Enhancing the accuracy of rainfall-induced landslide prediction along mountain roads with a GIS-based random forest classifier

Along mountain roads, rainfall-triggered landslides are typical disasters that cause significant human casualties. Thus, to establish effective mitigation measures, it would be very useful were government agencies and practicing land-use planners to have the capability to make an accurate landslide evaluation. Here, we propose a machine learning methodology for the spatial prediction of rainfall-induced landslides along mountain roads which is based on a random forest classifier (RFC) and a GIS-based dataset. The RFC is used as a supervised learning technique to generalize the classification boundary that separates the input information of ten landslide conditioning factors (slope, aspect, relief amplitude, toposhape, topographic wetness index, distance to roads, distance to rivers, lithology, distance to faults, and rainfall) into two distinctive class labels: ‘landslide’ and ‘non-landslide’. Experimental results with a cross validation process and sensitivity analysis on the RFC model parameters reveal that the proposed model achieves a superior prediction accuracy with an area under the curve  of 0.92. The RFC significantly outperforms other benchmarking methods, including discriminant analysis, logistic regression, artificial neural networks, relevance vector machines, and support vector machines. Based on our experimental outcome and comparative analysis, we strongly recommend the RFC as a very capable tool for spatial modeling of rainfall-induced landslides.

     

Prediction of long-term deflections of reinforced-concrete members using a novel swarm optimized extreme gradient boosting machine

During the life cycle of buildings and infrastructure systems, the deflection of reinforced-concrete members generally increases due to both internal and external factors. Accurate forecasting of long-term deflection of these members can significantly enhance the effectiveness of structural maintenance processes. This research develops a hybrid data-driven method which employs the extreme gradient boosting machine and the particle swarm optimization metaheuristic for predicting long-term deflections of reinforced-concrete members. The former, a machine learning technique, generalizes a non-linear mapping function that helps to infer long-term deflection results from the input data. The later, a swarm-based metaheuristic, aims at optimizing the machine learning model by fine-tuning its hyper-parameters. The proposed hybridization of machine learning and swarm intelligence is constructed and verified by a dataset consisting of 217 experiments. The experiment results, supported by statistical tests, point out that the hybrid framework is able to attain good predictive performances with average root-mean-square error of 11.38 (a reduction of 17.4%), and average coefficient of determination of 0.88 (an increase of 6.0%) compared to the non-hybrid model. These results also outperform those obtained by other popular techniques, including Backpropagation Neural Networks and Regression Tree in several popular benchmarks, such as root-mean-square error, mean absolute percentage error, and the coefficient of determination R². This is backed up by statistical tests with the level of significance \(\alpha = 0.05\). Therefore, the newly developed model can be a promising tool to assist civil engineers in forecasting deflections of reinforced-concrete members.