Climate controls over ecosystem metabolism: insights from a fifteen-year inductive artificial neural network synthesis for a subalpine forest

Albert, Loren P.; Keenan, Trevor F.; Burns, Sean P.; Huxman, Travis E.; Monson, Russell K.

doi:10.1007/s00442-017-3853-0

Cited by 24 publications

(11 citation statements)

References 67 publications

(87 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is important to note that while we draw linkages between decreasing photosynthesis, decreasing SIF, and increasing xanthophyll cycle activity, there are many other coinciding potential drivers of ecosystem productivity. At Niwot Ridge, the spring onset of photosynthesis is associated with increasing temperature, hydraulic system recovery, and an increase in carboxylation capacity (27,52,53). We expect not only that winter acclimation corresponds to changes in the xanthophyll cycle, but also that a variety of carotenoids, such as lutein and beta-carotene, may play a photoprotective role during the transition seasons and winter (30,54).…”

Section: Seasonal and Diurnal Dynamics Of Canopy Photosynthesis And Sifmentioning

confidence: 99%

Mechanistic evidence for tracking the seasonality of photosynthesis with solar-induced fluorescence

Magney

Bowling

Logan

et al. 2019

Proc. Natl. Acad. Sci. U.S.A.

Self Cite

273

270

View full text Add to dashboard Cite

Northern hemisphere evergreen forests assimilate a significant fraction of global atmospheric CO2 but monitoring large-scale changes in gross primary production (GPP) in these systems is challenging. Recent advances in remote sensing allow the detection of solar-induced chlorophyll fluorescence (SIF) emission from vegetation, which has been empirically linked to GPP at large spatial scales. This is particularly important in evergreen forests, where traditional remote-sensing techniques and terrestrial biosphere models fail to reproduce the seasonality of GPP. Here, we examined the mechanistic relationship between SIF retrieved from a canopy spectrometer system and GPP at a winter-dormant conifer forest, which has little seasonal variation in canopy structure, needle chlorophyll content, and absorbed light. Both SIF and GPP track each other in a consistent, dynamic fashion in response to environmental conditions. SIF and GPP are well correlated (R2 = 0.62–0.92) with an invariant slope over hourly to weekly timescales. Large seasonal variations in SIF yield capture changes in photoprotective pigments and photosystem II operating efficiency associated with winter acclimation, highlighting its unique ability to precisely track the seasonality of photosynthesis. Our results underscore the potential of new satellite-based SIF products (TROPOMI, OCO-2) as proxies for the timing and magnitude of GPP in evergreen forests at an unprecedented spatiotemporal resolution.

show abstract

Section: Seasonal and Diurnal Dynamics Of Canopy Photosynthesis And Sifmentioning

confidence: 99%

Mechanistic evidence for tracking the seasonality of photosynthesis with solar-induced fluorescence

Magney

Bowling

Logan

et al. 2019

Proc. Natl. Acad. Sci. U.S.A.

Self Cite

273

270

View full text Add to dashboard Cite

show abstract

“…Despite potentially limited process-level insights, ensembles of ANNs have been used to identify dominant drivers of changes in greenhouse gas fluxes from eddy covariance time series (Albert et al 2017), where data constraints are not a concern. Because ANNs can identify dominant drivers from data, they may be useful as an inductive approach when elaborating model processes as described in Fig.…”

Section: Deemphasising Model Structurementioning

confidence: 99%

Making ecological models adequate

et al. 2017

View full text Add to dashboard Cite

Critical evaluation of the adequacy of ecological models is urgently needed to enhance their utility in developing theory and enabling environmental managers and policymakers to make informed decisions. Poorly supported management can have detrimental, costly or irreversible impacts on the environment and society. Here, we examine common issues in ecological modelling and suggest criteria for improving modelling frameworks. An appropriate level of process description is crucial to constructing the best possible model, given the available data and understanding of ecological structures. Model details unsupported by data typically lead to over parameterisation and poor model performance. Conversely, a lack of mechanistic details may limit a model's ability to predict ecological systems' responses to management. Ecological studies that employ models should follow a set of model adequacy assessment protocols that include: asking a series of critical questions regarding state and control variable selection, the determinacy of data, and the sensitivity and validity of analyses. We also need to improve model elaboration, refinement and coarse graining procedures to better understand the relevancy and adequacy of our models and the role they play in advancing theory, improving hind and forecasting, and enabling problem solving and management.

show abstract

“…Neural Networks have been widely applied to ecological problems such as pollen classification in honey products [75], time-series analysis to investigate climate drivers in subalpine forests [76], weather forecasting [77], modeling non-linear relationships in aquatic ecology [78] and future warming [79], predicting species distribution [80] and water resources [81]. For paleoecology, the NNs are a promising approach for automated pollen grain recognition that would aid in the pollen identification process [82].…”

Section: Methodsmentioning

confidence: 99%

Predictive pollen-based biome modeling using machine learning

Sobol

Finkelstein

2018

PLoS ONE

View full text Add to dashboard Cite

This paper investigates suitability of supervised machine learning classification methods for classification of biomes using pollen datasets. We assign modern pollen samples from Africa and Arabia to five biome classes using a previously published African pollen dataset and a global ecosystem classification scheme. To test the applicability of traditional and machine-learning based classification models for the task of biome prediction from high dimensional modern pollen data, we train a total of eight classification models, including Linear Discriminant Analysis, Logistic Regression, Naïve Bayes, K-Nearest Neighbors, Classification Decision Tree, Random Forest, Neural Network, and Support Vector Machine. The ability of each model to predict biomes from pollen data is statistically tested on an independent test set. The Random Forest classifier outperforms other models in its ability correctly classify biomes given pollen data. Out of the eight models, the Random Forest classifier scores highest on all of the metrics used for model evaluations and is able to predict four out of five biome classes to high degree of accuracy, including arid, montane, tropical and subtropical closed and open systems, e.g. forests and savanna/grassland. The model has the potential for accurate reconstructions of past biomes and awaits application to fossil pollen sequences. The Random Forest model may be used to investigate vegetation changes on both long and short time scales, e.g. during glacial and interglacial cycles, or more recent and abrupt climatic anomalies like the African Humid Period. Such applications may contribute to a better understanding of past shifts in vegetation cover and ultimately provide valuable information on drivers of climate change.

show abstract

Climate controls over ecosystem metabolism: insights from a fifteen-year inductive artificial neural network synthesis for a subalpine forest

Cited by 24 publications

References 67 publications

Mechanistic evidence for tracking the seasonality of photosynthesis with solar-induced fluorescence

Mechanistic evidence for tracking the seasonality of photosynthesis with solar-induced fluorescence

Making ecological models adequate

Predictive pollen-based biome modeling using machine learning

Contact Info

Product

Resources

About