A Semi-Automated Object-Based Gully Networks Detection Using Different Machine Learning Models: A Case Study of Bowen Catchment, Queensland, Australia

Abstract

Gully erosion is a dominant source of sediment and particulates to the Great Barrier Reef (GBR) World Heritage area. We selected the Bowen catchment, a tributary of the Burdekin Basin, as our area of study; the region is associated with a high density of gully networks. We aimed to use a semi-automated object-based gully networks detection process using a combination of multi-source and multi-scale remote sensing and ground-based data. An advanced approach was employed by integrating geographic object-based image analysis (GEOBIA) with current machine learning (ML) models. These included artificial neural networks (ANN), support vector machines (SVM), and random forests (RF), and an ensemble ML model of stacking to deal with the spatial scaling problem in gully networks detection. Spectral indices such as the normalized difference vegetation index (NDVI) and topographic conditioning factors, such as elevation, slope, aspect, topographic wetness index (TWI), slope length (SL), and curvature, were generated from Sentinel 2A images and the ALOS 12-m digital elevation model (DEM), respectively. For image segmentation, the ESP2 tool was used to obtain three optimal scale factors. On using object pureness index (OPI), object matching index (OMI), and object fitness index (OFI), the accuracy of each scale in image segmentation was evaluated. The scale parameter of 45 with OFI of 0.94, which is a combination of OPI and OMI indices, proved to be the optimal scale parameter for image segmentation. Furthermore, segmented objects based on scale 45 were overlaid with 70% and 30% of a prepared gully inventory map to select the ML models’ training and testing objects, respectively. The quantitative accuracy assessment methods of Precision, Recall, and an F1 measure were used to evaluate the model’s performance. Integration of GEOBIA with the stacking model using a scale of 45 resulted in the highest accuracy in detection of gully networks with an F1 measure value of 0.89. Here, we conclude that the adoption of optimal scale object definition in the GEOBIA and application of the ensemble stacking of ML models resulted in higher accuracy in the detection of gully networks.

GIS-Based Gully Erosion Susceptibility Mapping: A Comparison of Computational Ensemble Data Mining Models

“…These methods extract related patterns in historical data to predict future events [73]. Data mining methods used to predict gully erosion include logistic regression (LR) [2,30,[74][75][76][77], artificial neural network (ANN) [20,48,[78][79][80], random subspace (RS) [48,62,81], maximum entropy (ME) [82], artificial neural fuzzy system (ANFIS) [56,[83][84][85][86], support vector machine (SVM) [18,59,73], fuzzy analytical network (FAN) [37], multi-criteria decision analysis (MCDA) [87,88], evidential belief function (EBF) [88,89], classification and regression tree (CART) [90,91], random forest (RF) [39,52,[92][93][94], rotation forest (RoF) [95], weights of evidence (WofE) [96], frequency ratio (FR) [28,97], BFTree for gully headcut [81], boosted regression [24], ADTree, RF-ADTree [73,76,98], and naive B...…”

Flood susceptibility mapping using an improved analytic network process with statistical models

“…Recently, several methods and models have been used to study flood hazards. The wildly applied methods and models for flood hazard mapping are Logistic Regression (LR) (Hong et al 2018;Lee et al 2018;Rahmati et al 2019;Malik et al 2020a), Weights of Evidence (WofE) (Hong et al 2018), Support Vector Machine (SVM) (Hong et al 2018;Tavakkoli Piralilou et al 2019;Ghorbanzadeh et al 2019c), Random Forest (RF) (Avand et al 2019;Chen et al 2019;Darabi et al 2019;Shahabi et al 2019), Frequency Ratio (FR) (Lee et al 2018;Rahman et al 2019), Decision Tree (DT) (Chen et al 2019) and Naïve Bayes Tree (NBT) (Khosravi et al 2019). In addition to these models, multi-criteria decision-making techniques such as the analytic hierarchy process (AHP) (Satty 1980) and the Analytic Network Process (ANP), which is an extended version of the AHP and consider as a more appropriate approach for complex decision problems can also be used for flood hazard mapping (Ahmadlou et al 2019;Kanani-Sadat et al 2019).…”

Earthquake Vulnerability Mapping Using Different Hybrid Models

“…The accuracy of the final map of earthquake susceptibility was evaluated using a ROC. The ROC is a relative factor that shows the position of a class compared to the actual map using the Boolean method and specifies the likelihood of that class [79]. In this method, the area under the curve (AUC) is a graph whose vertical axis represents the actual positive percentage and the horizontal axis represents the false positive percentage [80].…”