Continued developments in instrumentation and modeling have driven progress in monitoring methane (${\mathrm{CH}}_4$) emissions at a range of spatial scales. The sites that emit ${\mathrm{CH}}_4$ such as landfills, oil and gas extraction or storage infrastructure, intensive livestock farms account for a large share of global emissions, and need to be monitored on a continuous basis to verify the effectiveness of reductions policies. Low cost sensors are valuable to monitor methane (${\mathrm{CH}}_4$) around such facilities because they can be deployed in a large number to sample atmospheric plumes and retrieve emission rates using dispersion models. Here we present two tests of three different versions of Figaro^® TGS tin-oxide sensors for estimating ${\mathrm{CH}}_4$ concentrations variations, at levels similar to current atmospheric values, with a sought accuracy of 0.1 to 0.2 ppm. In the first test, we characterize the variation of the resistance of the tin-oxide semi-conducting sensors to controlled levels of ${\mathrm{CH}}_4$, ${\mathrm{H}}_2\mathrm{O}$ and $\mathrm{CO}$ in the laboratory, to analyze cross-sensitivities. In the second test, we reconstruct observed ${\mathrm{CH}}_4$ variations in a room, that ranged from 1.9 and 2.4 ppm during a three month experiment from observed time series of resistances and other variables. To do so, a machine learning model is trained against true ${\mathrm{CH}}_4$ recorded by a high precision instrument. The machine-learning model using 30% of the data for training reconstructs ${\mathrm{CH}}_4$ within the target accuracy of 0.1 ppm only if training variables are representative of conditions during the testing period. The model-derived sensitivities of the sensors resistance to ${\mathrm{H}}_2\mathrm{O}$ compared to ${\mathrm{CH}}_4$ are larger than those observed under controlled conditions, which deserves further characterization of all the factors influencing the resistance of the sensors.

中文翻译：

---

低成本氧化锡传感器与机器学习相结合的潜力，可用于估算背景浓度附近的大气CH4变化

仪器和建模的不断发展推动了甲烷监测的进展（${\mathrm{CH}}_4$）在一系列空间尺度上的排放。发射的网站${\mathrm{CH}}_4$诸如垃圾掩埋场，油气开采或存储基础设施等，集约化畜牧场在全球排放量中占很大比重，需要进行连续监控以验证减排政策的有效性。低成本传感器对于监测甲烷（${\mathrm{CH}}_4$），因为它们可以大量部署以采样大气羽流并使用扩散模型获取排放率。这里，我们提出的三个不同版本费加罗的两个测试^® TGS锡氧化物传感器，用于估计${\mathrm{CH}}_4$浓度变化，其水平与当前大气值相似，精确度为0.1至0.2 ppm。在第一个测试中，我们表征了氧化锡半导体传感器的电阻在受控水平上的变化。${\mathrm{CH}}_4$， ${\mathrm{H}}_2\mathrm{Ø}$ 和 $\mathrm{一氧化碳}$在实验室中，分析交叉敏感性。在第二个测试中，我们重建观察到的${\mathrm{CH}}_4$在三个月的实验中，根据观察到的电阻和其他变量的时间序列，房间中的变化范围为1.9 ppm和2.4 ppm。为此，针对真实情况训练了机器学习模型${\mathrm{CH}}_4$用高精度仪器记录。使用30％的数据进行训练的机器学习模型可重构${\mathrm{CH}}_4$仅当训练变量代表测试期间的条件时，才在0.1 ppm的目标精度内。传感器对传感器的模型灵敏度${\mathrm{H}}_2\mathrm{Ø}$ 相比 ${\mathrm{CH}}_4$ 大于在受控条件下观察到的值，这值得进一步表征影响传感器电阻的所有因素。