Caren Marzban

A Neural Network for Tornado Prediction Based on Doppler Radar-Derived Attributes

Abstract The National Severe Storms Laboratorys (NSSL) mesocyclone detection algorithm (MDA) is designed to scotch for patterns in Doppler velocity radar data that are associated with rotating updrafts in severe thunderstorms. These storm-scale circulations are typically precursors to tornados and severe weather in thunderstorms, yet not all circulations produce such phenomena. A neural network has been designed to diagnose which circulations detected by the NSSL MDA yield tornados. The data used both for the training and the testing of the network are obtained from the NSSL MDA. In particular, 23 variables characterizing the circulations are selected to be used as the input nodes of a feed-forward neural network. The output of the network is chosen to be the existence/nonexistence of tornados, based on ground observations. It is shown that the network outperforms the rule-based algorithm existing in the MDA, as well as statistical techniques such as discriminant analysis and logistic regression. Additio...

The ROC Curve and the Area under It as Performance Measures

Abstract The receiver operating characteristic (ROC) curve is a two-dimensional measure of classification performance. The area under the ROC curve (AUC) is a scalar measure gauging one facet of performance. In this short article, five idealized models are utilized to relate the shape of the ROC curve, and the area under it, to features of the underlying distribution of forecasts. This allows for an interpretation of the former in terms of the latter. The analysis is pedagogical in that many of the findings are already known in more general (and more realistic) settings; however, the simplicity of the models considered here allows for a clear exposition of the relation. For example, although in general there are many reasons for an asymmetric ROC curve, the models considered here clearly illustrate that an asymmetry in the ROC curve can be attributed to unequal widths of the distributions. Furthermore, it is shown that AUC discriminates well between “good” and “bad” models, but not between good models.

Scalar Measures of Performance in Rare-Event Situations

A set of 14 scalar, nonprobabilistic measures—some old, some new—is examined in the rare-event situation. The set includes measures of accuracy, association, discrimination, bias, and skill. It is found that all measures considered herein are inequitable in that they induce under- or overforecasting. One condition under which such bias is not induced (for some of the measures) is when the underlying class-conditional distributions are Gaussian (normal) and equivariant.

A Bayesian Neural Network for Severe-Hail Size Prediction

The National Severe Storms Laboratory has developed algorithms that compute a number of Doppler radar and environmental attributes known to be relevant for the detection/prediction of severe hail. Based on these attributes, two neural networks have been developed for the estimation of severe-hail size: one for predicting the severe-hail size in a physical dimension, and another for assigning a probability of belonging to one of three hail size classes. Performance is assessed in terms of multidimensional (i.e., nonscalar) measures. It is shown that the network designed to predict severe-hail size outperforms the existing method for predicting severe-hail size. Although the network designed for classifying severe-hail size produces highly reliable and discriminatory probabilities for two of the three hail-size classes (the smallest and the largest), forecasts of midsize hail, though highly reliable, are mostly nondiscriminatory.

Cluster analysis for verification of precipitation fields

Abstract A statistical method referred to as cluster analysis is employed to identify features in forecast and observation fields. These features qualify as natural candidates for events or objects in terms of which verification can be performed. The methodology is introduced and illustrated on synthetic and real quantitative precipitation data. First, it is shown that the method correctly identifies clusters that are in agreement with what most experts might interpret as features or objects in the field. Then, it is shown that the verification of the forecasts can be performed within an event-based framework, with the events identified as the clusters. The number of clusters in a field is interpreted as a measure of scale, and the final “product” of the methodology is an “error surface” representing the error in the forecasts as a function of the number of clusters in the forecast and observation fields. This allows for the examination of forecast error as a function of scale.

Artificial Intelligence Methods in the Environmental Sciences

How can environmental scientists and engineers use the increasing amount of available data to enhance our understanding of planet Earth, its systems and processes? This book describes various potential approaches based on artificial intelligence (AI) techniques, including neural networks, decision trees, genetic algorithms and fuzzy logic. Part I contains a series of tutorials describing the methods and the important considerations in applying them. In Part II, many practical examples illustrate the power of these techniques on actual environmental problems. International experts bring to life ways to apply AI to problems in the environmental sciences. While one culture entwines ideas with a thread, another links them with a red line. Thus, a red thread ties the book together, weaving a tapestry that pictures the natural data-driven AI methods in the light of the more traditional modeling techniques, and demonstrating the power of these data-based methods.

Neural Networks for Postprocessing Model Output: ARPS

Abstract The temperature forecasts of the Advanced Regional Prediction System are postprocessed by a neural network. Specifically, 31 stations are considered, and for each a neural network is developed. The nine input variables to the neural network are forecast hour, model forecast temperature, relative humidity, wind direction and speed, mean sea level pressure, cloud cover, and precipitation rate and amount. The single dependent variable is observed temperature at a given station. It is shown that the model temperature forecasts are improved in terms of a variety of performance measures. An average of 40% reduction in mean-squared error across all stations is accompanied by an average reduction in bias and variance of 70% and 20%, respectively.

A Neural Network for Damaging Wind Prediction

Abstract A neural network is developed to diagnose which circulations detected by the National Severe Storms Laboratory’s Mesocyclone Detection Algorithm yield damaging wind. In particular, 23 variables characterizing the circulations are selected to be used as the input nodes of a feed-forward, supervised neural network. The outputs of the network represent the existence/nonexistence of damaging wind, based on ground observations. A set of 14 scalar, nonprobabilistic measures and a set of two multidimensional, probabilistic measures are employed to assess the performance of the network. The former set includes measures of accuracy, association, discrimination, skill, and the latter consists of reliability and refinement diagrams. Two classification schemes are also examined. It is found that a neural network with two hidden nodes outperforms a neural network with no hidden nodes when performance is gauged with any of the 14 scalar measures, except for a measure of discrimination where the results are opp...

Cluster Analysis for Object-Oriented Verification of Fields: A Variation

Abstract In a recent paper, a statistical method referred to as cluster analysis was employed to identify clusters in forecast and observed fields. Further criteria were also proposed for matching the identified clusters in one field with those in the other. As such, the proposed methodology was designed to perform an automated form of what has been called object-oriented verification. Herein, a variation of that methodology is proposed that effectively avoids (or simplifies) the criteria for matching the objects. The basic idea is to perform cluster analysis on the combined set of observations and forecasts, rather than on the individual fields separately. This method will be referred to as combinative cluster analysis (CCA). CCA naturally lends itself to the computation of false alarms, hits, and misses, and therefore, to the critical success index (CSI). A desirable feature of the previous method—the ability to assess performance on different spatial scales—is maintained. The method is demonstrated on ...

Heterotic string modifications of Einstein's and Yang-Mills' actions

Abstract We derive the quartic curvature and quartic gauge field modifications to the low-energy effective action in the heterotic string theory by studying tree level four-point scattering amplitudes. The results provide further constraints on compactification of the ten-dimensional spacetime; in particular, it appears that Calabi-Yau manifolds do not provide consistent compactification of the heterotic string.