Repository logo
 
Publication

Irrigation optimization with a deep reinforcement learning model: Case study on a site in Portugal

2022Journal article Restricted access
Simple item page
dc.contributor.authorAlibabaei, Khadijeh
dc.contributor.authorGaspar, Pedro Dinis
dc.contributor.authorAssunção, Eduardo Timóteo
dc.contributor.authorAlirezazadeh, Saeid
dc.contributor.authorLima, Tânia M.
dc.date.accessioned2024-01-22T16:44:40Z
dc.date.available2024-01-22T16:44:40Z
dc.date.issued2022
dc.description.abstractIn the field of agriculture, the water used for irrigation should be given special treatment, as it is responsible for a large proportion of total water consumption. Irrigation scheduling is critical to food production because it guarantees producers a consistent harvest and minimizes the risk of losses due to water shortages. Therefore, the creation of an automatic irrigation method using new technologies is essential. New methods such as deep learning algorithms have attracted a lot of attention in agriculture and are already being used successfully. In this work, a Deep Q-Network was trained for irrigation scheduling. The agent was trained to schedule irrigation for a tomato field in Portugal. Two Long Short Term Memory models were used as the agent environment. One predicts the total water in the soil profile on the next day. The other one was employed to estimate the yield based on the environmental condition during a season and then measure the net return. The agent uses this information to decide the following irrigation amount. An Artificial Neural Network, a Long Short Term Memory, and a Convolutional Neural Network were used to estimating the Q-table during training. Unlike the Long-Short Terms Memory model, the Artificial Neural Network and the Convolutional Neural Network could not estimate the Q-table, and the agent’s reward decreased during training. The comparison of the performance of the model was done with fixed base irrigation and threshold based irrigation. The trained model increased productivity by 11% and decreased water consumption by 20–30% compared to the fixed method.pt_PT
dc.description.sponsorshipThis work is supported by the project Centro-01-0145- FEDER000017-EMaDeS-Energy, Materials, and Sustainable Development, co-funded by the Portugal 2020 Program (PT 2020), within the Regional Operational Program of the Center (CENTRO 2020) and the EU through the European Regional Development Fund (ERDF). Fundaç˜ ao para a Ciˆencia e a Tecnologia (FCT-MCTES) also provided financial support via project UIDB/00151/2020 (C-MAST). Saeid Alirezazadeh was supported by operation Centro-01-0145-FEDER-000019 - C4 - Centro de Competˆencias em Cloud Computing, co-financed by the European Regional Development Fund (ERDF) through the Programa Operacional Regional do Centro (Centro 2020), in the scope of the Sistema de Apoio a ` Investigaçao ˜ Científica e Tecnologica - Programas Integrados de IC&DT. We would like to express our sincere gratitude for the support provided by AppiZˆezere and DRAP-Centro with the data from the meteorological stations near Fadagosa.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.doi10.1016/j.agwat.2022.107480pt_PT
dc.identifier.urihttp://hdl.handle.net/10400.6/14102
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.relationCentre for Mechanical and Aerospace Science and Technologies
dc.subjectAgriculturept_PT
dc.subjectLSTMpt_PT
dc.subjectDeep Reinforcement Learningpt_PT
dc.subjectIrrigation Schedulingpt_PT
dc.titleIrrigation optimization with a deep reinforcement learning model: Case study on a site in Portugalpt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleCentre for Mechanical and Aerospace Science and Technologies
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F00151%2F2020/PT
oaire.citation.startPage107480pt_PT
oaire.citation.titleAgricultural Water Managementpt_PT
oaire.citation.volume263pt_PT
oaire.fundingStream6817 - DCRRNI ID
person.familyNameAlibabaei
person.familyNameGaspar
person.familyNameAssunção
person.familyNameAlirezazadeh
person.familyNameLima
person.givenNameKhadijeh
person.givenNamePedro Dinis
person.givenNameEduardo Timóteo
person.givenNameSaeid
person.givenNameTânia
person.identifier1710267
person.identifier.ciencia-id6111-9F05-2916
person.identifier.ciencia-id421E-B6CA-E3A1
person.identifier.ciencia-idAC15-2EB3-17DA
person.identifier.ciencia-id771E-3B60-A936
person.identifier.orcid0000-0002-2319-8211
person.identifier.orcid0000-0003-1691-1709
person.identifier.orcid0000-0001-6027-7763
person.identifier.orcid0000-0002-4440-7211
person.identifier.orcid0000-0002-7540-3854
person.identifier.ridN-3016-2013
person.identifier.ridV-5052-2017
person.identifier.scopus-author-id57419570900
person.identifier.scopus-author-id48661120000
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.embargofct© 2022 Elsevier B.V. All rights reserved.pt_PT
rcaap.rightsclosedAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublication42cdea19-a0b8-4e67-89cd-405635dede48
relation.isAuthorOfPublicationb69e2ba0-43af-4cf7-873e-090fd9fc6c94
relation.isAuthorOfPublicationb7f58757-7f13-41ff-9e05-cfbbe587172a
relation.isAuthorOfPublication861343ab-c356-4091-bfeb-143b60a2bb6e
relation.isAuthorOfPublicationef58bc1e-8e06-46cc-93e3-bba8e6ed8388
relation.isAuthorOfPublication.latestForDiscovery861343ab-c356-4091-bfeb-143b60a2bb6e
relation.isProjectOfPublicationc1aeadcb-d7fa-4d70-959a-2447dc0b2276
relation.isProjectOfPublication.latestForDiscoveryc1aeadcb-d7fa-4d70-959a-2447dc0b2276

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
IJI0043-Irrigation optimization with a deep reinforcement learning model.pdf
Size:
5.84 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ICI - C4 | Centro de Competências em Cloud Computing | Documentos por Auto-Depósito
FE - DEM | Documentos por Auto-Depósito
ICI - C-MAST | Documentos por Auto-Depósito