
>_
Description
This is the part B of project 8. The overall goal is to develop digital twin and machine learning algorithms for addressing key aspects of LED driven pod-based hydroponic farming, resource use efficiency, and related plant pathogen challenges, using data and models from the companion project 8 (Part A). We are motivated by recent products which are presented without much analysis or optimization so that their efficacy is unclear. These are essentially self-contained pods, made of 40-foot-long shipping containers filled with cutting-edge, high-tech equipment for hydroponic agriculture.
If successful, this project will have a huge impact on providing predictive/analytical models to the food industry for predicting spread of pathogens and decontamination, realistic simulation of hydroponic systems, quantitative comparison of the performance of these systems with conventional greenhouses and outdoor farming and increasing their widespread usage. The specific focus of the research team on pathogens is timely, considering the ongoing spread of the COVID-19 related pathogens. It is expected that the proposed methods, i.e., digital twins and deep learning, as well as the project deliverables will contribute to revolutionizing the food processing industry.
Learn more about our other indoor farming research projects.
>_
Team

Tarek Zohdi
Principal Investigator

Khalid Mosalam
Co Principal Investigator

Ethan Ligon
Co Principal Investigator

Simo Mäkiharju
Co Principal Investigator

Francesco Borrelli
Co Principal Investigator

Rebecca Abergel
Co Principal Investigator

Mark Mueller
Co Principal Investigator

Nitin Nitin
Collaborator

Ilias Tagkopoulos
Collaborator
>_
Publications

Crop-driven Optimization of Agrivoltaics Using a Digital-replica Framework

A Machine-learning Digital-twin for Rapid Large-scale Solar-thermal Energy System Design

Placement and Drone Flight Path Mapping of Agricultural Soil Sensors Using Machine Learning

A Note on Rapid Genetic Calibration of Artificial Neural Networks

A Digital-twin Framework for Genomic-based Optimization of an Agrophotovoltaic Greenhouse System

An Adaptive Digital Framework for Energy Management of Complex Multi-device Systems

Machine-learning and Digital-twins for Rapid Evaluation and Design of Injected Vaccine Immune-system Responses

A Digital-twin and Machine-learning Framework for Precise Heat and Energy Management of Data-centers

A Digital-twin and Machine-learning Framework for the Design of Multiobjective Agrophotovoltaic Solar Farms

A Digital-Twin and Machine-Learning Framework for Ventilation System Optimization for Capturing Infectious Disease Respiratory Emissions
