I-Corps: Translation Potential of a marine-adapted radio frequency identification (RFID) and analytics platform for digital inventory management in shellfish aquaculture

This I-Corps project is based on the development of a digital farm-management platform for commercial shellfish aquaculture. Shellfish farmers manage crops numbering in the millions, yet inventory records and production decisions still commonly rely on handwritten logs, memory, whiteboards, spreadsheets, and disconnected applications that are difficult to maintain. Inaccurate or incomplete records can limit farmers’ ability to coordinate labor and gear, track crop performance, and manage proactively. This technology integrates durable, marine-adapted radio frequency identification (RFID) infrastructure with automated data-processing pipelines to generate continuous, high-resolution datasets on shellfish growth and gear movement. These longitudinal records support a centralized inventory and decision-support system and enable the development of machine-learning approaches for modeling and potentially predicting growth rates and management needs. The technology may improve operational visibility and support more consistent, timely, and informed decisions to develop a more efficient and reliable domestic shellfish supply. This I-Corps project utilizes experiential learning coupled with first-hand investigation of the industry ecosystem to assess the translation potential of a machine learning-enabled decision-support platform built on marine-adapted radio frequency identification (RFID) infrastructure for shellfish aquaculture. Existing predictive tools are limited because reliable digital inventory systems have not generated the high-resolution historical datasets required to train and validate such models. This technology uses passive, low-frequency RFID tags affixed to production gear, which are read during routine farm activities, producing serialized, time-stamped observations that are enriched with metadata and routed through Python-based middleware into a relational database and interactive dashboard. This technology provides the integration of persistent gear identification, automated longitudinal data capture, and machine-learning algorithms capable of linking crop growth, gear movement, husbandry history, and environmental conditions to forecast production timing and management needs. Previous research has demonstrated the feasibility of identifying tagged gear in operational farm settings and linking scans to digital inventory records. Users may benefit from reducing recordkeeping burden, improving inventory accuracy and operational visibility, and supporting more timely, consistent, and proactive farm-management decisions. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.