Water quality guidelines to reduce mortality rate of red tilapia (oreochromis spp.) raised in outdoor earthen ponds with a recirculating aquaculture system using machine learning techniques

Name: Putra, Ali Syahbana Matondang

LCSH: Kasetsart University -- Theses. M.S. (Fishery Science and Technology) 2022

Classification :.LCCS: SH167.T54

LCSH: Kasetsart University. -- Faculty of Fisheries -- Theses

LCSH: Tilapia

LCSH: Fish culture

LCSH: Aquaculture

LCSH: Water quality

LCSH: Machine learning

Abstract: Machine learning techniques have been widely adopted over the last few decades, especially in the field of fisheries. This study aims to determine water quality guidelines and a predictive model of machine learning techniques in reducing the mortality rate of red tilapia (Oreochromis spp.) raised in outdoor earthen ponds with a recirculating aquaculture system. The study began by collecting water quality parameters and mortality rate (fish day-1). The water quality parameters were measured in the form of dissolved oxygen (mg L -1), pH, temperature (°C), total ammonia nitrogen (mg L-1), nitrite-nitrogen (mg L1), alkalinity (mg L-1), and transparency (cm). The results of this study showed decision tree can be applied in determining the best water quality management practice to reduce the mortality rate of red tilapia during the nursing and grow-out period; accuracy reached 89.67% ± 5.11% and 82.11% ± 5.86%, precision reached 86.71% ± 18.02% and 64.41%, and recall reached 72.50% ± 24.86% and 42.22% ± 23.89%, with the most influential factors were nitrite-nitrogen (NO2-N) and total ammonia nitrogen (TAN), respectively. On the other hand, the random forest has the best performance model in predicting the mortality rate of red tilapia during the nursing and growout period; accuracy reached 86.00% ± 11.40% and 94.90% ± 1.80%, precision reached 100.00% ± 0.00% and 95.70% ± 2.40%, and recall reached 82.30% ± 13.40% and 97.90% ± 2.90%, respectively. Based on the results of this study, machine learning techniques can be applied to support fish farmers' decisions and actions to increase red tilapia (Oreochromis spp.) productivity and prevent water quality factors that could result in the aquaculture system experiencing mass mortality.

Kasetsart University. Office of the University Library

Address: Bangkok

Email: tdckulib@ku.ac.th

Name: Wara Taparhudee

Role: Thesis Advisor

Name: Rueangchary Yoonpund

Role: Thesis CO-Advisor

Name: Roongparit Jongjaraunsuk

Role: Thesis CO-Advisor

Created: 2022

Modified: 2025-07-24

Issued: 2025-07-24

วิทยานิพนธ์/Thesis

application/pdf

URL: https://www.lib.ku.ac.th/KUthesis/2565/putra-ali-all.pdf

CallNumber: SH167.T54 .P88

eng

DegreeName: Master of Science

Level: Master's Degree

Descipline: Fishery Science and Technology

Grantor: Kasetsart University

©copyrights Kasetsart University

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	putra-ali-all.pdf	1.5 MB

ใช้เวลา

0.021863 วินาที