The Rise of Groundwater Due to Rainfall and the Control of Landslide by Zero-Energy Groundwater Withdrawal System

Alsubal, Shamsan; Sapari, Nasiman; Harahap, Indra Sati Hamonangan

doi:10.14419/ijet.v7i2.29.14284

Cited by 8 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The memory cell is updated each time step by the forget gate and the input gate, enabling the cell to store information for a long time without a gradient vanishing problem. The output of the memory cell C t is calculated using Equation (18). The forget gate is responsible for forgetting irrelevant information from the past [52,54].…”

Section: Background: Long Short-term Memorymentioning

confidence: 99%

“…Additionally, the rain infiltrating the slope increases the degree of saturation and the unit weight of soil. The resultant increase in soil saturation also causes a decrease in the matric suction and shear strength of the unsaturated soil [16][17][18][19], which can adversely impact the safety of geosystems such as slopes. The magnitude and rate of the impact on the soil properties and the safety factor of a slope depend on the intensity and the duration of the rain [20,21].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Long Short-Term Memory Based Subsurface Drainage Control for Rainfall-Induced Landslide Prevention

et al. 2022

View full text Add to dashboard Cite

Subsurface drainage has been widely accepted to mitigate the hazard of landslides in areas prone to flooding. Specifically, the use of drainage wells with pumping systems has been recognized as an effective short-term solution to lower the groundwater table. However, this method has not been well considered for long-term purposes due to potentially high labor costs. This study aims to investigate the idea of an autonomous pumping system for subsurface drainage by leveraging conventional geotechnical engineering solutions and a deep learning technique—Long-Short Term Memory (LSTM)—to establish a geotechnical cyber-physical system for rainfall-induced landslide prevention. For this purpose, a typical soil slope equipped with three pumps was considered in a computer simulation. Forty-eight cases of rainfall events with a wide range of varieties in duration, total rainfall depths, and different rainfall patterns were generated. For each rainfall event, transient seepage analysis was performed using newly proposed Python code to obtain the corresponding pump’s flow rate data. A policy of water pumping for maintaining groundwater at a desired level was assigned to the pumps to generate the data. The LSTM takes rainfall event data as the input and predicts the required pump’s flow rate. The results from the trained model were validated using evaluation metrics of root mean square error (RMSE), mean absolute error (MAE), and R2. The R2-scores of 0.958, 0.962, and 0.954 for the predicted flow rates of the three pumps exhibited high accuracy of the predictions using the trained LSTM model. This study is intended to make a pioneering step toward reaching an autonomous pumping system and lowering the operational costs in controlling geosystems.

show abstract

Section: Background: Long Short-term Memorymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Long Short-Term Memory Based Subsurface Drainage Control for Rainfall-Induced Landslide Prevention

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In Central America and the Caribbean, for example, heavy rainfall was the cause of approximately 90% of the landslides recorded in the Enhanced Durham Fatal Landslides Database (EDFLD) [ 5 ]. Prolonged intense rainfall events reduce the stability of the slope by increasing the groundwater table and the degree of saturation above the groundwater table and consequently decreasing the unsaturated soil shear strength [ 6 , 7 , 8 , 9 ]. The frequency of heavy rainfall events has escalated in recent years as a result of climate change, which has increased the likelihood of landslide occurrence in general [ 10 , 11 , 12 ].…”

Section: Introductionmentioning

confidence: 99%

Intelligent Control of Groundwater in Slopes with Deep Reinforcement Learning

Biniyaz

Azmoon²,

Liu³

2022

Sensors

View full text Add to dashboard Cite

The occurrence of landslides has been increasing in recent years due to intense and prolonged rainfall events. Lowering the groundwater in natural and man-made slopes can help to mitigate the hazards. Subsurface drainage systems equipped with pumps have traditionally been regarded as a temporary remedy for lowering the groundwater in geosystems, whereas long-term usage of pumping-based techniques is uncommon due to the associated high operational costs in labor and energy. This study investigates the intelligent control of groundwater in slopes enabled by deep reinforcement learning (DRL), a subfield of machine learning for automated decision-making. The purpose is to develop an autonomous geosystem that can minimize the operating cost and enhance the system’s safety without introducing human errors and interventions. To prove the concept, a seepage analysis model was implemented using a partial differential equation solver, FEniCS, to simulate the geosystem (i.e., a slope equipped with a pump and subjected to rainfall events). A Deep Q-Network (i.e., a DRL learning agent) was trained to learn the optimal control policy for regulating the pump’s flow rate. The objective is to enable intermittent control of the pump’s flow rate (i.e., 0%, 25%, 50%, 75%, and 100% of the pumping capacity) to keep the groundwater close to the target level during rainfall events and consequently help to prevent slope failure. A comparison of the results with traditional proportional-integral-derivative-controlled and uncontrolled water tables showed that the geosystem integrated with DRL can dynamically adapt its response to diverse weather events by adjusting the pump’s flow rate and improve the adopted control policy by gaining more experience over time. In addition, it was observed that the DRL control helped to mitigate slope failure during rainfall events.

show abstract

“…(Li et al, 2020) also compared the effect of rain on changes in groundwater levels to the in uence of the population development in an area. The changes in the slope factor of safety due to variation in rainfall were also discussed by (Alsubal, Sapari and Harahap, 2018). It was discovered that the slope factor of safety with high soil permeability drops from 1.312 to 1.292 and 1.093 after the third rainfall event for the slope with and without pumping groundwater, respectively.…”

Section: Introductionmentioning

confidence: 99%

Effectiveness of Horizontal Sub-drain to Increase Slope Stability with Vertical Cracks and Weathering Soil in Areas with High Rainfall Intensity

Sari

Mochtar

Chaiyaput

2022

Preprint

View full text Add to dashboard Cite

A landslide occurred a few meters from the foot of the power plant tower in a hilly area in the Tulakan District, Pacitan, East Java Province, Indonesia. This incidence occurred after the area was flooded with a cumulative intensity of more than 1000 mm in one month and a maximum daily rainfall above 300 mm. Previous reports considered horizontal sub-drain cost-effective to reduce the groundwater level and the impact of rainwater seepage into the soil on slope stability. Therefore, this study aims to determine the effectiveness of horizontal sub-drain as an alternative for managing groundwater and rainwater that seeps into the soil to increase the slope factor of safety. The effect of real-time rainfall for 30 days before the landslide, hydraulic conductivity, changes in soil parameters due to cracking and weathering, and the existing groundwater level are also considered. The analyses were carried out using the coupled program SEEP/W for transient seepage and SLOPE/W with finite element method and limit equilibrium. The result showed that horizontal sub-drain increases the slope factor of safety from critical limit to more than 1.1 in 30 days of rainfall in high ground water level condition. The hydraulic conductivity parameters of the soil, the location of the horizontal sub-drain, as well as the cracked and weathered conditions in the soil also affect the effectiveness. In low-level ground water conditions, the duration of the rain and the intensity of the rain also greatly affect the effectiveness of the horizontal sub-drain as well as the number of cracks. In this condition, the safety factor on the slope with the horizontal sub-drain can increase the safety factor from less than one to more than one thus the slope becomes more stable. The results of this study also show that the effectiveness of the horizontal sub-drain is very sensitive to many things, therefore in its planning it is necessary to review many aspects more carefully.

show abstract

The Rise of Groundwater Due to Rainfall and the Control of Landslide by Zero-Energy Groundwater Withdrawal System

Cited by 8 publications

References 28 publications

Long Short-Term Memory Based Subsurface Drainage Control for Rainfall-Induced Landslide Prevention

Long Short-Term Memory Based Subsurface Drainage Control for Rainfall-Induced Landslide Prevention

Intelligent Control of Groundwater in Slopes with Deep Reinforcement Learning

Effectiveness of Horizontal Sub-drain to Increase Slope Stability with Vertical Cracks and Weathering Soil in Areas with High Rainfall Intensity

Contact Info

Product

Resources

About