全球变化知识资源中心

Dams provide water supply, flood protection, and hydropower generation benefits, but also harm native species by altering the natural flow regime, and degrading the aquatic and riparian habitats. In the present study, which comprised the Douro River basin located in the North of Portugal, the cost-benefit assessment of dams was based upon a balance between the touristic benefits of a dammed Douro, and the ecological benefits of less fragmented Douro sub-catchments. Focused on four sub-catchments (Sabor, Tamega, Coa and Corgo), a probabilistic stream connectivity model was developed and implemented to recommend priorities for dam removal, where this action could significantly improve the movement of potadromous fish species along the local streams. The proposed model accounts for fish movement across the dam or weir (permeability), which is a novel issue in connectivity models. However, before any final recommendation on the fate of a dam or weir, the connectivity results will be balanced with other important socio-economic interests. While implementing the connectivity model, an inventory of barriers (dams and weirs) was accomplished through an observation of satellite images. Besides identification and location of any obstacles, the inventory comprised the compilation of data on surrounding land use, reservoir water use, characteristics of the riparian gallery, and permeability conditions for fish, among others. All this information was stored in a geospatial dataset that also included geographical information on the sub-catchment drainage network. The linear (drainage network) and point (barriers) source data were processed in a computer program that provided or returned numbers for inter-barrier stream lengths (habitat), and the barrier permeability. These numbers were finally used in the same computer program to calculate a habitat connector index, and a link improvement index, used to prioritize dam removal based upon structural connectivity criteria. The results showed that habitat patch connectivity in the Sabor, Tamega and Coa sub-catchments is not dramatically affected by the installed obstacles, because most link improvement values were generally low. For the opposite reason, in the Corgo sub-catchment, obstacles may constitute a relatively higher limitation to connectivity, and in this case the removal of eight obstacles could significantly improve this connectivity. Using the probabilistic model of structural connectivity, it was possible to elaborate a preliminary selection of dams/weirs that critically limit stream connectivity, and that will be the focus of field hydraulic characterization to precisely determine fish movement along the associated river stretches. Future work will also include the implementation of a multi-criteria decision support system for dam removal or mitigation of the critical structures, as well to define exclusion areas for additional obstacles.