In vivo fluorometers use chlorophyll a fluorescence (F_chl) as a proxy to monitor phytoplankton biomass. However, the fluorescence yield of F_chl is affected by photoprotection processes triggered by increased irradiance (nonphotochemical quenching; NPQ), creating diurnal reductions in F_chl that may be mistaken for phytoplankton biomass reductions. Published correction methods are mostly designed for pelagic oceans and are ill suited for inland waters or for high‐frequency data collection. A machine learning‐based method was developed to correct vertical profiler data from an oligotrophic lake. NPQ was estimated as a percent reduction in F_chl by comparing daytime values to mean, unquenched values from the previous night. A random forest regression was trained on sensor data collected coincident with F_chl; including solar radiation, water temperature, depth, and dissolved oxygen saturation. The accuracy of the model was assessed using a grouped 10‐fold cross validation (mean absolute error [MAE]: 7.6%; root mean square error [RMSE]: 10.2%), which was then used to correct F_chl profiles. The model also predicted NPQ and corrected unseen F_chl profiles from a future period with excellent results (MAE: 9.0%; RMSE: 14.4%). F_chl profiles were then correlated to laboratory results, allowing corrected profiles to be compared directly to collected samples. The correction reduced error (RMSE) due to NPQ from 0.67 μg L⁻¹ to 0.33 μg L⁻¹ when compared to uncorrected F_chl data. These results suggest that the use of machine learning models may be an effective way to correct for NPQ and may have universal applicability.

中文翻译：

---

使用机器学习校正高频体内荧光计数据中的非光化学猝灭

体内荧光计使用叶绿素a荧光（F _chl）作为代理来监测浮游植物的生物量。但是，F _chl的荧光产量受辐照度增加（非光化学猝灭； NPQ）触发的光保护过程的影响，导致F _chl的昼夜减少，这可能被误认为是浮游植物生物量的减少。已发布的校正方法主要是为远洋设计的，不适用于内陆水域或高频数据收集。开发了一种基于机器学习的方法来校正贫营养湖的垂直剖面数据。NPQ估计为F _chl减少的百分比通过将白天的值与前一天晚上的平均值进行比较，得出结果。在与F _chl一致的传感器数据上进行了森林随机回归训练; 包括太阳辐射，水温，深度和溶解氧饱和度。使用分组的10倍交叉验证（平均绝对误差[MAE]：7.6％；均方根误差[RMSE]：10.2％）评估模型的准确性，然后将其用于校正F _chl轮廓。该模型还预测了NPQ，并在以后的一段时间内纠正了看不见的F _chl谱图，结果非常出色（MAE：9.0％； RMSE：14.4％）。˚F _CHL然后将轮廓与实验室结果相关联，从而可以将校正后的轮廓直接与收集的样品进行比较。从0.67由于NPQ校正减小误差（RMSE）  μ克L- ^-1〜0.33  μ克L- ^-1时相比未校正˚F_叶绿素数据。这些结果表明，机器学习模型的使用可能是纠正NPQ的有效方法，并且可能具有普遍适用性。