This page has only limited features, please log in for full access.
Understanding climate and human impacts on water storage is critical for sustainable water-resources management. Here we assessed climate and human drivers of total water storage (TWS) variability from Gravity Recovery and Climate Experiment (GRACE) satellites compared with drought severity and irrigation water use in 14 major aquifers in the United States. Results show that long-term variability in TWS tracked by GRACE satellites is dominated by interannual variability in most of the 14 major US aquifers. Low TWS trends in the humid eastern U.S. are linked to low drought intensity. Although irrigation pumpage in the humid Mississippi Embayment aquifer exceeded that in the semi-arid California Central Valley, a surprising lack of TWS depletion in the Mississippi Embayment aquifer is attributed to extensive streamflow capture. Marked storage depletion in the semi-arid southwestern Central Valley and south-central High Plains totaled ∼90 km3, about three times greater than the capacity of Lake Mead, the largest U.S. reservoir. Depletion in the Central Valley was driven by long-term droughts (⩽5 yr) amplified by switching from mostly surface water to groundwater irrigation. Low or slightly rising TWS trends in the northwestern (Columbia and Snake Basins) US are attributed to dampening drought impacts by mostly surface water irrigation. GRACE satellite data highlight synergies between climate and irrigation, resulting in little impact on TWS in the humid east, amplified TWS depletion in the semi-arid southwest and southcentral US, and dampened TWS deletion in the northwest and north central US Sustainable groundwater management benefits from conjunctive use of surface water and groundwater, inefficient surface water irrigation promoting groundwater recharge, efficient groundwater irrigation minimizing depletion, and increasing managed aquifer recharge. This study has important implications for sustainable water development in many regions globally.
Bridget R Scanlon; Ashraf Rateb; Donald R Pool; Ward Sanford; Himanshu Save; Alexander Sun; Di Long; Brian Fuchs. Effects of climate and irrigation on GRACE-based estimates of water storage changes in major US aquifers. Environmental Research Letters 2021, 16, 094009 .
AMA StyleBridget R Scanlon, Ashraf Rateb, Donald R Pool, Ward Sanford, Himanshu Save, Alexander Sun, Di Long, Brian Fuchs. Effects of climate and irrigation on GRACE-based estimates of water storage changes in major US aquifers. Environmental Research Letters. 2021; 16 (9):094009.
Chicago/Turabian StyleBridget R Scanlon; Ashraf Rateb; Donald R Pool; Ward Sanford; Himanshu Save; Alexander Sun; Di Long; Brian Fuchs. 2021. "Effects of climate and irrigation on GRACE-based estimates of water storage changes in major US aquifers." Environmental Research Letters 16, no. 9: 094009.
Fractional calculus-based differential equations were found by previous studies to be promising tools in simulating local-scale anomalous diffusion for pollutants transport in natural geological media (geomedia), but efficient models are still needed for simulating anomalous transport over a broad spectrum of scales. This study proposed a hierarchical framework of fractional advection-dispersion equations (FADEs) for modeling pollutants moving in the river corridor at a full spectrum of scales. Applications showed that the fixed-index FADE could model bed sediment and manganese transport in streams at the geomorphologic unit scale, whereas the variable-index FADE well fitted bedload snapshots at the reach scale with spatially varying indices. Further analyses revealed that the selection of the FADEs depended on the scale, type of the geomedium (i.e., riverbed, aquifer, or soil), and the type of available observation dataset (i.e., the tracer snapshot or breakthrough curve (BTC)). When the pollutant BTC was used, a single-index FADE with scale-dependent parameters could fit the data by upscaling anomalous transport without mapping the sub-grid, intermediate multi-index anomalous diffusion. Pollutant transport in geomedia, therefore, may exhibit complex anomalous scaling in space (and/or time), and the identification of the FADE’s index for the reach-scale anomalous transport, which links the geomorphologic unit and watershed scales, is the core for reliable applications of fractional calculus in hydrology.
Yong Zhang; Dongbao Zhou; Wei Wei; Jonathan Frame; Hongguang Sun; Alexander Sun; Xingyuan Chen. Hierarchical Fractional Advection-Dispersion Equation (FADE) to Quantify Anomalous Transport in River Corridor over a Broad Spectrum of Scales: Theory and Applications. Mathematics 2021, 9, 790 .
AMA StyleYong Zhang, Dongbao Zhou, Wei Wei, Jonathan Frame, Hongguang Sun, Alexander Sun, Xingyuan Chen. Hierarchical Fractional Advection-Dispersion Equation (FADE) to Quantify Anomalous Transport in River Corridor over a Broad Spectrum of Scales: Theory and Applications. Mathematics. 2021; 9 (7):790.
Chicago/Turabian StyleYong Zhang; Dongbao Zhou; Wei Wei; Jonathan Frame; Hongguang Sun; Alexander Sun; Xingyuan Chen. 2021. "Hierarchical Fractional Advection-Dispersion Equation (FADE) to Quantify Anomalous Transport in River Corridor over a Broad Spectrum of Scales: Theory and Applications." Mathematics 9, no. 7: 790.
The Gravity Recovery and Climate Experiment (GRACE) satellite mission and its follow‐on, GRACE‐FO, have provided unprecedented opportunities to quantify the impact of climate extremes and human activities on total water storage at large scales. The approximately one‐year data gap between the two GRACE missions needs to be filled to maintain data continuity and maximize mission benefits. In this study, we applied an automated machine learning (AutoML) workflow to perform gridwise GRACE‐like data reconstruction. AutoML represents a new paradigm for optimal algorithm selection, model structure selection, and hyperparameter tuning, addressing some of the most challenging issues in machine learning applications. We demonstrated the workflow over the conterminous U.S. (CONUS) using six types of machine learning models and multiple groups of meteorological and climatic variables as predictors. Results indicate that the AutoML‐assisted gap filling achieved satisfactory performance over the CONUS. On the testing data, the mean gridwise Nash‐Sutcliffe efficiency is around 0.85, the mean correlation coefficient is around 0.95, and the mean normalized root‐mean square error is about 0.09. Trained models maintain good performance when extrapolating to the mission gap and to GRACE‐FO periods (after 2017/06). Results further suggest that no single algorithm provides the best predictive performance over the entire CONUS, stressing the importance of using an end‐to‐end workflow to train, optimize, and combine multiple machine learning models to deliver robust performance, especially when building large‐scale hydrological prediction systems and when predictor importance exhibiting strong spatial variability.This article is protected by copyright. All rights reserved.
Alexander Y. Sun; Bridget R. Scanlon; Himanshu Save; Ashraf Rateb. Reconstruction of GRACE Total Water Storage Through Automated Machine Learning. Water Resources Research 2021, 57, 1 .
AMA StyleAlexander Y. Sun, Bridget R. Scanlon, Himanshu Save, Ashraf Rateb. Reconstruction of GRACE Total Water Storage Through Automated Machine Learning. Water Resources Research. 2021; 57 (2):1.
Chicago/Turabian StyleAlexander Y. Sun; Bridget R. Scanlon; Himanshu Save; Ashraf Rateb. 2021. "Reconstruction of GRACE Total Water Storage Through Automated Machine Learning." Water Resources Research 57, no. 2: 1.
GRACE satellite data are widely used to estimate groundwater (GW) storage (GWS) changes in aquifers globally; however, comparisons with GW monitoring and modeling data are limited. Here we compared GWS changes from GRACE over 15 years (yr) (2002–2017) in 14 major U.S. aquifers with GW‐level (GWL) monitoring data in ~23,000 wells and with regional and global hydrologic and land surface models. Results show declining GWS trends from GRACE data in the six south‐western and south‐central U.S. aquifers, totaling ‐90 km3 over 15 yr, related to long‐term (5–15 yr) droughts, and exceeding Lake Mead volume by ~2.5×. GWS trends in most remaining aquifers were stable or slightly rising. GRACE‐derived GWS changes agree with GWL monitoring data in most aquifers (correlation coefficients, R=0.52–0.95), showing that GRACE satellites capture GW dynamics. Regional GW models (8 models) generally show similar or greater GWS trends than those from GRACE. Large discrepancies in the Mississippi Embayment aquifer, with modeled GWS decline ~4× that of GRACE, may reflect uncertainties in model storage parameters, stream capture, pumpage, and/or recharge rates. Global hydrologic models (2003–2014), which include GW pumping, generally overestimate GRACE GWS depletion (total: ~‐172 to ‐186 km3) in heavily‐exploited aquifers in south‐western and south‐central U.S. by ~2.4× (GRACE: ‐74 km3), underscoring needed modeling improvements relative to anthropogenic impacts. Global land surface models tend to track GRACE GWS dynamics better than global hydrologic models. Intercomparing remote sensing, monitoring, and modeling data underscores the importance of considering all data sources to constrain GWS uncertainties.
Ashraf Rateb; Bridget R. Scanlon; Donald R. Pool; Alexander Sun; Zizhan Zhang; Jianli Chen; Brian Clark; Claudia C. Faunt; Connor J. Haugh; Mary Hill; Christopher Hobza; Virginia L. McGuire; Meredith Reitz; Hannes Müller Schmied; Edwin H. Sutanudjaja; Sean Swenson; David Wiese; Youlong Xia; Wesley Zell. Comparison of Groundwater Storage Changes From GRACE Satellites With Monitoring and Modeling of Major U.S. Aquifers. Water Resources Research 2020, 56, 1 .
AMA StyleAshraf Rateb, Bridget R. Scanlon, Donald R. Pool, Alexander Sun, Zizhan Zhang, Jianli Chen, Brian Clark, Claudia C. Faunt, Connor J. Haugh, Mary Hill, Christopher Hobza, Virginia L. McGuire, Meredith Reitz, Hannes Müller Schmied, Edwin H. Sutanudjaja, Sean Swenson, David Wiese, Youlong Xia, Wesley Zell. Comparison of Groundwater Storage Changes From GRACE Satellites With Monitoring and Modeling of Major U.S. Aquifers. Water Resources Research. 2020; 56 (12):1.
Chicago/Turabian StyleAshraf Rateb; Bridget R. Scanlon; Donald R. Pool; Alexander Sun; Zizhan Zhang; Jianli Chen; Brian Clark; Claudia C. Faunt; Connor J. Haugh; Mary Hill; Christopher Hobza; Virginia L. McGuire; Meredith Reitz; Hannes Müller Schmied; Edwin H. Sutanudjaja; Sean Swenson; David Wiese; Youlong Xia; Wesley Zell. 2020. "Comparison of Groundwater Storage Changes From GRACE Satellites With Monitoring and Modeling of Major U.S. Aquifers." Water Resources Research 56, no. 12: 1.
Meixian Liu; Alexander Y. Sun. A Physical Agricultural Drought Index Based on Root Zone Water Availability: Model Development and Application. Geophysical Research Letters 2020, 47, 1 .
AMA StyleMeixian Liu, Alexander Y. Sun. A Physical Agricultural Drought Index Based on Root Zone Water Availability: Model Development and Application. Geophysical Research Letters. 2020; 47 (22):1.
Chicago/Turabian StyleMeixian Liu; Alexander Y. Sun. 2020. "A Physical Agricultural Drought Index Based on Root Zone Water Availability: Model Development and Application." Geophysical Research Letters 47, no. 22: 1.
There is considerable concern about water depletion caused by climate extremes (e.g., drought) and human water use in the U.S. and globally. Major U.S. aquifers provide an ideal laboratory to assess water storage changes from GRACE satellites because the aquifers are intensively monitored and modeled. The objective of this study was to assess the relative importance of climate extremes and human water use on GRACE Total Water Storage Anomalies in 14 major U.S. aquifers and to evaluate the reliability of the GRACE data by comparing with groundwater level monitoring (~-23,000 wells) and regional and global models. We quantified total water and groundwater storage anomalies over 2002 – 2017 from GRACE satellites and compared GRACE data with groundwater level monitoring and regional and global modeling results.
The results show that water storage changes were controlled primarily by climate extremes and amplified or dampened by human water use, primarily irrigation. The results were somewhat surprising, with stable or rising long-term trends in the majority of aquifers with large scale depletion limited to agricultural areas in the semi-arid southwest and southcentral U.S. GRACE total water storage in the California Central Valley and Central/Southern High Plains aquifers was depleted by drought and amplified by groundwater irrigation, totaling ~70 km3 (2002–2017), about 2× the capacity of Lake Mead, the largest surface reservoir in the U.S. In the Pacific Northwest and Northern High Plains aquifers, lower drought intensities were partially dampened by conjunctive use of surface water and groundwater for irrigation and managed aquifer recharge, increasing water storage by up to 22 km3 in the Northern High Plains over the 15 yr period. GRACE-derived total water storage changes in the remaining aquifers were stable or slightly rising throughout the rest of the U.S.
GRACE data compared favorably with composite groundwater level hydrographs for most aquifers except for those with very low signals, indicating that GRACE tracks groundwater storage dynamics. Comparison with regional models was restricted to the limited overlap periods but showed good correspondence for modeled aquifers with the exception of the Mississippi Embayment, where the modeled trend is 4x the GRACE trend. The discrepancy is attributed to uncertainties in model storage parameters and groundwater/surface water interactions. Global hydrologic models (WGHM-2d and PCR-GLOBWB-5.0 overestimated trends in groundwater storage in heavily exploited aquifers in the southwestern and southcentral U.S. Land surface models (CLSM-F2.5 and NOAH-MP) seem to track GRACE TWSAs better than global hydrologic models but underestimated TWS trends in aquifers dominated by irrigation.
Intercomparing GRACE, traditional hydrologic monitoring, and modeling data underscore the importance of considering all data sources to constrain water storage changes. GRACE satellite data have critical implications for many nationally important aquifers, highlighting the importance of conjunctively using surface-water and groundwater and managed aquifer recharge to enhance sustainable development.
Bridget Scanlon; Ashraf Rateb; Alexander Sun; Himanshu Save. Assessing Impacts of Climate Extremes and Human Water Use on GRACE Total Water Storage Trends in Major U.S. Aquifers. 2020, 1 .
AMA StyleBridget Scanlon, Ashraf Rateb, Alexander Sun, Himanshu Save. Assessing Impacts of Climate Extremes and Human Water Use on GRACE Total Water Storage Trends in Major U.S. Aquifers. . 2020; ():1.
Chicago/Turabian StyleBridget Scanlon; Ashraf Rateb; Alexander Sun; Himanshu Save. 2020. "Assessing Impacts of Climate Extremes and Human Water Use on GRACE Total Water Storage Trends in Major U.S. Aquifers." , no. : 1.
Floods pose a threat to the lives of millions of people globally each year, with economic losses exceeding those of any other natural hazard. Improving flood forecasting with longer lead times can support enhanced risk management strategies and reduce associated socioeconomic losses. The objective of this study was to assess the detectability of floods using newly developed GRACE daily and regular monthly total water storage data.
We compared total water storage (TWS) maxima from GRACE and GRACE-FO with flood occurrences from 2002 to 2020. GRACE daily TWS maxima were based on three daily GRACE solutions (UTCSR-RSWM, GFZ-RBF, and ITSG-2018) derived using statistical learning and geophysical models for the GRACE period (2002-2017). Monthly GRACE and GRACE-FO data were based on mascons solutions from UT-CSR and NASA-JPL for 2002-2020. A flood susceptibility index was developed based on the climate signal portion in the TWSA and compared with other flood indices (e.g., standardized precipitation index and streamflow). We evaluated the spatiotemporal coincidence rate of change of the 90th percentile of the daily and monthly precipitation based on the GPM-Imerg and GPCP rainfall data and the corresponding 90th percentile of the daily and monthly TWSA. The coincidence rate between GRACE TWSA maxima and precipitation were also compared relative to actual flood data (~3000 events) from the Dartmouth flood Observatory (DFO) catalog.
Preliminary results using precipitation data from GPCP reveal that monthly GRACE/GRACE-FO data have a high predication rate for the monthly maxima precipitation > 90th percentile with a lead time of ~ two months across the tropical rain belt. Assessment against the real flood events shows that the three daily GRACE data perform well for flood events resulting from heavy and monsoonal rain and slightly differ for the events triggered by snowmelt and storm surges. The duration of flood events from GRACE data is generally shorter than the periods reported by DFO. An empirical relationship was derived between floods' duration based on the cause and the expected precursor coincidence rate from daily GRACE data. Further analysis is necessary to evaluate the GRACE precursor rate using different lead times and tolerance windows, quantify the change in rate relative to climate, topography, and soil types, and interpret the different performance GRACE products. This preliminary analysis suggests the high potential for GRACE/GRACE-FO data to extend flood forecast lead times and potentially improve the mitigation strategies
Ashraf Rateb; Alexander Sun; Bridget Scanlon; Himanshu Save. Assessing Detectability of Global Flood Occurrences using Daily and Monthly GRACE/GRACE-FO. 2020, 1 .
AMA StyleAshraf Rateb, Alexander Sun, Bridget Scanlon, Himanshu Save. Assessing Detectability of Global Flood Occurrences using Daily and Monthly GRACE/GRACE-FO. . 2020; ():1.
Chicago/Turabian StyleAshraf Rateb; Alexander Sun; Bridget Scanlon; Himanshu Save. 2020. "Assessing Detectability of Global Flood Occurrences using Daily and Monthly GRACE/GRACE-FO." , no. : 1.
The GRACE satellite mission and its follow-on, GRACE-FO, have provided unprecedented opportunities to quantify the impact of climate extremes and human activities on total water storage at large scales. The approximately one-year data gap between the two GRACE missions needs to be filled to maintain data continuity and maximize mission benefits. There is strong interest in using machine learning (ML) algorithms to reconstruct GRACE-like data to fill this gap. So far, most studies attempted to train and select a single ML algorithm to work for global basins. However, hydrometeorological predictors may exhibit strong spatial variability which, in turn, may affect the performance of ML models. Existing studies have already shown that no single algorithm consistently outperformed others over all global basins. In this study, we applied an automated machine learning (AutoML) workflow to perform GRACE data reconstruction. AutoML represents a new paradigm for optimal model structure selection, hyperparameter tuning, and model ensemble stacking, addressing some of the most challenging issues related to ML applications. We demonstrated the AutoML workflow over the conterminous U.S. (CONUS) using six types of ML algorithms and multiple groups of meteorological and climatic variables as predictors. Results indicate that the AutoML-assisted gap filling achieved satisfactory performance over the CONUS. For the testing period (2014/06–2017/06), the mean gridwise Nash-Sutcliffe efficiency is around 0.85, the mean correlation coefficient is around 0.95, and the mean normalized root-mean square error is about 0.09. Trained models maintain good performance when extrapolating to the mission gap and to GRACE-FO periods (after 2017/06). Results further suggest that no single algorithm provides the best predictive performance over the entire CONUS, stressing the importance of using an end-to-end workflow to train, optimize, and combine multiple machine learning models to deliver robust performance, especially when building large-scale hydrological prediction systems and when predictor importance exhibits strong spatial variability.
Alex Sun; Bridget Scanlon; Himanshu Save; Ashraf Rateb. Reconstruction of GRACE Total Water Storage Through Automated Machine Learning. 2020, 1 .
AMA StyleAlex Sun, Bridget Scanlon, Himanshu Save, Ashraf Rateb. Reconstruction of GRACE Total Water Storage Through Automated Machine Learning. . 2020; ():1.
Chicago/Turabian StyleAlex Sun; Bridget Scanlon; Himanshu Save; Ashraf Rateb. 2020. "Reconstruction of GRACE Total Water Storage Through Automated Machine Learning." , no. : 1.
Model-based optimization plays a central role in energy system design and management. The complexity and high-dimensionality of many process-level models, especially those used for geosystem energy exploration and utilization, often lead to formidable computational costs when the dimension of decision space is also large. This work adopts elements of recently advanced deep learning techniques to solve a sequential decision-making problem in applied geosystem management. Specifically, a deep reinforcement learning framework was formed for optimal multiperiod planning, in which a deep Q-learning network (DQN) agent was trained to maximize rewards by learning from high-dimensional inputs and from exploitation of its past experiences. To expedite computation, deep multitask learning was used to approximate high-dimensional, multistate transition functions. Both DQN and deep multitask learning are pattern based. As a demonstration, the framework was applied to optimal carbon sequestration reservoir planning using two different types of management strategies: monitoring only and brine extraction. Both strategies are designed to mitigate potential risks due to pressure buildup. Results show that the DQN agent can identify the optimal policies to maximize the reward for given risk and cost constraints. Experiments also show that knowledge the agent gained from interacting with one environment is largely preserved when deploying the same agent in other similar environments.
Alexander Y. Sun. Optimal carbon storage reservoir management through deep reinforcement learning. Applied Energy 2020, 278, 115660 .
AMA StyleAlexander Y. Sun. Optimal carbon storage reservoir management through deep reinforcement learning. Applied Energy. 2020; 278 ():115660.
Chicago/Turabian StyleAlexander Y. Sun. 2020. "Optimal carbon storage reservoir management through deep reinforcement learning." Applied Energy 278, no. : 115660.
Waterflooding, during which water is injected in the reservoir to increase pressure and therefore boost oil production, is extensively used as a secondary oil recovery technology. Tracking the extent and efficacy of waterflooding (i.e., fluid distributions) is a primary task of reservoir engineers and is traditionally achieved by running full reservoir models. In this work, we design and implement a proxy model using a conditional deep convolutional generative neural network (cDC-GAN), which can be used to quickly calculate the dynamic fluid distribution of a heterogeneous reservoir under waterflooding. Zero-sum game theory is the basis for the cDC-GAN, which includes a pair of generative discriminative models. The generative model tries to learn the relationship between input and output and makes the generated output as close as possible to the training data, while the discriminative model tries to distinguish the fake output and the real data used for training, such that the cDC-GAN learns the real data distribution at the end. In our cDC-GAN formulation, the reservoir properties (permeability distribution in this research) and forecast time information are treated as input, and water saturation is the desired output. The reservoir fluid production rate can be calculated based on the material balance principle. The most significant contribution of this work resides in training a cDC-GAN proxy model to accurately predict fluid saturation. A cDC-GAN has several advantages over the traditional full-model based workflow. First, the model parameters estimated from history matching help to improve reservoir characterization. Second, this proposed proxy model can predict the water and oil saturation distributions simultaneously, which can be used to calculate the water and oil flow rates. Third, this proposed proxy model can be used for waterflooding optimization and uncertainty analysis with far less computational effort than with the traditional method, which uses a reservoir simulator.
Zhi Zhong; Alexander Y. Sun; Yanyong Wang; Bo Ren. Predicting field production rates for waterflooding using a machine learning-based proxy model. Journal of Petroleum Science and Engineering 2020, 194, 107574 .
AMA StyleZhi Zhong, Alexander Y. Sun, Yanyong Wang, Bo Ren. Predicting field production rates for waterflooding using a machine learning-based proxy model. Journal of Petroleum Science and Engineering. 2020; 194 ():107574.
Chicago/Turabian StyleZhi Zhong; Alexander Y. Sun; Yanyong Wang; Bo Ren. 2020. "Predicting field production rates for waterflooding using a machine learning-based proxy model." Journal of Petroleum Science and Engineering 194, no. : 107574.
Carbon capture and storage (CCS) is being pursued globally as a geoengineering measure for reducing the emission of anthropogenic CO2 into the atmosphere. Comprehensive monitoring, verification, and accounting programs must be established for demonstrating the safe storage of injected CO2. One of the most commonly deployed monitoring techniques is time‐lapse seismic reservoir monitoring (also known as 4D seismic), which involves comparing 3D seismic survey data taken at the same study site but over different times. Analyses of 4D seismic data volumes can help improve the quality of storage reservoir characterization, track the movement of injected CO2 plume, and identify potential CO2 spillover/leakage from the storage reservoir However, the derivation of high resolution CO2 saturation maps from 4D seismic data is a highly nonlinear and ill‐posed inverse problem, often requiring significant computational effort. In this research, we apply a physics‐based deep learning method to facilitate the solution of both the forward and inverse problems in seismic inversion while honoring physical constraints. A cycle generative adversarial neural network (CycleGAN) model is trained to learn the bi‐directional functional mappings between the reservoir dynamic property changes and seismic attribute changes, such that both forward and inverse solutions can be obtained efficiently from the trained model. We show that our CycleGAN‐based approach not only improves the reliability of 4D seismic inversion, but also expedites the quantitative interpretation. Our deep learning based workflow is generic and can be readily used for reservoir characterization and reservoir model updates involving the use of 4D seismic data.
Zhi Zhong; Alexander Y. Sun; Xinming Wu. Inversion of Time‐Lapse Seismic Reservoir Monitoring Data Using CycleGAN: A Deep Learning‐Based Approach for Estimating Dynamic Reservoir Property Changes. Journal of Geophysical Research: Solid Earth 2020, 125, 1 .
AMA StyleZhi Zhong, Alexander Y. Sun, Xinming Wu. Inversion of Time‐Lapse Seismic Reservoir Monitoring Data Using CycleGAN: A Deep Learning‐Based Approach for Estimating Dynamic Reservoir Property Changes. Journal of Geophysical Research: Solid Earth. 2020; 125 (3):1.
Chicago/Turabian StyleZhi Zhong; Alexander Y. Sun; Xinming Wu. 2020. "Inversion of Time‐Lapse Seismic Reservoir Monitoring Data Using CycleGAN: A Deep Learning‐Based Approach for Estimating Dynamic Reservoir Property Changes." Journal of Geophysical Research: Solid Earth 125, no. 3: 1.
Zhi Zhong; Alexander Y. Sun; Hoonyoung Jeong. Predicting CO 2 Plume Migration in Heterogeneous Formations Using Conditional Deep Convolutional Generative Adversarial Network. Water Resources Research 2019, 55, 5830 -5851.
AMA StyleZhi Zhong, Alexander Y. Sun, Hoonyoung Jeong. Predicting CO 2 Plume Migration in Heterogeneous Formations Using Conditional Deep Convolutional Generative Adversarial Network. Water Resources Research. 2019; 55 (7):5830-5851.
Chicago/Turabian StyleZhi Zhong; Alexander Y. Sun; Hoonyoung Jeong. 2019. "Predicting CO 2 Plume Migration in Heterogeneous Formations Using Conditional Deep Convolutional Generative Adversarial Network." Water Resources Research 55, no. 7: 5830-5851.
Seasonal water storage fluctuations are critical for evaluating water scarcity linked to climate forcing and human intervention. Here we compare seasonal changes in land total water storage anomalies using seven global hydrologic and land surface models (WGHM, PCR‐GLOBWB, and five GLDAS models) to GRACE satellite data in 183 river basins globally. This work builds on previous analysis that focused on total water storage anomaly trends. Results show that most models underestimate seasonal water storage amplitudes in tropical and (semi)arid basins and land surface models generally overestimate amplitudes in northern basins. Some models (CLM‐5.0 and PCR‐GLOBWB) agree better with GRACE than others. Causes of model‐GRACE discrepancies are attributed to missing storage compartments (e.g., surface water and/or groundwater) and underestimation of modeled storage capacities in tropical basins and to variations in modeled fluxes in northern basins. This study underscores the importance of considering water storage, in addition to water fluxes, to improve global models.
B. R. Scanlon; Z. Zhang; A. Rateb; A. Sun; D. Wiese; H. Save; H. Beaudoing; M. H. Lo; H. Müller‐Schmied; P. Döll; R. van Beek; S. Swenson; D. Lawrence; M. Croteau; R. C. Reedy. Tracking Seasonal Fluctuations in Land Water Storage Using Global Models and GRACE Satellites. Geophysical Research Letters 2019, 46, 5254 -5264.
AMA StyleB. R. Scanlon, Z. Zhang, A. Rateb, A. Sun, D. Wiese, H. Save, H. Beaudoing, M. H. Lo, H. Müller‐Schmied, P. Döll, R. van Beek, S. Swenson, D. Lawrence, M. Croteau, R. C. Reedy. Tracking Seasonal Fluctuations in Land Water Storage Using Global Models and GRACE Satellites. Geophysical Research Letters. 2019; 46 (10):5254-5264.
Chicago/Turabian StyleB. R. Scanlon; Z. Zhang; A. Rateb; A. Sun; D. Wiese; H. Save; H. Beaudoing; M. H. Lo; H. Müller‐Schmied; P. Döll; R. van Beek; S. Swenson; D. Lawrence; M. Croteau; R. C. Reedy. 2019. "Tracking Seasonal Fluctuations in Land Water Storage Using Global Models and GRACE Satellites." Geophysical Research Letters 46, no. 10: 5254-5264.
Big Data and machine learning (ML) technologies have the potential to impact many facets of environment and water management (EWM). Big Data are information assets characterized by high volume, velocity, variety, and veracity. Fast advances in high-resolution remote sensing techniques, smart information and communication technologies, and social media have contributed to the proliferation of Big Data in many EWM fields, such as weather forecasting, disaster management, smart water and energy management systems, and remote sensing. Big Data brings about new opportunities for data-driven discovery in EWM, but it also requires new forms of information processing, storage, retrieval, as well as analytics. ML, a subdomain of artificial intelligence (AI), refers broadly to computer algorithms that can automatically learn from data. ML may help unlock the power of Big Data if properly integrated with data analytics. Recent breakthroughs in AI and computing infrastructure have led to the fast development of powerful deep learning (DL) algorithms that can extract hierarchical features from data, with better predictive performance and less human intervention. Collectively Big Data and ML techniques have shown great potential for data-driven decision making, scientific discovery, and process optimization. These technical advances may greatly benefit EWM, especially because (1) many EWM applications (e.g., early flood warning) require the capability to extract useful information from a large amount of data in autonomous manner and in real time, (2) EWM researches have become highly multidisciplinary, and handling the ever increasing data volume/type using the traditional workflow is simply not an option, and last but not least, (3) the current theoretical knowledge about many EWM processes is still incomplete, but which may now be complemented through data-driven discovery. A large number of applications on Big Data and ML have already appeared in the EWM literature in recent years. The purposes of this survey are to (1) examine the potential and benefits of data-driven research in EWM, (2) give a synopsis of key concepts and approaches in Big Data and ML, (3) provide a systematic review of current applications, and finally (4) discuss major issues and challenges, and recommend for future research directions. EWM includes a broad range of research topics. Instead of attempting to survey each individual EWM area, this review focuses on areas of nexus in EWM, with an emphasis on elucidating the potential benefits of increased data availability and predictive analytics to improving the EWM research.
Alexander Y. Sun; Bridget R Scanlon. How can Big Data and machine learning benefit environment and water management: a survey of methods, applications, and future directions. Environmental Research Letters 2019, 14, 073001 .
AMA StyleAlexander Y. Sun, Bridget R Scanlon. How can Big Data and machine learning benefit environment and water management: a survey of methods, applications, and future directions. Environmental Research Letters. 2019; 14 (7):073001.
Chicago/Turabian StyleAlexander Y. Sun; Bridget R Scanlon. 2019. "How can Big Data and machine learning benefit environment and water management: a survey of methods, applications, and future directions." Environmental Research Letters 14, no. 7: 073001.
Carbon capture and storage (CCS) has been extensively investigated as a potential engineering measure to reduce anthropogenic carbon emission to the atmosphere. Real-time monitoring of the safety and integrity of carbon storage reservoirs is a critical aspect of any commercial-scale CCS deployment. Pressure-based sensing is cost effective, suitable for real-time monitoring, and scalable to large monitoring networks. However, questions remain on how to best harness intelligent information from the high-frequency pressure monitoring sensors to support real-time decisions. This work presents a deep-learning-based framework for analyzing and detecting anomalies in pressure data streams by using a convolutional long short-term memory (ConvLSTM) neural network model, which allows for the fusion of both static and dynamic reservoir data. In ConvLSTM, the convolutional neural network (CNN) is used for spatial pattern mining and the LSTM is used for temporal pattern recognition. The performance of the ConvLSTM model for real-time anomaly detection is demonstrated using a set of pressure monitoring data collected from Cranfield, Mississippi, an active enhanced-oil-recovery field. The anomaly detection model is trained using bottom-hole pressure data acquired from the base experiment (without leak event) and then tested on pressure data collected during a series of controlled CO2 release experiments (with artificially created leak events). Results show that the ConvLSTM neural network model successfully detected anomalies in the pressure time series obtained from the controlled release experiments. Inclusion of static information into the model further improves the robustness of ConvLSTM.
Zhi Zhong; Alexander Y. Sun; Qian Yang; Qi Ouyang. A deep learning approach to anomaly detection in geological carbon sequestration sites using pressure measurements. Journal of Hydrology 2019, 573, 885 -894.
AMA StyleZhi Zhong, Alexander Y. Sun, Qian Yang, Qi Ouyang. A deep learning approach to anomaly detection in geological carbon sequestration sites using pressure measurements. Journal of Hydrology. 2019; 573 ():885-894.
Chicago/Turabian StyleZhi Zhong; Alexander Y. Sun; Qian Yang; Qi Ouyang. 2019. "A deep learning approach to anomaly detection in geological carbon sequestration sites using pressure measurements." Journal of Hydrology 573, no. : 885-894.
Rapid evolution of Internet-of-Things is driving the increased deployment of smart sensors in environmental applications, contributing to many big data characteristics of environmental monitoring. Most of the current environmental monitoring systems are not designed to handle real-time datastreams, and the best practices for datastream processing and predictive analytics are yet to be established. This work presents a complex event processing (CEP) engine for detecting anomalies in real time, and demonstrates it using a series of real monitoring data from the geological carbon sequestration domain. We show that the service-based CEP engine is instrumental for enabling environmental intelligent monitoring systems to ingest heterogeneous datastreams with scalable performance. Our CEP framework requires minimal coding from the user and can be easily extended for other similar environmental monitoring applications.
Alexander Y. Sun; Zhi Zhong; Hoonyoung Jeong; Qian Yang. Building complex event processing capability for intelligent environmental monitoring. Environmental Modelling & Software 2019, 116, 1 -6.
AMA StyleAlexander Y. Sun, Zhi Zhong, Hoonyoung Jeong, Qian Yang. Building complex event processing capability for intelligent environmental monitoring. Environmental Modelling & Software. 2019; 116 ():1-6.
Chicago/Turabian StyleAlexander Y. Sun; Zhi Zhong; Hoonyoung Jeong; Qian Yang. 2019. "Building complex event processing capability for intelligent environmental monitoring." Environmental Modelling & Software 116, no. : 1-6.
Global hydrological and land surface models are increasingly used for tracking terrestrial total water storage (TWS) dynamics, but the utility of existing models is hampered by conceptual and/or data uncertainties related to various underrepresented and unrepresented processes, such as groundwater storage. The gravity recovery and climate experiment (GRACE) satellite mission provided a valuable independent data source for tracking TWS at regional and continental scales. Strong interests exist in fusing GRACE data into global hydrological models to improve their predictive performance. Here we develop and apply deep convolutional neural network (CNN) models to learn the spatiotemporal patterns of mismatch between TWS anomalies (TWSA) derived from GRACE and those simulated by NOAH, a widely used land surface model. Once trained, our CNN models can be used to correct the NOAH simulated TWSA without requiring GRACE data, potentially filling the data gap between GRACE and its follow‐on mission, GRACE‐FO. Our methodology is demonstrated over India, which has experienced significant groundwater depletion in recent decades that is nevertheless not being captured by the NOAH model. Results show that the CNN models significantly improve the match with GRACE TWSA, achieving a country‐average correlation coefficient of 0.94 and Nash‐Sutcliff efficient of 0.87, or 14% and 52% improvement respectively over the original NOAH TWSA. At the local scale, the learned mismatch pattern correlates well with the observed in situ groundwater storage anomaly data for most parts of India, suggesting that deep learning models effectively compensate for the missing groundwater component in NOAH for this study region.
Alexander Y. Sun; Bridget R. Scanlon; Zizhan Zhang; David Walling; Soumendra N. Bhanja; Abhijit Mukherjee; Zhi Zhong. Combining Physically Based Modeling and Deep Learning for Fusing GRACE Satellite Data: Can We Learn From Mismatch? Water Resources Research 2019, 55, 1179 -1195.
AMA StyleAlexander Y. Sun, Bridget R. Scanlon, Zizhan Zhang, David Walling, Soumendra N. Bhanja, Abhijit Mukherjee, Zhi Zhong. Combining Physically Based Modeling and Deep Learning for Fusing GRACE Satellite Data: Can We Learn From Mismatch? Water Resources Research. 2019; 55 (2):1179-1195.
Chicago/Turabian StyleAlexander Y. Sun; Bridget R. Scanlon; Zizhan Zhang; David Walling; Soumendra N. Bhanja; Abhijit Mukherjee; Zhi Zhong. 2019. "Combining Physically Based Modeling and Deep Learning for Fusing GRACE Satellite Data: Can We Learn From Mismatch?" Water Resources Research 55, no. 2: 1179-1195.
Here we present an efficient and robust calculation scheme for two-phase, one-dimensional (1D) steady state steam condensation in the presence of CO2, based on conservation rules and thermodynamic phase relations. The mixing of fluids and phases is assumed to be homogeneous. Heat transfer is considered between the fluids and the ambient formations. For convenience, state equations are presented in terms of the entropy changes of individual phases, and the simple additive rule for the mixture. To monitor phase changes, the phase rule is checked. This investigation has practical significance for steam injection operation and long-distance pipe flow applications in the geothermal and mid- and up-stream oil and gas industries.
Akand Islam; Alexander Sun; Kamy Sepehrnoori. An Efficient Computational Scheme for Two-Phase Steam Condensation in the Presence of CO2 for Wellbore and Long-Distance Flow. ChemEngineering 2019, 3, 4 .
AMA StyleAkand Islam, Alexander Sun, Kamy Sepehrnoori. An Efficient Computational Scheme for Two-Phase Steam Condensation in the Presence of CO2 for Wellbore and Long-Distance Flow. ChemEngineering. 2019; 3 (1):4.
Chicago/Turabian StyleAkand Islam; Alexander Sun; Kamy Sepehrnoori. 2019. "An Efficient Computational Scheme for Two-Phase Steam Condensation in the Presence of CO2 for Wellbore and Long-Distance Flow." ChemEngineering 3, no. 1: 4.
This project aims to develop a Pressure-based Inversion and Data Assimilation System (PIDAS) for detecting CO2 leakage from storage formations. Carbon capture, utilization, and sequestration (CCUS) has the potential to enable deep reductions in global carbon emissions if high storage efficiency can be achieved. A major hurdle to industrial-scale implementation of geological carbon sequestration (GCS) projects is the potential migration of fluids (either brine or injected CO2) from the storage formations and the resulting legal and financial liabilities. The capability to accurately identify leakage pathways by which stored CO2 could leak, has leaked, or is leaking from the targeted storage zone is thus of paramount importance to site licensees and regulators. Although many MVA techniques have been devised, pressure-based monitoring technology remains the most sensitive and reliable technique for early detection. Pressure-based monitoring has consistently received the highest score in terms of benefit/cost ratio and it provides the greatest potential for leakage detection with broad areal coverage. Under this project we have (a) demonstrated the utility of the proposed well testing technique for leakage detection through integrated theoretical and numerical analysis, laboratory experiments, and field tests; (b) developed effective data analysis and inversion algorithms for identifying leakage pathways by fusingmore » data generated during well testing; (c) provided a designing tool for maximizing the utility of the developed PIDAS tool for early leakage detection. « less
Alexander Sun; Lawrence Berkeley National Lab. Pressure-Based Inversion and Data Assimilation System (PIDAS) for CO2 Leakage Detection. Pressure-Based Inversion and Data Assimilation System (PIDAS) for CO2 Leakage Detection 2018, 1 .
AMA StyleAlexander Sun, Lawrence Berkeley National Lab. Pressure-Based Inversion and Data Assimilation System (PIDAS) for CO2 Leakage Detection. Pressure-Based Inversion and Data Assimilation System (PIDAS) for CO2 Leakage Detection. 2018; ():1.
Chicago/Turabian StyleAlexander Sun; Lawrence Berkeley National Lab. 2018. "Pressure-Based Inversion and Data Assimilation System (PIDAS) for CO2 Leakage Detection." Pressure-Based Inversion and Data Assimilation System (PIDAS) for CO2 Leakage Detection , no. : 1.
This paper presents a new perspective on modeling of CO2 and miscible gas injection into shale oil plays for potential enhanced oil recovery (EOR) and CO2 storage. Our major points are the conceptual understandings of the dominant trapping and the oil recovery mechanisms behind miscible gas injection. This paper investigates the efficiency of miscible gas (solvent) injection into shale oil reservoirs with a wide range of permeability (from 1 to 100 µD). We set up a large-scale numerical model to simulate and capture the important mechanisms behind various miscible gas injection and geological storage scenarios. This numerical study demonstrates that injecting miscible gas such as CO2 and recycled gas rich in ethane substantially increases oil recovery in shale oil reservoirs. Numerical simulation models reveal that miscibility and CO2 adsorption, along with gas diffusion, are important physical mechanisms. However, recycled-enriched gas injection demonstrated a larger oil recovery rate compared to miscible CO2 injection. On the other hand, CO2 trapping is considerable, because of adsorption and other traditional trapping mechanisms in shale plays. The amount of CO2 trapped in unconventional reservoirs can be a significant fraction of the total injected amount (∼25 to50% including the important and dominant trapping mechanisms, e.g. CO2 dissolution in oil and water, adsorption, residual, and mobile gas saturations). Results show that molecular diffusion can speed CO2 flux delivery to larger matrix area and thus contribute to oil recovery, and become trapped and adsorbed on minerals or organic contents.
Hamid R. Lashgari; Alexander Sun; Tongwei Zhang; Gary A. Pope; Larry W. Lake. Evaluation of carbon dioxide storage and miscible gas EOR in shale oil reservoirs. Fuel 2018, 241, 1223 -1235.
AMA StyleHamid R. Lashgari, Alexander Sun, Tongwei Zhang, Gary A. Pope, Larry W. Lake. Evaluation of carbon dioxide storage and miscible gas EOR in shale oil reservoirs. Fuel. 2018; 241 ():1223-1235.
Chicago/Turabian StyleHamid R. Lashgari; Alexander Sun; Tongwei Zhang; Gary A. Pope; Larry W. Lake. 2018. "Evaluation of carbon dioxide storage and miscible gas EOR in shale oil reservoirs." Fuel 241, no. : 1223-1235.