Optical gas imaging and deep learning for quantifying enteric methane emissions from rumen fermentation in vitro

Mohamed G Embaby, Toqi Tahamid Sarker, Amer AbuGhazaleh, Khaled Ahmed

Abstract:

This study investigated the possibility of using a laser methane detector (LMD) and optical gas imaging (OGI) to detect and quantify enteric methane (CH$_4$) produced by ruminants \textit{in vitro}. Four single-flow continuous fermenters were used for rumen culture incubation with four different treatment diets: Control (50:50 forage to concentrate [F:C] ratio), Control + Bromoform (CBR), Low Forage (LF; 20:80), and High Forage (HF; 80:20). After 10 days of incubation, all fermenter contents were transferred and used in a 24h ANKOM batch culture to measure CH$_4$ gas production with LMD and OGI. We introduce the Controlled Diet (CD) dataset, a large-scale collection of 4,885 CH$_4$ plume images captured using a FLIR GF77 OGI camera under varying dietary conditions. We compared the performance of
six semantic segmentation models (FCN, U-Net, Vision Transformer, Swin Transformer, DeepLabv3+, and Gasformer) on the CD dataset. Results showed that LMD data for CH$_4$ followed a similar pattern to the gas chromatography (GC) instrument results. The \textit{in vitro} results showed that different diets and F:C ratios had an impact on CH$_4$ gas production and rumen fermentation characteristics. Adding bromoform to the control diet fully inhibited CH$_4$ emission. The HF diet produced more CH$_4$ compared to all treatments ($P<0.01$) when measured with GC and LMD. CBR produced the lowest CH$_4$ values when measured with GC and LMD. The Gasformer architecture achieved the highest performance with mean IoU of 85.1\% and mean F-score of 91.72\%. These findings demonstrate that OGI technology combined with advanced semantic segmentation models offers a promising solution for predicting and quantifying CH$_4$ emissions in the livestock sector, potentially aiding in the development of mitigation strategies to combat climate change.