A novel conformable fractional seasonal Grey Bernoulli Model with new information priority: case studies in urban water demand forecasting

Purpose Rapid urbanization, population growth, and shifting consumption patterns have placed increasing pressure on urban water supply systems, making reliable forecasting of monthly clean water delivery essential for effective infrastructure planning and sustainable resource management. To address this need, this study proposes a novel seasonal grey model to forecast monthly urban water demand. Design/methodology/approach This study proposes a novel Seasonal Optimized New Information Priority Conformable Fractional Grey Bernoulli Model, integrating a two-step moving average seasonal decomposition, a conformable fractional accumulation operator satisfying the new information priority principle, a nonlinear grey Bernoulli differential equation, and the Jaya algorithm for simultaneous parameter tuning. Findings The proposed model is validated on the monthly observations of clean water demand in Istanbul and benchmarked against several forecasting models including the Seasonal Autoregressive Integrated Moving Average (SARIMA) model and Long Short-Term Memory (LSTM). The results reveal that the proposed model outperforms traditional forecasting models in terms of both accuracy and predictive power. Its transferability is further examined through two additional case studies on monthly water supply in Izmir, Turkey and monthly residential water consumption in Austin, Texas, where the model likewise achieves highly accurate forecasts. Research limitations/implications A limitation of this study stems from the unavailability of complete annual data for the most recent years — 2024 and 2025 for Istanbul, and 2025 for Izmir and Austin, where only partial-year observations were available at the time of analysis. As with any data-driven methodology, this constraint may affect the accuracy of forecasts for subsequent years. Originality/value This study is the first to integrate the new information priority conformable fractional accumulation operator into a seasonal grey Bernoulli framework and the first to apply it to urban water demand forecasting, preserving computational simplicity while ensuring that recent observations receive greater influence.