Search for: All records

AmeriFlux is a network of hundreds of sites across the contiguous United States providing tower-based ecosystem-scale carbon dioxide flux measurements at 30 min temporal resolution. While geographically wide-ranging, over its existence the network has suffered from multiple issues including towers regularly ceasing operation for extended periods and a lack of standardization of measurements between sites. In this study, we use machine learning algorithms to predict CO2 flux measurements at NEON sites (a subset of Ameriflux sites), creating a model to gap-fill measurements when sites are down or replace measurements when they are incorrect. Machine learning algorithms also have the ability to generalize to new sites, potentially even those without a flux tower. We compared the performance of seven machine learning algorithms using 35 environmental drivers and site-specific variables as predictors. We found that Extreme Gradient Boosting (XGBoost) consistently produced the most accurate predictions (Root Mean Squared Error of 1.81 μmolm−2s−1, R2 of 0.86). The model showed excellent performance testing on sites that are ecologically similar to other sites (the Mid Atlantic, New England, and the Rocky Mountains), but poorer performance at sites with fewer ecological similarities to other sites in the data (Pacific Northwest, Florida, and Puerto Rico). The results show strong potential for machine learning-based models to make more skillful predictions than state-of-the-art process-based models, being able to estimate the multi-year mean carbon balance to within an error ±50 gCm−2y−1 for 29 of our 44 test sites. These results have significant implications for being able to accurately predict the carbon flux or gap-fill an extended outage at any AmeriFlux site, and for being able to quantify carbon flux in support of natural climate solutions. 

As of 03/03/2024, the Sevilleta Long-Term Ecological Research Program is equipped with a total of 65 digital RGB cameras, or PhenoCams, across the Sevilleta National Wildlife Refuge. These cameras are installed on eddy covariance flux towers and at a number of precipitation manipulation experiments to track vegetation phenology and productivity across dryland ecotones. PhenoCams have been paired with eddy covariance flux tower data at the site since 2014, while some Mean-Variance Experiment PhenoCams were installed as recently as June 2023. For information on PhenoCam data processing and formatting, see Richardson et al., 2018, Scientific Data (https://doi.org/10.1038/sdata.2018.28), Seyednasrollah et al., 2019, Scientific Data (https://doi.org/10.1038/s41597-019-0229-9), and the PhenoCam Network web page (https://phenocam.nau.edu/webcam/). The PhenoCam Network uses imagery from digital cameras to track vegetation phenology and seasonal changes in vegetation activity in diverse ecosystems across North America and around the world. Imagery is uploaded to the PhenoCam server hosted at Northern Arizona University, where it is made publicly available in near-real time, every 30 minutes from sunrise to sunset, 365 days a year. The data are processed using simple image analysis tools to yield a measure of canopy greenness, from which phenological metrics are extracted, characterizing the start and end of the growing season. These transition dates have been shown to align well with on-the-ground observations at various research sites. Long-term PhenoCam data can be used to track the impact of climate variability and change on the rhythm of the seasons. 

Abstract The National Ecological Observatory Network (NEON) provides over 180 distinct data products from 81 sites (47 terrestrial and 34 freshwater aquatic sites) within the United States and Puerto Rico. These data products include both field and remote sensing data collected using standardized protocols and sampling schema, with centralized quality assurance and quality control (QA/QC) provided by NEON staff. Such breadth of data creates opportunities for the research community to extend basic and applied research while also extending the impact and reach of NEON data through the creation of derived data products—higher level data products derived by the user community from NEON data. Derived data products are curated, documented, reproducibly‐generated datasets created by applying various processing steps to one or more lower level data products—including interpolation, extrapolation, integration, statistical analysis, modeling, or transformations. Derived data products directly benefit the research community and increase the impact of NEON data by broadening the size and diversity of the user base, decreasing the time and effort needed for working with NEON data, providing primary research foci through the development via the derivation process, and helping users address multidisciplinary questions. Creating derived data products also promotes personal career advancement to those involved through publications, citations, and future grant proposals. However, the creation of derived data products is a nontrivial task. Here we provide an overview of the process of creating derived data products while outlining the advantages, challenges, and major considerations. 

ABSTRACT AimTo quantify the intra‐community variability of leaf‐out (ICVLo) among dominant trees in temperate deciduous forests, assess its links with specific and phylogenetic diversity, identify its environmental drivers and deduce its ecological consequences with regard to radiation received and exposure to late frost. LocationEastern North America (ENA) and Europe (EUR). Time Period2009–2022. Major Taxa StudiedTemperate deciduous forest trees. MethodsWe developed an approach to quantify ICVLo through the analysis of RGB images taken from phenological cameras. We related ICVLo to species richness, phylogenetic diversity and environmental conditions. We quantified the intra‐community variability of the amount of radiation received and of exposure to late frost. ResultsLeaf‐out occurred over a longer time interval in ENA than in EUR. The sensitivity of leaf‐out to temperature was identical in both regions (−3.4 days per °C). The distributions of ICVLo were similar in EUR and ENA forests, despite the latter being more species‐rich and phylogenetically diverse. In both regions, cooler conditions and an earlier occurrence of leaf‐out resulted in higher ICVLo. ICVLo resulted in ca. 8% difference of radiation received from leaf‐out to September among individual trees. Forest communities in ENA had shorter safety margins as regards the exposure to late frosts, and were actually more frequently exposed to late frosts. Main ConclusionsWe conducted the first intercontinental analysis of the variability of leaf‐out at the scale of tree communities. North American and European forests showed similar ICVLo, in spite of their differences in terms of species richness and phylogenetic diversity, highlighting the relevance of environmental controls on ICVLo. We quantified two ecological implications of ICVLo (difference in terms of radiation received and exposure to late frost), which should be explored in the context of ongoing climate change, which affects trees differently according to their phenological niche.