Supervised Machine Learning to Assess Methane Emissions of a Dairy Building with Natural Ventilation

Sabrina Hempel,Julian Adolphs,Niels Landwehr,Dilya Willink,David Janke,Thomas Amon

doi:10.3390/app10196938

Sabrina Hempel, Julian Adolphs + Show 4 more

Open Access

https://doi.org/10.3390/app10196938

Copy DOI

Abstract

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.

Highlights

Climate change is one of the great challenges of our century
When housed in barns with solid floor and manure scraper, a substantial part of the methane emissions from dairy cattle husbandry is associated with the fermentation activity in the rumen, where approximately 92% of the gas leaves the body via eructation and breath [11]
We investigated the following two hypotheses related to the estimation of methane emission factors from cattle barns with solid floor with manure scraper: (1) The accuracy of the model prediction can be improved if the squared temperature value is included as an additional feature in the modeling process, while considering a logarithmic function as in the case of ammonia is not useful, because preceding studies have indicated that emissions from the digestive system show rather a parabolic dependence on the temperature

Summary

Introduction

Climate change is one of the great challenges of our century. In order to develop adequate mitigation measures, greenhouse gas emissions in all economic sectors, including agriculture, need to be soundly quantified [1,2,3]. In the context of livestock husbandry, methane is a substance of particular importance [4,5,6,7]. It emerges during decomposition processes in manure and during ruminants digestion and makes up about 44% of the sector’s greenhouse gas emissions [8]. The Food and Agricultural Organization (FAO) of the United Nations estimated that dairy cattle husbandry contributes 20% of the total greenhouse gas emissions from the livestock sector. One important issue in this context is that the emission dynamics from the digestive system of the ruminants and from the manure are different. When housed in barns with solid floor and manure scraper (i.e., no significant manure storage inside the building), a substantial part of the methane emissions from dairy cattle husbandry is associated with the fermentation activity in the rumen, where approximately 92% of the gas leaves the body via eructation and breath [11]

Methods

Results

Discussion

Conclusion