Use of Noise to Augment Training Data: A Neural Network Method of Mineral–Potential Mapping in Regions of Limited Known Deposit Examples

One of the main factors that affects the performance of MLP neural networks trained using the backpropagation algorithm in mineral-potential mapping isthe paucity of deposit relative to barren training patterns. To overcome this problem, random noise is added to the original training patterns in order to create additional synthetic deposit training data. Experiments on the effect of the number of deposits available for training in the Kalgoorlie Terrane orogenic gold province show that both the classification performance of a trained network and the quality of the resultant prospectivity map increasesignificantly with increased numbers of deposit patterns. Experiments are conducted to determine the optimum amount of noise using both uniform and normally distributed random noise. Through the addition of noise to the original deposit training data, the number of deposit training patterns is increased from approximately 50 to 1000. The percentage of correct classifications significantly improves for the independent test set as well as for deposit patterns in the test set. For example, using ±40% uniform random noise, the test-set classification performance increases from 67.9% and 68.0% to 72.8% and 77.1% (for test-set overall and test-set deposit patterns, respectively). Indices for the quality of the resultant prospectivity map, (i.e. D/A, D × (D/A), where D is the percentage of deposits and A is the percentage of the total area for the highest prospectivity map-class, and area under an ROC curve) also increase from 8.2, 105, 0.79 to 17.9, 226, 0.87, respectively. Increasing the size of the training-stop data set results in a further increase in classification performance to 73.5%, 77.4%, 14.7, 296, 0.87 for test-set overall and test-set deposit patterns, D/A, D × (D/A), and area under the ROC curve, respectively.     

Use of Fuzzy Membership Input Layers to Combine Subjective Geological Knowledge and Empirical Data in a Neural Network Method for Mineral-Potential Mapping

Use of GIS layers, in which the cell values represent fuzzy membership variables, is an effective method of combining subjective geological knowledge with empirical data in a neural network approach to mineral-prospectivity mapping. In this study, multilayer perceptron (MLP), neural networks are used to combine up to 17 regional exploration variables to predict the potential for orogenic gold deposits in the form of prospectivity maps in the Archean Kalgoorlie Terrane of Western Australia. Two types of fuzzy membership layers are used. In the first type of layer, the statistical relationships between known gold deposits and variables in the GIS thematic layer are used to determine fuzzy membership values. For example, GIS layers depicting solid geology and rock-type combinations of categorical data at the nearest lithological boundary for each cell are converted to fuzzy membership layers representing favorable lithologies and favorable lithological boundaries, respectively. This type of fuzzy-membership input is a useful alternative to the 1-of-N coding used for categorical inputs, particularly if there are a large number of classes. Rheological contrast at lithological boundaries is modeled using a second type of fuzzy membership layer, in which the assignment of fuzzy membership value, although based on geological field data, is subjective. The methods used here could be applied to a large range of subjective data (e.g., favorability of tectonic environment, host stratigraphy, or reactivation along major faults) currently used in regional exploration programs, but which normally would not be included as inputs in an empirical neural network approach.     

Aspects of the loss-on-ignition (LOI) technique in the context of clay-rich, glaciolacustrine sediments

The loss‐on‐ignition (LOI) technique for organic matter determination is evaluated with reference to clay‐rich, glaciolacustrine sediments. Examples of the use of LOI in glaciolacustrine literature are inconsistent in their methodology, and standardisation is called for. Problems with application of the technique to glaciolacustrine sediments stem mainly from the effects of additional weight loss due to release of structurally bound water and exposure time to ignition temperatures. Exposure time should be increased from 1 hour to 2.5 hours in the light of significant additional weight loss occurring between 2 and 2.5 hours in clay‐rich samples. The reason for this sudden increase in LOI after 2 hours (up to 86% of total LOI in some cases) appears to be the build‐up of a distinct surface crust during heating that insulates the core of the sample from ignition temperatures. Some time between 2 and 2.5 hours, the crust breaks down and exposes the sample core to ignition temperatures, increasing weight loss significantly. Overestimation of LOI due to loss of structural water is thought to be insignificant. Replicates of LOI at 550 and 1000°C in non‐calcareous, clay‐rich (>40%) sediments, show differences of <0.25%, which, for the purpose of inferring broad changes in glacier extent in lake catchments, is an acceptable error.     

Reproductive cycles of Mytilus edulis L. on the west and east coasts of Iceland

Studies evaluating the reproductive pattern of Mytilus edulis L. were conducted in western and eastern Iceland at two sites at about the same latitude but with different temperature regimes. Mussels were sampled once or sometimes twice a month during two years in Breidifjördur, western Iceland and one year at Mjoifjördur, eastern Iceland. Gonad development was monitored by microscopic observation of thin sections of the gonads. The initiation of gonad development was observed in January in Breidifjördur while in Mjoifjördur some of the animals started developing gonads in October, a month before spawning was over in the population. Spawning started in late June or July, peaked in August and continued until November at both sites. Nutrient reserve stores seemed to be limited and used for initiation of gonad development in winter but were not sufficient for maturation of the gonads. The main growth of the gonads occured in spring in conjunction with phytoplankton blooming and renewal of food resources.     

Wind velocity and sand transport on a barchan dune

We present measurements of wind velocity and sand flux performed on the windward side of a large barchan dune in Jericoacoara, northeastern Brazil. From the measured profile, we calculate the air shear stress using an analytical approximation and treat the problem of flow separation by an heuristic model. We find that the results from this approach agree well with our field data. Moreover, using the calculated shear velocity, we predict the sand flux according to well-known equilibrium relations and with a phenomenological continuum saltation model that includes saturation transients and thus allows for nonequilibrium conditions. Based on the field data and theoretical predicted results, we indicate the principal differences between saturated and nonsaturated sand flux models. Finally, we show that the measured dune moves with invariant shape and predict its velocity from our data and calculations.