Mostrar el registro sencillo del ítem
dc.contributor.author
Jiménez, Andrés F.
dc.contributor.author
Ortiz, Brenda V.
dc.contributor.author
Bondesan, Luca
dc.contributor.author
Morata, Guilherme
dc.contributor.author
Damianidis, Damianos
dc.date.available
2022-10-25T10:43:31Z
dc.date.issued
2020-06
dc.identifier.citation
Jiménez, Andrés F.; Ortiz, Brenda V.; Bondesan, Luca; Morata, Guilherme; Damianidis, Damianos; Evaluation of two recurrent neural network methods for prediction of irrigation rate and timing; American Society of Agricultural and Biological Engineers; Transactions of the ASABE; 63; 5; 6-2020; 1327-1348
dc.identifier.issn
2151-0032
dc.identifier.uri
http://hdl.handle.net/11336/174695
dc.description.abstract
The implementation of adequate irrigation strategies could be done through real-time monitoring of soil water status at several soil depths; however, this could also represent a complex nonlinear problem due to the plant-soil-weather relationships. In this study, two recurrent neural network (RNN) models were evaluated to estimate irrigation prescriptions. Data for this study were collected from an on-farm corn irrigation study conducted between 2017 and 2019 in Samson, Alabama. The study used hourly data of weather and soil matric potential (SMP) monitored at three soil depths from 13 sensor probes installed on a loamy fine sand soil and a sandy clay loam soil. Two neural network methods, i.e., a nonlinear autoregressive with exogenous (NARX) input system and long short-term memory (LSTM), were trained, validated, and tested with a maximum dataset of 20,052 records and a maximum of eight categorical attributes to estimate one-step irrigation prescriptions. The performance of both methods was evaluated by varying the model development parameters (neurons or blocks, dropout, and epochs) and determining their impact on the final model prediction. Results showed that both RNN models demonstrated good capability in the prediction of irrigation prescriptions for the soil types studied, with a coefficient of determination (R2) > 0.94 and root mean square error (RMSE) < 1.2 mm. The results of this study indicate that after training the RNNs using the dataset collected in the field, models using only SMP sensors at three soil depths obtained the best performance, followed by models that used only data of solar radiation, temperature, and relative humidity in the prediction of irrigation prescriptions. For future applicability, the RNN models can be extended using datasets from other places for training, which would allow the adoption of a unique data-driven soil moisture model for irrigation scheduling useful in a wide range of soil types.
dc.format
application/pdf
dc.language.iso
eng
dc.publisher
American Society of Agricultural and Biological Engineers
dc.rights
info:eu-repo/semantics/restrictedAccess
dc.rights.uri
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.subject
CORN
dc.subject
IRRIGATION SCHEDULING
dc.subject
MACHINE LEARNING
dc.subject
MODELING
dc.subject
SOIL MATRIC POTENTIAL SENSOR
dc.subject.classification
Agricultura
dc.subject.classification
Agricultura, Silvicultura y Pesca
dc.subject.classification
CIENCIAS AGRÍCOLAS
dc.title
Evaluation of two recurrent neural network methods for prediction of irrigation rate and timing
dc.type
info:eu-repo/semantics/article
dc.type
info:ar-repo/semantics/artículo
dc.type
info:eu-repo/semantics/publishedVersion
dc.date.updated
2022-09-19T15:04:13Z
dc.identifier.eissn
2151-0040
dc.journal.volume
63
dc.journal.number
5
dc.journal.pagination
1327-1348
dc.journal.pais
Estados Unidos
dc.journal.ciudad
Michigan
dc.description.fil
Fil: Jiménez, Andrés F.. Universidad de Los Llanos; Colombia. Universidad Nacional de Colombia; Colombia
dc.description.fil
Fil: Ortiz, Brenda V.. Auburn University.; Estados Unidos
dc.description.fil
Fil: Bondesan, Luca. Auburn University.; Estados Unidos
dc.description.fil
Fil: Morata, Guilherme. Auburn University.; Estados Unidos
dc.description.fil
Fil: Damianidis, Damianos. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe; Argentina. Auburn University.; Estados Unidos
dc.journal.title
Transactions of the ASABE
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/10.13031/TRANS.13765
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/url/https://elibrary.asabe.org/abstract.asp?AID=51763&t=3&dabs=Y&redir=&redirType=
Archivos asociados