In the present study, an improved adaptive neuro fuzzy inference system (ANFIS) and multilayer perceptron (MLP) models are hybridized with a sunflower optimization (SO) algorithm and are introduced for lake water level simulation. The Urmia Lake water level is predicted and assessed using the potential of the proposed advanced artificial intelligence (AI) models. The sunflower optimization algorithm is implemented to find the optimal tuning parameters. The results indicated that the ANFIS-SO model with the combination of three lags of rainfall and temperature as input attributes attained the best predictability performance. The minimal values of the root mean square error were RMSE = 1.89 m and 1.92 m for the training and testing modeling phases, respectively. The worst prediction capacity was attained for the long lead (i.e., six months rainfall lag times). The uncertainty analysis showed that the ANFIS-SO model had less uncertainty based on the percentage of more responses in the confidence band and lower bandwidth. Also, different scenarios of water harvesting were investigated with the consideration of environmental restrictions and fair water allocation to stakeholders. Further, studying Urmia Lake water harvesting scenarios displayed that the 30% water harvesting scenario of the lake water improves the lake’s water level.

在本研究中，将改进的自适应神经模糊推理系统（ANFIS）和多层感知器（MLP）模型与向日葵优化（SO）算法混合，并引入到湖水位模拟中。乌尔米亚湖的水位是利用建议的高级人工智能（AI）模型的潜力进行预测和评估的。执行向日葵优化算法以找到最佳调整参数。结果表明，将降雨和温度的三个滞后相结合作为输入属性的ANFIS-SO模型获得了最佳的可预测性。在训练和测试建模阶段，均方根误差的最小值分别为RMSE = 1.89 m和1.92 m。对于长潜在客户而言，预测能力最差（例如，六个月的降雨滞后时间）。不确定性分析表明，基于置信带中更多响应和更低带宽的百分比，ANFIS-SO模型的不确定性较小。此外，还考虑了环境限制和公平分配给利益相关者的情况，研究了不同的集水方案。此外，对Urmia湖集水方案的研究表明，湖水集水方案的30％可以改善湖泊的水位。