Predicting soil moisture quantity could directly help the people engaged in sustainable agriculture and associated socio-economic structures. Recently researchers have engaged traditional and machine learning based models to predict soil moisture quantity. In the current study a modified Flower Pollination Algorithm (MFPA) has been employed to train Artificial Neural Network (ANN) to predict soil moisture quantity. The proposed method is compared with well known PSO (Particle Swarm optimization) supported ANN and Cuckoo Search (CS) supported ANN along with MLP-FFN classifier. The stability of the proposed model in presence of varying weather conditions has been established by performing a stability analysis using data level perturbation. Experimental results have indicated that NN-MFPA achieved an average RMSE of 0.0019 and outperformed other models. The ingenuity of the proposed model is further established by performing Wilcoxon rank test with 5% level of significance.

预测土壤湿度可以直接帮助从事可持续农业和相关社会经济结构的人们。最近，研究人员采用了传统的和基于机器学习的模型来预测土壤湿度。在当前的研究中，已采用改进的花授粉算法（MFPA）来训练人工神经网络（ANN）来预测土壤水分含量。将该方法与著名的PSO（粒子群优化）支持的ANN和布谷鸟搜索（CS）支持的ANN以及MLP-FFN分类器进行了比较。通过使用数据级别摄动进行稳定性分析，可以确定所提出模型在不同天气条件下的稳定性。实验结果表明，NN-MFPA的平均RMSE为0。0019，并胜过其他型号。通过执行具有5％显着性水平的Wilcoxon等级检验，进一步建立了所提出模型的独创性。