Mechanics of a Drone-based System for Algal Bloom Detection Utilizing Deep Learning and LLMs

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The emergence of harmful algal blooms (HABs) along the U.S. East Coast has necessitated the development of an innovative drone-based detection system, a response to the growing challenges posed by climate change and pollution. This multifaceted approach involves the collection of high-resolution images from drones and smartphone cameras, the detection and classification of algae using Transformer Neural Networks and Large Language Models (LLMs), and the application of a data segmentation approach for efficient data analysis. The system enhances traditional monitoring techniques by integrating unique custom data gathered from New Jersey's water bodies with public data collected by the state's Environmental Protection Department. It offers a more precise and efficient method for HAB detection.

Original languageEnglish
Title of host publicationIEEE MIT Undergraduate Research Technology Conference, URTC 2023 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350308600
DOIs
StatePublished - 2023
Event2023 IEEE MIT Undergraduate Research Technology Conference, URTC 2023 - Hybrid, Cambridge, United States
Duration: 6 Oct 20238 Oct 2023

Publication series

NameIEEE MIT Undergraduate Research Technology Conference, URTC 2023 - Proceedings

Conference

Conference2023 IEEE MIT Undergraduate Research Technology Conference, URTC 2023
Country/TerritoryUnited States
CityHybrid, Cambridge
Period6/10/238/10/23

Keywords

  • data segmentation
  • drones
  • HABs classification
  • HABs detection
  • LLMs
  • marine ecosystems
  • transformers

Fingerprint

Dive into the research topics of 'Mechanics of a Drone-based System for Algal Bloom Detection Utilizing Deep Learning and LLMs'. Together they form a unique fingerprint.

Cite this