Long Short-Term Memory Neural Network for irrigation management: a case study from Southern Alabama, USA
- PDF / 3,391,284 Bytes
- 18 Pages / 439.37 x 666.142 pts Page_size
- 43 Downloads / 204 Views
Long Short‑Term Memory Neural Network for irrigation management: a case study from Southern Alabama, USA Andres‑F. Jimenez1,2,3 · Brenda V. Ortiz1 · Luca Bondesan1,4 · Guilherme Morata1 · Damianos Damianidis1
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract The metabolism and growth of vegetation are highly dependent on the changes in soil water content. Irrigation scheduling and application of water at the right time and rate are a key aspect for precision irrigation. In this study, the Long Short-Term Memory (LSTM) Neural Network model was studied to predict irrigation prescriptions for 1, 3, 6, 12 and 24 h in advance. Training data for LSTM were collected from a precision irrigation study conducted in Alabama, USA. The prediction estimation of irrigation prescription used soil matric potential data measured within two contrasting soil types. Performance of the LSTM models were evaluated by comparing neural network parameters and prediction capability by soil type. The optimal learning algorithm for each case was also determined. The LSTM Neural Network showed good prediction capabilities for both soil types, with R2 ranging between 0.82 and 0.98 for one hour ahead prescription and getting smaller as prediction time increases. The irrigation rate prediction was verified by actual observations that demonstrate the suitability of the machine learning technique as a decision-support tool for irrigation scheduling. Keywords Corn · Irrigation prescription · Long-Short Term Memory Neural Network · Precision irrigation · Soil matric potential
Introduction Irrigation can reduce crop production risks and even increase the crop yield, especially on areas with degraded soils or irregular rainfall (Gutzler et al. 2015). Adopting improved land and water management practices among other sustainable activities can assist farmers in the definition of irrigation scheduling and, therefore, achieve an increase of water use efficiency (Levidow et al. 2014). Precision irrigation is the sustainable management of water resources and involves the application of water to the crop at the right time, in the right amount, right place and right manner, to meet specific plant water demands, while avoiding excessive or insufficient irrigation (Adeyemi et al. 2018). * Andres‑F. Jimenez [email protected] Extended author information available on the last page of the article
13
Vol.:(0123456789)
Precision Agriculture
For ensuring an adequate soil water for crop growth, real-time monitoring of soil moisture can be used at several soil depths (Seidel et al. 2016). However, this monitoring and the estimations derived represent a complex non-linear problem due to the relationship between climatic parameters, soil hydraulic properties, and soil moisture dynamics (Mashayekhi et al. 2016). Spatial variability of soil moisture is related to within-field variability of soil properties and elevation and their assessment are necessary to support variable rate irrigation (Levidow et al. 2014). Temporal
Data Loading...
