Department of Natural Resources Engineering, University of Hormozgan, Bandar-Abbas, Hormozgan, Iran.
Department of Electrical and Computer Engineering, University of Hormozgan, Bandar-Abbas, Hormozgan, Iran.
Sci Rep. 2022 Sep 7;12(1):15167. doi: 10.1038/s41598-022-19357-4.
This research introduces a new combined modelling approach for mapping soil salinity in the Minab plain in southern Iran. This study assessed the uncertainty (with 95% confidence limits) and interpretability of two deep learning (DL) models (deep boltzmann machine-DBM) and a one dimensional convolutional neural networks (1DCNN)-long short-term memory (LSTM) hybrid model (1DCNN-LSTM) for mapping soil salinity by applying DeepQuantreg and game theory (Shapely Additive exPlanations (SHAP) and permutation feature importance measure (PFIM)), respectively. Based on stepwise forward regression (SFR)-a technique for controlling factor selection, 18 of 47 potential controls were selected as effective factors. Inventory maps of soil salinity were generated based on 476 surface soil samples collected for measuring electrical conductivity (ECe). Based on Taylor diagrams, both DL models performed well (RMSE < 20%), but the 1DCNN-LSTM hybrid model performed slightly better than the DBM model. The uncertainty range associated with the ECe values predicted by both models estimated using DeepQuantilreg were similar (0-25 dS/m for the 1DCNN-LSTM hybrid model and 2-27 dS/m for DBM model). Based on the SFR and PFIM (permutation feature importance measure)-a measure in game theory, four controls (evaporation, sand content, precipitation and vertical distance to channel) were selected as the most important factors for soil salinity in the study area. The results of SHAP (Shapely Additive exPlanations)-the second measure used in game theory-suggested that five factors (evaporation, vertical distance to channel, sand content, cation exchange capacity (CEC) and digital elevation model (DEM)) have the strongest impact on model outputs. Overall, the methodology used in this study is recommend for applications in other regions for mapping environmental problems.
本研究提出了一种新的联合建模方法，用于绘制伊朗南部米纳布平原的土壤盐度图。本研究通过应用 DeepQuantreg 和博弈论（Shapely Additive exPlanations (SHAP) 和排列特征重要性度量 (PFIM)），分别评估了两种深度学习 (DL) 模型（深度玻尔兹曼机-DBM）和一维卷积神经网络 (1DCNN)-长短期记忆 (LSTM) 混合模型（1DCNN-LSTM）在映射土壤盐度方面的不确定性（置信限为 95%）和可解释性。基于逐步正向回归 (SFR)——一种控制因子选择的技术，从 47 个潜在控制因素中选择了 18 个作为有效因素。根据 476 个采集土壤电导率 (ECe) 的表层土壤样本生成土壤盐度库存图。基于 Taylor 图，两种 DL 模型均表现良好（RMSE < 20%），但 1DCNN-LSTM 混合模型的性能略优于 DBM 模型。使用 DeepQuantilreg 估计的与两个模型预测的 ECe 值相关的不确定性范围相似（1DCNN-LSTM 混合模型为 0-25 dS/m，DBM 模型为 2-27 dS/m）。基于逐步正向回归 (SFR) 和排列特征重要性度量 (PFIM)——博弈论中的一种度量方法，选择了四个控制因素（蒸发、沙含量、降水和垂直距离到河道）作为研究区域土壤盐度的最重要因素。博弈论中的第二种度量方法 SHAP（Shapely Additive exPlanations）的结果表明，有五个因素（蒸发、垂直距离到河道、沙含量、阳离子交换量 (CEC) 和数字高程模型 (DEM)) 对模型输出的影响最强。总的来说，本研究中使用的方法推荐用于其他地区绘制环境问题的地图。
