Wetlands are often vital physical and social components of a country’s natural capital, as well as providers of ecosystem services to local and national communities. We performed a network analysis to prioritize Sustainable Development Goal (SDG) targets for sustainable development in iconic wetlands and wetlandscapes around the world. The analysis was based on the information and perceptions on 45 wetlandscapes worldwide by 49 wetland researchers of the Global Wetland Ecohydrological Network (GWEN). We identified three 2030 Agenda targets of high priority across the wetlandscapes needed to achieve sustainable development: Target 6.3—“Improve water quality”; 2.4—“Sustainable food production”; and 12.2—“Sustainable management of resources”. Moreover, we found specific feedback mechanisms and synergies between SDG targets in the context of wetlands. The most consistent reinforcing interactions were the influence of Target 12.2 on 8.4—“Efficient resource consumption”; and that of Target 6.3 on 12.2. The wetlandscapes could be differentiated in four bundles of distinctive priority SDG-targets: “Basic human needs”, “Sustainable tourism”, “Environmental impact in urban wetlands”, and “Improving and conserving environment”. In general, we find that the SDG groups, targets, and interactions stress that maintaining good water quality and a “wise use” of wetlandscapes are vital to attaining sustainable development within these sensitive ecosystems.

The prediction of monthly rainfall is greatly beneficial for water resources management and flood control projects. Machine learning (ML) techniques, as an increasingly popular approach, have been applied in diverse climatic regions, showing their respective superiority. On top of that, the ensemble learning model that synthesizes the advantages of different ML models deserves more attention. In this study, an ensemble learning model based on stacking approach was proposed. Four prevalent ML models, namely k-nearest neighbors (KNN), extreme gradient boosting (XGB), support vector regression (SVR), and artificial neural networks (ANN) are taken as base models. To combine the outputs from the base models, the weighting algorithm is used as second-layer learner to generate predictions. Large-scale climate indices, large-scale atmospheric variables, and local meteorological variables were used as predictors. R², RMSE and MAE, were used as evaluation metrics. The results show that the performance of base models varied among the nine stations in the Taihu Basin, while the stacking approach generally performed better than the four base models. The stacking model showed better performance in spring and winter than in summer and autumn. During wet months, the accuracy of model prediction varied more significantly. On the whole, based on performance evaluation measures, it is concluded that the proposed stacking ensemble multi-ML model can provide a flexible and reasonable prediction framework applicable to other regions.

Mining and ore excavation can cause the acidification and heavy metal pollution of downstream water systems. It can be difficult to assess the load contributions from individual mining areas, which is commonly required for environmental impact assessments. In the current study, we quantified the net impact of the unmonitored mining activities in the Zaamar Goldfield (Mongolia) on heavy metal transport in the downstream Tuul River–Selenga River–Lake Baikal water systems. We also noted that the Zaamar site shares the conditions of limited monitoring with many rapidly developing regions of the world. The heavy metal concentrations and flow data were obtained from historical measurement campaigns, long-term monitoring, and a novel field campaign. The results indicate that natural mass flows of heavy metals in dissolved form increased by an order of magnitude because of mining. Prevailing alkaline conditions in the vicinity of Zaamar can limit the dissolution, maintaining the on-site concentrations below health-risk based guideline values. However, suspended river concentrations are much higher than the dissolved concentrations. The placer gold mining at the Zaamar site has increased the total riverine mass flows of Al, As, Cu, Fe, Mn, Pb and Zn by 44.300, 30.1, 65.7, 47.800, 1.480, 76.0 and 65.0 tonnes per year respectively. We suggest that local to regional transformation and enrichment processes in combination with suspended sediment transport from numerous existing upstream mining areas contribute to high concentrations of dissolved heavy metals in downstream parts of the Selenga River, including its delta area at Lake Baikal. Furthermore, single hydrological events can increase the suspended load concentrations by at least one order of magnitude. Overall, the Selenga River Basin, which drains into Lake Baikal, should be recognised as one of the world's most impacted areas with regard to heavy metal loads, and it contributes to 1% and 3% of the world flux of dissolved Fe and Pb, respectively.

The northern Eurasian regions and Arctic Ocean will very likely undergo substantial changes during the next decades. The Arctic–boreal natural environments play a crucial role in the global climate via albedo change, carbon sources and sinks as well as atmospheric aerosol production from biogenic volatile organic compounds. Furthermore, it is expected that global trade activities, demographic movement, and use of natural resources will be increasing in the Arctic regions. There is a need for a novel research approach, which not only identifies and tackles the relevant multi-disciplinary research questions, but also is able to make a holistic system analysis of the expected feedbacks. In this paper, we introduce the research agenda of the Pan-Eurasian Experiment (PEEX), a multi-scale, multi-disciplinary and international program started in 2012 (https://www.atm.helsinki.fi/peex/). PEEX sets a research approach by which large-scale research topics are investigated from a system perspective and which aims to fill the key gaps in our understanding of the feedbacks and interactions between the land–atmosphere–aquatic–society continuum in the northern Eurasian region. We introduce here the state of the art for the key topics in the PEEX research agenda and present the future prospects of the research, which we see relevant in this context.