Toward Sustainable Farming: Implementing Artificial Intelligence to Predict Optimum Water and Energy Requirements for Sensor-Based Micro Irrigation Systems Powered by Solar PV

Future trends in climate change, water scarcity, and energy costs will motivate agriculturists to develop innovative agricultural systems. In order to achieve sustainable farming in arid regions, there is an urgent need to use artificial intelligence (AI) to predict and estimate the optimum water and energy requirements for the irrigation of date palms. Therefore, this study aimed to predict the optimum water and energy requirements for date palm irrigation depending on the optimum water use efficiency (WUE) and yield in arid conditions. To achieve this aim, four solar-powered micro irrigation systems were developed and evaluated under six irrigation levels for date palm irrigation. Soil moisture sensor-based controllers were used to automate irrigation scheduling for the micro irrigation systems. The water pumping in these systems was powered using a solar photovoltaic (PV) system. In addition, four machine-learning (ML) algorithms, including linear regression (LR), support vector regression (SVR), long short-term memory (LSTM) neural network, and extreme gradient boosting (XGBoost), were developed and validated for prediction purposes. These models were developed in Python programing language using the Keras library. The results indicated that the optimum WUS was achieved when the maximum setpoints of irrigation control were adjusted at the field capacity and by adjusting the minimum setpoints at 40, 50, 70, and 80% of the available water (AW). The optimum yield was achieved by adjusting the minimum setpoints at 60, 70, 80, and 90% of AW for subsurface irrigation, subsurface drip irrigation, drip irrigation, and bubbler irrigation, respectively. Therefore, the dataset was prepared at these levels for four years to train and test the models, and a fifth year was used to validate the performance of the best model. The evaluation of the models showed that the LSTM followed by XGBoost models were more accurate than the SVR and LR models for predicting the optimum irrigation water and energy requirements. The validation result showed that the LSTM was able to predict the water and energy requirements for all irrigation systems with R2 ranging from 0.90 to 0.92 based on limited meteorological variables and date palm age. The findings of the current study demonstrated that the developed LSTM model can be a powerful tool in irrigation water and energy management as a fast and easy-to-use approach.

[1]  H. Ghazzawy,et al.  Combined Impact of Irrigation, Potassium Fertilizer, and Thinning Treatments on Yield, Skin Separation, and Physicochemical Properties of Date Palm Fruits , 2023, Plants.

[2]  H. El-Shafie,et al.  Development and Validation of Innovative Machine Learning Models for Predicting Date Palm Mite Infestation on Fruits , 2023, Agronomy.

[3]  H. Ghazzawy,et al.  Design and Evaluation of a Smart Ex Vitro Acclimatization System for Tissue Culture Plantlets , 2022, Agronomy.

[4]  B. Numbi,et al.  Development of a Linear Regression Model Based on the Most Influential Predictors for a Research Office Cooling Load , 2022, Energies.

[5]  M. Mohammed,et al.  Design of a Smart IoT-Based Control System for Remotely Managing Cold Storage Facilities , 2022, Sensors.

[6]  M. Mohammed,et al.  Prediction of Date Fruit Quality Attributes during Cold Storage Based on Their Electrical Properties Using Artificial Neural Networks Models , 2022, Foods.

[7]  Jesús Cejas Montero,et al.  Prediction Model of Photovoltaic Power in Solar Pumping Systems Based on Artificial Intelligence , 2022, Agronomy.

[8]  M. Munir,et al.  Effects of Automated Irrigation Systems and Water Regimes on Soil Properties, Water Productivity, Yield and Fruit Quality of Date Palm , 2022, Agriculture.

[9]  Travis J. Esau,et al.  Precision Irrigation Management Using Machine Learning and Digital Farming Solutions , 2022, AgriEngineering.

[10]  Ángel Arroyo,et al.  Humidity forecasting in a potato plantation using time-series neural models , 2022, J. Comput. Sci..

[11]  M. Mohammed,et al.  Effects of Deficit Irrigation Scheduling on Water Use, Gas Exchange, Yield, and Fruit Quality of Date Palm , 2021, Agronomy.

[12]  M. Munir,et al.  Effects of Pollination Interventions, Plant Age and Source on Hormonal Patterns and Fruit Set of Date Palm (Phoenix dactylifera L.) , 2021, Horticulturae.

[13]  M. Eltawil,et al.  Design of a solar PV powered variable frequency drive for a bubbler irrigation system in palm trees fields , 2021 .

[14]  Matthijs J. Warrens,et al.  The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation , 2021, PeerJ Comput. Sci..

[15]  Hala Hamdoun,et al.  Deep LSTM-Based Transfer Learning Approach for Coherent Forecasts in Hierarchical Time Series , 2021, Sensors.

[16]  Alaa El. Sagheer,et al.  Energy time series forecasting-analytical and empirical assessment of conventional and machine learning models , 2021, J. Intell. Fuzzy Syst..

[17]  Khaled Riad,et al.  Efficient IoT-Based Control for a Smart Subsurface Irrigation System to Enhance Irrigation Management of Date Palm , 2021, Sensors.

[18]  Liheng Tuo,et al.  Time series forecast of sales volume based on XGBoost , 2021 .

[19]  H. J. Shareef,et al.  Adapting date palm offshoots to long-term irrigation using groundwater in sandy soil , 2021 .

[20]  Alaa Sagheer,et al.  A Cloud-Based IoT Platform for Precision Control of Soilless Greenhouse Cultivation , 2020, Sensors.

[21]  M. Munir,et al.  Impact of a Novel Water-Saving Subsurface Irrigation System on Water Productivity, Photosynthetic Characteristics, Yield, and Fruit Quality of Date Palm under Arid Conditions , 2020, Agronomy.

[22]  Jongyun Kim,et al.  Maintaining a constant soil moisture level can enhance the growth and phenolic content of sweet basil better than fluctuating irrigation , 2020 .

[23]  Salinda Buyamin,et al.  IoT-based monitoring and data-driven modelling of drip irrigation system for mustard leaf cultivation experiment , 2020 .

[24]  Hui Qin,et al.  Comparison of support vector regression and extreme gradient boosting for decomposition-based data-driven 10-day streamflow forecasting , 2020, Journal of Hydrology.

[25]  Rubén San-Segundo,et al.  A Decision Support System for Irrigation Management: Analysis and Implementation of Different Learning Techniques , 2020, Water.

[26]  Alaa Sagheer,et al.  Unsupervised Pre-training of a Deep LSTM-based Stacked Autoencoder for Multivariate Time Series Forecasting Problems , 2019, Scientific Reports.

[27]  H. Piepho.  A coefficient of determination (R2) for generalized linear mixed models , 2019, Biometrical journal. Biometrische Zeitschrift.

[28]  A. Al-Omran,et al.  Crop water requirements of date palm based on actual applied water and Penman–Monteith calculations in Saudi Arabia , 2019, Applied Water Science.

[29]  Qunying Liu,et al.  XGBoost-Based Algorithm Interpretation and Application on Post-Fault Transient Stability Status Prediction of Power System , 2019, IEEE Access.

[30]  Alaa El. Sagheer,et al.  Time series forecasting of petroleum production using deep LSTM recurrent networks , 2019, Neurocomputing.

[31]  Ahmed Tealab,et al.  Time series forecasting using artificial neural networks methodologies: A systematic review , 2018, Future Computing and Informatics Journal.

[32]  C. Rama Krishna,et al.  An IoT based smart irrigation management system using Machine learning and open source technologies , 2018, Computers and Electronics in Agriculture.

[33]  M. Meron,et al.  Applying high-resolution visible-channel aerial imaging of crop canopy to precision irrigation management , 2018, Agricultural Water Management.

[34]  Yeqiang Wen,et al.  Optimization of irrigation scheduling for spring wheat with mulching and limited irrigation water in an arid climate , 2017 .

[35]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[36]  J. Mailhol,et al.  Compensatory uptake functions in empirical macroscopic root water uptake models: experimental and numerical analysis , 2015 .

[37]  Shafiqur Rehman,et al.  Performance Comparison of Diesel and Solar Photovoltaic Power Systems for Water Pumping in Saudi Arabia , 2015 .

[38]  H. Samia,et al.  Date Palm (Phoenix dactylifera L.) Irrigation Water Requirements as Affected by Salinity in Oued Righ Conditions, North Eastern Sahara, Algeria , 2015 .

[39]  S. M. Ismail,et al.  OPTIMIZATION OF IRRIGATION WATER USE, YIELD, AND QUALITY OF 'NABBUT‐SAIF' DATE PALM UNDER DRY LAND CONDITIONS , 2014 .

[40]  Paulo Cortez,et al.  Evolutionary Support Vector Machines for Time Series Forecasting , 2012, ICANN.

[41]  Effi Tripler,et al.  Long-term growth, water consumption and yield of date palm as a function of salinity , 2011 .

[42]  R. Tol,et al.  Water scarcity and the impact of improved irrigation management: a computable general equilibrium analysis , 2011 .

[43]  Ravi Sankar,et al.  Time Series Prediction Using Support Vector Machines: A Survey , 2009, IEEE Computational Intelligence Magazine.

[44]  Rob J Hyndman,et al.  Another look at measures of forecast accuracy , 2006 .

[45]  S. Alam.  Nutrient Uptake by Plants Under Stress Conditions , 1999 .

[46]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[47]  Trinh Tan Dat,et al.  Stock-Price Forecasting Based on XGBoost and LSTM , 2022, Comput. Syst. Sci. Eng..

[48]  Abhishek Jain,et al.  IoT and Machine Learning Approaches for Automation of Farm Irrigation System , 2020 .

[49]  Dharam J. Shah,et al.  Implementation of artificial intelligence in agriculture for optimisation of irrigation and application of pesticides and herbicides , 2020, Artificial Intelligence in Agriculture.

[50]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[51]  Corso Elvezia.  Bridging Long Time Lags by Weight Guessing and \long Short Term Memory" , 1996 .