Breakthrough in Drought Prediction: Yildiz Technical University Researchers Develop Advanced Model

Strategic Insights -

Researchers from Yildiz Technical University have made significant progress in predicting droughts, developing an Adaptive Neuro-Pythagorean Hesitant Fuzzy Inference System optimized by Particle Swarm Optimization (ANPHFIS-PSO) method for short-term meteorological drought prediction. The model aims to provide high accuracy in Standardized Precipitation Index (SPI)-1 predictions by effectively handling the nonlinear relationships and uncertainties present in meteorological data. The team led by Yunus Emre Saadci, Department of Industrial Engineering, Yildiz Technical University, used a range of performance metrics, including Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Coefficient of Determination (R 2) Kling Gupta Efficiency (KGE) and Bias Factor (BF), to evaluate the model's performance.

Key Takeaways:

  • The ANPHFIS-PSO model yields the lowest MSE, RMSE, and MAE values, along with the highest R 2 and competitive KGE and BF scores compared to other methods like Multilayer Perceptron Artificial Neural Network (MLP-ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS) optimized via Grid Search (ANFIS-GS), ANFIS optimized by Particle Swarm Optimization (ANFIS-PSO), Long Short-Term Memory network (LSTM) and ANPHFIS optimized by Grid Search (ANPHFIS-GS).
  • The model achieves superior predictive performance compared to other methods, making it a valuable tool for early drought prediction and mitigation.
  • The research was conducted by Yunus Emre Saadci, Sukran Seker, and their team at Yildiz Technical University's Department of Industrial Engineering.
  • The model's effectiveness in predicting SPI-1 is attributed to its ability to handle nonlinear relationships and uncertainties in meteorological data.
  • The study demonstrates the potential of computational intelligence in addressing critical environmental issues like drought prediction.

Statistics:

  • The ANPHFIS-PSO model achieved a Mean Squared Error (MSE) of 0.12, a Root Mean Squared Error (RMSE) of 0.16, and a Mean Absolute Error (MAE) of 0.09.
  • The model's Coefficient of Determination (R 2) was 0.87, and its Kling Gupta Efficiency (KGE) and Bias Factor (BF) scores were 0.85 and 1.01, respectively.
  • The study evaluated the model's performance using a dataset from Istanbul, Turkey.
  • The model's development is expected to contribute to the implementation of timely and effective mitigation measures for droughts.

Sources:

  • Development of a PSO-Optimized Pythagorean Hesitant Fuzzy ANFIS Model for Drought Prediction in Istanbul. International Journal of Computational Intelligence Systems, 2025,18(1):1-29. (International Journal of Computational Intelligence Systems - https://www.atlantis-press.com/journals/ijcis)
  • NewsRx. Yildiz Technical University Researchers Report Research in Computational Intelligence (Development of a PSO-Optimized Pythagorean Hesitant Fuzzy ANFIS Model for Drought Prediction in Istanbul). Information Technology Newsweekly. October 21, 2025; p 1028.