Search for: All records

Abstract. Photosynthesis plays an important role in carbon,nitrogen, and water cycles. Ecosystem models for photosynthesis arecharacterized by many parameters that are obtained from limited in situmeasurements and applied to the same plant types. Previous site-by-sitecalibration approaches could not leverage big data and faced issues likeoverfitting or parameter non-uniqueness. Here we developed an end-to-endprogrammatically differentiable (meaning gradients of outputs to variablesused in the model can be obtained efficiently and accurately) version of thephotosynthesis process representation within the Functionally AssembledTerrestrial Ecosystem Simulator (FATES) model. As a genre ofphysics-informed machine learning (ML), differentiable models couplephysics-based formulations to neural networks (NNs) that learn parameterizations(and potentially processes) from observations, here photosynthesis rates. Wefirst demonstrated that the framework was able to correctly recover multiple assumedparameter values concurrently using synthetic training data. Then, using areal-world dataset consisting of many different plant functional types (PFTs), welearned parameters that performed substantially better and greatly reducedbiases compared to literature values. Further, the framework allowed us togain insights at a large scale. Our results showed that the carboxylationrate at 25 ∘C (Vc,max25) was more impactful than a factorrepresenting water limitation, although tuning both was helpful inaddressing biases with the default values. This framework could potentiallyenable substantial improvement in our capability to learn parameters andreduce biases for ecosystem modeling at large scales. 

Abstract. Soil pore water (SPW) chemistry can vary substantially acrossmultiple scales in Arctic permafrost landscapes. The magnitude of thesevariations and their relationship to scale are critical considerations forunderstanding current controls on geochemical cycling and for predictingfuture changes. These aspects are especially important for Arctic changemodeling where accurate representation of sub-grid variability may benecessary to predict watershed-scale behaviors. Our research goal is tocharacterize intra- and inter-watershed soil water geochemical variations attwo contrasting locations in the Seward Peninsula of Alaska, USA. We thenattempt to identify the key factors controlling concentrations of importantpore water solutes in these systems. The SPW geochemistry of 18 locationsspanning two small Arctic catchments was examined for spatial variabilityand its dominant environmental controls. The primary environmental controlsconsidered were vegetation, soil moisture and/or redox condition, water–soilinteractions and hydrologic transport, and mineral solubility. The samplinglocations varied in terms of vegetation type and canopy height, presence orabsence of near-surface permafrost, soil moisture, and hillslope position.Vegetation was found to have a significant impact on SPW NO3-concentrations, associated with the localized presence of nitrogen-fixingalders and mineralization and nitrification of leaf litter from tall willowshrubs. The elevated NO3- concentrations were, however, frequentlyequipoised by increased microbial denitrification in regions with sufficientmoisture to support it. Vegetation also had an observable impact on soil-moisture-sensitive constituents, but the effect was less significant. Theredox conditions in both catchments were generally limited by Fe reduction,seemingly well-buffered by a cache of amorphous Fe hydroxides, with the mostreducing conditions found at sampling locations with the highest soilmoisture content. Non-redox-sensitive cations were affected by a widevariety of water–soil interactions that affect mineral solubility andtransport. Identification of the dominant controls on current SPWhydrogeochemistry allows for qualitative prediction of future geochemicaltrends in small Arctic catchments that are likely to experience warming andpermafrost thaw. As source areas for geochemical fluxes to the broaderArctic hydrologic system, geochemical processes occurring in theseenvironments are particularly important to understand and predict withregards to such environmental changes. 

Process-based modelling offers interpretability and physical consistency in many domains of geosciences but struggles to leverage large datasets efficiently. Machine-learning methods, especially deep networks, have strong predictive skills yet are unable to answer specific scientific questions. In this Perspective, we explore differentiable modelling as a pathway to dissolve the perceived barrier between process-based modelling and machine learning in the geosciences and demonstrate its potential with examples from hydrological modelling. ‘Differentiable’ refers to accurately and efficiently calculating gradients with respect to model variables or parameters, enabling the discovery of high-dimensional unknown relationships. Differentiable modelling involves connecting (flexible amounts of) prior physical knowledge to neural networks, pushing the boundary of physics-informed machine learning. It offers better interpretability, generalizability, and extrapolation capabilities than purely data-driven machine learning, achieving a similar level of accuracy while requiring less training data. Additionally, the performance and efficiency of differentiable models scale well with increasing data volumes. Under data-scarce scenarios, differentiable models have outperformed machine-learning models in producing short-term dynamics and decadal-scale trends owing to the imposed physical constraints. Differentiable modelling approaches are primed to enable geoscientists to ask questions, test hypotheses, and discover unrecognized physical relationships. Future work should address computational challenges, reduce uncertainty, and verify the physical significance of outputs. 

Abstract Plants invest a considerable amount of leaf nitrogen in the photosynthetic enzyme ribulose-1,5-bisphosphate carboxylase-oxygenase (RuBisCO), forming a strong coupling of nitrogen and photosynthetic capacity. Variability in the nitrogen-photosynthesis relationship indicates different nitrogen use strategies of plants (i.e., the fraction nitrogen allocated to RuBisCO; fLNR), however, the reason for this remains unclear as widely different nitrogen use strategies are adopted in photosynthesis models. Here, we use a comprehensive database of in situ observations, a remote sensing product of leaf chlorophyll and ancillary climate and soil data, to examine the global distribution in fLNR using a random forest model. We find global fLNR is 18.2 ± 6.2%, with its variation largely driven by negative dependence on leaf mass per area and positive dependence on leaf phosphorus. Some climate and soil factors (i.e., light, atmospheric dryness, soil pH, and sand) have considerable positive influences on fLNR regionally. This study provides insight into the nitrogen-photosynthesis relationship of plants globally and an improved understanding of the global distribution of photosynthetic potential. 

Forest dynamics arise from the interplay of environmental drivers and disturbances with the demographic processes of recruitment, growth, and mortality, subsequently driving biomass and species composition. However, forest disturbances and subsequent recovery are shifting with global changes in climate and land use, altering these dynamics. Changes in environmental drivers, land use, and disturbance regimes are forcing forests toward younger, shorter stands. Rising carbon dioxide, acclimation, adaptation, and migration can influence these impacts. Recent developments in Earth system models support increasingly realistic simulations of vegetation dynamics. In parallel, emerging remote sensing datasets promise qualitatively new and more abundant data on the underlying processes and consequences for vegetation structure. When combined, these advances hold promise for improving the scientific understanding of changes in vegetation demographics and disturbances.