Feed-Forward Neural Network for Prediction of Reference Evapotranspiration and Irrigation Scheduling
Keywords:
Evapotranspiration, FNN (Feed-forward Neural Network), Hargreaves-Samani, Irrigation SchedulingAbstract
Water scarcity is a global concern and impacts several facets of human life. India is facing a severe decline in water levels due to overuse in agriculture. Punjab is an agricultural state of India witnessed huge overconsumption of groundwater that needs precise irrigation scheduling. Evapotranspiration is an essential process in hydrology that estimates crop water requirements from evaporation and transpiration losses. The use of weather parameters to predict evapotranspiration is a cost-effective approach for scheduling irrigation in areas without access to specialised evapotranspiration measuring equipment. This study presents and assesses a multilayer Feedforward Neural Network (FNN) for predicting reference evapotranspiration (ETo) in the Fatehgarh Sahib districts of Punjab. The model utilizes an input layer with a number of neurons equivalent to the input parameters. It also incorporates two hidden layers that are activated by the Rectified Linear Unit (ReLU) activation function and an output layer that corresponds to the output. The dataset utilised for testing and training purposes is obtained from a weather forecast website. The dataset employed the Hargreaves-Samani approach to calculate the ETo. The model underwent testing of combinations of input parameters, including Tmean, Tmin, Tmax, Humidity, Wind Speed, Pressure and Cloudiness. The efficacy of the models was evaluated with R2, MSE, and MAE metrics. The optimal outcomes were achieved by considering the parameters Tmean, Tmin, Tmax, Humidity, Wind speed, and Cloudiness, resulting in a R2 of 0.972, MSE of 0.090, and MAE of 0.221. The paper emphasises the utilisation of ETo in the scheduling of irrigation and proposes that in future studies, the model be validated using a larger dataset including many sites in order to further expand its practicality.
Downloads
References
“CGWB Ground Water Resources,” cgwb_ground_water_resources - INDIA WRIS WIKI,
A. A. Farooque et al., “Forecasting daily evapotranspiration using artificial neural networks for sustainable irrigation scheduling,” Irrigation Science, vol. 40, no. 1, pp. 55–69, 2021. doi:10.1007/s00271-021-00751-1
D. D. Khedkar, P. K.Singh, And S. R. Bhakar, “Estimation of evapotranspiration using neural network approach,” Journal of Agrometeorology, vol. 21, no. 2, pp. 233–235, Nov. 2021.
F. Unes, S. Doğan, B. Taşar, and Y. Kaya, “The Evaluation and Comparison of Daily Reference Evapotranspiration with ANN and Empirical Methods,” Natural and Engineering Sciences, pp. 55–63, 2018.
H. Tabari, “Evaluation of Reference Crop Evapotranspiration Equations in Various Climates,” Water Resources Management, vol. 2311–2337, no. 10, Dec. 2009.
History bulk weather data - openweathermap,
J. Abdullahi and G. Elkiran, “Prediction of the future impact of climate change on reference evapotranspiration in Cyprus using artificial neural network,” Procedia Computer Science, vol. 276–283, Jan. 2017.
J. P. Kia, T. A. Far, M. Omid, and R. Alimardani, “Intelligent control based fuzzy logic for automation of greenhouse irrigation system and evaluation in relation to conventional systems,” World Applied Sciences Journal, vol. 6, pp. 6–23, 2009.
K. Djaman et al., “Evaluation of sixteen reference evapotranspiration methods under Sahelian conditions in the Senegal River Valley,” Journal of Hydrology: Regional Studies, vol. 139–159, Mar. 2015.
K. W. Migliaccio, B. Schaffer, J. H. Crane, and F. S. Davies, “Plant response to evapotranspiration and soil water sensor irrigation scheduling methods for papaya production in south Florida,” Agricultural Water Management, vol. 97, no. 10, pp. 1452–1460, Oct. 2010.
M. K. Saggi and S. Jain, “Reference evapotranspiration estimation and modeling of the Punjab Northern India using deep learning,” Computers and Electronics in Agriculture, vol. 156, pp. 387–398, Jan. 2019.
M. Michael, Irrigation Theory and Practice, 2nd ed. S Chand, 2008.
M. T. Sattari, H. Apaydin, S. S. Band, A. Mosavi, and R. Prasad, “Comparative analysis of kernel-based versus ANN and deep learning methods in monthly reference evapotranspiration estimation,” Hydrology and Earth System Sciences, vol. 25, no. 2, pp. 603–618, Feb. 2021.
Mérida García, I. Fernández García, E. Camacho Poyato, P. Montesinos Barrios, and J. A. Rodríguez Díaz, “Coupling irrigation scheduling with solar energy production in a smart irrigation management system,” Journal of Cleaner Production, vol. 175, pp. 670–682, Feb. 2018.
N. Manikumari, A. Murugappan, and G. Vinodhini, “Time Series Forecasting of Daily Reference Evapotranspiration by Neural Network Ensemble Learning for Irrigation System,” IOP Conference Series: Earth and Environmental Science, 2017
Özgür and S. S. Yamaç, “Modelling of daily reference evapotranspiration using deep neural network in different climates,” arXiv Preprint, 2020.
P. De Oliveira E Lucas, M. A. Alves, P. C. De Lima E Silva, and F. G. Guimarães, “Reference evapotranspiration time series forecasting with ensemble of convolutional neural networks,” Computers and Electronics in Agriculture, vol. 105700, Oct. 2020.
S. Adamala, “Temperature based generalized wavelet-neural network models to estimate evapotranspiration in India,” Information Processing in Agriculture, vol. 5, no. 1, pp. 149–155, Mar. 2018.
S. K. Jain, P. C. Nayak, and K. P. Sudheer, “Models for estimating evapotranspiration using artificial neural networks, and their physical interpretation,” Hydrological Processes, vol. 22, no. 13, pp. 2225–2234, 2008, doi: 10.1002/hyp.6819.
S. S. Zanetti, E. F. Sousa, V. P. Oliveira, F. T. Almeida, and S. Bernardo, “Estimating Evapotranspiration Using Artificial Neural Network and Minimum Climatological Data,” Journal of Irrigation and Drainage Engineering, vol. 133, no. 2, pp. 83–89, Apr. 2007, doi: 10.1061/(asce)0733-9437(2007)133:2(83).
S. Shahidian, R. Serralheiro, J. Serrano, J. Teixeira, N. Haie, and F. Santos, “Hargreaves and Other Reduced-Set Methods for Calculating Evapotranspiration,” Evapotranspiration - Remote Sensing and Modeling, Jan. 2012, doi: 10.5772/18059.
S. Walls, A. D. Binns, J. Levison, and S. MacRitchie, “Prediction of actual evapotranspiration by artificial neural network models using data from a Bowen ratio energy balance station,” Neural Computing and Applications, vol. 32, no. 17, pp. 14001–14018, Mar. 2020.
T. Ogunrinde, I. Emmanuel, M. A. Enaboifo, T. A. Ajayi, and Q. B. Pham, “Spatio-temporal calibration of Hargreaves–Samani model in the Northern Region of Nigeria - Theoretical and Applied Climatology,” Theoretical and Applied Climatology, Dec. 2021.
V. Y.Chandrappa, B.Ray, N.Ashwath, and P. Shrestha, “Application of Internet of Things (IoT) to Develop a Smart Watering System for Cairns Parklands – A Case Study,” IEEE Region 10 Symposium (TENSYMP), 2020.
V. Z.Antonopoulos and A. V. Antonopoulos, “Daily reference evapotranspiration estimates by artificial neural networks technique and empirical equations using limited input climate variables,” Computers and Electronics in Agriculture, 132, 86–96,2017.
W. Wang, S. Zou, Z. Luo, W. Zhang, D. Chen, and J. Kong, “Prediction of the Reference Evapotranspiration Using a Chaotic Approach,” The Scientific World Journal, vol. 1–13, Jan. 2014, doi: 10.1155/2014/347625.
Z. Gu, Z. Qi, R. Burghate, S. Yuan, X. Jiao, and J. Xu, “Irrigation Scheduling Approaches and Applications: A Review,” Journal of Irrigation and Drainage Engineering, vol. 146, no. 6, Jun. 2020.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
