Wetland bird species have been declining in population size worldwide as climate warming and land-use change affect their suitable habitats. We used species distribution models (SDMs) to predict changes in range dynamics for 64 non-passerine wetland birds breeding in Europe, including range size, position of centroid, and margins. We fitted the SDMs with data collected for the first European Breeding Bird Atlas and climate and land-use data to predict distributional changes over a century (the 1970s–2070s). The predicted annual changes were then compared to observed annual changes in range size and range centroid over a time period of 30 years using data from the second European Breeding Bird Atlas. Our models successfully predicted ca. 75% of the 64 bird species to contract their breeding range in the future, while the remaining species (mostly southerly breeding species) were predicted to expand their breeding ranges northward. The northern margins of southerly species and southern margins of northerly species, both, predicted to shift northward. Predicted changes in range size and shifts in range centroids were broadly positively associated with the observed changes, although some species deviated markedly from the predictions. The predicted average shift in core distributions was ca. 5 km yr⁻¹ towards the north (5% northeast, 45% north, and 40% northwest), compared to a slower observed average shift of ca. 3.9 km yr⁻¹. Predicted changes in range centroids were generally larger than observed changes, which suggests that bird distribution changes may lag behind environmental changes leading to ‘climate debt’. We suggest that predictions of SDMs should be viewed as qualitative rather than quantitative outcomes, indicating that care should be taken concerning single species. Still, our results highlight the urgent need for management actions such as wetland creation and restoration to improve wetland birds’ resilience to the expected environmental changes in the future.

Detailed maps of vegetation facilitate spatial conservation planning. Such information can be difficult to map from remotely sensed data with the detail (thematic resolution) required for ecological applications. For grass-dominated habitats in the South-East of the UK, it was evaluated which of the following choices improved classification accuracies at various thematic resolutions: 1) Hyperspectral data versus data with a reduced spectral resolution of eight and 13 bands, which were simulated from the hyperspectral data. 2) A vegetation classification system using a detailed description of vegetation (sub)-communities (the British National Vegetation Classification, NVC) versus clustering based on the dominant plant species (Dom-Species). 3) The month of imagery acquisition. Hyperspectral data produced the highest accuracies for vegetation away from edges using the NVC (84-87%). Simulated 13-band data performed also well (83-86% accuracy). Simulated 8-band data performed poorer at finer thematic resolutions (77-78% accuracy), but produced accuracies similar to those from simulated 13-band or hyperspectral data for coarser thematic resolutions (82-86%). Grouping vegetation by NVC (84-87% accuracy for hyperspectral data) usually achieved higher accuracies compared to Dom-Species (81-84% for hyperspectral data). Highest discrimination rates were achieved around the time vegetation was fully developed. The results suggest that using a detailed description of vegetation (sub)-communities instead of one based on the dominating species can result in more accurate mapping. The NVC may reflect differences in site conditions in addition to differences in the composition of dominant species, which may benefit vegetation classification. The results also suggest that using hyperspectral data or the 13-band multispectral data can help to achieve the fine thematic resolutions that are often required in ecological applications. Accurate vegetation maps with a high thematic resolution can benefit a range of applications, such as species and habitat conservation.

When one or several classes are much less prevalent than another class (unbalanced data), class error rates and variable importances of the machine learning algorithm random forest can be biased, particularly when sample sizes are smaller, imbalance levels higher, and effect sizes of important variables smaller. Using simulated data varying in size, imbalance level, number of true variables, their effect sizes, and the strength of multicollinearity between covariates, we evaluated how eight versions of random forest ranked and selected true variables out of a large number of covariates despite class imbalance. The version that calculated variable importance based on the area under the curve (AUC) was least adversely affected by class imbalance. For the same number of true variables, effect sizes, and multicollinearity between covariates, the AUC variable importance ranked true variables still highly at the lower sample sizes and higher imbalance levels at which the other seven versions no longer achieved high ranks for true variables. Conversely, using the Hellinger distance to split trees or downsampling the majority class already ranked true variables lower and more variably at the larger sample sizes and lower imbalance levels at which the other algorithms still ranked true variables highly. In variable selection, a higher proportion of true variables were identified when covariates were ranked by AUC importances and the proportion increased further when the AUC was used as the criterion in forward variable selection. In three case studies, known species–habitat relationships and their spatial scales were identified despite unbalanced data.

Global policy for future biodiversity conservation is ultimately implemented at landscape and local scales. In parallel, green infrastructure planning needs to account for socioeconomic dynamics at national and global scales. Progress towards policy goals must, in turn, be evaluated at the landscape scale. Evaluation tools are often environmental quality indicators. How developments of different organism groups will relate to developments of these indicators is unclear. We evaluated three management scenarios for a 100,000 hectare boreal forest landscape in the coming 100 years in terms of their effects on the future habitat suitability/occupancy of four bird species, six wood‐decaying fungi and one lichen, most of them red‐listed. The scenarios optimize financial returns and account for downscaled projected global demand of wood given a middle‐of‐the road Shared Socioeconomic Pathway (SSP2). We contrast a reference scenario meeting the wood demand against an economy scenario with no upper harvest limit, and a green infrastructure scenario optimizing the levels of environmental indicators. Environmental indicators generally reached the highest and lowest levels in the green infrastructure and economy scenarios, respectively. Most indicators increased further in set‐asides. The profit was 14% lower in the green infrastructure and 2% higher in the economy than in the reference scenario. In the green infrastructure scenario, the species increased on average by 135%, followed by the reference scenario (+65%), and the economy scenario (+47%). All bird species increased in the green infrastructure scenario, while in the other scenarios, only hazel grouse increased and Siberian tit instead decreased. Most fungi increased in the production forest of the green infrastructure scenario but decreased in the economy scenario. All increased in set‐asides. In all scenarios, the lichen Lobaria pulmonaria increased, owing to host tree retention. Synthesis and applications. Effects of global socioeconomic developments can be downscaled and accounted for in planning landscape‐scale forest and conservation management. Accounting for indicators of environmental quality identified forest management scenarios for reaching targets on both revenue and conservation. Rebuilding green infrastructure in the production forest was possible at a relatively minor economic cost and to the benefit of species of conservation concern.

Aim: To evaluate the utility of opportunistic data from citizen science programmes for forecasting species distributions against forecasts with a model of individual‐based population dynamics.Location: Sweden.Methods: We evaluated whether alternative methods for building habitat suitability models (HSMs) based on opportunistic data from citizen science programmes produced forecasts that were consistent with forecasts from two benchmark models: (1) a HSM based on data from systematic monitoring and (2) an individual‐based model for spatially explicit population dynamics based on empirical demographic and movement data. We forecasted population numbers and habitat suitability for three realistic, future forest landscapes for a forest bird, the Siberian jay (Perisoreus infaustus). We ranked simulated forest landscapes with respect to their benefits to Siberian jays for each modelling method and compared the agreement of the rankings among methods.Results: Forecasts based on our two benchmark models were consistent with each other and with expectations based on the species’ ecology. Forecasts from logistic regression models based on opportunistic data were consistent with the benchmark models if species detections were combined with high‐quality inferred absences derived via retrospective interviews with experienced “super‐reporters.” In contrast, forecasts with three other widely used methods were inconsistent with the benchmark models, sometimes with misleading rankings of future scenarios.Main conclusions: Our critical evaluation of alternative HSMs against a spatially explicit IBM demonstrates that information on species absences critically improves forecasts of species distributions using opportunistic data from citizen science programmes. Moreover, high‐quality information on species absences can be retrospectively inferred from surveys of the consistency of reporting of individual species and the identification skills of participating reporters. We recommend that citizen science projects incorporate procedures to evaluate reporting behaviour. Inferred absences may be especially useful for improving forecasts for species and regions poorly covered by systematic monitoring schemes.