Reconstruction of high-frequency methane atmospheric concentration peaks from measurements using metal oxide low-cost sensors

<p>Detecting and quantifying CH<span class="inline-formula">₄</span> gas emissions at industrial facilities is an important goal for being able to reduce these emissions. The nature of CH<span class="inline-formula">₄</span> emissions through “leaks” is episodic and spatially variable, making their monitoring a complex task; this is partly being addressed by atmospheric surveys with various types of instruments. Continuous records are preferable to snapshot surveys for monitoring a site, and one solution would be to deploy a permanent network of sensors. Deploying such a network with research-level instruments is expensive, so low-cost and low-power sensors could be a good alternative. However, low cost usually entails lower accuracy and the existence of sensor drifts and cross-sensitivity to other gases and environmental parameters. Here we present four tests conducted with two types of Figaro^® Taguchi gas sensors (TGSs) in a laboratory experiment. The sensors were exposed to ambient air and peaks of CH<span class="inline-formula">₄</span> concentrations. We assembled four chambers, each containing one TGS sensor of each type. The first test consisted in comparing parametric and non-parametric models to reconstruct the CH<span class="inline-formula">₄</span> peak signal from observations of the voltage variations of TGS sensors. The obtained relative accuracy is better than 10 % to reconstruct the maximum amplitude of peaks (RMSE <span class="inline-formula">≤2</span> ppm). Polynomial regression and multilayer perceptron (MLP) models gave the highest performances for one type of sensor (TGS 2611C, RMSE <span class="inline-formula">=0.9</span> ppm) and for the combination of two sensors (TGS 2611C <span class="inline-formula">+</span> TGS 2611E, RMSE <span class="inline-formula">=0.8</span> ppm), with a training set size of 70 % of the total observations. In the second test, we compared the performance of the same models with a reduced training set. To reduce the size of the training set, we employed a stratification of the data into clusters of peaks that allowed us to keep the same model performances with only 25 % of the data to train the models. The third test consisted of detecting the effects of age in the sensors after 6 months of continuous measurements. We observed performance degradation through our models of between 0.6 and 0.8 ppm. In the final test, we assessed the capability of a model to be transferred between chambers in the same type of sensor and found that it is only possible to transfer models if the target range of variation of CH<span class="inline-formula">₄</span> is similar to the one on which the model was trained.</p>