Geochemical and environmental assessment of potential effects of trace elements in soils, water, and sediments around abandoned mining sites in the northern Iberian Peninsula (NW Spain).

The mineral deposits and traces in the Iberian Peninsula are very numerous and of varied mineralogy. This study aimed to analyze the geochemical and environmental changes detected in soil, water, and sediments around the La Sierre mine, and to determine if contamination persists over time. The concentrations of ten trace elements (As, Co, Cr, Cu, Fe, Mn, Ni, Pb, V, Zn) were measured in 20 soil samples, 10 water samples, and 6 sediment samples, sampling at the most affected points.

Multilayer perceptron architecture optimization using parallel computing techniques.

The objective of this research was to develop a methodology for optimizing multilayer-perceptron-type neural networks by evaluating the effects of three neural architecture parameters, namely, number of hidden layers (HL), neurons per hidden layer (NHL), and activation function type (AF), on the sum of squares error (SSE). The data for the study were obtained from quality parameters (physicochemical and microbiological) of milk samples. Architectures or combinations were organized in groups (G1, G2, and G3) generated upon interspersing one, two, and three layers.