LSTM model to predict missing data of dissolved oxygen in land-based aquaculture farm

被引：0

作者：

Lee, Sang-Yeon ^{[1
]}

Jeong, Deuk-Young ^{[2
]}

Choi, Jinseo ^{[3
]}

Jo, Seng-Kyoun ^{[1
]}

Park, Dae-Heon ^{[1
]}

Kim, Jun-Gyu ^{[1
]}

机构：

[1] Elect & Telecommun Res Inst ETRI, Agr Anim Aquaculture & Ocean Intelligence Res Ctr, Daejeon, South Korea

[2] Seoul Natl Univ, Coll Agr & Life Sci, Res Inst Agr & Life Sci, Dept Rural Syst Engn, Seoul 151921, South Korea

[3] Pukyong Natl Univ, Dept Aquaculture & Appl Life Sci, Busan, South Korea

来源：

ETRI JOURNAL | 2024年 / 46卷 / 06期

关键词：

aquaculture farm; data imputation; dissolved oxygen; machine learning; recurrent neural network; AMMONIA-NITROGEN; NEURAL-NETWORK; BEHAVIOR; SYSTEMS;

D O I：

10.4218/etrij.2023-0337

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

A long short-term memory (LSTM) model is introduced to predict missing datapoints of dissolved oxygen (DO) in an eel (Anguilla japonica) recirculating aquaculture system. Field experiments allow to determine periodic patterns in DO data corresponding to day-night cycles and a DO decrease after feeding. To improve the accuracy of DO prediction by using a training-to-test data ratio of 5:1, training with data in sequential and reverse orders is performed and evaluated. The LSTM model used to predict DO levels in the fish tank has an error of approximately 3.25%. The proposed LSTM model trained on DO data has a high applicability and may support water quality control in aquaculture farms.

引用

页码：1047 / 1060

页数：14

共 50 条

[41] Ammonia variations in phytotreatment ponds of land-based fish farm wastewater
Porrello, S
Ferrari, G
Lenzi, M
Persia, E
AQUACULTURE, 2003, 219 (1-4) : 485 - 494
[42] A Novel and Automated Approach to Detect Sea- and Land-Based Aquaculture Facilities
Veroli, Maxim
Martinoli, Marco
Martini, Arianna
Napolitano, Riccardo
Pulcini, Domitilla
Tonachella, Nicolo
Capoccioni, Fabrizio
AGRIENGINEERING, 2025, 7 (01):
[43] Algal bioproducts derived from suspended solids in intensive land-based aquaculture
Castine, Sarah A.
Paul, Nicholas A.
Magnusson, Marie
Bird, Michael I.
de Nys, Rocky
BIORESOURCE TECHNOLOGY, 2013, 131 : 113 - 120
[44] Wastewater treatment for land-based aquaculture: improvements and value-adding alternatives in model systems from Australia
Castine, Sarah A.
McKinnon, A. David
Paul, Nicholas A.
Trott, Lindsay A.
de Nys, Rocky
AQUACULTURE ENVIRONMENT INTERACTIONS, 2013, 4 (03) : 285 - 300
[45] RIVER DISSOLVED OXYGEN PREDICTION BASED ON RANDOM FOREST AND LSTM
Huan, Juan
Chen, Bo
Xu, Xian Gen
Li, Hui
Li, Ming Bao
Zhang, Hao
APPLIED ENGINEERING IN AGRICULTURE, 2021, 37 (05) : 901 - 910
[46] Land-based dissolved organic nitrogen dynamics and bioavailability in Jiaozhou Bay, China
Li, Keqiang
Liu, Cuicui
Ma, Yunpeng
Wang, Xiulin
ESTUARINE COASTAL AND SHELF SCIENCE, 2019, 220 : 13 - 24
[47] Temporal prediction of dissolved oxygen based on CEEMDAN and multi-strategy LSTM hybrid model
Roushangar, Kiyoumars
Davoudi, Sina
Shahnazi, Saman
ENVIRONMENTAL EARTH SCIENCES, 2024, 83 (06)
[48] Dissolved Oxygen Prediction Model in Ponds Based on Improved Beetle Antennae Search and LSTM Network
Sun L.
Wu Y.
Sun X.
Zhang S.
Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery, 2021, 52 : 252 - 260
[49] Temporal prediction of dissolved oxygen based on CEEMDAN and multi-strategy LSTM hybrid model
Kiyoumars Roushangar
Sina Davoudi
Saman Shahnazi
Environmental Earth Sciences, 2024, 83
[50] An Enhanced Naive Bayes Model for Dissolved Oxygen Forecasting in Shellfish Aquaculture
Li, Dashe
Sun, Jiajun
Yang, Huanhai
Wang, Xueying
IEEE ACCESS, 2020, 8 : 217917 - 217927

← 1 2 3 4 5 →