AI-Driven Cost-Benefit Analysis of Smart Aquaculture Technologies

Smart aquaculture, artificial intelligence, costbenefit analysis, machine learning, net present value, water-quality monitoring

Bhagyashree Shendkar1
Department of Computer Science and
Engineering, MIT School of Computing, MIT
Art, Design and Technology University, Loni
Kalbhor, Pune, India
Email: bhagyashree.d.shendkar@gmail.com
ORCID ID: 0000-0003-4808-2642

Gurunath Waghale2
School of Commerce and Management
Sri Balaji University, Pune
Email: guruwaghale111@gmail.com
ORCID: 0009-0007-4217-6249

Ashish Bhasme3
Department of Computer Science and
Engineering, MIT School of Computing, MIT
Art, Design and Technology University, Loni
Kalbhor, Pune, India,
Email: ashish.bhasme@gmail.com
ORCID: 0009-0004-6488-3794

Kiran Shinde4
Department of Computer Science and
Engineering, MIT School of Computing, MIT
Art, Design and Technology University, Loni
Kalbhor, Pune, India,
Email: kiran.shinde@mituniversity.edu.in
ORCID: 0000-0001-7388-9312

Dipak Umbarkar5
School of Management
Pimpri Chinchwad University, Pune, India
Email: dsumbarkar@gmail.com
ORCID: 0009-0006-9854-3987

Kiran Sakat6
Department of Economics
Padmabhushan Vasantraodada Patil
Mahavidyalaya, Kavathe Mahankal, Sangli, India
Email: sakatkiran@gmail.com
ORCID: 0009-000-9181-7579

Corresponding Author:
Bhagyashree Shendkar
Department of Computer Science and Engineering,
MIT School of Computing, MIT Art, Design and
Technology University, Loni Kalbhor, Pune, India.
Email:bhagyashree.d.shendkar@gmail.com

Received: 19-06-2026
Revised: 22-07-2026
Accepted: 24-07-2026

European Journal of Prosthodontics and Restorative Dentistry (2026) 34 (5s), 178–191

AI-Driven Cost-Benefit Analysis of Smart Aquaculture Technologies

Smart aquaculture technologies are gaining traction as solutions to better manage water quality, boost productivity, and enhance the efficiency of investments, but are still hard to quantify in economic value under farm-level uncertainty. This study created an AI based scenario-based cost benefit framework for the assessment of smart aquaculture technologies with the public pond level aquaculture data from Andhra Pradesh, India. The smart aquaculture functions were first categorized as monitoring, management with equipment, advisory decision support, follow-up monitoring, correctiveaction implementation, and self-initiated management. A pond-level analytical dataset was then created by merging water-quality, stocking, harvest, equipment and sensor-campaign data records. Multiple machinelearning models were developed to predict yield, and the best model was integrated into a counterfactual cost-benefit analysis between a ‘business-asusual’ (BAU) and a ‘smart-aquaculture' (SA) scenario. The present net value, benefit-cost ratio, return on investment, payback period, sensitivity analysis and Monte Carlo simulation were used to assess economic feasibility. Extra Trees was the best performing model with an R2 value of 40.5%. The scenario-based framework estimated a median NPV of USD 46,718.91, median BCR of 7.42 and 65.70% economically feasible ponds based on the specified baseline economic assumptions. Analysis of the adoption gap revealed that there was a higher potential for marginal gains where the existing level of smart-technology intensity was lower, which informed targeted investment decisions. The framework provides a decision-support pathway for the assessment of smart aquaculture investment options that can be replicated in other situations with limited data and assumptions.

•••••••••••••••••••••••••••••••• ejprd.org - Published by Riset Publication Services LLC

EJPRD

Copyright ©2026 by Riset Publication Services