We identified a set of core biological and ecological processes necessary to predict ecosystem-level properties: primary production for autotrophs, and eating, metabolism, growth, reproduction, dispersal, and mortality for heterotrophs (Figure 1 and Box 1). We modelled both marine and terrestrial environments but excluded freshwater ecosystems. We included all photoautotrophs, and all heterotrophs that feed on living organisms (i.e., we did not include chemoautotrophs and detritivores). We generally represented only macroscopic organisms (>1×10⁻³ g), except that we included plankton in the marine realm because of their known importance to the marine food web [18]. All plant biomass in the terrestrial realm was modelled, but only leaves, flowers, fruits, and seeds were available as a food source for herbivores and omnivores. The marine component included phytoplanktonic autotrophs, which provide more than 90% of primary productivity in the oceans [18]. Seagrasses, mangroves, macroalgae, and corals, which are important autotrophs in coastal systems, are not yet included. In this proof-of-concept model, we consider a world without any human impacts, except that we used modern-day climatic conditions. The model and user guide can be downloaded from www.madingleymodel.org, and simulation outputs for main manuscript figures can be downloaded from the Dryad Digital Repository: doi:10.5061/dryad.5m96v [19].

Traditional approaches to mechanistic modelling in community ecology focus on densities or abundances of individuals belonging to different species [16],[20]. These are well suited to modelling a small set of focal species, but are unfeasible for modelling whole ecosystems at a global scale, because the vast majority of the world's species remain to be described, or are at best represented by few data describing their distribution and ecology [21]–[23].

Instead, we adopted a trait-based approach [24] where individuals are characterized by their functional traits: categorical traits, such as feeding mode, which determine the mechanisms by which organisms exist and which were used to define functional groups; and continuous traits, such as body mass, which modulate those mechanisms but do not determine functional grouping. Taxonomic identity of individuals is ignored for three reasons. First, there is insufficient species-level information to model whole ecosystems worldwide. Second, it is more feasible to model the role of individuals in ecosystems in terms of their traits than in terms of their taxonomic identity, because of limited taxonomic knowledge and data [21]–[23]. Third, in comparison to taxonomic identity, organisms' functional traits are more directly relevant to most ecosystem functions and ecosystem services [25],[26].

A separate issue is whether to define the model in terms of population densities and biomasses within functional groups (i.e., “stocks” or “pools”), or as collections of interacting individuals each characterized by their combination of functional traits (individual-based). For all organisms except autotrophs, we used an individual-based approach, because this allowed the model to be more finely resolved, and because it enabled us to capture variation in body mass—one of the most important traits for determining the rates of ecological processes [27]–[29] over the lifetime of an individual. It also enabled us to follow the fates of individual organisms. Higher level ecosystem properties emerge from these individual-based rules. Capturing this emergence was a central aim of this initial work.

Autotrophs were represented as stocks—that is, the total biomasses of such organisms—because either the definition of an individual was problematic (terrestrial plants) or rates of turnover were faster than the modelled time step (marine phytoplankton).

For heterotrophs, simulating every individual separately would have been computationally intractable given the vast number of individuals in global ecosystems. Therefore, we adopted a computational approach based on cohorts. A cohort consisted of a group of organisms occurring within the same grid cell, with identical traits—that is, in the same functional group and with identical continuous traits—but not necessarily belonging to the same taxon. This cohort-based approach allowed us to define the model in exactly the way that one would do in a fully individual-based model (i.e., processes defined at an individual level), but also allowed us to keep the number of computations low enough to be feasible.

All stocks and cohorts belong to a functional group, defined according to the categorical traits of the individuals in that stock or cohort (Tables 1 and 2).

Individuals in the same functional group interact with one another and with their environment in a qualitatively similar manner. Therefore, cohorts within the same functional group are modelled using the same mathematical representations of the ecological processes, though the rates predicted by those functions differ according to continuous traits that differ between cohorts, such as body mass. Individuals belonging to different functional groups have at least one qualitatively different interaction with other individuals or with their environment. We use the same functional forms for analogous functional groups in the ocean and on land, but with different parameter values, where justified by previous research.

Body mass affects many individual properties and interactions, including feeding preferences and rates, metabolic rates, and dispersal [27]–[29]. Therefore, body mass was included as a parameter in nearly all ecological processes of heterotrophs (Figure 1).

The environment is defined as a two-dimensional layer representing the land surface and the upper mixed layer (top 100 m) of the oceans. This layer is divided into grid cells within which individuals and stocks are assumed to be well mixed. The ecological processes can be affected by the size of the grid cell, the physical environment at that cell, and dispersal of organisms among adjacent grid cells. The model can be employed for any number of grid cells, at any resolution, locally or globally, subject to computational limitations. For the results presented here, we used either simulations for individual 1°×1° grid cells, or a 2°×2° grid covering the whole globe (see below, and Tables 3 and 4) except for high latitudes (>65°) because remotely sensed, exogenous environmental data currently used are not available for the polar regions. Each grid cell in the model is assigned to either the terrestrial or marine realm based on a land/ocean mask [30]. Environmental conditions for each grid cell are read as model inputs from publicly available datasets: for the terrestrial realm air temperature [31], precipitation [31], soil water availability [32], number of frost days [31], and seasonality of primary productivity [33]; and for the marine realm sea-surface temperature [34], NPP [35], and ocean current velocity (Table S1) [34]. The model is flexible with respect to the specific environmental data used, and future simulated environmental conditions can be used.

We provide a summary of how simulations are run in Figure 1 and Box 1, and an overview of how the ecological processes are modelled, with the main mathematical functions, is summarised in Tables 5 and 6. Full details are provided in Text S1.

The properties of individuals and communities that we present below are “emergent”; that is, they are not prescribed, but instead emerge through time as a result of the large number of interactions that take place between individual organisms (approximated as cohorts). As a result of these interactions, life histories of individuals are formed over time and can be tracked, and communities and ecosystems of individuals self-assemble. Moreover, the dynamics of any one grid cell are affected by the exchange of individuals with other grid cells, which occurs due to dispersal. Thus macroscale predictions (e.g., over the generation length of an individual cohort, across functional groups, or across entire ecosystems) emerge from microscale biological mechanisms. The macroscale predictions differ for ecosystems in different climates, but only because the microscale biology is sensitive to the climate. Similarly, the macroscale predictions differ between the land and sea, but only because microscale biology differs between land and sea. We compared these emergent properties to empirical data.

We carried out four distinct types of simulations for different assessments of model capabilities (Table 3).

Terrestrial grid cells were seeded with two autotroph stocks, deciduous and evergreen, as detailed above, and marine grid cells were seeded with a single phytoplankton stock. Grid cells were seeded with around 1,000 cohorts each, with 112 cohorts in each of nine functional groups in the terrestrial realm and 100 cohorts in each of 10 functional groups in the marine realm. Juvenile and adult body masses of cohorts were drawn at random from a prespecified range (Table 2), and initial abundance was scaled negatively with initial body mass to provide reasonable initial densities (see Text S1 for full details).

Detailed numerical analyses were conducted on four focal grid cells (Study 1, Table 3) to investigate ecosystem dynamics over longer time scales. These simulations were used to check for the persistence of key community components (autotrophs, herbivores, carnivores, and omnivores), and to determine the typical time scales for the dynamics to reach some form of equilibrium. These analyses used the same climatological time series per year to remove the effects of interannual environmental variation. For each focal grid cell, we ran 10 model simulations for 1,000 y at a monthly time step. To test the effect of the cohort-merging regime on modelled dynamics, we repeated the simulation ensembles for each focal grid cell with the threshold number of cohorts at which merging is activated set at 500, 1,000, 5,000, and 10,000 cohorts and for a shorter period of 100 y.

Additional detailed simulations were carried out for the focal grid cells over a 100-y period to generate highly resolved predictions of emergent ecosystem properties at two levels of biological organisation: individual and ecosystem level (Study 2, Table 3).

We compared the properties of individual organisms with empirical data. Importantly, none of these properties were defined in the model as parameters, but rather they emerged as a result of the ecological interactions among individuals. The predicted relationship between body mass and growth rates was compared to estimates for reptiles, mammals, birds, and fish [46]–[48], and the relationship between body mass and time to reach maturity to estimates for invertebrates, reptiles, mammals, birds, and fish [49]–[57] (where necessary body masses were estimated from body lengths using relationships in [58]–[61]). The predicted relationship between body mass and mortality rates was compared with data for invertebrates, mammals, birds, and fish, taken from a single study [62]. The predicted relationship between body mass and lifetime reproductive success was compared with data for mammals, birds, and a few insect species [63]–[71]. Of these emergent properties, the growth rate of organisms derives most closely from the functional forms and input parameters. Specifically, growth rate could theoretically be a simple sum of food assimilation rates under conditions of saturating prey density minus metabolic costs. To test whether this was the case, we calculated the theoretical growth rate for organisms of a range of body masses under these conditions.

We compared our novel predictions of complete ecosystem structure in two grid cells (T1 and M1) (Table 4) to empirical data: the biomass density of large herbivores with an estimate for Uganda [72], and the predicted herbivore to autotroph biomass ratios with average observed ratios for similar ecosystems [73]. We further compared the modelled relationships between body mass and population density with empirical estimates derived from fish assemblages [74],[75].

To test the ability of our model to capture broad-scale patterns in the basic trophic structure of ecosystems, we compared our model predictions (Study 3, Table 3) to empirical estimates from the same dataset used to calculate the global average trophic structure ([73]; see above), but this time using specific values for 14 sites for which we could identify the spatial location (Table S3). This dataset is the most geographically wide-ranging dataset on ecosystem structure that we are aware of, including sites in both the terrestrial and marine realms.

We also generated model outputs at a global scale (Study 4, Table 3). These were used in two ways: firstly, to investigate the mechanisms giving rise to variation in ecosystem structure by assessing the relationship between trophic structure and productivity in the model along large gradients of autotroph productivity in both terrestrial (along a meridional transect from the low productivity Saharan desert to high productivity Congo Basin tropical forest region) and marine (along a meridional transect from low productivity Antarctic waters to high productivity East Atlantic upwelling zones) realms; and secondly, to make novel predictions of as-yet unmeasured global properties (e.g., latitudinal gradients in total biomass) and to compare to other modelled estimates of total biomass and density at a global scale [76]. We also compared modelled global average ratios of herbivore to autotroph biomass with the average ratios observed in the same dataset that we used to test the predictions made by individual cells [73]. Finally, we investigated how modelled marine ecosystem structure responded to mechanisms that have been proposed to cause inverted trophic biomass pyramids, such as dispersal [77], turnover rate of autotrophs, and turnover rate of consumers [77]–[79]. To do this, we simulated the global marine realm with no dispersal permitted between grid cells (Study 5, Table 3) and the effects of reducing the turnover rate of biomass through the ecosystem (Study 6, Table 3).

For the 1,000-y simulations (Study 1), model dynamics converged rapidly (<100 y) to dynamic equilibria for all 10 replicates in all four focal grid cells (Figure 2). Autotrophs, herbivores, omnivores, and carnivores persisted in all simulations. The dynamics of total biomass by functional group differed markedly among the four grid cells. Terrestrial grid cells were dominated by autotroph biomass and, among heterotrophic organisms, by herbivores, with lower biomasses of omnivores and carnivores. Marine grid cells, in comparison, had much lower biomasses of autotrophs, and omnivorous and carnivorous organisms were more dominant. Unsurprisingly, the seasonal grid cells in both the terrestrial and marine realms (Figure 2B and 2D) exhibited much greater fluctuations in biomasses within years, particularly for lower trophic levels. The high-productivity marine grid cell exhibited large-amplitude, high-frequency variations in zooplankton abundance. Biomass dynamics were robust to the choice of the threshold number of cohorts at which to activate merging above a threshold of 1,000 cohorts (Figure S2).

The power-law relationships between body mass and the properties of individual organisms that emerged from the model were generally consistent with empirical data (Figure 3). For growth rates and times taken to reach reproductive maturity, the modelled and empirical values were very similar, although the slope of the relationship between predicted growth rates and body mass was steeper. In absolute terms the predicted growth rates tended to be higher and the predicted times to maturity tended to be lower than those observed in the empirical data (Table S4).

Our assumptions about underlying ecological processes, such as handling times and metabolic rates, place a fundamental limit on the growth rate of organisms of a given body mass (i.e., the net growth rate of individuals that are feeding at the maximum rate). If most individuals attained this maximum, then the growth rates would not be emergent, so much as defined by the model assumptions. But this was not the case. The emergent relationship between body mass and growth rate was not a simple function of maximum possible food assimilation and metabolic costs: modelled growth rates were typically one-tenth of theoretical maximum model growth rates and showed large variation for any given body mass (Figure S3). This variation resulted from the many other factors that affected growth rate, most notably the abundance and body masses of potential prey and predators competing for the same prey.

Predicted mortality rates showed a negative power-law relationship with body mass (Figure 3C), qualitatively consistent with empirical data, although the relationship was generally shallower and absolute rates were higher (Table S4). Finally, predicted reproductive rates in the terrestrial realm showed a weak positive power-law relationship with body mass, broadly consistent with empirical estimates (Figure 3D, Table S4), whereas predicted reproductive rates in the marine realm were weakly negative. Predicted reproductive rates were substantially more variable than the empirical data (Figure 3D).

For the four focal grid cells, terrestrial ecosystems exhibited a pyramid of biomass across the different trophic levels (Figure 4A), which is widely accepted to be present in terrestrial systems [80]. The predicted herbivore biomass as a proportion of producer biomass (0.98%) was consistent with empirical terrestrial estimates (median value = 0.93%) (Table S5) [73]. However, predicted biomass of large-bodied herbivores was four to six times higher than estimated from a field study [72]. Consistent with current opinion and observations [78],[81]–[84], marine ecosystems exhibited an inverted pyramid of biomass structure [73],[82], with the highest biomasses in the highest trophic levels (Figure 4C). Marine systems exhibited relatively faster flow rates of productivity from autotrophs to higher trophic levels compared with terrestrial ecosystems—and at rates much higher than those estimated to date (Figure 4A and 4C) [85]. Predicted herbivore biomass as a proportion of producer biomass for the marine grid cells was much higher than in terrestrial ecosystems (63%), and of a similar magnitude to empirical estimates (median value = 52%) (Table S5) [73].

Expressed as abundance rather than biomass, and consistent with theoretical expectations [86],[87], trophic pyramids were not inverted in either realm: that is, communities contained a greater number of herbivores than carnivores (Figure S4).However, omnivores were more abundant than herbivores, by a factor of 3 in the terrestrial cell and by two orders of magnitude in the marine cell. This was because the average size of omnivores was smaller than the average size of herbivores or carnivores.

In both terrestrial and marine grid cells, densities of organisms showed a negative, approximately log-linear relationship with individual body mass (Figure 4B and 4D), the slopes of which fell within observed ranges in fish community assemblages from some sources (Figure S5) [75], although not from others (Table S6) [74].

Predicted ratios of heterotroph to autotroph biomass were broadly consistent with empirical estimates in many of the terrestrial and marine locations (Figure 5). For terrestrial ecosystems, the model and empirical data were in closest agreement in the two savannah ecosystems (Figure 5J and N). For the other ecosystem types—desert, tundra, deciduous forest, and tropical forest—there was lower agreement between model and empirical estimates of trophic structure, with modelled heterotroph to autotroph biomass ratios generally greater than empirical estimates, sometimes by orders of magnitude (Figure 5).

Modelled ecosystems in the marine realm generally showed closer agreement with empirical estimates than in the terrestrial realm. However, in both Santa Monica Bay, San Francisco (Figure 5A), and the Swartkops estuary in South Africa (Figure 5F), median modelled herbivore to autotroph biomass ratios were three orders of magnitude larger than empirical estimates.

The structure of both marine and terrestrial ecosystems showed marked changes along a gradient of increasing NPP (Figure 6). Marine ecosystems showed increasing biomass for all three heterotroph types (carnivores, omnivores, and herbivores), and flat then declining and highly variable autotroph standing biomass (Figure 6A). Terrestrial ecosystems also showed a trend of increasing heterotrophic biomass with productivity (Figure 6B). Carnivores increased in biomass with productivity more steeply than for other trophic levels, and were entirely absent from the lowest productivity desert ecosystem. In the most productive terrestrial ecosystems, carnivores typically had higher biomass densities than omnivores.

Global patterns of total heterotroph biomass, averaged across the final year of the simulation (Figure 7A), were similar to patterns of primary productivity (Figure S6). In the marine realm, our modelled estimate of median heterotroph biomass density was 167,147 kg km⁻², approximately 7–30 times greater than previous modelled estimates, which range from 5,500–25,000 kg km⁻² [76],[88]–[90]. However, a recent empirical study into mesopelagic fish biomass suggests that some fish biomass densities are likely to be an order of magnitude higher than these previous estimates [90] and so our prediction is plausible. Global median ratios of herbivore to primary producer biomass estimated by the model were 0.8% for terrestrial and 189% for marine ecosystems, compared to 0.93% and 52% for empirical estimates (Table S5) [73]. Our modelled estimate of median total terrestrial heterotroph biomass density was 151,089 kg km⁻², a prediction which, as far as we are aware, has never been made previously.

In the marine realm, high heterotroph biomass is predicted in upwelling systems and areas of high annual productivity (e.g., the North Atlantic). In the terrestrial realm, predicted heterotroph biomass was highest in naturally forested areas and lowest in deserts. There was no clear latitudinal gradient of biomass density in either system, but latitudinal variability was substantially greater in the terrestrial realm. At subtropical latitudes in the northern hemisphere in the terrestrial realm, there was a band in which carnivores had higher biomass density than omnivores, whereas elsewhere omnivores had greater biomass density. This switch in the relative dominance of omnivores in the northern hemisphere coincided with a decline in mean herbivore biomass density. No discernible decline in mean herbivore biomass densities was observed at subtropical latitudes in the terrestrial southern hemisphere.

Not all grid cells conformed to the pattern of inverted biomass pyramids in the marine realm and noninverted biomass pyramids in the terrestrial realm. Out of all terrestrial cells modelled, 9% were predicted with more omnivore than herbivore biomass and 46% with greater carnivore than omnivore biomass (Figure S7). Conversely in the marine realm, 12% of cells had less herbivore than autotroph biomass, 10% of cells had less omnivore than herbivore biomass, and 0.4% of cells had less carnivore than omnivore biomass (Figure S7). The spatial extent and frequency of cells in the marine realm with noninverted pyramids was significantly higher when dispersal was prevented from occurring (Figures S8 and S9). There was also evidence that noninverted trophic structure was more likely when the turnover rate of phytoplankton was lower and when the rate and efficiency with which matter is transferred through the system were reduced (Figure S10).

The model reached a dynamic steady state in all grid cells, with the persistence of all trophic levels, which is expected in the absence of perturbation [91]. Real ecosystems are not expected to exhibit such stable dynamics because they are subject to numerous interannual environmental fluctuations and perturbations. These were not incorporated for this study, but could be in the future. The global simulations (which included dispersal) converged to equilibria with similar characteristics to the focal grid cells, although with higher biomass densities. The higher biomass must have been a result of dispersal, as this is the only difference between the focal-cell simulations and may be owing to a rescue effect from neighbouring grid cells. Nonetheless, the similarity of the simulations with and without dispersal provides support for the use of isolated focal grid cells in more detailed studies.

One form of instability in the dynamics was the large temporal variation in biomasses in the high-productivity, seasonal marine grid cell. Plankton and zooplankton are known to exhibit marked biomass fluctuations, but the modelled variation was much greater, and has a different temporal signature (chaotic variation within the productive season, whereas real cycles are repeatable year to year). This appears to be an artefact of the long time step used, allowing massive unconstrained changes in biomass over a single time step. Model simulations carried out using a daily time step (only feasible over shorter time periods and for single grid cells due to the computational demand) produced substantially more stable dynamics. However, the mean predicted biomass was similar between simulations using different time steps, suggesting that most of the properties of our results are robust. Nevertheless, future research is needed into numerical and computational methods for more appropriately simulating small organisms in GEMs (see Table 7 and Text S2).

Many aspects of the life history of individuals emerge from the underlying ecological processes and interactions with other organisms. For example, growth rates are determined by a combination of food assimilation rates and metabolic losses, which themselves depend on the abundance and properties of the other individuals at the location, and are also constrained by the maximum possible rate of assimilation and environmentally determined metabolic rate. Modelled growth rates varied widely among cohorts, between the maximum and minimum theoretically possible rates (Figure S3), but showed good correspondence with observed values (Figure 3A). Predicted mortality rates were much higher than empirically observed rates, especially for larger organisms (Figure 3C). This may reflect a mismatch with the data, as discussed below; in this case, empirical mortality rates were observed in laboratory conditions in the absence of predation mortality. Comparing the empirical data and model predictions at a higher level of resolution, for example within functional groups or biomes, might help us to better diagnose discrepancies in the future.

Growth rates were slightly faster and times to maturity slightly shorter than those from observation. Modelled rates of biomass transfer calculated for the two focal grid cells were higher than empirically observed rates, particularly in the marine realm (Figure 4) [85]. At least in part, this discrepancy may result from a bias in the data toward larger organisms, leading to empirical estimates underestimating real biomass flow rates.

Similarly, the negative log-linear relationship between individual body mass and organism density is consistent with ecological theory [92], although uni- [93],[94] or multimodal [95],[96] relationships have been observed. The modelled slopes were shallower than empirical estimates for a log-linear relationship, which again might indicate that turnover rates in the model were overestimated, causing greater suppression of smaller organism abundance and higher abundance of larger organisms than in real ecosystems.

Another difference between the model and data was that the modelled biomass of large-bodied herbivores was several times higher than observations [72]. Modelled ratios of herbivore to autotroph biomass were also higher than empirical estimates in most cases, especially for terrestrial ecosystems. There are three potential explanations for this. The first is that herbivores, like predators, are eating too efficiently in the model, which might result from incorrect functional forms or missing processes. The second explanation is that because the available data are extremely sparse, the data are thus potentially not representative of the system. Thirdly, human impacts might have reduced large herbivore biomass in the empirical data compared to the undisturbed ecosystem assumed in these simulations of the model.

The closer match between modelled and empirical trophic structure for marine and savannah ecosystems, compared to forests, might be because these ecosystems conform much better to the assumption that individuals are well mixed. This assumption implies that herbivores can find all plant material and predators can find all prey. In all ecosystems, but most obviously in forests, many leaves are physically out of reach of many herbivores, and many prey are able to find refuge from predation. This may act to slow down biomass turnover in forests in comparison to the ocean and savannas, in a way that cannot be captured by a model that assumes complete mixing within a grid cell. On the other hand, the discrepancy could also be caused by incomplete empirical data. It is easier to estimate whole-ecosystem properties in savannas (where animals tend to be highly visible) and in the ocean (which can be trawled with nets) compared with forests. Alternatively, the terrestrial plant model might be inaccurately capturing the allocation of productivity to structural or nonstructural matter at these specific forest sites. However, this appears less likely, as the allocation function of this model has been rigorously constrained using a global dataset, and evaluation shows the model predicts well for this property [36]. We note, however, that at finer, site-level scales, plant allocation strategies will certainly be more heterogeneous and will certainly be different from the larger scale average predicted by the global model.

It is important to note that differences between the marine and terrestrial realms were not imposed on the model as top-down limits on the structure of ecosystems but rather emerged from individual-scale ecology. A necessarily different set of representative functional groups was defined for the marine environment compared to the terrestrial environment, but all functional groups in the model followed the same fundamental ecological functions. The only other encoded differences between marine and terrestrial cohorts were the proportion of total autotroph biomass available for consumption by a given herbivore cohort, the different optimal prey body sizes for predators, and the assumption that marine ectotherms are not thermally restricted in their capacity to function. The primary cause of the much lower ratio of herbivore biomass to autotroph biomass in the focal terrestrial cells versus in the oceans was the allocation by terrestrial plants of primary productivity to structural tissues, which are inedible to all herbivores in the model (Figure S11). This assumption probably made it more likely that terrestrial cells would exhibit a conventional pyramid of biomass structure. However, the model predicted considerable variation in the shape of the trophic biomass pyramid across terrestrial and marine cells, including an inverted structure in some terrestrial cells and a noninverted structure in some marine cells (Figure S7).

The modelled global estimates of biomass density represent the first attempt to assess the scaling of ecosystem properties from individuals to communities at a global level, and to apply a general ecological modelling methodology consistently across both the marine and terrestrial realms.

Some of these properties have been estimated previously in specific locations, but none have been estimated globally using mechanistic models (although marine animal biomass and biomass densities have been predicted mechanistically [76],[88],[89]). In addition, we have calculated emergent properties that are, as far as we are aware, unprecedented (Table 8), and we discuss these below.

In developing the first global GEM, our strategy was to start with a “simple” model that can be improved later. To keep it simple, we excluded numerous aspects of ecology—some of which are captured by existing models of particular ecosystems [14],[15]. Adding this ecology back into our model would, arguably, make it more realistic. Then again, attempting to include all known ecological processes occurring in every ecosystem around the world would not only be completely impractical but would also be excessive for most of the purposes for which a GEM is intended. Thus, we would expect the set of ecological processes represented in GEMs to evolve over time and to depend on the ways in which GEMs come to be used. Moreover, there are several other important ways in which our model could be improved, as outlined in Table 7, and discussed below.

Our model is the first step towards the development of a more ecologically refined GEM (and GEMs) that occupies a very different niche to the more specialised modelling approaches that have been used to inform biodiversity policy to date, and is more akin to the global climate models that inform global climate science and policy [8]. Our GEM necessarily made numerous simplifying assumptions in order to capture a broad range of ecological processes and organisms. This nevertheless provides a new approach to answering important outstanding questions in ecology and with which to begin to ask entirely new questions—questions that require an integrated, mechanistic understanding of whole ecosystems; the connections among them; and their response to environmental variation and natural or human perturbations. In the following sections, we briefly discuss how GEMs could be used to inform ecological science and conservation policy.

We have developed the first General Ecosystem Model (GEM) that synthesizes fundamental aspects of ecological theory, to model, simulate, and predict how the structure and function of ecosystems at multiple scales emerges from the biology and interactions of individual organisms. Our model matches a broad range of empirical data well, to a first approximation. Where it departs from either observations or expectations, it does so in ways that afford interesting avenues for future ecological research, future model development, and empirical data collection. It also provides a set of novel predictions that can be independently assessed. We anticipate that this will be the beginning of a long-term exploration of GEMs, and we call upon ecologists, biologists, mathematicians, and computer scientists to join in creating a modelling community surrounding GEMs that can catalyse the development of more realistic, sophisticated, yet better understood models of ecosystems worldwide. Our hope is that GEMs will form the basis of new science in ecology and, in particular, science that proves actionable to those charged with conserving the biosphere on which we all depend.