Abstract. African and South American (ASA) wildfires account for more than 70 % of global burned areas and have strong connection to local climate for sub-seasonal to seasonal wildfire dynamics. However, representation of the wildfire-climate relationship remains challenging, due to spatiotemporally heterogenous responses of wildfires to climate variability and human influences. Here, we developed an interpretable Machine Learning (ML) fire model (AttentionFire_v1.0) to resolve the complex spatial- heterogenous and time-lagged controls from climate on burned area and to better predict burned areas over ASA regions. Our ML fire model substantially improved predictability of burned area for both spatial and temporal dynamics compared with five commonly used machine learning models. More importantly, the model revealed strong time-lagged control from climate wetness on the burned areas. The model also predicted that under a high emission future climate scenario, the recently observed declines in burned area will reverse in South America in the near future due to climate changes. Our study provides reliable and interpretable fire model and highlights the importance of lagged wildfire-climate relationships in historical and future predictions.

No abstract

<p>Photosynthesis is the largest flux of carbon between the atmosphere and Earth’s surface and is driven by proteins that require nitrogen. Thus, photosynthesis is a key linkage between the terrestrial carbon and nitrogen cycles, and the representation of this linkage is  critical for coupled carbon-nitrogen land surface models. Most models use a scheme that assumes that photosynthetic nitrogen is driven by soil nitrogen availability. This contributes to projected future reductions in the CO<sub>2</sub> fertilization of photosynthesis, as this fertilization becomes limited by nitrogen availability. However, recent results suggest that photosynthetic nitrogen is determined by leaf nitrogen demand, which is set by aboveground conditions, and that future increases in temperature and atmospheric CO<sub>2</sub> should reduce photosynthetic nitrogen demand. Here, we used recently developed photosynthetic optimality theory to incorporate the effect of reduced photosynthetic demand for nitrogen into the land surface component of the Energy Exascale Earth System Model (ELM). We simulated land surface processes under future elevated CO<sub>2</sub> conditions to 2100 using the RCP 8.5 scenario. Our simulations showed that photosynthesis increases under future conditions, but leaf nitrogen declines. This nitrogen savings led to an increase in simulated leaf area, which increased GPP and ecosystem carbon in 2100. These results suggest that land surface models may overestimate future nitrogen limitation of photosynthesis if they do not incorporate future reductions in photosynthetic nitrogen demand.</p>

<p>Soils contain the largest actively-cycling terrestrial carbon pool, which is itself composed of chemically heterogeneous and measurable pools that vary in their persistence. Fundamental uncertainties in terrestrial carbon-climate feedbacks still depend on the timing, sign, and magnitude of the response of soil carbon, and its underlying pools, to environmental change. However, model comparisons typically focus on benchmarking only bulk soil carbon stocks and climatological temperature sensitivities. Underlying microbial and mineral-associated pools, and their response to global change, have received increasing attention among empirical studies, yet data limitations still hinder benchmarking of these pools and processes in models at ecosystem- to global-scales. Here we examined the distribution of carbon within particulate and mineral-associated fractions across an ensemble of global soil biogeochemical models, and compared model estimates to a global database of soil fractions. We found that, while bulk soil carbon stocks were seemingly comparable in magnitude and geographic distribution across the models and observations, the spread in underlying pools was much more pronounced. Indeed, the ensemble of models varied nearly 6-fold in the proportion of carbon in mineral-associated fractions, and the majority of models greatly underestimated mineral-associated carbon stocks compared to the observations. Latitudinal differences between the models resulted in divergent pool-specific climatological temperature sensitivities, with implications on projections to global change scenarios. Our study elucidates key structural and theoretical differences between models that drive divergent soil carbon projections, and clearly highlights the need to benchmark underlying carbon pools, in addition to bulk soil carbon stocks.</p>

No abstract