The time is now: For decades, scientists have been raising calls for societal changes that will reduce our impacts on nature. Though much conservation has occurred, our natural environment continues to decline under the weight of our consumption. Humanity depends directly on the output of nature; thus, this decline will affect us, just as it does the other species with which we share this world. Díaz et al. review the findings of the largest assessment of the state of nature conducted as of yet. They report that the state of nature, and the state of the equitable distribution of nature's support, is in serious decline. Only immediate transformation of global business-as-usual economies and operations will sustain nature as we know it, and us, into the future. Science , this issue p. eaax3100

Although a key driver of Earth’s climate system, global land-atmosphere energy fluxes are poorly constrained. Here we use machine learning to merge energy flux measurements from FLUXNET eddy covariance towers with remote sensing and meteorological data to estimate global gridded net radiation, latent and sensible heat and their uncertainties. The resulting FLUXCOM database comprises 147 products in two setups: (1) 0.0833° resolution using MODIS remote sensing data (RS) and (2) 0.5° resolution using remote sensing and meteorological data (RS + METEO). Within each setup we use a full factorial design across machine learning methods, forcing datasets and energy balance closure corrections. For RS and RS + METEO setups respectively, we estimate 2001–2013 global (±1 s.d.) net radiation as 75.49 ± 1.39 W m⁻² and 77.52 ± 2.43 W m⁻², sensible heat as 32.39 ± 4.17 W m⁻² and 35.58 ± 4.75 W m⁻², and latent heat flux as 39.14 ± 6.60 W m⁻² and 39.49 ± 4.51 W m⁻² (as evapotranspiration, 75.6 ± 9.8 × 10³ km³ yr⁻¹ and 76 ± 6.8 × 10³ km³ yr⁻¹). FLUXCOM products are suitable to quantify global land-atmosphere interactions and benchmark land surface model simulations.

Spatio-temporal fields of land–atmosphere fluxes derived from data-driven models can complement simulations by process-based land surface models. While a number of strategies for empirical models with eddy-covariance flux data have been applied, a systematic intercomparison of these methods has been missing so far. In this study, we performed a cross-validation experiment for predicting carbon dioxide, latent heat, sensible heat and net radiation fluxes across different ecosystem types with 11 machine learning (ML) methods from four different classes (kernel methods, neural networks, tree methods, and regression splines). We applied two complementary setups: (1) 8-day average fluxes based on remotely sensed data and (2) daily mean fluxes based on meteorological data and a mean seasonal cycle of remotely sensed variables. The patterns of predictions from different ML and experimental setups were highly consistent. There were systematic differences in performance among the fluxes, with the following ascending order: net ecosystem exchange (R² < 0.5), ecosystem respiration (R² > 0.6), gross primary production (R²> 0.7), latent heat (R² > 0.7), sensible heat (R² > 0.7), and net radiation (R² > 0.8). The ML methods predicted the across-site variability and the mean seasonal cycle of the observed fluxes very well (R² > 0.7), while the 8-day deviations from the mean seasonal cycle were not well predicted (R² < 0.5). Fluxes were better predicted at forested and temperate climate sites than at sites in extreme climates or less represented by training data (e.g., the tropics). The evaluated large ensemble of ML-based models will be the basis of new global flux products.

Despite early speculation to the contrary, all tropical forests studied to date display seasonal variations in the presence of new leaves, flowers, and fruits. Past studies were focused on the timing of phenological events and their cues but not on the accompanying changes in leaf area that regulate vegetation–atmosphere exchanges of energy, momentum, and mass. Here we report, from analysis of 5 years of recent satellite data, seasonal swings in green leaf area of ≈25% in a majority of the Amazon rainforests. This seasonal cycle is timed to the seasonality of solar radiation in a manner that is suggestive of anticipatory and opportunistic patterns of net leaf flushing during the early to mid part of the light-rich dry season and net leaf abscission during the cloudy wet season. These seasonal swings in leaf area may be critical to initiation of the transition from dry to wet season, seasonal carbon balance between photosynthetic gains and respiratory losses, and litterfall nutrient cycling in moist tropical forests.