More Like this

1. Applying Deep Learning to the Cache Replacement Problem

   Zhan Shi, Xiangru Huang ( October 2019 , International Symposium on Microrchitecture)

   Despite its success in many areas, deep learning is a poor fit for use in hardware predictors because these models are impractically large and slow, but this paper shows how we can use deep learning to help design a new cache replacement policy. We first show that for cache replacement, a powerful LSTM learning model can in an offline setting provide better accuracy than current hardware predictors. We then perform analysis to interpret this LSTM model, deriving a key insight that allows us to design a simple online model that matches the offline model's accuracy with orders of magnitude lower cost. The result is the Glider cache replacement policy, which we evaluate on a set of 33 memory-intensive programs from the SPEC 2006, SPEC 2017, and GAP (graph-processing) benchmark suites. In a single-core setting, Glider outperforms top finishers from the 2nd Cache Replacement Championship, reducing the miss rate over LRU by 8.9%, compared to reductions of 7.1% for Hawkeye, 6.5% for MPPPB, and 7.5% for SHiP++. On a four-core system, Glider improves IPC over LRU by 14.7%, compared with improvements of 13.6% (Hawkeye), 13.2% (MPPPB), and 11.4% (SHiP++). 

   more » « less
2. A Framework for Sustainable Groundwater Management

   https://doi.org/10.3390/w14213416  

   Anandhi, Aavudai ; Karunanidhi, D. ; Sankar, G. Muthu ; Panda, Sudhanshu ; Kannan, Narayanan ( November 2022 , Water)

   This manuscript aims to present the framework for the development of a four-stage tool for sustainable groundwater management as one of the highly interactive three-day workshop products. The four stages in the tool are (1) representing the target system, (2) description of the target system using components of DPSIR framework (drivers, pressures, state, impact, responses), (3) development of causal chains/loops, and (4) identifying knowledge gaps and articulating next steps. The tool is an output from the two-day Indo-US bilateral workshop on "Integrated Hydrochemical Modeling for Sustainable Development and Management of Water Supply Aquifers”. Four case studies from the invited talks, panel discussions, and breakout sessions were selected to demonstrate the developed four-stage framework to a coastal aquifer (India) and in high plains in Floridian, Piedmont, and Blueridge aquifers (United States of America). The developed tool can be practically used in the development of strategies for the sustainable use of groundwater in various regions around the world (e.g., planning/building/maintaining groundwater recharging structures). Continued work can result in establishing a center for excellence as well as developing a network project. The recommendations from the workshop were: (1) developing vulnerability analysis models for groundwater managers; (2) treatment and new ways of using low-quality groundwater; (3) adopting groundwater recharge; (4) mitigating pollutants getting into the aquifer; and (5) reducing groundwater use. This study provides a framework for future researchers to study the groundwater table related to the effectiveness of water recharging structures, developing a quantitative model from the framework. Finally, recommendations for a future study are more data collection on groundwater quality/recharge as well as enhancing outreach activities for sustainable groundwater management. 

   more » « less
3. A Robust Hybrid Deep Learning Model for Spatiotemporal Image Fusion

   https://doi.org/10.3390/rs13245005  

   Yang, Zijun ; Diao, Chunyuan ; Li, Bo ( December 2021 , Remote Sensing)

   Dense time-series remote sensing data with detailed spatial information are highly desired for the monitoring of dynamic earth systems. Due to the sensor tradeoff, most remote sensing systems cannot provide images with both high spatial and temporal resolutions. Spatiotemporal image fusion models provide a feasible solution to generate such a type of satellite imagery, yet existing fusion methods are limited in predicting rapid and/or transient phenological changes. Additionally, a systematic approach to assessing and understanding how varying levels of temporal phenological changes affect fusion results is lacking in spatiotemporal fusion research. The objective of this study is to develop an innovative hybrid deep learning model that can effectively and robustly fuse the satellite imagery of various spatial and temporal resolutions. The proposed model integrates two types of network models: super-resolution convolutional neural network (SRCNN) and long short-term memory (LSTM). SRCNN can enhance the coarse images by restoring degraded spatial details, while LSTM can learn and extract the temporal changing patterns from the time-series images. To systematically assess the effects of varying levels of phenological changes, we identify image phenological transition dates and design three temporal phenological change scenarios representing rapid, moderate, and minimal phenological changes. The hybrid deep learning model, alongside three benchmark fusion models, is assessed in different scenarios of phenological changes. Results indicate the hybrid deep learning model yields significantly better results when rapid or moderate phenological changes are present. It holds great potential in generating high-quality time-series datasets of both high spatial and temporal resolutions, which can further benefit terrestrial system dynamic studies. The innovative approach to understanding phenological changes’ effect will help us better comprehend the strengths and weaknesses of current and future fusion models. 

   more » « less
4. A Coupled SWAT-AEM Modelling Framework for a Comprehensive Hydrologic Assessment

   https://doi.org/10.3390/w14172753  

   Sangeetha, K. ; Narasimhan, Balaji ; Srinivasan, R. ( September 2022 , Water)

   This study attempts to integrate a Surface Water (SW) model Soil and Water Assessment Tool (SWAT) with an existing steady-state, single layer, unconfined heterogeneous aquifer Analytic Element Method (AEM) based Ground Water (GW) model, named Bluebird AEM engine, for a comprehensive assessment of SW and GW resources and its management. The main reason for integrating SWAT with the GW model is that the SWAT model does not simulate the distribution and dynamics of GW levels and recharge rates. To overcome this issue, often the SWAT model is coupled with the numerical GW model (either using MODFLOW or FEFLOW), wherein the spatial and temporal patterns of the interactions are better captured and assessed. However, the major drawback in integrating the two models (SWAT with—MODFLOW/FEM) is its conversion from Hydrological Response Unit’s (HRU)/sub-basins to grid/elements. To couple them, a spatial translation system is necessary to move the inputs and outputs back and forth between the two models due to the difference in discretization. Hence, for effective coupling of SW and GW models, it may be desirable to have both models with a similar spatial discretization and reduce the need for rigorous numerical techniques for solving the PDEs. The objective of this paper is to test the proof of concept of integrating a distributed hydrologic model with an AEM model at the same spatial units, primarily focused on surface water and groundwater interaction with a shallow unconfined aquifer. Analytic Element Method (AEM) based GW models seem to be ideal for coupling with SWAT due to their innate character to consider the HRU, sub-basin, River, and lake boundaries as individual analytic elements directly without the need for any further discretization or modeling units. This study explores the spatio-temporal patterns of groundwater (GW) discharge rates to a river system in a moist-sub humid region with SWAT-AEM applied to the San Jacinto River basin (SJRB) in Texas. The SW-GW interactions are explored throughout the watershed from 2000–2017 using the integrated SWAT-AEM model, which is tested against stream flow and GW levels. The integrated SWAT-AEM model results show good improvement in predicting the stream flow (R2 = 0.65–0.80) and GW levels as compared to the standalone SWAT model. Further, the integrated model predicted the low flows better compared to the standalone SWAT model, thus accounting for the SW-GW interactions. Almost 80% of the stream network experiences an increase in groundwater discharge rate between 2000 and 2017 with an annual average GW discharge rate of 1853 Mm3/year. The result from the study seems promising for potential applications of SWAT-AEM coupling in regions with considerable SW-GW interactions. 

   more » « less
5. Forecasting Groundwater Table in a Flood Prone Coastal City with Long Short-term Memory and Recurrent Neural Networks

   https://doi.org/10.3390/w11051098  

   Bowes, Benjamin D. ; Sadler, Jeffrey M. ; Morsy, Mohamed M. ; Behl, Madhur ; Goodall, Jonathan L. ( May 2019 , Water)

   Many coastal cities are facing frequent flooding from storm events that are made worse by sea level rise and climate change. The groundwater table level in these low relief coastal cities is an important, but often overlooked, factor in the recurrent flooding these locations face. Infiltration of stormwater and water intrusion due to tidal forcing can cause already shallow groundwater tables to quickly rise toward the land surface. This decreases available storage which increases runoff, stormwater system loads, and flooding. Groundwater table forecasts, which could help inform the modeling and management of coastal flooding, are generally unavailable. This study explores two machine learning models, Long Short-term Memory (LSTM) networks and Recurrent Neural Networks (RNN), to model and forecast groundwater table response to storm events in the flood prone coastal city of Norfolk, Virginia. To determine the effect of training data type on model accuracy, two types of datasets (i) the continuous time series and (ii) a dataset of only storm events, created from observed groundwater table, rainfall, and sea level data from 2010–2018 are used to train and test the models. Additionally, a real-time groundwater table forecasting scenario was carried out to compare the models’ abilities to predict groundwater table levels given forecast rainfall and sea level as input data. When modeling the groundwater table with observed data, LSTM networks were found to have more predictive skill than RNNs (root mean squared error (RMSE) of 0.09 m versus 0.14 m, respectively). The real-time forecast scenario showed that models trained only on storm event data outperformed models trained on the continuous time series data (RMSE of 0.07 m versus 0.66 m, respectively) and that LSTM outperformed RNN models. Because models trained with the continuous time series data had much higher RMSE values, they were not suitable for predicting the groundwater table in the real-time scenario when using forecast input data. These results demonstrate the first use of LSTM networks to create hourly forecasts of groundwater table in a coastal city and show they are well suited for creating operational forecasts in real-time. As groundwater table levels increase due to sea level rise, forecasts of groundwater table will become an increasingly valuable part of coastal flood modeling and management. 

   more » « less