Groundwater quality, vulnerability and potential assessment in Kobo Valley development project, Ethiopia

This study deals with investigating the groundwater quality for irrigation purpose, the vulnerability of the aquifer system to pollution and also the aquifer potential for sustainable water resources development in Kobo Valley development project. The groundwater quality is evaluated up on predicting the best possible distribution of hydrogeochemicals using geostatistical method and comparing them with the water quality guidelines given for the purpose of irrigation. The hydro geochemical parameters considered are SAR, EC, TDS, Cl-, Na+, Ca++, SO4 2- and HCO3 -. The spatial variability map reveals that these parameters falls under safe, moderate and severe or increasing problems. In order to present it clearly, the aggregated Water Quality Index (WQI) map is constructed using Weighted Arithmetic Mean method. It is found that Kobo-Gerbi sub basin is suffered from bad water quality for the irrigation purpose. Waja Golesha sub-basin has moderate and Hormat Golena is the better sub basin in terms of water quality. The groundwater vulnerability assessment of the study area is made using the GOD rating system. It is found that the whole area is experiencing moderate to high risk of vulnerability and it is a good warning for proper management of the resource. The high risks of vulnerability are noticed in Hormat Golena and Waja Golesha sub basins. The aquifer potential of the study area is obtained using weighted overlay analysis and 73.3% of the total area is a good site for future water well development. The rest 26.7% of the area is not considered as a good site for spotting groundwater wells. Most of this area fall under Kobo-Gerbi sub basin.

Predicting market movement with Artificial Neural Networks

This paper presents an application of an Artificial Neural Network (ANN) to the prediction of stock market direction in the US. Using a multilayer perceptron neural network and a backpropagation algorithm for the training process, the model aims at learning the hidden patterns in the daily movement of the S&P500 to correctly identify if the market will be in a Trend Following or Mean Reversion behavior. The ANN is able to produce a successful investment strategy which outperforms the buy and hold strategy, but presents instability in its overall results which compromises its practical application in real life investment decisions.

Using artificial neural networks to generate trading signals for crude oil, copper and gold futures

In this thesis, a feed-forward, back-propagating Artificial Neural Network using the gradient descent algorithm is developed to forecast the directional movement of daily returns for WTI, gold and copper futures. Out-of-sample back-test results vary, with some predictive abilities for copper futures but none for either WTI or gold. The best statistically significant hit rate achieved was 57% for copper with an absolute return Sharpe Ratio of 1.25 and a benchmarked Information Ratio of 2.11.