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.
more »
« less
Rainfall pulses increased short-term biocrust chlorophyll but not fungal abundance or N availability in a long-term dryland rainfall manipulation experiment
More Like this
-
-
Niinemets, Ülo (Ed.)Abstract High latitude forests cope with considerable variation in moisture and temperature at multiple temporal scales. To assess how their photosynthetic physiology responds to short- and long-term temperature variation, we measured photosynthetic capacity for four tree species growing in an open-air experiment in the boreal-temperate ecotone `Boreal Forest Warming at an Ecotone in Danger' (B4WarmED). The experiment factorially manipulated temperature above- and below-ground (ambient, +3.2 °C) and summer rainfall (ambient, 40% removal). We measured A/Ci curves at 18, 25 and 32 °C for individuals of two boreal (Pinus banksiana Lamb., Betula papyrifera Marsh.) and two temperate species (Pinus strobus L., Acer rubrum L.) experiencing the long-term warming and/or reduced-rainfall conditions induced by our experimental treatments. We calculated the apparent photosynthetic capacity descriptors VCmax,Ci and Jmax,Ci and their ratio for each measurement temperate. We hypothesized that (i) VCmax,Ci and Jmax,Ci would be down-regulated in plants experiencing longer term (e.g., weeks to months) warming and reduced rainfall (i.e., have lower values at a given measurement temperature), as is sometimes found in the literature, and that (ii) plants growing at warmer temperatures or from warmer ranges would show greater sensitivity (steeper slope) to short-term (minutes to hours) temperature variation. Neither hypothesis was supported as a general trend across the four species, as there was not a significant main effect (across species) of either warming or rainfall reduction on VCmax,Ci and Jmax,Ci. All species markedly increased VCmax,Ci and Jmax,Ci (and decreased their ratio) with short-term increases in temperature (i.e., contrasting values at 18, 25 and 32 °C), and those responses were independent of long-term treatments and did not differ among species. The Jmax,Ci:VCmax,Ci ratio was, however, significantly lower across species in warmed and reduced rainfall treatments. Collectively, these results suggest that boreal trees possess considerable short-term plasticity that may allow homeostasis of VCmax,Ci and Jmax,Ci to a longer term temperature treatment. Our results also caution against extrapolating results obtained under controlled and markedly contrasting temperature treatments to responses of photosynthetic parameters to more modest temperature changes expected in the near-term with climate warming in field conditions.more » « less
-
null (Ed.)Abstract. In the past decades, data-driven machine-learning (ML) models have emerged as promising tools for short-term streamflow forecasting. Among other qualities, the popularity of ML models for such applications is due to their relative ease in implementation, less strict distributional assumption, and competitive computational and predictive performance. Despite the encouraging results, most applications of ML for streamflow forecasting have been limited to watersheds in which rainfall is the major source of runoff. In this study, we evaluate the potential of random forests (RFs), a popular ML method, to make streamflow forecasts at 1 d of lead time at 86 watersheds in the Pacific Northwest. These watersheds cover diverse climatic conditions and physiographic settings and exhibit varied contributions of rainfall and snowmelt to their streamflow. Watersheds are classified into three hydrologic regimes based on the timing of center-of-annual flow volume: rainfall-dominated, transient, and snowmelt-dominated. RF performance is benchmarked against naïve and multiple linear regression (MLR) models and evaluated using four criteria: coefficient of determination, root mean squared error, mean absolute error, and Kling–Gupta efficiency (KGE). Model evaluation scores suggest that the RF performs better in snowmelt-driven watersheds compared to rainfall-driven watersheds. The largest improvements in forecasts compared to benchmark models are found among rainfall-driven watersheds. RF performance deteriorates with increases in catchment slope and soil sandiness. We note disagreement between two popular measures of RF variable importance and recommend jointly considering these measures with the physical processes under study. These and other results presented provide new insights for effective application of RF-based streamflow forecasting.more » « less
-
Hydroclimate interpretations of stalagmite δ18O records from tropical regions requires an understanding of the temporal integration of rainfall amount and its isotopic composition by drip waters that form stalagmite deposits. This study presents oxygen (δ18O) and hydrogen (δD) isotopic results from over 1200 groundwater, rainfall and drip water samples, collected at ~weekly time intervals, over three hydrological years at Río Secreto Cave, in the Yucatán Peninsula, Mexico. Cave environmental conditions and the isotopic composition of drip water were monitored in three chambers with different degrees of air ventilation, along with temperature and relative humidity conditions at the surface. We examined 16 drips and observed that annual δD and δ18O variability reflects the isotopic variability of rainfall to varying degrees. The observed annual amplitude of drip water isotopic variability represents between 5% and 95% of that of rainfall, reflecting epikarst water reservoir size and the complexity of flow paths. Drips that closely reflect the isotopic variability of rainfall and best preserve the isotopic signal of individual rainfall events are observed, but they are uncommon. Only two drips out of 16 were found to have potential to record rainfall isotopic shifts associated with tropical cyclones if sampled at weekly resolution. The relationship between δD and δ18O in drip water suggests that recharge is biased toward the rainy season (June to November), which represents up to 80% of total annual precipitation. We find that over the course of a year most drips reflect the annual δ18O composition of rainfall, in support of quantitative precipitation estimates from stalagmite δ18O records. We find evidence that the effective recharge in this cave system is controlled by precipitation amount and that recharge is not limited to the months when precipitation exceeds evaporation.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1016/j.soilbio.2019.107693
