This study focused on employing Linear Genetic Programming (LGP), Ensemble Empirical Mode Decomposition (EEMD), and the Self-Organizing Map (SOM) in modeling the rainfall-runoff relationship in a mid-size catchment. Models were assessed with regard to their ability to capture daily discharge at Lock and Dam 10 along the Kentucky River as well as the hybrid design of EEM-SOM-LGP to make predictions multiple time-steps ahead. Different model designs were implemented to demonstrate the improvements of hybrid designs compared to LGP as a standalone application. Additionally, LGP was utilized to gain a better understanding of the catchment in question and to assess its ability to capture different aspects of the flow hydrograph. As a standalone application, LGP was able to outperform published Artificial Neural Network (ANN) results over the same dataset, posting an average absolute relative error (AARE) of 17.118 and Nash-Sutcliff (E) of 0.937. Utilizing EEMD derived IMF runoff subcomponents for forecasting daily discharge resulted in an AARE of 14.232 and E of 0.981. Clustering the EEMD-derived input space through an SOM before LGP application returned the strongest results, posting an AARE of 10.122 and E of 0.987. Applying LGP to the distinctive low and high flow seasons demonstrated a loss in correlation for the low flow season with an under-predictive nature signified by a normalized mean biased error (NMBE) of ¡2.353. Separating the rising and falling trends of the hydrograph showed that the falling trends were more easily captured with an AARE of 8.511 and E of 0.968 compared to the rising trends AARE of 38.744 and E of 0.948. Utilizing the EEMD-SOM-LGP design to make predictions multiple-time-steps ahead resulted in a AARE of 43.365 and E of 0.902 for predicting streamflow three days ahead. The results demonstrate the effectiveness of utilizing EEMD and an SOM in conjunction with LGP for streamflow forecasting.
The notion that Lake Superior proper is inhospitable to dreissenid mussel survival has been challenged by recent finds on shipwrecks and rocky reefs in the Apostle Islands region. Motivated by concerns surrounding these finds, we conducted an intensive sampling campaign of Apostle Islands waters in 2017 to understand Dreissena prevalence and distribution. The 100-site effort combined random and targeted sites and collected zooplankton, benthos, video, environmental DNA, and supporting water quality data. We did not find settled Dreissena in any video footage or benthos samples, and quantitative PCR applied to eDNA samples was negative for Dreissena. Dreissena veligers were found in almost half the zooplankton samples but at orders of magnitude lower densities than reported from other Laurentian Great Lakes. Veligers were most prevalent around the western islands and associated with shallower depths and slightly higher phosphorus and chlorophyll, but did not spatially match known (still very localized) settled Dreissena colonies. This is the first study to conduct veliger-targeted sampling in western Lake Superior and the first to report consistent detection of veligers there. We speculate that these Apostle Islands veligers are not a new locally-spawned component of the zooplankton community, but instead are transported from an established population in the St. Louis River estuary (~100 km away) by longshore currents; i.e., low-density propagule pressure that may have been present for years. Small-mesh zooplankton data collected along a gradient from the Apostle Islands to the St. Louis River estuary and enumerated with thorough veliger searching would help elucidate these alternatives.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.