Gerardo-Parra et al. (2026) Development of a Neural Network-Based Controller for a Greenhouse Irrigation System at Laboratory Scale

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Agriculture
• Year: 2026
• Date: 2026-01-18
• Authors: Cesar Gerardo-Parra, Luis E. Barreto-Salazar, Lidia Madeleine Flores-López, Julio César Picos-Ponce, David Enrique Castro-Palazuelos, Guillermo Javier Rubio-Astorga
• DOI: 10.3390/agriculture16020245

Research Groups

Not explicitly mentioned in the provided text.

Short Summary

This study designs and experimentally validates a neural network-based irrigation control strategy implemented on an industrial programmable logic controller for a drip irrigation system in a laboratory-scale greenhouse, demonstrating significant improvements in water use efficiency and crop growth compared to a conventional on–off strategy.

Objective

• To evaluate the real-time performance of an intelligent neural network-based irrigation controller under practical operating conditions and to quantify its impact on water use efficiency and crop growth compared to a conventional on–off strategy.

Study Configuration

• Spatial Scale: Laboratory-scale micro-tunnel greenhouse.
• Temporal Scale: 67 days for experimental validation.

Methodology and Data

• Models used: Neural network-based irrigation control strategy.
• Data sources: 1039 experimental data samples collected from the micro-tunnel greenhouse environment and crop response, divided into training (70%), validation (15%), and test (15%) datasets.

Main Results

• The neural network controller achieved higher soil moisture regulation accuracy with a mean squared error (MSE) of 3.2159%, mean absolute error (MAE) of 0.7560%, and standard error (SE) of 0.00001687%.
• It reduced the average daily water consumption per plant by 50.18% compared to the on–off controller.
• The absolute growth rate of serrano chili pepper (Capsicum annuum L.) increased by 26.42% with statistically significant differences.

Contributions

• Demonstrates the effective implementation of neural network-based control on industrial hardware (PLC) for precision irrigation systems.
• Provides tangible benefits for water-efficient agriculture by significantly reducing water consumption and enhancing crop growth in protected environments.

Funding

Not explicitly mentioned in the provided text.

Citation

@article{GerardoParra2026Development,
  author = {Gerardo-Parra, Cesar and Barreto-Salazar, Luis E. and Flores-López, Lidia Madeleine and Picos-Ponce, Julio César and Castro-Palazuelos, David Enrique and Rubio-Astorga, Guillermo Javier},
  title = {Development of a Neural Network-Based Controller for a Greenhouse Irrigation System at Laboratory Scale},
  journal = {Agriculture},
  year = {2026},
  doi = {10.3390/agriculture16020245},
  url = {https://doi.org/10.3390/agriculture16020245}
}