Spatial assessment employing fusion logistic regression and frequency ratio models to monitor landslide susceptibility in the upper Blue Nile basin of Ethiopia: Muger watershed

ENVIRONMENTAL SYSTEMS RESEARCH, Journal Year: 2024, Volume and Issue: 13(1)

Published: Nov. 22, 2024

At the global level, landslides are a dreadful hazard that restricts socio-economic and ecological balances. Recent human activities in hilly areas, coupled with geological predispositions, have potentially exacerbated landslide frequency magnitude. However, impacts of these factors on occurrences upper Blue Nile basin Ethiopia remain largely unexplored. This study aims to identify triggers, quantify landslide-susceptible zones, validate models. Topographic parameters, geology, hydrology, land use-land cover inventories were utilized generate susceptibility map. The analyzed using combination logistic regression (LR) ratio (FR) area under curve (AUC) receiver operating characteristic (ROC) was used compare performance result indicates about 185 sq. km (40.2%) total falls high very-high susceptible 92 (20%) moderate susceptibility. Yet, 183.1 is classified low-to-no zones. LR FR model validation demonstrated an average predictive 75 81.45%, indicating good precision. evaluation can help policymakers LSH zones for early warning systems mitigation purposes.

Language: Английский

---

Landslide Hazard Risk and Vulnerability Monitoring—GIS Based Approach

Advances in natural and technological hazards research, Journal Year: 2024, Volume and Issue: unknown, P. 53 - 86

Published: Jan. 1, 2024

Language: Английский

---

Geomatics, soft computing, and innovative simulator: prediction of susceptibility to landslide risk

AIMS Geosciences, Journal Year: 2024, Volume and Issue: 10(2), P. 399 - 418

Published: Jan. 1, 2024

<abstract> <p>Landslides represent a growing threat among the various morphological processes that cause damage to territories. To address this problem and prevent associated risks, it is essential quickly find adequate methodologies capable of predicting these phenomena in advance. The following study focuses on implementation an experimental WebGIS infrastructure designed built predict susceptibility index specific presumably at-risk area real time (using input data) response extreme weather events (such as heavy rain). climate data values are calculated through innovative atmospheric simulator developed by authors, which providing meteorological variables with high spatial precision. end, terrain represented cellular automata, implementing suitable neural network useful for producing desired output. effectiveness methodology was tested two debris flow occurred Calabria region, specifically province Reggio Calabria, 2001 2005, caused extensive damage. (forecast) results obtained proposed were compared (known) historical data, confirming method (and therefore signaling possibility imminent landslide event) higher than known one provided (to date) Higher Institute Environmental Protection Research (ISPRA), validating result actual subsequent occurrence event under investigation. Therefore, today not aimed at local movement small area, but primarily change or improving variation compare predicted value current relevant bodies thus alert entire investigation.</p> </abstract>

Language: Английский

---

Coping with the tale of natural resources and environmental inequality: an application of the machine learning tools

Environmental Science and Pollution Research, Journal Year: 2024, Volume and Issue: 31(40), P. 52841 - 52854

Published: Aug. 20, 2024

Language: Английский

---

Evaluating landslide hazard, vulnerability, and risk using machine learning; A case study from the Alaknanda Valley, NW Himalaya

Environment Development and Sustainability, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 5, 2024

Language: Английский

---