Spatial Downscaling of GRACE TWSA Data to Identify Spatiotemporal Groundwater Level Trends in the Upper Floridan Aquifer, Georgia, USA

Accurate assessments of groundwater resources in major aquifers across the globe are crucial for sustainable management of freshwater reservoirs. Observations from the Gravity Recovery and Climate Experiment (GRACE) satellite have become invaluable as a means to identify regions groundwater change. While there is a large body of research that focuses on downscaling coarse (1°) GRACE products, few studies have attempted to spatially downscale GRACE to produce fine resolution (5 km) maps that are more useful to resource managers. This study trained a boosted regression tree model to statistically downscale GRACE total water storage anomaly to monthly 5 km groundwater level anomaly maps in the karstic upper Floridan aquifer (UFA) using multiple hydrologic datasets. Evaluation of spatial predictions with existing groundwater wells indicated satisfactory performance (R = 0.79, NSE = 0.61). Results demonstrate that groundwater levels were stable between 2002–2016 but varied seasonally. The data also highlights areas where groundwater pumping is exacerbating UFA water-level declines. While results demonstrate the applicability of machine learning based methods for spatial downscaling of GRACE data, future studies should account for preferential flowpaths (i.e., conduits, lineaments) in karstic systems.

Download Full-text

Seismically induced changes in groundwater levels and temperatures following the ML5.8 (ML5.1) Gyeongju earthquake in South Korea

Hydrogeology Journal ◽

10.1007/s10040-021-02328-w ◽

2021 ◽

Author(s):

Soo-Hyoung Lee ◽

Jae Min Lee ◽

Sang-Ho Moon ◽

Kyoochul Ha ◽

Yongcheol Kim ◽

...

Keyword(s):

South Korea ◽

Groundwater Level ◽

Seismic Waves ◽

Groundwater Resources ◽

Fluid Pressure ◽

Water Levels ◽

Aquifer System ◽

Groundwater Levels ◽

Monitoring Wells ◽

Gyeongju Earthquake

AbstractHydrogeological responses to earthquakes such as changes in groundwater level, temperature, and chemistry, have been observed for several decades. This study examines behavior associated with ML 5.8 and ML 5.1 earthquakes that occurred on 12 September 2016 near Gyeongju, a city located on the southeast coast of the Korean peninsula. The ML 5.8 event stands as the largest recorded earthquake in South Korea since the advent of modern recording systems. There was considerable damage associated with the earthquakes and many aftershocks. Records from monitoring wells located about 135 km west of the epicenter displayed various patterns of change in both water level and temperature. There were transient-type, step-like-type (up and down), and persistent-type (rise and fall) changes in water levels. The water temperature changes were of transient, shift-change, and tendency-change types. Transient changes in the groundwater level and temperature were particularly well developed in monitoring wells installed along a major boundary fault that bisected the study area. These changes were interpreted as representing an aquifer system deformed by seismic waves. The various patterns in groundwater level and temperature, therefore, suggested that seismic waves impacted the fractured units through the reactivation of fractures, joints, and microcracks, which resulted from a pulse in fluid pressure. This study points to the value of long-term monitoring efforts, which in this case were able to provide detailed information needed to manage the groundwater resources in areas potentially affected by further earthquakes.

Download Full-text

A global bibliometric perspective on soil erosion modelling

10.5194/egusphere-egu2020-2919 ◽

2020 ◽

Author(s):

Nejc Bezak ◽

Keyword(s):

Conference Proceedings ◽

Soil Erosion ◽

Regression Tree ◽

Tree Model ◽

Boosted Regression Tree ◽

Field Activity ◽

Erosion Modelling ◽

Meta Information ◽

Number Of Citations ◽

Regression Tree Model

Systematic bibliometric investigations are useful to evaluate and compare the scientific impact of journal papers, book chapters and conference proceedings. Such studies allow the detection of emerging research topics, the analyses of cooperation networks, and the collection of in-depth insights into a specific research topic. In the presented work, we carried out a bibliometric study in order to obtain an in-depth knowledge on soil erosion modelling applications worldwide.As a starting point, we used the soil erosion modelling meta-analysis data collection generated by the authors of this abstract in a joint community effort. This database contains meta-information of more than 3,000 documents published between 1994 and 2018 that are indexed in the SCOPUS database. The documents were reviewed and database entries verified. The database contains various types of meta-information about the modelling studies (e.g., model used, study area, input data, calibration, etc.). The bibliometric information was also included in the database (e.g., number of citations, type of publication, Scopus category, etc.). We investigated differences among publication types and differences between papers published in journals that are part of various Scopus categories. Moreover, relationships between publication CiteScore, number of authors, and number of citations were analyzed. A boosted regression tree model was used to detect the relative impact of the selected meta-information such as erosion model used, spatial modelling scale, study period, field activity on the total number of citations. Detailed investigation of the most cited papers was also conducted. The VOSviewer software was used to analyze citations, co-citations, bibliographic coupling, and co-authorship networks of the database entries. &#160;Our bibliometric investigations demonstrated that journal publications, on average, receive more citations than book series or conference proceedings. There were differences among the erosion models used, and some specific models such as the WaTEM/SEDEM model, on average, receive more citations than other models (e.g., USLE). It should also be noted that self-citation rates in case of most frequently used models were similar. Global studies, on average, receive more citations than studies dealing with plot, regional, or national scales. According to the boosted regression tree model, model calibration, validation, or field activity do not have significant impact on the obtained publication citations. Co-citation investigation revealed some interesting patterns. Our results also indicate that papers about soil erosion modeling also attract citations from different fields and better international cooperation is needed to advance this field of research with regard to its visibility and impact on human societies.&#160;&#160;&#160;&#160;

Download Full-text

Assessing the suitability of extreme learning machines (ELM) for groundwater level prediction

Journal of Water and Land Development ◽

10.1515/jwld-2017-0012 ◽

2017 ◽

Vol 32 (1) ◽

pp. 103-112 ◽

Cited By ~ 22

Author(s):

Basant Yadav ◽

Sudheer Ch ◽

Shashi Mathur ◽

Jan Adamowski

Keyword(s):

Soft Computing ◽

Groundwater Level ◽

Groundwater Resources ◽

Support Vector ◽

Complex Nature ◽

Data Set ◽

Groundwater Levels ◽

Soft Computing Techniques ◽

Learning Machine ◽

The Comparative Study

Abstract Fluctuation of groundwater levels around the world is an important theme in hydrological research. Rising water demand, faulty irrigation practices, mismanagement of soil and uncontrolled exploitation of aquifers are some of the reasons why groundwater levels are fluctuating. In order to effectively manage groundwater resources, it is important to have accurate readings and forecasts of groundwater levels. Due to the uncertain and complex nature of groundwater systems, the development of soft computing techniques (data-driven models) in the field of hydrology has significant potential. This study employs two soft computing techniques, namely, extreme learning machine (ELM) and support vector machine (SVM) to forecast groundwater levels at two observation wells located in Canada. A monthly data set of eight years from 2006 to 2014 consisting of both hydrological and meteorological parameters (rainfall, temperature, evapotranspiration and groundwater level) was used for the comparative study of the models. These variables were used in various combinations for univariate and multivariate analysis of the models. The study demonstrates that the proposed ELM model has better forecasting ability compared to the SVM model for monthly groundwater level forecasting.

Download Full-text

Identifying anthropogenic effects into Doñana aquifer (SW Spain) through hydrogram clustering of piezometric database

10.5194/egusphere-egu2020-7830 ◽

2020 ◽

Author(s):

Carolina Guardiola-Albert ◽

Nuria Naranjo-Fernández ◽

Héctor Aguilera ◽

Esperanza Montero-González

Keyword(s):

Time Series ◽

Groundwater Level ◽

Groundwater Resources ◽

Data Series ◽

Time Series Clustering ◽

Missing Data Imputation ◽

Groundwater Levels ◽

Aquifer Systems ◽

Visual Clustering ◽

Selection Of

Nowadays, the application of time series clustering is increasing in hydrogeology works. Groundwater level long data series provides a useful record to identify different hydrological behaviors and to validate the conceptual model of groundwater flow in aquifer systems. Piezometers also register the response to any changes that directly affect the amount of available groundwater resources (recharge or exploitation).What are the expected variations of groundwater levels in an aquifer under high exploitation pressure? In this work, groundwater level time series from 160 piezometers in the hydrological years from 1975 to 2016 were analyzed. Especially, 24 piezometers are deeply studied. Data were preprocessed and transformed: selection of points, missing data imputation and data standardization. Visual clustering, k-means clustering and time series clustering were applied to classify groundwater level hydrographs using the available database. Six and seven groups of piezometers were identified to be associated with the different hydrofacies and extraction rates. Time series clustering was found to be the best method to analyze the studied piezometric database. Moreover, it was possible to characterize actual hydrodynamics, which will be useful for groundwater managers to make sustainable decisions.

Download Full-text

Deep Learning based assessment of groundwater level development in Germany until 2100

10.5194/egusphere-egu21-9590 ◽

2021 ◽

Author(s):

Andreas Wunsch ◽

Tanja Liesch ◽

Stefan Broda

Keyword(s):

Climate Change ◽

Groundwater Level ◽

Climate Models ◽

Groundwater Resources ◽

Groundwater Abstraction ◽

Water Shortages ◽

Entire Area ◽

Groundwater Levels ◽

The Past ◽

Skill Scores

Clear signs of climate stress on groundwater resources have been observed in recent years even in generally water-rich regions such as Germany. Severe droughts, resulting in decreased groundwater recharge, led to declining groundwater levels in many regions and even local drinking water shortages have occurred in past summers. We investigate how climate change will directly influence the groundwater resources in Germany until the year 2100. For this purpose, we use a machine learning groundwater level forecasting framework, based on Convolutional Neural Networks, which has already proven its suitability in modelling groundwater levels. We predict groundwater levels on more than 120 wells distributed over the entire area of Germany that showed strong reactions to meteorological signals in the past. The inputs are derived from the RCP8.5 scenario of six climate models, pre-selected and pre-processed by the German Meteorological Service, thus representing large parts of the range of the expected change in the next 80 years. Our models are based on precipitation and temperature and are carefully evaluated in the past and only wells with models reaching high forecasting skill scores are included in our study. We only consider natural climate change effects based on meteorological changes, while highly uncertain human factors, such as increased groundwater abstraction or irrigation effects, remain unconsidered due to a lack of reliable input data. We can show significant (p<0.05) declining groundwater levels for a large majority of the considered wells, however, at the same time we interestingly observe the opposite behaviour for a small portion of the considered locations. Further, we show mostly strong increasing variability, thus an increasing number of extreme groundwater events. The spatial patterns of all observed changes reveal stronger decreasing groundwater levels especially in the northern and eastern part of Germany, emphasizing the already existing decreasing trends in these regions

Download Full-text

Case Fatality Ratio Estimates for the 2013–2016 West African Ebola Epidemic: Application of Boosted Regression Trees for Imputation

Clinical Infectious Diseases ◽

10.1093/cid/ciz678 ◽

2019 ◽

Vol 70 (12) ◽

pp. 2476-2483 ◽

Cited By ~ 3

Author(s):

Alpha Forna ◽

Pierre Nouvellet ◽

Ilaria Dorigatti ◽

Christl A Donnelly

Keyword(s):

Characteristic Curve ◽

Regression Tree ◽

Case Fatality ◽

West African ◽

Boosted Regression Trees ◽

Survival Outcomes ◽

Tree Model ◽

Boosted Regression Tree ◽

Case Fatality Ratio ◽

Out Of Sample

Abstract Background The 2013–2016 West African Ebola epidemic has been the largest to date with >11 000 deaths in the affected countries. The data collected have provided more insight into the case fatality ratio (CFR) and how it varies with age and other characteristics. However, the accuracy and precision of the naive CFR remain limited because 44% of survival outcomes were unreported. Methods Using a boosted regression tree model, we imputed survival outcomes (ie, survival or death) when unreported, corrected for model imperfection to estimate the CFR without imputation, with imputation, and adjusted with imputation. The method allowed us to further identify and explore relevant clinical and demographic predictors of the CFR. Results The out-of-sample performance (95% confidence interval [CI]) of our model was good: sensitivity, 69.7% (52.5–75.6%); specificity, 69.8% (54.1–75.6%); percentage correctly classified, 69.9% (53.7–75.5%); and area under the receiver operating characteristic curve, 76.0% (56.8–82.1%). The adjusted CFR estimates (95% CI) for the 2013–2016 West African epidemic were 82.8% (45.6–85.6%) overall and 89.1% (40.8–91.6%), 65.6% (61.3–69.6%), and 79.2% (45.4–84.1%) for Sierra Leone, Guinea, and Liberia, respectively. We found that district, hospitalisation status, age, case classification, and quarter (date of case reporting aggregated at three-month intervals) explained 93.6% of the variance in the naive CFR. Conclusions The adjusted CFR estimates improved the naive CFR estimates obtained without imputation and were more representative. Used in conjunction with other resources, adjusted estimates will inform public health contingency planning for future Ebola epidemics, and help better allocate resources and evaluate the effectiveness of future inventions.

Download Full-text

Two-Stage Boosted Regression Tree Model to Characterize Southern Flounder Distribution in Texas Estuaries at Varying Population Sizes

Marine and Coastal Fisheries ◽

10.1080/19425120.2015.1079577 ◽

2016 ◽

Vol 8 (1) ◽

pp. 222-231 ◽

Cited By ~ 11

Author(s):

John T. Froeschke ◽

Bridgette F. Froeschke

Keyword(s):

Regression Tree ◽

Tree Model ◽

Two Stage ◽

Boosted Regression Tree ◽

Southern Flounder ◽

Population Sizes ◽

Regression Tree Model ◽

Varying Population

Download Full-text

Spatiotemporal patterns and agroecological risk factors for cutaneous and renal glomerular vasculopathy (Alabama Rot) in dogs in the UK

Veterinary Record ◽

10.1136/vr.104892 ◽

2018 ◽

Vol 183 (16) ◽

pp. 502-502 ◽

Cited By ~ 4

Author(s):

Kim B Stevens ◽

Rosanne Jepson ◽

Laura Phillipa Holm ◽

David John Walker ◽

Jacqueline Martina Cardwell

Keyword(s):

Seasonal Pattern ◽

Regression Tree ◽

Tree Model ◽

Boosted Regression Tree ◽

Relative Contribution ◽

Annual Reporting ◽

Climatic Drivers ◽

Maximum Temperatures ◽

The Uk ◽

Permutation Statistic

The annual outbreaks of cutaneous and renal glomerular vasculopathy (CRGV) reported in UK dogs display a distinct seasonal pattern (November to May) suggesting possible climatic drivers of the disease. The objectives of this study were to explore disease clustering and identify associations between agroecological factors and CRGV occurrence. Kernel-smoothed maps were generated to show the annual reporting distribution of CRGV, Kuldorff’s space–time permutation statistic used to identify significant spatiotemporal case clusters and a boosted regression tree model developed to quantify associations between CRGV case locations and a range of agroecological factors. The majority of diagnoses (92 per cent) were reported between November and May while the number of regions reporting the disease increased between 2012 and 2017. Two significant spatiotemporal clusters were identified—one in the New Forest during February and March 2013, and one adjacent to it (April 2015 to May 2017)—showing significantly higher and lower proportions of cases than the rest of the UK, respectively, for the indicated time periods. A moderately significant high-risk cluster (P=0.087) was also identified in the Manchester area of northern England between February and April 2014. Habitat was the predictor with the highest relative contribution to CRGV distribution (20.3 per cent). Cases were generally associated with woodlands, increasing mean maximum temperatures in winter, spring and autumn, increasing mean rainfall in winter and spring and decreasing cattle and sheep density. Understanding of such factors may help develop causal models for CRGV occurrence.

Download Full-text

Impact of coal mining on groundwater of Luohe Formation in Binchang mining area

International Journal of Coal Science & Technology ◽

10.1007/s40789-020-00366-5 ◽

2020 ◽

Author(s):

Kui Sun ◽

Limin Fan ◽

Yucheng Xia ◽

Cheng Li ◽

Jianping Chen ◽

...

Keyword(s):

Coal Mining ◽

Groundwater Level ◽

Water Conservation ◽

Underground Mining ◽

Groundwater Resources ◽

Vertical Direction ◽

Mining Area ◽

Aquifer System ◽

Groundwater Levels ◽

Spring Flow

Abstract Groundwater of Luohe Formation is the main water source for industrial and agricultural and residential use in Binchang mining area, which is one of the key elements to water conservation coal mining. However, few studies are available to document the enrichment characteristics and influence of underground coal mining on groundwater for the Luohe Formation. This study evaluates the changes of groundwater levels and spring flow caused by mining activities to explore the influence mechanism of coal mining on groundwater by comparatively analysing existing mining data and survey data combined with a series of mapping methods. The results show that the aquifer of Luohe Formation are gradually thinning south-eastwards, disappeared at the mining boundary. In the vertical direction, the lithological structure is distinct, due to alternative sedimentation of meandering river facies and braided river facies. According to the yielding property, the aquifer is divided into three sections, namely, strong water-rich section, medium water-rich section, and weak water-rich section, which are located in northwest and central part, southwest, and the rest part of the mining area, respectively. Mining of Tingnan Coal Mine since 2004 has caused a 3.16 to 194.87 meters drop in groundwater level of Luohe Formation. Until 2015, 70.10% of the mining area undergoes a groundwater level drop larger than 10.00 meters. Another influence of underground mining is that the total flow from 34 springs in 8 southern coal mines of the area has decreased by 286.48 L/s with a rate of decrease at 46.95% from 2007 to 2017. The areas that groundwater level falls or spring flow declines are manly located in the mine gob areas. Results also indicate that the ratio of the height of water conducted fracture zone to the mining height in Binchang mining area is between 16.85 and 27.92. This may increase ground water flow in vertical direction, causing a water level in the aquifer system to drop and ultimately decreasing the flow from the springs. The research results will provide data and theoretical support for the protection of groundwater resources and water conservation coal mining of Luohe Formation in Binchang mining area.

Download Full-text