Danandeh Mehr Ali, Shadkani Sadra, Abualigah Laith, Safari Mir Jafar Sadegh, Migdady Hazem
Civil Engineering Department, Antalya Bilim University, Antalya, 07190, Turkey.
Department of Water Engineering, University of Tabriz, Tabriz, Iran.
Heliyon. 2024 Jul 4;10(13):e34142. doi: 10.1016/j.heliyon.2024.e34142. eCollection 2024 Jul 15.
Existing artificial neural networks (ANNs) have attempted to efficiently identify underlying patterns in environmental series, but their structure optimization needs a trial-and-error process or an external optimization effort. This makes ANNs time consuming and more complex to be applied in practice. To alleviate these issues, we propose a stabilized ANNs, called SANN. The SANN efficiently optimizes ANN structure via incorporation of an additional numeric parameter into every layer of the ANN. To exemplify the efficacy and efficiency of the proposed approach, we provided two practical case studies involving meteorological drought forecasting at cities of Burdur and Isparta, Türkiye. To enhance SANN forecasting accuracy, we further suggested the hybrid VMD-SANN that integrated variation mode decomposition (VMD) with SANN. To validate the new hybrid model, we compared its results with those obtained from hybrid VMD-ANN and VMD-Radial Base Function (VMD-RBF) models. The results showed superiority of the VMD-SANN to its counterparts. Regarding Nash Sutcliffe Efficiency measure, the VMD-SANN achieves accurate forecasts as high as 0.945 and 0.980 in Burdur and Isparta cities, respectively.
现有的人工神经网络（ANNs）已尝试有效识别环境序列中的潜在模式，但其结构优化需要反复试验过程或外部优化努力。这使得人工神经网络在实际应用中既耗时又复杂。为缓解这些问题，我们提出了一种稳定的人工神经网络，称为SANN。SANN通过在人工神经网络的每一层中加入一个额外的数值参数来有效优化人工神经网络结构。为举例说明所提方法的有效性和效率，我们提供了两个实际案例研究，涉及土耳其布尔杜尔市和伊斯帕尔塔市的气象干旱预测。为提高SANN的预测准确性，我们进一步提出了将变分模态分解（VMD）与SANN相结合的混合VMD-SANN。为验证新的混合模型，我们将其结果与从混合VMD-ANN和VMD-径向基函数（VMD-RBF）模型获得的结果进行了比较。结果表明VMD-SANN优于其同类模型。关于纳什-萨特克利夫效率度量，VMD-SANN在布尔杜尔市和伊斯帕尔塔市分别实现了高达0.945和0.980的准确预测。
