Development of a Soil Moisture Prediction Model Based on Recurrent Neural Network Long Short-Term Memory (RNN-LSTM) in Soybean Cultivation
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. There...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/4/1976 |
| _version_ | 1797618290660474880 |
|---|---|
| author | Soo-Hwan Park Bo-Young Lee Min-Jee Kim Wangyu Sang Myung Chul Seo Jae-Kyeong Baek Jae E Yang Changyeun Mo |
| author_facet | Soo-Hwan Park Bo-Young Lee Min-Jee Kim Wangyu Sang Myung Chul Seo Jae-Kyeong Baek Jae E Yang Changyeun Mo |
| author_sort | Soo-Hwan Park |
| collection | DOAJ |
| description | 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<sup>2</sup>) 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<sup>2</sup> 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<sup>2</sup> of 0.999, a loss of 0.016, and a validation loss of 0.098 and an R<sup>2</sup> 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. |
| first_indexed | 2024-03-11T08:11:01Z |
| format | Article |
| id | doaj.art-96212c0800a844618a7f929fc0ac3f10 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T08:11:01Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-96212c0800a844618a7f929fc0ac3f102023-11-16T23:08:40ZengMDPI AGSensors1424-82202023-02-01234197610.3390/s23041976Development of a Soil Moisture Prediction Model Based on Recurrent Neural Network Long Short-Term Memory (RNN-LSTM) in Soybean CultivationSoo-Hwan Park0Bo-Young Lee1Min-Jee Kim2Wangyu Sang3Myung Chul Seo4Jae-Kyeong Baek5Jae E Yang6Changyeun Mo7Interdisciplinary Program in Smart Agriculure, Kangwon National University, Chuncheon 24341, Republic of KoreaInterdisciplinary Program in Smart Agriculure, Kangwon National University, Chuncheon 24341, Republic of KoreaAgriculture and Life Sciences Research Institute, Kangwon National University, Chuncheon 24341, Republic of KoreaDivison of Crop Physiology and Production, National Institute of Crop Science, Rural Development Administration, Hyoksin-ro 181, Iseo-myeon, Wanju-gun 55365, Republic of KoreaDivison of Crop Physiology and Production, National Institute of Crop Science, Rural Development Administration, Hyoksin-ro 181, Iseo-myeon, Wanju-gun 55365, Republic of KoreaDivison of Crop Physiology and Production, National Institute of Crop Science, Rural Development Administration, Hyoksin-ro 181, Iseo-myeon, Wanju-gun 55365, Republic of KoreaDepartment of Natural Resources and Environmental Sciences, Kangwon National University, Chuncheon 24341, Republic of KoreaInterdisciplinary Program in Smart Agriculure, Kangwon National University, Chuncheon 24341, Republic of KoreaDue 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<sup>2</sup>) 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<sup>2</sup> 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<sup>2</sup> of 0.999, a loss of 0.016, and a validation loss of 0.098 and an R<sup>2</sup> 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.https://www.mdpi.com/1424-8220/23/4/1976smart farmingtime series analysissoil moisturedeep learningRNN-LSTM |
| spellingShingle | Soo-Hwan Park Bo-Young Lee Min-Jee Kim Wangyu Sang Myung Chul Seo Jae-Kyeong Baek Jae E Yang Changyeun Mo Development of a Soil Moisture Prediction Model Based on Recurrent Neural Network Long Short-Term Memory (RNN-LSTM) in Soybean Cultivation Sensors smart farming time series analysis soil moisture deep learning RNN-LSTM |
| title | Development of a Soil Moisture Prediction Model Based on Recurrent Neural Network Long Short-Term Memory (RNN-LSTM) in Soybean Cultivation |
| title_full | Development of a Soil Moisture Prediction Model Based on Recurrent Neural Network Long Short-Term Memory (RNN-LSTM) in Soybean Cultivation |
| title_fullStr | Development of a Soil Moisture Prediction Model Based on Recurrent Neural Network Long Short-Term Memory (RNN-LSTM) in Soybean Cultivation |
| title_full_unstemmed | Development of a Soil Moisture Prediction Model Based on Recurrent Neural Network Long Short-Term Memory (RNN-LSTM) in Soybean Cultivation |
| title_short | Development of a Soil Moisture Prediction Model Based on Recurrent Neural Network Long Short-Term Memory (RNN-LSTM) in Soybean Cultivation |
| title_sort | development of a soil moisture prediction model based on recurrent neural network long short term memory rnn lstm in soybean cultivation |
| topic | smart farming time series analysis soil moisture deep learning RNN-LSTM |
| url | https://www.mdpi.com/1424-8220/23/4/1976 |
| work_keys_str_mv | AT soohwanpark developmentofasoilmoisturepredictionmodelbasedonrecurrentneuralnetworklongshorttermmemoryrnnlstminsoybeancultivation AT boyounglee developmentofasoilmoisturepredictionmodelbasedonrecurrentneuralnetworklongshorttermmemoryrnnlstminsoybeancultivation AT minjeekim developmentofasoilmoisturepredictionmodelbasedonrecurrentneuralnetworklongshorttermmemoryrnnlstminsoybeancultivation AT wangyusang developmentofasoilmoisturepredictionmodelbasedonrecurrentneuralnetworklongshorttermmemoryrnnlstminsoybeancultivation AT myungchulseo developmentofasoilmoisturepredictionmodelbasedonrecurrentneuralnetworklongshorttermmemoryrnnlstminsoybeancultivation AT jaekyeongbaek developmentofasoilmoisturepredictionmodelbasedonrecurrentneuralnetworklongshorttermmemoryrnnlstminsoybeancultivation AT jaeeyang developmentofasoilmoisturepredictionmodelbasedonrecurrentneuralnetworklongshorttermmemoryrnnlstminsoybeancultivation AT changyeunmo developmentofasoilmoisturepredictionmodelbasedonrecurrentneuralnetworklongshorttermmemoryrnnlstminsoybeancultivation |