This study evaluates the relationships between El Nino-Southern Oscillation (ENSO) indices and South Florida hydrology and proposes applications to water management decision making. ENSO relations to the Upper Kissimmee Basin rainfall, watershed for Lake Okeechobee, and cumulative sea surface temperature (SST) anomalies at Nino 3.4 were evaluated. Additionally, relationship between ENSO and Lake Okeechobee inflows, Arbuckle Creek and Josephine Creek flows were analyzed. Hydrology of the northern watersheds of the South Florida water management system is linked to ENSO events. Dry season (November-May) rainfall and flows are higher than average during El Nino years and lower during La Nina years, at the 90% confidence level or higher. The relationship is strongest when the ENSO event is strong as shown with analysis of correlation. ENSO prediction has more certainty than hydrologic prediction for a region. Identifying ENSO and hydrologic relationships can aid water management decision making by providing a lead-time of months to mitigate drought or flood impacts. The ENSO tracking method, which was published in a previous study, is presented to track ENSO strength and event type to provide supplemental outlook on dry season rainfall for Lake Okeechobee operations. Lake Okeechobee, which is the main storage in the South Florida water management system, is regulated by a schedule with a limited band of stage fluctuation because of susceptibility of the Herbert Hoover Dike to wave erosion and seepage at high stages. An early decision making approach to storage management with respect to ENSO related hydrology, is presented based on tracking the strength of ENSO events.

El Niño-Southern Oscillation Link to South Florida Hydrology and Water Management Applications

Study region The study region encompasses the Upper Colorado River Basin (UCRB), which provides water for 40 million people and is a vital part of the water supply in the western U.S. Study focus Groundwater and surface water can be considered a single water resource and thus it is important to understand groundwater contributions to streamflow, or baseflow, within a region. Previously, quantification of baseflow using chemical mass balance at large numbers of sites was not possible because of data limitations. A new method using regression-derived daily specific conductance values with conductivity mass balance hydrograph separation allows for baseflow estimation at sites across large regions. This method was applied to estimate baseflow discharge at 229 sites across the UCRB. Subsequently, climate, soil, topography, and land cover characteristics were statistically evaluated using principal component analysis (PCA) to determine their influence on baseflow discharge. New hydrological insights for the region Results suggest that approximately half of the streamflow in the UCRB is baseflow derived from groundwater discharge to streams. Higher baseflow yields typically occur in upper elevation areas of the UCRB. PCA identified precipitation, snow, sand content of soils, elevation, land surface slope, percent grasslands, and percent natural barren lands as being positively correlated with baseflow yield; whereas temperature, potential evapotranspiration, silt and clay content of soils, percent agriculture, and percent shrublands were negatively correlated with baseflow yield.

Regional Scale Estimates of Baseflow and Factors Influencing Baseflow in the Upper Colorado River Basin

Identification and pairing of hydrologic events form the basis of various analyses, from identifying events for the calibration of hydrologic models, to calculation of event runoff coefficients for catchment characterization. Despite this, there is no unified approach for identifying hydrologic events. Here, using the R package, hydroEvents (https://CRAN.R-project.org/package=hydroEvents), we compare multiple methods of extracting and pairing hydrologic events focussing on the relationship between rainfall and runoff. We find the four common analytical approaches used to identify runoff events—based on either event threshold, local maxima/minima, or proportion of baseflow contribution, give similar results. However, when rainfall events are paired to runoff, the type of algorithm and the direction of pairing (either from rainfall to runoff, or runoff to rainfall) make a considerable difference to the final event pairs identified and resulting analyses. Here, we demonstrate the value of automated event extraction and pairing algorithms for large‐sample hydrology analysis by calculating event runoff coefficients across Australia. Our results show that climatology is a key driver of catchment rainfall‐runoff response with much of Australia dominated by excess rainfall runoff generation. However, our results also show that the variability due to pairing method can introduce a variability equal to that of the climatology due to biasing the runoff mechanism within the sample. With this analysis we demonstrate the importance of systematic and consistent approaches to hydrologic characterization when identifying and pairing hydrological events.

Understanding event runoff coefficient variability across Australia using the hydroEvents R package

A novel ensemble model for long-term forecasting of wind and hydro power generation

Baseflow estimation and evaluation are two critical and essential tasks for water quality and quantity, drought management, water supply, and groundwater protection. Observed baseflows are rarely available and are limited to focused pilot studies. In this study, an exhaustive evaluation of four different baseflow separation methods (HYSEP, WHAT, BFLOW, and PART) using surrogates of observed baseflows estimated with the conductivity mass balance (CMB) method is carried out using data from several streamflow gauging sites from the South Atlantic-Gulf (SAG) region comprised of nine states in the Southeastern U.S. Daily discharge data from 75 streamflow gauging sites for the period 1970–2013, located in the least anthropogenically affected basins in the SAG region were used to estimate the baseflow index (BFI), which quantifies the contribution of baseflow from streamflows. The focus of this study is to compare the four different baseflow separation methods and calibrate and validate these methods using CMB method based estimates of baseflows to evaluate the variation of BFI values derived from these methods. Results from the study suggest that the PART and HYSEP methods provide the highest and lowest average BFI values of 0.62 and 0.52, respectively. Similarities in BFI values estimated from these methods are noted based on a strong correlation between WHAT and BFLOW. The highest BFI values were found in April in the eastern, western, and central parts of the SAG region, and the highest contribution of baseflow to the streamflow was noted in October in the southern region. However, the lowest BFI values were noted in the month of September in all regions of SAG. The calibrated WHAT method using data from the CMB method provides the highest correlation as noted by the coefficient of determination. This study documents an exhaustive and comprehensive evaluation of baseflow separation methods in the SAG region, and results from this work can aid in the selection of the best method based on different metrics reported in this study. The use of the best method can aid in the short and long term management of low flows at a regional level that supports a sustainable aquatic environment and mitigates the effects of droughts effectively.

https://www.mdpi.com/2073-4441/12/1/120/pdf

Comparative Analysis of Four Baseflow Separation Methods in the South Atlantic-Gulf Region of the U.S.

. Streamflow forecasts are traditionally effective in mitigating water scarcity and flood defense. This study developed an artificial intelligence (AI)-based management methodology that integrated multi-step streamflow forecasts and multi-objective reservoir operation optimization for water resource allocation. Following the methodology, we aimed to assess forecast quality and forecast-informed reservoir operation performance together due to the influence of inflow forecast uncertainty.
Varying combinations of climate and hydrological variables were input into
three AI-based models, namely a long short-term memory (LSTM), a gated recurrent unit (GRU), and a least-squares support vector machine (LSSVM), to forecast short-term streamflow. Based on three deterministic forecasts, the stochastic inflow scenarios were further developed using Bayesian model
averaging (BMA) for quantifying uncertainty. The forecasting scheme was
further coupled with a multi-reservoir optimization model, and the
multi-objective programming was solved using the parameterized
multi-objective robust decision-making (MORDM) approach. The AI-based management framework was applied and demonstrated over a multi-reservoir system (25 reservoirs) in the Zhoushan Islands, China. Three main conclusions were drawn from this study: (1) GRU and LSTM performed equally well on streamflow forecasts, and GRU might be the preferred method over LSTM, given that it had simpler structures and less modeling time; (2) higher forecast performance could lead to improved reservoir operation, while uncertain forecasts were more valuable than deterministic forecasts, regarding two performance metrics, i.e., water supply reliability and operating costs; (3) the relationship between the forecast horizon and reservoir operation was complex and depended on the operating configurations (forecast quality and uncertainty) and performance measures. This study reinforces the potential of an AI-based stochastic streamflow forecasting scheme to seek robust strategies under uncertainty.

/pdf/ai-based-techniques-for-multi-step-streamflow-forecasts-4xllqm72bj.pdf

AI-based techniques for multi-step streamflow forecasts: application for multi-objective reservoir operation optimization and performance assessment

A weights combined model for middle and long-term streamflow forecasts and its value to hydropower maximization

Optimal implementation and monitoring of wind energy generation hinge on reliable power modeling that is vital for understanding turbine control, farm operational optimization, and grid load balance. Based on the idea of similar wind condition leads to similar wind power; this paper constructs a modeling scheme that orderly integrates three types of ensemble learning algorithms, bagging, boosting, and stacking, and clustering approaches to achieve optimal power modeling. It also investigates applications of different clustering algorithms and methodology for determining cluster numbers in wind power modeling. The results reveal that all ensemble models with clustering exploit the intrinsic information of wind data and thus outperform models without it by approximately 15% on average. The model with the best farthest first clustering is computationally rapid and performs exceptionally well with an improvement of around 30%. The modeling is further boosted by about 5% by introducing stacking that fuses ensembles with varying clusters. The proposed modeling framework thus demonstrates promise by delivering efficient and robust modeling performance.

Hao Chen

Papers

Comparative Analysis of Four Baseflow Separation Methods in the South Atlantic-Gulf Region of the U.S.

AI-based techniques for multi-step streamflow forecasts: application for multi-objective reservoir operation optimization and performance assessment

A weights combined model for middle and long-term streamflow forecasts and its value to hydropower maximization

Cluster-based ensemble learning for wind power modeling with meteorological wind data

Noise-intensification data augmented machine learning for day-ahead wind power forecast