A new conceptual framework for spatial predictive modelling of land degradation in a semiarid area

Abstract

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.

Land Subsidence Susceptibility Mapping Using Interferometric Synthetic Aperture Radar (InSAR) and Machine Learning Models in a Semiarid Region of Iran

“…In order to assess the efficacy of the ML models, a commonly employed approach involves partitioning the available dataset into training and validation subsets, typically using a 70% to 30% data split [41]. For the identification of model inputs, the recursive feature elimination (RFE) model was used [42], and jackknife resampling was used to determine the most influential variables [43]. Additional detailed information is provided in the forthcoming text.…”

“…For example, the jackknife (cross-validation) test is a type of valuable analysis that helps to identify the relationship between LS occurrence, vulnerability, and influencing variables. Hence, this study investigated the importance of 27 variables used in modeling LS maps using the Jackknife test [43,78] in RStudio software.…”

“…ML is now considered as a practical tool to improve environmental management practices in LS-prone regions [95]. To address the most determinant LS susceptibility variables, the jackknife test [43,78] was applied to evaluate the relative importance of each variable. For all three models, distance from a mine (DFM), distance from a syncline (DFS), distance from a dam (DFD), and distance from a fault (DFF) were identified as the most crucial input variables, as shown in Figure 7.…”