Jo Ann Parikh

An evolutionary system for recognition and tracking of synoptic-scale storm systems

Abstract An evolutionary system was developed for generation of complete tracks of northern midlatitude synoptic-scale storm systems based on optical flow and cloud motion analyses of global satellite-based datasets produced by the International Satellite Cloud Climatology Project (ISCCP). The tracking results were compared with low sea level pressure anomaly (SLPA) tracks obtained from the NASA Goddard Institute for Space Studies (GISS). The SLPA tracks were produced at GISS by analysis of meteorological, ground-based National Center for Environmental Prediction (NCEP) datasets. Results from the evolutionary system were also compared with results from using (a) the k -nearest neighbor rule ( k -NN) and (b) self-organizing maps (SOM) to determine correspondences between consecutive locations within a track. The consistency of our evolutionary storm tracking results with the behavior of the low sea level pressure anomaly tracks, the ability of our evolutionary system to generate and evaluate complete tracks, and the close comparison between the results obtained by the evolutionary, k -NN, and SOM analyses of the ISCCP-derived datasets at tracking steps in which proximity or optical flow information sufficed to determine movement, demonstrate the applicability and the potential of evolutionary systems for tracking midlatitude storm systems through low-resolution ISCCP cloud product datasets.

Comparison of genetic algorithm systems with neural network and statistical techniques for analysis of cloud structures in midlatitude storm systems

Abstract Cloud analyses provide information which is vital to the detection, understanding and prediction of meteorological trends and environmental changes. This paper compares statistical, neural network and genetic algorithm methods for recognition and tracking of midlatitude storm clouds in sequences of low-resolution cloud-top pressure data sets. Regions of interest are identified and tracked from one image frame to the next consecutive frame in an eight-frame sequence. Classification techniques are used to determine the relationships between regions of interest in consecutive time frames. A genetic algorithm procedure is then used to revise classifier outputs to ensure that consistency constraints are not violated.

A Lidar Collaboratory Data Management System

A data management system has been developed for the Connecticut State University (CSU) Lidar Collaboratory to facilitate user authentication, scheduling of remote lidar instrumentation control sessions, storage and retrieval of lidar datasets and generation of new data products. In addition to providing for efficient archival and retrieval of lidar data products, a major design goal of the data management system is to support collaborative, multidisciplinary, atmospheric sciences research projects. In this paper, we describe the framework of the CSU Lidar Collaboratory data management system and how the system interacts with the data acquisition and data analysis software.

Selective detection of linear features in geological remote sensing data

One of the major problems in the development of computer-assisted systems for geologic mapping is how to individualize the system to meet user needs. Ideally, the system should be responsive to specifications of desired types of output structures. Also, the system should be able to incorporate the users knowledge of regional characteristics into the feature extraction/selection and classification components. Automatic techniques for classification of remote sensing data typically require relatively large, labeled training sets which are well- organized with respect to the desired mapping between input and output patterns. The present paper focuses on the feature extraction/selection component of the system. Kohonen self- organizing feature maps in conjunction with image processing procedures for linear feature extraction are used for explorative data analysis, feature selection, and construction of exemplar patterns. The results of training Kohonen feature maps with different pattern sets and different feature combinations provide insight into the nature of pattern relationships which enables the user to develop sets of positive and negative training patterns for the classification component.

Data Analyis System Design for Lidar Experimentation

A Web-based Lidar Experimentation and Data Analysis System (LEDAS) was developed, with support from a National Science Foundation award, to support resource sharing of lidar equipment, datasets and data analysis routines and collaboration between members of the Connecticut State University System (CSUS) Lidar Collaboratory. The system allows users at different geographical locations to conduct remote sensing research and education over the Web through remote access and control of a single shared lidar system and Web-based data analysis. Users need not have any specialized instrumentation or software at their institutions, thereby making real remote sensing research available to students and faculty from institutions which may not have the internal budgets for such facilities. An original structure providing basic functionality was developed and implemented. This paper describes the second generation data analysis system which provides significant new enhancements and capabilities.

Unsupervised classification techniques for determination of storm region correspondences

The objective of this study is to compare statistical and unsupervised neural network techniques for determination of correspondences between storm system regions extracted from sequences of satellite images. Analysis was applied to the International Satellite Cloud Climatology Project (ISCCP) low resolution D1 database for selected storm systems during the period April 5 - 9, 1989. Cloud top pressure was used to delineate regions of interest and cloud optical thickness combined with spatial location was used to track regions throughout a given time sequence. The ability of the k-nearest neighbor classifier and of self-organizing maps to determine correspondences between storm regions was assessed. The two techniques generally yielded similar associations between regions of interest throughout the time sequence. Differences in final tracking results between the two techniques occurred primarily as a result of differences in the collections of points from a region in a time step t2 that corresponded to a region in an earlier time step t1. The tracking results were also compared to the results obtained at the NASA Goddard Institute for Space Studies using sea level pressure data from the National Meteorological Center (NMC). For the storm systems investigated in this study, the storm tracks exhibited the same general tracking behavior with expected variations between cloud system storm centers and low sea level pressure centers.

Application of evolutionary techniques to temporal classification of cloud systems using satellite imagery

The objective of this research is to automate the classification of the temporal behavior of storm cloud systems based on measurements derived from consecutive satellite images. The motivation behind this study is to develop improved descriptions of cloud dynamics which can be used in general circulation models for prediction of global climate change. Analysis was applied to the International Satellite Cloud Climatology Project (ISCCP) low resolution cloud top pressure database for the first six days in April 1989. A total of 296 midlatitude storm cloud components were tracked between consecutive 3-hour time frames. For each pair of components, temporal correspondence events were classified as either (1) direct, (2) merge, (3) split, or (4) reject. The reject class, which was used primarily to categorize pairs of unrelated systems, included storm cloud system dissipation and creation as well. Statistical, neural network, and evolutionary techniques were developed for finding solutions to the storm cloud correspondence problem. Evolutionary techniques applied to the problem consisted of (1) a constraint-handling hybrid evolutionary technique and (2) a genetic local search algorithm. The results demonstrate the potential of evolutionary techniques to yield meteorologically feasible solutions, given appropriate constraints, to the two- frame storm tracking problem.

Ultrasonic image texture classification using Markov random field models

Over the past several years we have been interested in the supervised classification of ultrasonic images of the liver based on quantitative texture features. Our most recent efforts are concerned with the inclusion of features computed from Markov random fields. After adding four such features to our existing model containing 17 features, we employed stepwise discriminant analysis to identify the features that could best discriminate among 184 previously classified normal and abnormal ultrasonic images. Three of the four features derived from Markov random field models were identified by stepwise discriminant analysis as being good discrimination along with 6 existing features. From these results we constructed a backpropagation neural network with an input layer consisting of 9 nodes. We found that this new model yielded slightly better results when compared to earlier models. Our most recent results yielded a sensitivity of 81%, a specificity of 77% and an overall accuracy of 79%.

Aerosol Layer Discrimination using Laser Radar and Genetic Algorithms

A technique has been developed to retrieve the height of the top of the aerosol layer from Micro Pulse Lidar (MPL) datasets. The technique combines first derivative estimates of normalized relative backscatter profiles with genetic algorithm refinements. The genetic algorithm is used to explore the gradient profiles to produce temporally coherent results. I. INTRODUCTION The distribution of aerosols over altitude and time has important effects on air quality, pollution,radiative forcing and climate, and rainfall patterns. Studies of aerosols also provide important information on atmospheric dynamics and transport. Thus atmospheric studies often require information on aerosol quantities and distributions. One important parameter for these studies is aerosol layer height. Lidar measurements of atmospheric backscatter may be used to track the height of the aerosol-rich layer over time. In this study, aerosol distribution data were obtained using the Connecticut State University (CSU) Lidar Collaboratorys Micro Pulse Lidar (MPL) system. The MPL is used to provide aerosol profiles for a variety of applications including air quality assessment and pollution control, climate modeling and studies of local atmospheric dynamics (1), (2), (3), (4). The CSU Lidar Collaboratory MPL is a Type 4 System from Sigma Space Corporation which monitors elastic backscatter at 527 nm. The system is eyesafe and thus may be operated autonomously. The MPL is a useful tool for boundary layer studies as it is capable of providing data in both daytime and nighttime conditions. Laser light pulses at 2500 Hz are transmitted vertically out of a beam-expansion telescope and the resulting backscatter is detected by a photon counting avalalanche photodiode. Detected intensity provides informa- tion on aerosol optical properties while timing of the scattered pulse return provides the altitude of the scatterer. Data used for this study were measured with an altitude resolution of 15 meters and a time interval of one minute. The data were range-corrected and also corrected for instrument artifacts and calibrations. The resulting datasets consist of time, altitude and normalized relative backscatter (NRB) signal intensity. These data are represented as images in which altitude is plotted on the vertical axis and time on the horizontal axis. The pixel value at each image pixel represents the NRB signal intensity. Examples of NRB datasets collected at New

Remote Internet-based lidar experimentation and education

Remote sensing projects typically require the collaboration and expertise of professionals from multiple disciplines. In order to motivate and train undergraduate students for future careers and/or education in the field of remote sensing, they should be exposed to remote sensing technologies and concepts throughout their undergraduate studies within their selected majors. This paper describes the design and development of a laboratory and Internet-based systems environment that facilitates remote sensing education and research based on cross-institutional resource sharing of lidar instrumentation