluded that temperature regulation of dairy cow buildings with concrete floor should be considered and further investigated as an emission mitigation measure. Our results further indicated that empirical modeling of methane emissions from the considered type of buildings with a second order polynomial for the independent variable air temperature can increase the accuracy of predicted long-term emission values for regions with pronounced seasonal temperature fluctuations