Texas A&M University 28-EQUI-ITB-1162

Development of information retrieval system - Flash Floods

The buyer is the Texas A&M Engineering Experiment Station (TEES), a state agency affiliated with Texas A&M University. The awarded contract is for the development of a domain-specific information retrieval system focused on flash flooding. The system will utilize computational intelligence techniques and machine learning algorithms to retrieve and filter flash flood event data from the National Oceanic and Atmospheric Administration (NOAA) Storm Events database and web search engines. The system will operate on AWS infrastructure, facilitating communication between users (primarily civil engineering and urban planning researchers) and backend machine learning models. The vendor is required to provide a minimum viable product (MVP) version of this system. The contract requires the vendor to submit three references demonstrating experience in the civil engineering field, documentation of AWS platform proficiency, and a detailed scope with timeline. Any developed product will be the sole property of TEES. Warranty coverage of at least 12 months for all parts and labor is mandated. Additionally, the vendor must submit a completed Voluntary Product Accessibility Template (VPAT). The only product line item is the development of the MVP information retrieval system, with a quantity of one job unit. No specific OEMs or other vendors are mentioned in the document. The place of performance is implied to be Texas, with the buyer contact located at Texas A&M University. The contract is funded under a federal contract or grant administered by a state agency.

Description

Invitation for Bid - Development of Informational Retrieval System - Flash Flood Data. The system will retrieve information about flash flood events in the US by creating event-specific search queries from the NOAA Storm Events database, filtering non-relevant webpages using a machine learning algorithm, and presenting relevant information to the user. The system will run on AWS infrastructure and communicate between users and machine learning algorithms in the back-end. The product developed will be the sole property of Texas A&M Engineering Experiment Station (TEES).

View original record