Comparison of On-Policy Deep Reinforcement Learning A2C with Off-Policy DQN in Irrigation Optimization: A Case Study at a Site in Portugal
Precision irrigation and optimization of water use have become essential factors in agriculture because water is critical for crop growth. The proper management of an irrigation system should enable the farmer to use water efficiently to increase productivity, reduce production costs, and maximize t...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/11/7/104 |
| _version_ | 1797433762384969728 |
|---|---|
| author | Khadijeh Alibabaei Pedro D. Gaspar Eduardo Assunção Saeid Alirezazadeh Tânia M. Lima Vasco N. G. J. Soares João M. L. P. Caldeira |
| author_facet | Khadijeh Alibabaei Pedro D. Gaspar Eduardo Assunção Saeid Alirezazadeh Tânia M. Lima Vasco N. G. J. Soares João M. L. P. Caldeira |
| author_sort | Khadijeh Alibabaei |
| collection | DOAJ |
| description | Precision irrigation and optimization of water use have become essential factors in agriculture because water is critical for crop growth. The proper management of an irrigation system should enable the farmer to use water efficiently to increase productivity, reduce production costs, and maximize the return on investment. Efficient water application techniques are essential prerequisites for sustainable agricultural development based on the conservation of water resources and preservation of the environment. In a previous work, an off-policy deep reinforcement learning model, Deep Q-Network, was implemented to optimize irrigation. The performance of the model was tested for tomato crop at a site in Portugal. In this paper, an on-policy model, Advantage Actor–Critic, is implemented to compare irrigation scheduling with Deep Q-Network for the same tomato crop. The results show that the on-policy model Advantage Actor–Critic reduced water consumption by 20% compared to Deep Q-Network with a slight change in the net reward. These models can be developed to be applied to other cultures with high production in Portugal, such as fruit, cereals, and wine, which also have large water requirements. |
| first_indexed | 2024-03-09T10:20:43Z |
| format | Article |
| id | doaj.art-d30e23110b0f4c6f9882c3ffa8fbc686 |
| institution | Directory Open Access Journal |
| issn | 2073-431X |
| language | English |
| last_indexed | 2024-03-09T10:20:43Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj.art-d30e23110b0f4c6f9882c3ffa8fbc6862023-12-01T22:02:12ZengMDPI AGComputers2073-431X2022-06-0111710410.3390/computers11070104Comparison of On-Policy Deep Reinforcement Learning A2C with Off-Policy DQN in Irrigation Optimization: A Case Study at a Site in PortugalKhadijeh Alibabaei0Pedro D. Gaspar1Eduardo Assunção2Saeid Alirezazadeh3Tânia M. Lima4Vasco N. G. J. Soares5João M. L. P. Caldeira6C-MAST Center for Mechanical and Aerospace Science and Technologies, University of Beira Interior, 6201-001 Covilhã, PortugalC-MAST Center for Mechanical and Aerospace Science and Technologies, University of Beira Interior, 6201-001 Covilhã, PortugalC-MAST Center for Mechanical and Aerospace Science and Technologies, University of Beira Interior, 6201-001 Covilhã, PortugalC4—Cloud Computing Competence Centre (C4-UBI), University of Beira Interior, Rua Marquês d’Ávila e Bolama, 6201-001 Covilhã, PortugalC-MAST Center for Mechanical and Aerospace Science and Technologies, University of Beira Interior, 6201-001 Covilhã, PortugalPolytechnic Institute of Castelo Branco, Av. Pedro Álvares Cabral nº 12, 6000-084 Castelo Branco, PortugalPolytechnic Institute of Castelo Branco, Av. Pedro Álvares Cabral nº 12, 6000-084 Castelo Branco, PortugalPrecision irrigation and optimization of water use have become essential factors in agriculture because water is critical for crop growth. The proper management of an irrigation system should enable the farmer to use water efficiently to increase productivity, reduce production costs, and maximize the return on investment. Efficient water application techniques are essential prerequisites for sustainable agricultural development based on the conservation of water resources and preservation of the environment. In a previous work, an off-policy deep reinforcement learning model, Deep Q-Network, was implemented to optimize irrigation. The performance of the model was tested for tomato crop at a site in Portugal. In this paper, an on-policy model, Advantage Actor–Critic, is implemented to compare irrigation scheduling with Deep Q-Network for the same tomato crop. The results show that the on-policy model Advantage Actor–Critic reduced water consumption by 20% compared to Deep Q-Network with a slight change in the net reward. These models can be developed to be applied to other cultures with high production in Portugal, such as fruit, cereals, and wine, which also have large water requirements.https://www.mdpi.com/2073-431X/11/7/104agriculturedeep learningon-policy deep reinforcement learningirrigation optimization |
| spellingShingle | Khadijeh Alibabaei Pedro D. Gaspar Eduardo Assunção Saeid Alirezazadeh Tânia M. Lima Vasco N. G. J. Soares João M. L. P. Caldeira Comparison of On-Policy Deep Reinforcement Learning A2C with Off-Policy DQN in Irrigation Optimization: A Case Study at a Site in Portugal Computers agriculture deep learning on-policy deep reinforcement learning irrigation optimization |
| title | Comparison of On-Policy Deep Reinforcement Learning A2C with Off-Policy DQN in Irrigation Optimization: A Case Study at a Site in Portugal |
| title_full | Comparison of On-Policy Deep Reinforcement Learning A2C with Off-Policy DQN in Irrigation Optimization: A Case Study at a Site in Portugal |
| title_fullStr | Comparison of On-Policy Deep Reinforcement Learning A2C with Off-Policy DQN in Irrigation Optimization: A Case Study at a Site in Portugal |
| title_full_unstemmed | Comparison of On-Policy Deep Reinforcement Learning A2C with Off-Policy DQN in Irrigation Optimization: A Case Study at a Site in Portugal |
| title_short | Comparison of On-Policy Deep Reinforcement Learning A2C with Off-Policy DQN in Irrigation Optimization: A Case Study at a Site in Portugal |
| title_sort | comparison of on policy deep reinforcement learning a2c with off policy dqn in irrigation optimization a case study at a site in portugal |
| topic | agriculture deep learning on-policy deep reinforcement learning irrigation optimization |
| url | https://www.mdpi.com/2073-431X/11/7/104 |
| work_keys_str_mv | AT khadijehalibabaei comparisonofonpolicydeepreinforcementlearninga2cwithoffpolicydqninirrigationoptimizationacasestudyatasiteinportugal AT pedrodgaspar comparisonofonpolicydeepreinforcementlearninga2cwithoffpolicydqninirrigationoptimizationacasestudyatasiteinportugal AT eduardoassuncao comparisonofonpolicydeepreinforcementlearninga2cwithoffpolicydqninirrigationoptimizationacasestudyatasiteinportugal AT saeidalirezazadeh comparisonofonpolicydeepreinforcementlearninga2cwithoffpolicydqninirrigationoptimizationacasestudyatasiteinportugal AT taniamlima comparisonofonpolicydeepreinforcementlearninga2cwithoffpolicydqninirrigationoptimizationacasestudyatasiteinportugal AT vascongjsoares comparisonofonpolicydeepreinforcementlearninga2cwithoffpolicydqninirrigationoptimizationacasestudyatasiteinportugal AT joaomlpcaldeira comparisonofonpolicydeepreinforcementlearninga2cwithoffpolicydqninirrigationoptimizationacasestudyatasiteinportugal |