Christian Gaviria Salazar, J. Alan Roebuck Jr, Allison N. Myers-Pigg, Susan Ziegler
{"title":"Self-diagnosis of model suitability for continuous measurements of stream-dissolved organic carbon derived from in situ UV–visible spectroscopy","authors":"Christian Gaviria Salazar, J. Alan Roebuck Jr, Allison N. Myers-Pigg, Susan Ziegler","doi":"10.1002/lom3.10559","DOIUrl":null,"url":null,"abstract":"<p>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<sup>−1</sup>, mean = 8.38 mg C L<sup>−1</sup>, training RMSE = 0.34 mg C L<sup>−1</sup>, internal validation RMSE = 0.50 mg C L<sup>−1</sup>, external validation RMSE = 2.43 mg C L<sup>−1</sup>). We further demonstrate using PLS model statistics to monitor performance and elucidate when and how models should be updated. These statistics, Hotelling's T<sup>2</sup> 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 T<sup>2</sup> 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 SUVA<sub>254</sub> 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<sup>−1</sup>. 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.</p>","PeriodicalId":18145,"journal":{"name":"Limnology and Oceanography: Methods","volume":"21 8","pages":"478-494"},"PeriodicalIF":2.1000,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Limnology and Oceanography: Methods","FirstCategoryId":"89","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/lom3.10559","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"LIMNOLOGY","Score":null,"Total":0}
引用次数: 1
Abstract
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.
在训练数据集难以开发的情况下(例如,偏远地区),以及由于环境或景观变化(例如,气候或土地利用变化),光学特征与溶解有机碳浓度变化之间的关系,应用溶解有机碳(DOC)的高频监测是困难的。我们开发并比较了三个偏最小二乘(PLS)模型,使用现场水位测量、电导率和紫外-可见光谱衰减来预测DOC。利用以山坡为主的森林或以低海拔湿地池塘为主的溪流集水区的数据,开发了两个特定地点的模型。第三个模型使用了两个站点的数据,显示出最佳性能(DOC范围 = 4–15.5 mg C L−1,平均值 = 8.38 mg C L−1,RMSE培训 = 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,并阐明了何时以及如何更新模型。这些统计数据,霍特林的T2和平方预测误差,是对所做预测的有用一致性检查,并检测潜在的不一致性,如果未检测到,可能会降低DOC预测的稳健性。例如,通过T2统计,我们将夏秋过渡确定为DOC组成与训练数据集中所示不同的时期。我们还确定,作为外部验证的一部分,SUVA254值的升高导致了在随后一年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降低到0.89 mg C L−1.本文提出的方法可应用于未来的监测程序,使模型更新能够在偏远地区或环境变化的情况下,从光学数据集(如衰减或荧光)准确监测DOC通量。实施这一方法还可以确定与气候和其他与陆地到水生通量相关的环境变化相关的可能的制度变化或景观和水文变化。
期刊介绍:
Limnology and Oceanography: Methods (ISSN 1541-5856) is a companion to ASLO''s top-rated journal Limnology and Oceanography, and articles are held to the same high standards. In order to provide the most rapid publication consistent with high standards, Limnology and Oceanography: Methods appears in electronic format only, and the entire submission and review system is online. Articles are posted as soon as they are accepted and formatted for publication.
Limnology and Oceanography: Methods will consider manuscripts whose primary focus is methodological, and that deal with problems in the aquatic sciences. Manuscripts may present new measurement equipment, techniques for analyzing observations or samples, methods for understanding and interpreting information, analyses of metadata to examine the effectiveness of approaches, invited and contributed reviews and syntheses, and techniques for communicating and teaching in the aquatic sciences.