A Machine Learning Method to Estimate Reference Evapotranspiration Using Soil Moisture Sensors
One of the most important applications of remote imaging systems in agriculture, with the greatest impact on global sustainability, is the determination of optimal crop irrigation. The methodology proposed by the Food and Agriculture Organization (FAO) is based on estimating crop evapotranspiration...
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Artikel |
| Sprache: | English |
| Veröffentlicht: |
MDPI AG
2020-03-01
|
| Schriftenreihe: | Applied Sciences |
| Schlagworte: | |
| Online Zugang: | https://www.mdpi.com/2076-3417/10/6/1912 |
| _version_ | 1831649848362795008 |
|---|---|
| author | Antonio Fernández-López Daniel Marín-Sánchez Ginés García-Mateos Antonio Ruiz-Canales Manuel Ferrández-Villena-García José Miguel Molina-Martínez |
| author_facet | Antonio Fernández-López Daniel Marín-Sánchez Ginés García-Mateos Antonio Ruiz-Canales Manuel Ferrández-Villena-García José Miguel Molina-Martínez |
| author_sort | Antonio Fernández-López |
| collection | DOAJ |
| description | One of the most important applications of remote imaging systems in agriculture, with the greatest impact on global sustainability, is the determination of optimal crop irrigation. The methodology proposed by the Food and Agriculture Organization (FAO) is based on estimating crop evapotranspiration (ETc), which is done by computing the reference crop evapotranspiration (ETo) multiplied by a crop coefficient (Kc). Some previous works proposed methods to compute Kc using remote crop images. The present research aims at complementing these systems, estimating ETo with the use of soil moisture sensors. A crop of kikuyu grass (<i>Pennisetum clandestinum</i>) was used as the reference crop. Four frequency-domain reflectometry sensors were installed, gathering moisture information during the study period from May 2015 to September 2016. Different machine learning regression algorithms were analyzed for the estimation of ETo using moisture and climatic data. The values were compared with respect to the ETo computed in an agroclimatic station using the Penman−Monteith method. The best method was the randomizable filtered classifier technique, based on the K* algorithm. This model achieved a correlation coefficient, <i>R</i>, of 0.9936, with a root-mean-squared error of 0.183 mm/day and 6.52% mean relative error; the second-best model used artificial neural networks, with an R of 0.9470 and 11% relative error. Thus, this new methodology allows obtaining accurate and cost-efficient prediction models for ETo, as well as for the water balance of the crops. |
| first_indexed | 2024-12-19T14:58:10Z |
| format | Article |
| id | doaj.art-0c09175cb5494a3c8089fd8ae537cf36 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-19T14:58:10Z |
| publishDate | 2020-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-0c09175cb5494a3c8089fd8ae537cf362022-12-21T20:16:39ZengMDPI AGApplied Sciences2076-34172020-03-01106191210.3390/app10061912app10061912A Machine Learning Method to Estimate Reference Evapotranspiration Using Soil Moisture SensorsAntonio Fernández-López0Daniel Marín-Sánchez1Ginés García-Mateos2Antonio Ruiz-Canales3Manuel Ferrández-Villena-García4José Miguel Molina-Martínez5Engineering Department, Miguel Hernandez University of Elche, 03312 Orihuela, SpainComputer Science and Systems Department, University of Murcia, 30100 Murcia, SpainComputer Science and Systems Department, University of Murcia, 30100 Murcia, SpainEngineering Department, Miguel Hernandez University of Elche, 03312 Orihuela, SpainEngineering Department, Miguel Hernandez University of Elche, 03312 Orihuela, SpainFood Engineering and Agricultural Equipment Department, Technical University of Cartagena, 30203 Cartagena, SpainOne of the most important applications of remote imaging systems in agriculture, with the greatest impact on global sustainability, is the determination of optimal crop irrigation. The methodology proposed by the Food and Agriculture Organization (FAO) is based on estimating crop evapotranspiration (ETc), which is done by computing the reference crop evapotranspiration (ETo) multiplied by a crop coefficient (Kc). Some previous works proposed methods to compute Kc using remote crop images. The present research aims at complementing these systems, estimating ETo with the use of soil moisture sensors. A crop of kikuyu grass (<i>Pennisetum clandestinum</i>) was used as the reference crop. Four frequency-domain reflectometry sensors were installed, gathering moisture information during the study period from May 2015 to September 2016. Different machine learning regression algorithms were analyzed for the estimation of ETo using moisture and climatic data. The values were compared with respect to the ETo computed in an agroclimatic station using the Penman−Monteith method. The best method was the randomizable filtered classifier technique, based on the K* algorithm. This model achieved a correlation coefficient, <i>R</i>, of 0.9936, with a root-mean-squared error of 0.183 mm/day and 6.52% mean relative error; the second-best model used artificial neural networks, with an R of 0.9470 and 11% relative error. Thus, this new methodology allows obtaining accurate and cost-efficient prediction models for ETo, as well as for the water balance of the crops.https://www.mdpi.com/2076-3417/10/6/1912reference evapotranspirationmoisture sensorsmachine learning regressionfrequency-domain reflectometryrandomizable filtered classifier |
| spellingShingle | Antonio Fernández-López Daniel Marín-Sánchez Ginés García-Mateos Antonio Ruiz-Canales Manuel Ferrández-Villena-García José Miguel Molina-Martínez A Machine Learning Method to Estimate Reference Evapotranspiration Using Soil Moisture Sensors Applied Sciences reference evapotranspiration moisture sensors machine learning regression frequency-domain reflectometry randomizable filtered classifier |
| title | A Machine Learning Method to Estimate Reference Evapotranspiration Using Soil Moisture Sensors |
| title_full | A Machine Learning Method to Estimate Reference Evapotranspiration Using Soil Moisture Sensors |
| title_fullStr | A Machine Learning Method to Estimate Reference Evapotranspiration Using Soil Moisture Sensors |
| title_full_unstemmed | A Machine Learning Method to Estimate Reference Evapotranspiration Using Soil Moisture Sensors |
| title_short | A Machine Learning Method to Estimate Reference Evapotranspiration Using Soil Moisture Sensors |
| title_sort | machine learning method to estimate reference evapotranspiration using soil moisture sensors |
| topic | reference evapotranspiration moisture sensors machine learning regression frequency-domain reflectometry randomizable filtered classifier |
| url | https://www.mdpi.com/2076-3417/10/6/1912 |
| work_keys_str_mv | AT antoniofernandezlopez amachinelearningmethodtoestimatereferenceevapotranspirationusingsoilmoisturesensors AT danielmarinsanchez amachinelearningmethodtoestimatereferenceevapotranspirationusingsoilmoisturesensors AT ginesgarciamateos amachinelearningmethodtoestimatereferenceevapotranspirationusingsoilmoisturesensors AT antonioruizcanales amachinelearningmethodtoestimatereferenceevapotranspirationusingsoilmoisturesensors AT manuelferrandezvillenagarcia amachinelearningmethodtoestimatereferenceevapotranspirationusingsoilmoisturesensors AT josemiguelmolinamartinez amachinelearningmethodtoestimatereferenceevapotranspirationusingsoilmoisturesensors AT antoniofernandezlopez machinelearningmethodtoestimatereferenceevapotranspirationusingsoilmoisturesensors AT danielmarinsanchez machinelearningmethodtoestimatereferenceevapotranspirationusingsoilmoisturesensors AT ginesgarciamateos machinelearningmethodtoestimatereferenceevapotranspirationusingsoilmoisturesensors AT antonioruizcanales machinelearningmethodtoestimatereferenceevapotranspirationusingsoilmoisturesensors AT manuelferrandezvillenagarcia machinelearningmethodtoestimatereferenceevapotranspirationusingsoilmoisturesensors AT josemiguelmolinamartinez machinelearningmethodtoestimatereferenceevapotranspirationusingsoilmoisturesensors |