Abstract：
The agricultural sector uses 70% of the world\'s freshwater. As clean water is extracted, groundwater quality decreases, making it difficult to grow crops. Brackish water desalination is a promising solution for agricultural areas, but the cost is a barrier to adoption. This study investigated the performance of the fertilizer drawn forward osmosis (FDFO) process for brackish water desalination using response surface methodology (RSM) and artificial neural network (ANN) approaches. The RSM model was used to identify the optimal operating conditions, and the ANN model was used to predict the water flux (Jw) and reverse solute flux (Js). Both models achieved high accuracy, with RSM excelling in predicting Js (R2 = 0.9614) and ANN performing better for Jw (R2 = 0.9801). Draw solution (DS) concentration emerged as the most critical factor for both models, having a relative importance of 100% for two outputs. The optimal operating conditions identified by RSM were a DS concentration of 22 mol L-1, and identical feed solution (FS) and DS velocities of 8.1 cm s-1. This configuration yielded a high Jw of 4.386 LMH and a low Js of 0.392 gMH. Furthermore, the study evaluated the applicability of FDFO for real brackish groundwater. The results confirm FDFO\'s potential as a viable technology for water recovery in agriculture. The standalone FO system proves to be less energy-intensive than other desalination technologies. However, FO exhibits a low recovery rate, which may necessitate further dilution for fertigation purposes.
摘要：
农业部门使用了世界上70%的淡水。当干净的水被提取出来时，地下水质量下降，使其难以种植庄稼。微咸水淡化是农业领域的一个有前途的解决方案，但是成本是采用的障碍。这项研究使用响应面法（RSM）和人工神经网络（ANN）方法研究了微咸水脱盐的肥料正向渗透（FDFO）工艺的性能。RSM模型用于确定最佳操作条件，并利用人工神经网络模型预测水通量(Jw)和反向溶质通量(Js)。两种模型都实现了高精度，RSM在预测Js方面表现优异（R2=0.9614），ANN在Jw方面表现更好（R2=0.9801）。汲取溶液(DS)浓度成为两种模型的最关键因素，对于两个输出具有100%的相对重要性。RSM确定的最佳操作条件是DS浓度为22molL-1，相同的进料溶液（FS）和DS速度为8.1cms-1。该配置产生4.386LMH的高Jw和0.392gMH的低Js。此外，该研究评估了FDFO对实际微咸地下水的适用性。结果证实了FDFO作为农业水回收可行技术的潜力。事实证明，独立的FO系统比其他海水淡化技术能耗低。然而,FO的回收率低，这可能需要进一步稀释以灌溉施肥。
