Research Project:

A Web-Based Implementation of Winter Maintenance Decision Support System (WMDSS) Using GIS and Remote Sensing

Screen shot of the Winter Maintenance Decision Support System

Web-based GIS tools for the transportation infrastructure management

Final Report

PDF version 1.2MB
HTML version 103k

Tech Transfer Summary 534 kb

Principal Investigator

Ramanathan Sugumaran
University of Northern Iowa
(319) 273-3816
sugu@uni.edu

External Project Contact

Dave Plazak
Iowa State University
(515) 296-0814
dplazak@iastate.edu

Project Objective

To implement a web-based winter maintenance decision support system that improves the ability of stakeholders to evaluate different procedures to optimally manage assets for snow removal. This will be accomplished by integrating geo-spatial analytical techniques, a snow removal asset management system (SRAMS) developed with support from the MTC, and spatial decision support systems.

Project Abstract

Winter maintenance, particularly snow removal and the stress of snow removal materials on public structures, is an enormous budgetary burden on municipalities and nongovernmental maintenance organizations in cold climates. Lately, geo-spatial technologies such as remote sensing, geographical information systems (GIS), and decision support tools are providing valuable assistance in planning snow removal operations. A few researchers recently used geo-spatial technologies for the development of winter maintenance tools. However, most of these winter maintenance tools, while having the potential to address some of the informational needs of snow removal agencies, are not typically placed in the hands of planners and other interested stakeholders. Most tools are not constructed with a nontechnical user in mind and lack an easy-to-use, easily understood interface.

A major goal of the project was to implement a web-based Winter Maintenance Decision Support System (WMDSS) for planning snow removal operations that enhances the capacity of stakeholders (city/county planners, resource managers, transportation personnel, citizens, and policy makers) to evaluate different procedures to manage snow removal assets optimally. This goal was accomplished by integrating geo-spatial analytical techniques (GIS and remote sensing), existing snow removal asset management systems (SRAMS), and web-based spatial decision support systems. In order to extract up-to-date transportation infrastructure features, this study used hyperspectral imagery from the high-resolution Airborne Visible/Infrared Imaging Spectrometer (AVIRIS). Classifiers such as the Spectral Angle Mapper (SAM), Mixture-tuned Matched Filtering (MTMF) and Mixture-Tuned Matched Filtering combined with Classification and Regression Tree (MTMF-CART) were used to extract the transportation infrastructures. The study found that the MTMF classification method produced the best overall results compared to both the SAM classifier and MTMF-CART methods, and the overall accuracies for the three classifications were 81.89%, 88.92%, and 84.32%, respectively. The web-based decision support system was implemented using the ESRI ArcIMS ActiveX Connector and related web technologies like ASP, JavaScript, HTML, and XML. The expert knowledge is represented as “business rules” using Visual Rule Studio, and is integrated with the system. The developed system not only manages and allocates resources, but also provides expert advice to assist complex decision making such as routing, optimal resource allocation, and live weather information monitoring. This system was developed in collaboration with Black Hawk County; the City of Columbia, MO; the Iowa DOT; and the cities of Cedar Falls, IA and Waterloo, IA. Demonstration versions of this product were also given to these agencies in order to improve the usability and applicability of the system.

Task Descriptions, Milestone, and Dates

FEATURE EXTRACTION FROM REMOTE SENSING DATA

Exploring remote sensing data availability, July 2003
Remote sensing software evaluation, December 2003
Evaluation of classification algorithms, May 2004
Extraction of transportation infrastructure, May 2004

WEB-BASED INTERACTIVE GIS TOOLS

Internet GIS software evaluation, July 2004
Prototype Implementation, July 2004
Evaluation by the end user, December 2004
Final implementation, December 2004

WMDSS

SRAMS modification, May 2004
SRAMS validation with End user, May 2004
SRAMS web based prototype, May 2004
Integration with Web GIS tools, May 2005
Prototype WMDSS, May 2005
Final Implementation of WMDSS, May 2005

DISSEMINATION

Publication and presentation, May 2005
Website implementation, May 2005
Revised manual, May 2005
Training and workshops, May 2005

Student Involvement (e.g., Thesis, Assistantships, Paid Employment)

One Graduate Student
Two Undergraduate Students

Relationship to Other Projects

The current SRAMS is PC based and developed only for the Cedar Falls and Waterloo area. This project will improve the existing SRAMS and its implementation in various ways.

Technology Transfer Activities

Technology transfer will be accomplished as follows:

The PI’s will publish results in refereed journals, present them at workshops and conferences, and integrate the research into their teaching.
A hands-on workshop showcasing the WMDSS to the end users.
Distribution of the findings to stakeholders involved in the study though online documents.

Potential Benefits of the Project

The project will deliver the following:

Transportation infrastructure map derived from remotely sensed data
An interactive website with GIS tools for viewing, managing, and updating transportation infrastructure data;
Web-based Winter Maintenance Decision Support System (WMDSS);
Complete documentation of the product developed
An interactive website showcasing this research and transferring the technology to end users

Budget

$132,609 (two-year project)

TRB Keywords

Winter maintenance, decision support, GIS, remote sensing, asset management, snow removal, geo-spatial, decision support