Application of high-frequency monitoring of dissolved organic carbon (DOC) is difficult in instances where training datasets are challenging to develop (e.g., remote locations) and the relationship between optical features and DOC concentration changes due to environmental or landscape shifts (e.g., climate or land-use change). We developed and compared three partial least squares (PLS) models using in situ water level measurements, conductivity, and UV–Vis spectral attenuation to predict DOC. Two site-specific models were developed using data from a hillslope-dominated forest or a low-relief wetland-pond-dominated stream catchment. The third model, using data from both sites, exhibited the best performance (DOC range = 4–15.5 mg C L⁻¹, mean = 8.38 mg C L⁻¹, training RMSE = 0.34 mg C L⁻¹, internal validation RMSE = 0.50 mg C L⁻¹, external validation RMSE = 2.43 mg C L⁻¹). We further demonstrate using PLS model statistics to monitor performance and elucidate when and how models should be updated. These statistics, Hotelling's T² and squared prediction errors, are useful consistency checks for the predictions made and detect underlying inconsistencies that, if undetected, can reduce the robustness of DOC prediction. For example, via the T² statistic, we identified the summer–autumn transition as a period when DOC composition differed from what was represented in the training dataset. We also determined that elevated SUVA₂₅₄ values contributed to the overall bias observed in predictions made during the subsequent year as part of the external validation. This enabled the application of a bias correction that reduced the RMSE from 2.43 to 0.89 mg C L⁻¹. The method presented here could be applied to future monitoring programs enabling model updates to monitor DOC fluxes accurately from optical datasets (e.g., attenuance or fluorescence) in the face of developing datasets in remote locations or environmental change. Implementation of this approach may also identify possible regime shifts or landscape and hydrologic change associated with climate and other environmental changes relevant to terrestrial to aquatic fluxes.

中文翻译：

---

通过原位紫外可见光谱连续测量流溶解有机碳的模型适用性的自我诊断

在训练数据集开发具有挑战性（例如，偏远地区）以及由于环境或景观变化（例如，气候变化）导致光学特征与 DOC 浓度变化之间的关系的情况下，应用溶解有机碳（DOC）高频监测会很困难。或土地利用变化）。我们使用原位水位测量、电导率和紫外-可见光谱衰减来开发和比较三个偏最小二乘 (PLS) 模型来预测 DOC。使用来自山坡为主的森林或低地势湿地池塘为主的河流流域的数据开发了两个特定地点模型。第三个模型使用来自两个站点的数据，表现出最佳性能（DOC 范围 = 4–15.5 mg C L ⁻¹，平均值 = 8.38 mg C L ⁻¹，训练 RMSE = 0.34 mg C L ⁻¹，内部验证 RMSE = 0.50 mg C L ⁻¹，外部验证 RMSE = 2.43 mg C L ⁻¹）。我们进一步演示了使用 PLS 模型统计数据来监控性能并阐明何时以及如何更新模型。这些统计数据（Hotelling 的 T ²和平方预测误差）对于所做的预测是有用的一致性检查，并检测潜在的不一致，如果未检测到，可能会降低 DOC 预测的稳健性。例如，通过 T ²统计，我们将夏秋季节确定为 DOC 成分与训练数据集中所表示的不同的时期。我们还确定了加高SUVA ₂₅₄作为外部验证的一部分，这些值导致了随后一年做出的预测中观察到的总体偏差。这使得能够应用偏差校正，将 RMSE 从 2.43 mg C L -1 降低至 0.89 mg C L ^-1。这里提出的方法可以应用于未来的监测计划，使模型更新能够在面对远程位置或环境变化的开发数据集时根据光学数据集（例如衰减或荧光）准确监测 DOC 通量。该方法的实施还可以确定与气候和与陆地到水生通量相关的其他环境变化相关的可能的制度转变或景观和水文变化。