On October 27, 2025, Dr. Diaa Salman, from the Department of Electrical Engineering – Dual Studies, Najjad Zeini Faculty of Engineering, Al-Quds University, published a new study in the journal Cogent Food & Agriculture (Taylor & Francis, ISSN: 2331-1932, Q2, Web of Science SCIE Indexed) titled:
“Multi-model forecasting framework for agricultural nutrient dynamics in India: A comparative analysis of ML and hybrid approaches for NPK consumption.”
The article aimed to develop and evaluate a comprehensive forecasting framework for predicting the dynamics of agricultural nutrients (N, P₂O₅, and K₂O) in India across consumption, export, and import dimensions. The study compared nine forecasting models—ARIMA, Random Forest, SVM, XGBoost, ANN, LSTM, GRU, and hybrid approaches (ARIMA–LSTM, XGBoost–LSTM)—to assess their predictive accuracy using historical FAO and FAI data.
The results demonstrated that ARIMA performed effectively in predicting trade for N and K₂O, while advanced ML models like XGBoost and Random Forest showed superior accuracy in forecasting agricultural consumption. Six-year-ahead forecasts (2024–2029) indicated rising nitrogen consumption, stable phosphorus usage, and increasing potassium demand. These findings provide valuable insights for agricultural policy-making and food security in India.
For more information about the study, please contact the main author at: This email address is being protected from spambots. You need JavaScript enabled to view it. or the Scientific Research Office at: This email address is being protected from spambots. You need JavaScript enabled to view it..
