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

Hejar Shahabi,Ben Jarihani,Omid Ghorbanzadeh,Mohammadtaghi Avand,Sepideh Tavakkoli Piralilou,David Chittleborough

doi:10.3390/s19224893

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.

Highlights

In most soil erosion studies, erosion by water is considered a natural part of the geomorphological cycle of the earth system which has destructive impacts on farming, land, and infrastructure.In some cases, the effects are irreparable, especially concerning loss of fertile soil and dam reservoirs sedimentations [1,2]
Within the Burdekin catchment, the Bowen sub-catchment has been identified as the primary source of sediment load to Great Barrier Reef (GBR) that is associated with a high density of gully networks [18,19]; there is the need to detect and predict where gully erosion networks form and expand in the landscape
We applied the multiresolution segmentation method in eCognition 9.1 based on three scale values the segmentation process, same shape index, compactness parameters, and(see bands weights were calculated by the ESP2 toolthe to produce image objects from Sentinel

Summary

Introduction

In most soil erosion studies, erosion by water is considered a natural part of the geomorphological cycle of the earth system which has destructive impacts on farming, land, and infrastructure.In some cases, the effects are irreparable, especially concerning loss of fertile soil and dam reservoirs sedimentations [1,2]. Every year water erosion delivers massive amounts of sediments to dams, estuaries, and near-shore marine environments [3] threatening inland and aquatic ecosystems. Of the four forms of soil erosion—sheet, rill, splash, and gully—gully erosion is recognized as a natural event that affects farmlands, infrastructures, and aquatic ecosystems [4,5,6]. Soil erosion causes these gullies to change the landscape, resulting in land degradation and geomorphic changes to river systems [7,8]. Within the Burdekin catchment, the Bowen sub-catchment has been identified as the primary source of sediment load to GBR that is associated with a high density of gully networks [18,19]; there is the need to detect and predict where gully erosion networks form and expand in the landscape. Our ability to accurately quantify sediment loads contributed by catchments, identify erosion hotspots, and prioritize and target management interventions is currently constrained by a lack of information—at an optimal scale—on both locations, density, and extent of gully systems

Objectives

Results

Discussion

Conclusion