Although land degradation (LD) is known as a severe environmental problem, spatial predictive modelling of this phenomenon remains a challenge. This research aimed to develop a new conceptual framework to predict LD susceptibility based on net primary production (NPP) and machine learning approaches. The annual NPP over the period 2001–2020 were obtained using MOD17A3 and the trend of NPP changes was considered to investigate the occurrence sites of LD within Qazvin Plain, in Qazvin Province, Iran, under a semiarid climate, with an area of about 9500 km². An inventory map of LD was generated based on the LD study sites. The locations were randomly split-sampled as training (70%) and testing (30%) datasets to evaluate the efficiency of the built models. Fifteen geo-environmental factors were considered as LD predictive variables such as altitude, slope, land use, and temperature. Four advanced machine-learning techniques were performed to model LD susceptibility. Finally, the predictive efficiency of the models was measured utilizing the area under the (ROC) curve Area Under the ROC Curve(AUC) and true skill as statics (TSS). The results indicated that the randomForest (RF), with the AUC = 0.81 and TSS = 0.5, showed the highest efficiency for predicting LD in the Qazvin Plain followed by boosted regression tree (BRT) with AUC = 0.76 and TSS = 0.47, support vector machine (SVM) with AUC = 0.71 and TSS = 0.39, and classification and regression tree (CART) with AUC = 0.63 and TSS = 0.31. The findings illustrated that altitude was the most influential variable within RF, BRT, and SVM while rainfall showed the most important contribution in modelling based on the CART algorithm. This study proposed a new modelling framework that is easily replicable in different contexts for the assessment of LD modelling and analysis.

中文翻译：

---

半干旱地区土地退化空间预测模型的新概念框架

尽管土地退化（LD）被认为是一个严重的环境问题，但这种现象的空间预测模型仍然是一个挑战。本研究旨在开发一个新的概念框架，以基于净初级生产 (NPP) 和机器学习方法预测 LD 易感性。使用MOD17A3获取2001-2020年的年NPP，并考虑NPP变化趋势，调查伊朗加兹温省加兹温平原内半干旱气候下LD的发生地点，面积约9500 km ². 根据 LD 研究地点生成 LD 清单图。这些位置被随机分割采样为训练（70%）和测试（30%）数据集，以评估所构建模型的效率。15 个地理环境因素被视为 LD 预测变量，例如海拔、坡度、土地利用和温度。执行了四种先进的机器学习技术来模拟 LD 敏感性。最后，利用ROC曲线下面积（ROC）和ROC曲线下面积（AUC）和静态技能（TSS）来衡量模型的预测效率。结果表明，AUC = 0.81 和 TSS = 0.5 的随机森林 (RF) 在 Qazvin 平原预测 LD 的效率最高，其次是 AUC = 0.76 和 TSS = 0.47 的增强回归树 (BRT)，支持向量AUC = 0 的机器 (SVM)。71 和 TSS = 0.39，以及 AUC = 0.63 和 TSS = 0.31 的分类和回归树 (CART)。研究结果表明，海拔是 RF、BRT 和 SVM 中影响最大的变量，而降雨在基于 CART 算法的建模中表现出最重要的贡献。本研究提出了一种新的建模框架，该框架易于在不同的环境中复制，用于评估 LD 建模和分析。