Technical note: Uncertainties in eddy covariance CO₂ fluxes in a semiarid sagebrush ecosystem caused by gap-filling approaches

Gap-filling eddy covariance CO2 fluxes is challenging at dryland sites due to small CO2 fluxes. Here, four machine learning (ML) algorithms including artificial neural network (ANN), k-nearest neighbors (KNNs), random forest (RF), and support vector machine (SVM) are employed and evaluated for gap-filling CO2 fluxes over a semiarid sagebrush ecosystem with different lengths of artificial gaps. The ANN and RF algorithms outperform the KNN and SVM in filling gaps ranging from hours to days, with the RF being more time efficient than the ANN. Performances of the ANN and RF are largely degraded for extremely long gaps of 2 months. In addition, our results suggest that there is no need to fill the daytime and nighttime net ecosystem exchange (NEE) gaps separately when using the ANN and RF. With the ANN and RF, the gap-filling-induced uncertainties in the annual NEE at this site are estimated to be within 16 g C m−2, whereas the uncertainties by the KNN and SVM can be as large as 27 g C m−2. To better fill extremely long gaps of a few months, we test a two-layer gap-filling framework based on the RF. With this framework, the model performance is improved significantly, especially for the nighttime data. Therefore, this approach provides an alternative in filling extremely long gaps to characterize annual carbon budgets and interannual variability in dryland ecosystems.

Technical note: Uncertainties in eddy covariance CO₂ fluxes in a semi-arid sagebrush ecosystem caused by gap-filling approaches

Gap-filling eddy covariance CO2 fluxes is challenging at dryland sites due to small CO2 fluxes. Here, four machine learning (ML) algorithms including artificial neural network (ANN), k-nearest neighbours (KNN), random forest (RF), and support vector machine (SVM) are employed and evaluated for gap-filling CO2 fluxes over a semi-arid sagebrush ecosystem with different lengths of artificial gaps. The ANN and RF algorithms outperform the KNN and SVM in filling gaps ranging from hours to days, with the RF being more time efficient than the ANN. Performances of the ANN and RF are largely degraded for extremely long gaps of two months. In addition, our results suggest that there is no need to fill the daytime and nighttime NEE gaps separately when using the ANN and RF. With the ANN and RF, the gap-filling induced uncertainties in the annual NEE at this site are estimated to be within 16 g C m−2, whereas the uncertainties by the KNN and SVM can be as large as 27 g C m−2. To better fill extremely long gaps of a few months, we test a two-layer gap-filling framework based on the RF. With this framework, the model performance is improved significantly, especially for the nighttime data. Therefore, this approach provides an alternative in filling extremely long gaps to characterize annual carbon budgets and interannual variability in dryland ecosystems.

Coproducing Science to Inform Working Lands: The Next Frontier in Nature Conservation

Conservationists are increasingly convinced that coproduction of science enhances its utility in policy, decision-making, and practice. Concomitant is a renewed reliance on privately owned working lands to sustain nature and people. We propose a coupling of these emerging trends as a better recipe for conservation. To illustrate this, we present five elements of coproduction, contrast how they differ from traditional approaches, and describe the role of scientists in successful partnerships. Readers will find coproduction more demanding than the loading dock approach to science delivery but will also find greater rewards, relevance, and impact. Because coproduction is novel and examples of it are rare, we draw on our roles as scientists within the US Department of Agriculture–led Sage Grouse Initiative, North America's largest effort to conserve the sagebrush ecosystem. As coproduction and working lands evolve, traditional approaches will be replaced in order to more holistically meet the needs of nature and people.