Development of a Soil Moisture Prediction Model Based on Recurrent Neural Network Long Short-Term Memory (RNN-LSTM) in Soybean Cultivation

被引：18

作者：

Park, Soo-Hwan ^{[1
]}

Lee, Bo-Young ^{[1
]}

Kim, Min-Jee ^{[2
]}

Sang, Wangyu ^{[3
]}

Seo, Myung Chul ^{[3
]}

Baek, Jae-Kyeong ^{[3
]}

Yang, Jae E. ^{[4
]}

Mo, Changyeun ^{[1
,2
]}

机构：

[1] Kangwon Natl Univ, Interdisciplinary Program Smart Agriculure, Chunchon 24341, South Korea

[2] Kangwon Natl Univ, Agr & Life Sci Res Inst, Chunchon 24341, South Korea

[3] Natl Inst Crop Sci, Rural Dev Adm, Div Crop Physiol & Prod, Hyoksin Ro 181, Iseo Myeon 55365, Wanju Gun, South Korea

[4] Kangwon Natl Univ, Dept Nat Resources & Environm Sci, Chunchon 24341, South Korea

来源：

SENSORS | 2023年 / 23卷 / 04期

关键词：

smart farming; time series analysis; soil moisture; deep learning; RNN-LSTM; AGRICULTURAL DROUGHT;

D O I：

10.3390/s23041976

中图分类号：

O65 [分析化学];

学科分类号：

070302 ; 081704 ;

摘要：

Due to climate change, soil moisture may increase, and outflows could become more frequent, which will have a considerable impact on crop growth. Crops are affected by soil moisture; thus, soil moisture prediction is necessary for irrigating at an appropriate time according to weather changes. Therefore, the aim of this study is to develop a future soil moisture (SM) prediction model to determine whether to conduct irrigation according to changes in soil moisture due to weather conditions. Sensors were used to measure soil moisture and soil temperature at a depth of 10 cm, 20 cm, and 30 cm from the topsoil. The combination of optimal variables was investigated using soil moisture and soil temperature at depths between 10 cm and 30 cm and weather data as input variables. The recurrent neural network long short-term memory (RNN-LSTM) models for predicting SM was developed using time series data. The loss and the coefficient of determination (R-2) values were used as indicators for evaluating the model performance and two verification datasets were used to test various conditions. The best model performance for 10 cm depth was an R-2 of 0.999, a loss of 0.022, and a validation loss of 0.105, and the best results for 20 cm and 30 cm depths were an R-2 of 0.999, a loss of 0.016, and a validation loss of 0.098 and an R-2 of 0.956, a loss of 0.057, and a validation loss of 2.883, respectively. The RNN-LSTM model was used to confirm the SM predictability in soybean arable land and could be applied to supply the appropriate moisture needed for crop growth. The results of this study show that a soil moisture prediction model based on time-series weather data can help determine the appropriate amount of irrigation required for crop cultivation.

引用

页数：16

共 50 条

[1] Sparse based recurrent neural network long short term memory (rnn-lstm) model for the classification of ecg signals
Sampath, A.
Sumithira, T. R.
APPLIED ARTIFICIAL INTELLIGENCE, 2022, 36 (01)
[2] Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network
Sherstinsky, Alex
arXiv, 2018,
[3] Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network
Sherstinsky, Alex
PHYSICA D-NONLINEAR PHENOMENA, 2020, 404 (404)
[4] Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) Power Forecasting
Alsabban, Maha S.
Salem, Nema
Malik, Hebatullah M.
APPEEC 2021: 2021 13TH IEEE PES ASIA PACIFIC POWER &AMP; ENERGY ENGINEERING CONFERENCE (APPEEC), 2021,
[5] Using a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) to Classify Network Attacks
Muhuri, Pramita Sree
Chatterjee, Prosenjit
Yuan, Xiaohong
Roy, Kaushik
Esterline, Albert
INFORMATION, 2020, 11 (05)
[6] Using a long short-term memory recurrent neural network (LSTM-RNN) to classify network attacks
Muhuri P.S.
Chatterjee P.
Yuan X.
Roy K.
Esterline A.
Information (Switzerland), 2020, 11 (05):
[7] Prediction of Indonesian Palm Oil Production Using Long Short-Term Memory Recurrent Neural Network (LSTM-RNN)
Sugiyarto, Aditya Wisnugraha
Abadi, Agus Maman
2019 1ST INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND DATA SCIENCES (AIDAS2019), 2019, : 53 - 57
[8] Short-Term Fault Prediction of Wind Turbines Based on Integrated RNN-LSTM
Rama, V. Siva Brahmaiah
Hur, Sung-Ho
Yang, Jung-Min
IEEE ACCESS, 2024, 12 : 22465 - 22478
[9] HOURLY DISCHARGE PREDICTION USING LONG SHORT-TERM MEMORY RECURRENT NEURAL NETWORK (LSTM-RNN) IN THE UPPER CITARUM RIVER
Enung
Kusuma, Muhammad Syahril Badri
Kardhana, Hadi
Suryadi, Yadi
Rohmat, Faizal Immaddudin Wira
INTERNATIONAL JOURNAL OF GEOMATE, 2022, 23 (98): : 147 - 154
[10] Long Short Term Memory Recurrent Neural Network (LSTM-RNN) Based Workload Forecasting Model For Cloud Datacenters
Kumar, Jitendra
Goomer, Rimsha
Singh, Ashutosh Kumar
6TH INTERNATIONAL CONFERENCE ON SMART COMPUTING AND COMMUNICATIONS, 2018, 125 : 676 - 682

← 1 2 3 4 5 →