Spatiotemporal Associations of Reservoir Nutrient Characteristics and the Invasive,Harmful Alga Prymnesium parvum in West Texas

Golden alga (Prymnesium parvum) is a harmful alga that has caused ecological and economic harm in freshwater and marine systems worldwide. In inland systems of North America, toxic blooms have nearly eliminated fish populations in some systems. Modifying nutrient profiles through alterations to land or water use may be a viable alternative for golden alga control in reservoirs. The main objective of this study was to improve our understanding of the nutrient dynamics that influence golden alga bloom formation and toxicity in west Texas reservoirs. We examined eight sites in the Upper Colorado River basin, Texas: three impacted reservoirs that have experienced repeated golden alga blooms; two reference reservoirs where golden alga is present but nontoxic; and three confluence sites downstream of the impacted and reference sites. Total, inorganic, and organic nitrogen and phosphorus and their ratios were quantified monthly along with golden alga abundance and ichthyotoxicity between December 2010 and July 2011. Blooms persisted for several months at the impacted sites, which were characterized by high organic nitrogen and low inorganic nitrogen. At impacted sites, abundance was positively associated with inorganic phosphorus and bloom termination coincided with increases in inorganic nitrogen and decreases in inorganic phosphorus in late spring. Management of both inorganic and organic forms of nutrients may create conditions in reservoirs unfavorable to golden alga.     

Modelling and Prediction of Diesel Engine Performance using Relevance Vector Machine

Diesel engines are being increasingly adopted by many car manufacturers today, yet no exact mathematical diesel engine model exists due to its highly nonlinear nature. In the current literature, black-box identification has been widely used for diesel engine modelling and many artificial neural network (ANN) based models have been developed. However, ANN has many drawbacks such as multiple local minima, user burden on selection of optimal network structure, large training data size, and over-fitting risk. To overcome these drawbacks, this article proposes to apply an emerging machine learning technique, relevance vector machine (RVM), to model and predict the diesel engine performance. The property of global optimal solution of RVM allows the model to be trained using only a few experimental data sets. In this study, the inputs of the model are engine speed, load, and cooling water temperature, while the output parameters are the brake-specific fuel consumption and the amount of exhaust emissions like nitrogen oxides and carbon dioxide. Experimental results show that the model accuracy is satisfactory even the training data is scarce. Moreover, the model accuracy is compared with that using typical ANN. Evaluation results also show that RVM is superior to typical ANN approach.