The complexity of the interactions between drivers in wind erosion processes and the absence of adequate and reliable data are major constraints to achieving a quantitative assessment of wind erosion. Bayesian Belief Networks (BBNs) provide a useful approach to address real-world problems, where available data and knowledge are disparate, limited or uncertain. We investigated the potential use of BBNs to assess soil erosion risk in a typical arid region that experiences severe wind erosion. The developed framework was based on a standard risk assessment procedure, where the risk of wind erosion was quantified by incorporating assessments of consequence and vulnerability. Performance of the constructed model was evaluated using scenario testing, sensitivity analysis, and wind-tunnel measurements. The model provided reasonable estimates of the soil vulnerability, consequence, and risk to/of wind erosion. The results showed that weather and management factors were the most important parameters affecting wind erosion risk. Based on the fitted regression lines, there were positive (R2 = 0.82) and negative (R2 = 0.72) relationships between the measured wind erosion rates and the predicted probabilities to ‘high’ and ‘low’ vulnerability classes, respectively.

风蚀过程中驱动程序之间相互作用的复杂性以及缺少足够可靠的数据是实现风蚀定量评估的主要限制。贝叶斯信念网络（BBN）提供了一种有用的方法来解决现实世界中的问题，在这些问题中，可用的数据和知识是分散的，有限的或不确定的。我们调查了BBN在潜在的遭受严重风蚀的典型干旱地区评估土壤侵蚀风险的潜在用途。制定的框架基于标准风险评估程序，其中通过合并后果和脆弱性评估来量化风蚀的风险。使用方案测试，灵敏度分析和风洞测量评估了构建模型的性能。该模型提供了土壤脆弱性，后果和风蚀风险的合理估计。结果表明，天气和管理因素是影响风蚀风险的最重要参数。根据拟合的回归线，测得的风蚀率与“高”和“低”脆弱性类别的预测概率之间分别存在正（R2 = 0.82）和负（R2 = 0.72）关系。