ABSTRACT
In the mountainous region of Asir region of Saudi Arabia, road construction activities are closely associated with frequent landslides, posing significant risks to both human life and infrastructural development. This highlights an urgent need for a highly accurate landslide susceptibility map to guide future development and risk mitigation strategies. Therefore, this study aims to (1) develop robust well-optimised deep learning (DL) models for predicting landslide susceptibility and (2) conduct a comprehensive sensitivity analysis to quantify the impact of each parameter influencing landslides. To achieve these aims, three advanced DL models-Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), and Bayesian-optimised CNN with an attention mechanism-were rigorously trained and validated. Model validation included eight matrices, calibration curves, and Receiver Operating Characteristic (ROC) and Precision-Recall curves. Multicollinearity was examined using Variance Inflation Factor (VIF) to ensure variable independence. Additionally, sensitivity analysis was used to interpret the models and explore the influence of parameters on landslide. Results showed that road networks significantly influenced the areas identified as high-risk zones. Specifically, in the 1-km buffer around roadways, CNN_AM identified 10.42% of the area as 'Very High' susceptibility-more than double the 4.04% indicated by DNN. In the extended 2-km buffer zone around roadways, Bayesian CNN_AM continued to flag a larger area as Very High risk (7.46%), in contrast to DNN's 3.07%. In performance metrics, CNN_AM outshined DNN and regular CNN models, achieving near-perfect scores in Area Under the Curve (AUC), precision-recall, and overall accuracy. Sensitivity analysis highlighted 'Soil Texture', 'Geology', 'Distance to Road', and 'Slope' as crucial for landslide prediction. This research offers a robust, high-accuracy model that emphasises the role of road networks in landslide susceptibility, thereby providing valuable insights for planners and policymakers to proactively mitigate landslide risks in vulnerable zones near existing and future road infrastructure.
Subject(s)
Deep Learning , Landslides , Humans , Geographic Information Systems , Bayes Theorem , Saudi ArabiaABSTRACT
The current study tries to cut carbon emissions by using various waste materials in place of cement, including sugarcane bagasse ash (SCBA), ground granulated blast furnace slag (GGBFS), and ladle furnace slag (LFS), individually and in a combined form also, which has not been studied yet. In the same context, effort was made to utilize the maximum amount of waste materials as the replacement of cement to create a sustainable environment. Besides this, another aim is checking the performance of these waste materials as binding materials with respect to compressive strength for sustainable rigid pavement construction without activating them or using any activating solution. For this purpose, the compressive strength test is done for GGBFS, LFS, and SCBA, and later on, the artificial neural network (ANN) technique is also used to check the novelty of results in a broad way. For the same purpose, M40 grade concrete was made by incorporating different selected waste materials in a varying proportion ranging from 0 to 35%. Based on the results obtained from the compressive strength test for different curing periods, i.e., 7, 14, and 28 days, it was observed that the GGBFS, LFS, and SCBA can be utilized individually up to 15%, respectively. Another observation made from the findings was that the use of LFS and SCBA in the individual form up to 20% was found to be possible as the maximum reduction in strength was found to be up to 2.63%. However, the cumulative impact of all these waste products was also examined. Based on the data, it was concluded that the best outcomes would arise from using these additives in combination to replace cement in the mix by up to 30% (i.e., without compromising the required characteristics of concrete), which will be proved as an aid to the environment and the society also. Besides this, the fluctuation in the compressive strength value of concrete mixes after integrating various waste materials was also examined in order to construct a model using the ANN approach. The model's outcomes suggest that the ANN model does a good job of forecasting the compressive strength of concrete.