Accurately predicting terrestrial ecosystem responses to climate change is crucial for addressing global challenges. This relies on mechanistic modelling of ecosystem processes through Land Surface Models (LSMs). Despite their importance, LSMs face significant uncertainties due to poorly constrained parameters, especially in carbon cycle predictions. This paper reviews the progress made in using data assimilation (DA) for LSM parameter optimisation, focusing on carbon-water-vegetation interactions, as well as discussing the technical challenges faced by the community. These challenges include identifying sensitive model parameters and their prior distributions, characterising errors due to observation biases and model-data inconsistencies, developing observation operators to interface between the model and the observations, tackling spatial and temporal heterogeneity as well as dealing with large and multiple datasets, and including the spin-up and historical period in the assimilation window. We then outline how machine learning (ML) can help address these issues, proposing different avenues for future work that integrate ML and DA to reduce uncertainties in LSMs. We conclude by highlighting future priorities, including the need for international collaborations, to fully leverage the wealth of available Earth observation datasets, harness machine learning advances, and enhance the predictive capabilities of LSMs.

Near-term ecological forecasts provide resource managers advance notice of changes in ecosystem services, such as fisheries stocks, timber yields, or water and air quality. Importantly, ecological forecasts can identify where uncertainty enters the forecasting system, which is necessary to refine and improve forecast skill and guide interpretation of forecast results. Uncertainty partitioning identifies the relative contributions to total forecast variance (uncertainty) introduced by different sources, including specification of the model structure, errors in driver data, and estimation of initial state conditions. Uncertainty partitioning could be particularly useful in improving forecasts of high-density cyanobacterial events, which are difficult to predict and present a persistent challenge for lake managers. Cyanobacteria can produce toxic or unsightly surface scums and advance warning of these events could help managers mitigate water quality issues. Here, we calibrate fourteen Bayesian state-space models to evaluate different hypotheses about cyanobacterial growth using data from eight summers of weekly cyanobacteria density samples in an oligotrophic (low nutrient) lake that experiences sporadic surface scums of the toxin-producing cyanobacterium, Gloeotrichia echinulata. We identify dominant sources of uncertainty for near-term (one-week to four-week) forecasts of G. echinulata densities over two years. Water temperature was an important predictor in calibration and at the four-week forecast horizon. However, no environmental covariates improved over a simple autoregressive (AR) model at the one-week horizon. Even the best fit models exhibited large variance in forecasted cyanobacterial densities and often did not capture rare peak density occurrences, indicating that significant explanatory variables in calibration are not always effective for near-term forecasting of low-frequency events. Uncertainty partitioning revealed that model process specification and initial conditions uncertainty dominated forecasts at both time horizons. These findings suggest that observed densities result from both growth and movement of G. echinulata, and that imperfect observations as well as spatial misalignment of environmental data and cyanobacteria observations affect forecast skill. Future research efforts should prioritize long-term studies to refine process understanding and increased sampling frequency and replication to better define initial conditions. Our results emphasize the importance of ecological forecasting principles and uncertainty partitioning to refine and understand predictive capacity across ecosystems.

Forecasts of forest responses to climate variability are governed by climate exposure and ecosystem sensitivity, but ecosystem model projections and process representations are under-constrained by data at multidecadal and longer timescales. Here, we assess ecosystem sensitivity to centennial-scale hydroclimate variability, by comparing dendroclimatic and pollen-inferred reconstructions of drought, forest composition and biomass for the last millennium with five ecosystem model simulations. In both observations and models, spatial patterns in ecosystem responses to hydroclimate variability are strongly governed by ecosystem sensitivity rather than climate exposure. Ecosystem sensitivity was highest in simpler models and higher than observations, suggesting that interactions among biodiversity, demography, and ecophysiology processes dampen the sensitivity of forest composition and biomass to climate variability and change. By integrating ecosystem models with observations from timescales extending beyond the instrumental record, we can better understand and forecast the mechanisms regulating forest sensitivity to climate variability in a complex and changing world.