Article
Geosciences, Multidisciplinary
Subhrendu Gangopadhyay, Connie A. Woodhouse, Gregory J. McCabe, Cody C. Routson, David M. Meko
Summary: The ongoing drought in the Upper Colorado River Basin has been found to be extremely severe, especially when compared to the tree-ring records from as early as 762 CE. Using gridded drought-atlas data and streamflow data, researchers have developed a streamflow reconstruction model for the Lees Ferry gage, revealing a second-century drought that surpasses the severity of the current drought and documented medieval period droughts. Limited data also support the occurrence of this exceptional second-century drought through analysis of individual tree-ring records and other paleoclimatic data.
GEOPHYSICAL RESEARCH LETTERS
(2022)
Article
Environmental Sciences
Subramaniam Nachimuthu Deepa, Narayanan Natarajan, Mohanadhas Berlin
Summary: This research proposes a new deep learning model for forecasting river streamflow, which combines enhanced variational mode decomposition and deep support vector machine kernels. The model effectively removes noise using singular spectrum analysis and achieves high prediction accuracy for streamflow.
ENVIRONMENTAL EARTH SCIENCES
(2023)
Article
Mathematics, Applied
James Baglama, Vasilije Perovic, Timothy Toolan
Summary: In this paper, the authors investigate the singular value decomposition (SVD) of E + xyH, where E is an m x n real diagonal matrix, x is in Cm, and y is in Cn. They propose a new method for computing the SVD of E + xyH by sequentially computing the eigen-decomposition of two separate hermitian rank-one modifications of a real diagonal matrix and exploiting the properties of the rank-two secular function. The authors also demonstrate how to compute the full set of associated left/right singular vectors in O(min(m, n)2) time.
APPLIED MATHEMATICS AND COMPUTATION
(2023)
Article
Environmental Sciences
J. Eli Asarian, Crystal Robinson, Laurel Genzoli
Summary: Low streamflows can increase vulnerability to warming, impacting coldwater fish. Water managers need tools to quantify these impacts and predict future water temperatures. Contrary to most statistical models' assumptions, many seasonally changing factors (e.g., water sources and solar radiation) cause relationships between flow and water temperature to vary throughout the year.
WATER RESOURCES RESEARCH
(2023)
Article
Environmental Sciences
David Woodson, Balaji Rajagopalan, Sarah Baker, Rebecca Smith, James Prairie, Erin Towler, Ming Ge, Edith Zagona
Summary: This study utilized temperature projections from Global Climate Models and machine learning techniques to predict multiyear mean flow in the Colorado River Basin, showing that the Random Forest method outperformed ESP and climatology models in flow projections.
WATER RESOURCES RESEARCH
(2021)
Article
Engineering, Environmental
Mohsen Mahmoody Vanolya, Hayrullah Agaccioglu
Summary: In this study, a method is proposed to differentiate return flow and streamflow in rivers located in urban and industrial watersheds. Trend analysis is performed using the Mann-Kendall method, and streamflow time series are divided into pre- and post-change sets using the Mann-Whitney change point method. The Two-Parameter Filtering (TPF) is utilized to separate baseflow and determine the return flow.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2023)
Article
Energy & Fuels
Xin-yue Fu, Zhong-kai Feng, Hui Cao, Bao-fei Feng, Zheng-yu Tan, Yin-shan Xu, Wen-jing Niu
Summary: This paper proposes an enhanced machine learning model, combining twin support vector regression, singular spectrum analysis, and grey wolf optimizer, for streamflow time series forecasting. The results show that the proposed model can yield superior results compared with traditional forecasting models.
Article
Engineering, Civil
Tianli Guo, Songbai Song, Vijay P. Singh, Ting Wei, Te Zhang, Xin Liu
Summary: This study developed a time-varying stepwise decomposition ensemble framework for nonsta-tionary and nonlinear streamflow series, along with an optimization strategy combining a two-stage calibration strategy with a particle swarm optimization algorithm. The results showed that the time-varying decomposition ensemble models were superior to the single models, and the TSC-PSO-PSO optimization strategy outperformed other optimization strategies. The TV-VMD-SVM model based on the TSC-PSO-PSO optimization strategy had the best streamflow forecasting performance.
JOURNAL OF HYDROLOGY
(2023)
Article
Engineering, Civil
Mehdi Jamei, Mumtaz Ali, Anurag Malik, Masoud Karbasi, Priya Rai, Zaher Mundher Yaseen
Summary: Accurate forecasting of monthly rainfall in the Himalayan region of India was achieved using a new multi-decomposition deep learning-based technique. The rainfall signals were decomposed using time-varying filter-based empirical mode decomposition and partial autocorrelation function. The decomposed signals were further decomposed using Singular Valued Decomposition to reduce dimensionality. Hybrid forecasting models using machine learning approaches outperformed standalone models, with TVF-EMD-SVD-EDBi-LSTM achieving the best results.
JOURNAL OF HYDROLOGY
(2023)
Article
Engineering, Electrical & Electronic
Lin Mei, Shuaiyong Li, Chao Zhang, Mingxiu Han
Summary: An adaptive signal enhancement method based on genetic algorithm optimized VMD and SVD is proposed in this study to address the low SNR issue in leak location in water-supply pipelines. Experimental results demonstrate that the proposed method is effective in reducing leak location errors.
IEEE SENSORS JOURNAL
(2021)
Article
Meteorology & Atmospheric Sciences
Taesam Lee, Taha B. M. J. Ouarda, Ousmane Seidou
Summary: The objective of this study is to compare techniques for forecasting low-frequency climate oscillation indices, with a focus on the Great Lakes system. Various time series models, including ARMA, DLM, GARCH, and NSOR, were tested for predicting the monthly ENSO and PDO indices, which have significant teleconnections with the NBS of the Great Lakes system. The aim is to forecast future water levels, ice extent, and temperature for planning and decision making. Results indicate that the DLM and GARCH models outperform others for forecasting the monthly ENSO index, while the traditional ARMA model shows good agreement with observed values for the monthly PDO index within a short lead time.
THEORETICAL AND APPLIED CLIMATOLOGY
(2023)
Article
Environmental Sciences
Marcos D. Robles, John C. Hammond, Stephanie K. Kampf, Joel A. Biederman, Eleonora M. C. Demaria
Summary: Recent research in the Upper Colorado River Basin suggests that despite warming temperatures and reduced snowfall, consistent streamflow declines have not been observed due to increased winter runoff. A study on nine gaged basins of the Salt River and its tributaries found that annual and seasonal streamflow patterns remained stable despite significant temperature increases from 1968-2011, with winter inputs playing a crucial role in streamflow production. Atmospheric rivers were identified as a key contributor to large winter streamflow peaks.
Article
Green & Sustainable Science & Technology
Sinvaldo Rodrigues Moreno, Viviana Cocco Mariani, Leandro dos Santos Coelho
Summary: Wind speed forecasting is challenging, with decomposition strategy key to improving accuracy. The proposed method combines amplitude and frequency modulation-demodulation signal theory with ARIMA, resulting in a new ensemble learning method VMD-SSA-ARIMA. Ensemble results demonstrate stabilization of forecasting errors and reduction in up to 12 steps-ahead forecasting errors.
Article
Water Resources
Melanie Meis, Manuel Benjamin, Daniela Rodriguez
Summary: The relation between discharge and social economy matters is of constant interest for decision makers, as unexpected fluctuations in discharge can easily impact various sectors such as agriculture and tourism. This study proposes the novel application of the one-sided dynamical principal components (ODPC) technique to hydrology, allowing for improved modeling and prediction of daily streamflow variability. A comparison between ODPC and traditional models showed that ODPC provides some improvement in the treatment and forecasting of discharge variability.
HYDROLOGICAL SCIENCES JOURNAL
(2022)
Article
Engineering, Civil
Hossien Riahi-Madvar, Majid Dehghani, Rasoul Memarzadeh, Bahram Gharabaghi
Summary: The study found that hybrid algorithms outperformed traditional models in streamflow prediction, with ANFIS-GWO1, ANFIS-GWO7, and ANFIS-GWO11 being the best performing models. Uncertainty analysis showed that hybrid models significantly reduced uncertainty levels compared to traditional models. The study also provided a simple explicit equation for streamflow forecasting based on hybrid ANFIS results, which is a major advantage over classical blackbox machine learning models.
WATER RESOURCES MANAGEMENT
(2021)