A Remote Sensing-Based Approach for Debris-Flow Susceptibility Assessment Using Artificial Neural Networks and Logistic Regression Modeling

Abstract

Efforts to map the distribution of debris flows, to assess the factors controlling their development, and to identify the areas susceptible to their occurrences are often hampered by the paucity of monitoring systems and historical databases in many parts of the world. In this paper, we develop and successfully apply methodologies that rely heavily on readily available remote-sensing datasets over the Jazan province in the Red Sea hills of Saudi Arabia. A fivefold exercise was conducted: 1) a geographical information system (GIS) with a Web interface was generated to host and analyze relevant coregistered remote-sensing data and derived products; 2) an inventory was compiled for debris flows identified from satellite datasets (e.g., GeoEye, Orbview), a subset of which was field verified; 3) spatial analyses were conducted in a GIS environment and 10 predisposing factors were identified; 4) an artificial neural network (ANN) model and a logistic regression (LR) model were constructed, optimized, and validated; and 5) the generated models were used to produce debris-flow susceptibility maps. Findings include: 1) excellent prediction performance for both models (ANN: 96.1%; LR: 96.3%); 2) the high correspondence between model outputs (91.5% of the predictions were common) reinforces the validity of the debris-flow susceptibility results; 3) the variables with the highest predictive power were topographic position index (TPI), slope, distance to drainage line (DTDL), and normalized difference vegetation index (NDVI); and 4) the adopted methodologies are reliable, cost-effective, and could potentially be applied over many of the world's data-scarce mountainous lands, particularly along the Red Sea Hills.Index Terms-Artificial neural networks (ANN), data mining, data-scarce field regions, debris flows, geographical information system (GIS), logistic regression (LR), remote sensing.

Landslide susceptibility mapping using random forest, boosted regression tree, classification and regression tree, and general linear models and comparison of their performance at Wadi Tayyah Basin, Asir Region, Saudi Arabia

“…3a, b). Other features that can help in detecting landslides include the presence of flow materials along gullies, rims, and streams with different erosional features, flow tracks, and depositional fans (Elkadiri et al 2014). In addition to these, circular and planar failures could be identified easily from the high-resolution satellite imagery according to different morphological features such as bare breaks and head and side scarps ( Fig.…”

“…Landslides are common erosion processes in the southwestern and western parts of Saudi Arabia, where many cities, highways, and roads are located along the Arabian shield, the main mountain ranges (Elkadiri et al 2014;Youssef et al 2014a, b, c). These mountain ranges are well known by the steep scarps that lead to the generation of spectacular landforms.…”

“…Elkadiri et al (2014) studied the debrisflow susceptibility assessment using artificial neural networks and logistic regression models. Youssef et al (2014b) assessed landslide susceptibility using ensemble FR and Logistic regression models for Fayfa Area, Saudi Arabia.…”

“…In recent years, several attempts of slope stability and landslide susceptibility mapping were applied in Saudi Arabia (Youssef et al 2012(Youssef et al , 2014aYoussef and Maerz 2013;Elkadiri et al 2014;Maerz et al 2014). …”

High-Resolution Debris Flow Volume Mapping With Unmanned Aerial Systems (Uas) and Photogrammetric Techniques

“…However, to our knowledge, so far very few publications exist that deal with UAS-based debris flow event mapping (Sotier et al, 2013;Wen et al, 2011). The use of other remote sensing data for this task, reported in the current literature, include high-resolution satellite imagery (Youssef et al, 2014;Elkadiri et al, 2014), manned aircraft photographs (Dietrich & Krautblatter, 2016), airborne laser scanning (ALS) (Bull et al, 2010;Scheidl et al, 2008) or a combination of the above (Willi et al, 2015).…”