Prediction of pore-water pressure response to rainfall using support vector regression

Babangida, Nuraddeen Muhammad; Mustafa, Muhammad Raza Ul; Yusuf, Khamaruzaman Wan; Isa, Mohamed Hasnain

Prediction of pore-water pressure response to rainfall using support vector regression | Prédiction de la réponse de la pression de l’eau interstitielle à la pluie en utilisant la régression à vecteurs de support Predicción de la respuesta de la presión del agua intersticial a la precipitación mediante regresión de vectores de soporte 采用支持向量回归分析预测孔隙水压力对降雨的响应 Predição da resposta da pressão da água no poro à chuva usando regressão por vetores de suporte

2016

Babangida, Nuraddeen Muhammad | Mustafa, Muhammad Raza Ul | Yusuf, Khamaruzaman Wan | Isa, Mohamed Hasnain

Nonlinear complex behavior of pore-water pressure responses to rainfall was modelled using support vector regression (SVR). Pore-water pressure can rise to disturbing levels that may result in slope failure during or after rainfall. Traditionally, monitoring slope pore-water pressure responses to rainfall is tedious and expensive, in that the slope must be instrumented with necessary monitors. Data on rainfall and corresponding responses of pore-water pressure were collected from such a monitoring program at a slope site in Malaysia and used to develop SVR models to predict pore-water pressure fluctuations. Three models, based on their different input configurations, were developed. SVR optimum meta-parameters were obtained using k-fold cross validation and a grid search. Model type 3 was adjudged the best among the models and was used to predict three other points on the slope. For each point, lag intervals of 30 min, 1 h and 2 h were used to make the predictions. The SVR model predictions were compared with predictions made by an artificial neural network model; overall, the SVR model showed slightly better results. Uncertainty quantification analysis was also performed for further model assessment. The uncertainty components were found to be low and tolerable, with d-factor of 0.14 and 74 % of observed data falling within the 95 % confidence bound. The study demonstrated that the SVR model is effective in providing an accurate and quick means of obtaining pore-water pressure response, which may be vital in systems where response information is urgently needed.

Show more [+]