What drives the ecological quality of surface waters? A review of 11 predictive modeling tools

What policy is needed to ensure that good-quality water is available for both people's needs and the environment? The EU Water Framework Directive (WFD), which came into force in 2000, established a framework for the assessment, management, protection and improvement of the status of water bodies across the European Union. However, recent reviews show that the ecological status of the majority of surface waters in the EU does not meet the requirement of good status. Thus, it is an important question what measures water management authorities should take to improve the ecological status of their water bodies. To find concrete answers, several institutes in the Netherlands cooperated to develop a software tool, the WFD Explorer, to assist water managers in selecting efficient measures. This article deals with the development of prediction tools that allow one to calculate the effect of restoration and mitigation measures on the biological quality, expressed in terms of Ecological Quality Ratios (EQRs). To find the ideal modeling tool we give a review of 11 predictive models: 10 models from the field of Machine Learning and, additionally, the Multiple Regression model. We present our results in terms of a 'prediction-interpretation competition'. All these models were tested in a multiple-stressor setting: the values of 15 stressors (or steering factors) are available to predict the EQR values of four biological quality elements (phytoplankton, other aquatic flora, benthic invertebrates and fish). Analyses are based on 29 data sets from various water clusters (streams, ditches, lakes, channels). All 11 models were ranked by their predictive performance and their level of model transparency. Our review shows a trade-off between these two aspects. Models that have the best EQR prediction performance show non-transparent model structures. These are Random Forest and Boosting. However, models with low prediction accuracies show transparent response relationships between EQRs on the one hand and individual steering factors on the other hand. These models are Multiple Regression, Regression Trees and Product Unit Neural Networks. To acknowledge both aspects of model quality - predictive power and transparency - we recommend that models from both groups are implemented in the WFD Explorer software.

Projecting terrestrial biodiversity intactness with GLOBIO 4

Scenario-based biodiversity modelling is a powerful approach to evaluate how possible future socio-economic developments may affect biodiversity. Here, we evaluated the changes in terrestrial biodiversity intactness, expressed by the mean species abundance (MSA) metric, resulting from three of the shared socio-economic pathways (SSPs) combined with different levels of climate change (according to representative concentration pathways [RCPs]): a future oriented towards sustainability (SSP1xRCP2.6), a future determined by a politically divided world (SSP3xRCP6.0) and a future with continued global dependency on fossil fuels (SSP5xRCP8.5). To this end, we first updated the GLOBIO model, which now runs at a spatial resolution of 10 arc-seconds (~300 m), contains new modules for downscaling land use and for quantifying impacts of hunting in the tropics, and updated modules to quantify impacts of climate change, land use, habitat fragmentation and nitrogen pollution. We then used the updated model to project terrestrial biodiversity intactness from 2015 to 2050 as a function of land use and climate changes corresponding with the selected scenarios. We estimated a global area-weighted mean MSA of 0.56 for 2015. Biodiversity intactness declined in all three scenarios, yet the decline was smaller in the sustainability scenario (-0.02) than the regional rivalry and fossil-fuelled development scenarios (-0.06 and -0.05 respectively). We further found considerable variation in projected biodiversity change among different world regions, with large future losses particularly for sub-Saharan Africa. In some scenario-region combinations, we projected future biodiversity recovery due to reduced demands for agricultural land, yet this recovery was counteracted by increased impacts of other pressures (notably climate change and road disturbance). Effective measures to halt or reverse the decline of terrestrial biodiversity should not only reduce land demand (e.g. by increasing agricultural productivity and dietary changes) but also focus on reducing or mitigating the impacts of other pressures.