CTF-former: A novel simplified multi-task learning strategy for simultaneous multivariate chaotic time series prediction

Neural Networks, Год журнала: 2024, Номер 174, С. 106234 - 106234

Опубликована: Март 14, 2024

Язык: Английский

---

A complex network approach to study the extreme precipitation patterns in a river basin

Chaos An Interdisciplinary Journal of Nonlinear Science, Год журнала: 2022, Номер 32(1)

Опубликована: Янв. 1, 2022

The quantification of spatial propagation extreme precipitation events is vital in water resources planning and disaster mitigation. However, quantifying these has always been challenging as many traditional methods are insufficient to capture the nonlinear interrelationships between event time series. Therefore, it crucial develop suitable for analyzing dynamics over a river basin with diverse climate complicated topography. Over last decade, complex network analysis emerged powerful tool study intricate spatiotemporal relationship variables compact way. In this study, we employ two concepts synchronization edit distance investigate pattern Ganga basin. We use degree understand rainfall identify essential sites respect potential prediction skills. also attempts quantify influence seasonality topography on events. findings reveal that (1) decreased southwest northwest direction, (2) timing 50th percentile within year influences distribution degree, (3) inversely related elevation, (4) lower elevation greatly connectivity sites. highlights could be promising alternative analyze event-like data by incorporating amplitude constructing networks extremes.

Язык: Английский

---

Precipitation trend identification with a modified innovative trend analysis technique over Lake Issyk-Kul, Kyrgyzstan

Journal of Water and Climate Change, Год журнала: 2023, Номер 14(6), С. 1798 - 1815

Опубликована: Май 30, 2023

Abstract The main concern of this study is using a new type innovative trend analysis (ITA) method with particular graphical illustration. It compares the results classic MK test at 95% confidence level. Among 15 annual and seasonal data series (3 weather stations annually, spring, summer, autumn, winter) studied, found significant increasing trends 3 (20%). However, ITA method, 6 (40%) ‘high’ ‘low’ simultaneously showed trend. can also detect all identified by test. As for values 12 (80%) exhibited patterns, 9 (60%) displayed patterns values. According to values, gain one (6.7%) manifested decreasing trends. These detailed precipitation evaluating findings demonstrated that runs counter previous ITA.

Язык: Английский

---

Geopolitical risk and uncertainty in energy markets: Evidence from wavelet-based methods

Energy Economics, Год журнала: 2025, Номер unknown, С. 108281 - 108281

Опубликована: Фев. 1, 2025

Язык: Английский

---

Wavelet Entropy for Efficiency Assessment of Price, Return, and Volatility of Brent and WTI During Extreme Events

Commodities, Год журнала: 2025, Номер 4(2), С. 4 - 4

Опубликована: Март 21, 2025

This study analyzes the market efficiency of crude oil markets, namely Brent and West Texas Intermediate (WTI), during three different periods: pre-COVID-19, COVID-19 pandemic, ongoing Russia–Ukraine military conflict. To evaluate wavelet entropy is computed from price, return, volatility series. Our empirical results show that WTI prices are predictable conflict, but difficult to predict same period. The were pandemic. Returns in more conflict than they Finally, carried information pandemic compared Also, series for These findings offer insightful investors, traders, policy makers relation energy under various extreme conditions.

Язык: Английский

---

Reservoir computing and non-linear dynamics for time series analysis: An application in the financial market

Physica D Nonlinear Phenomena, Год журнала: 2025, Номер unknown, С. 134698 - 134698

Опубликована: Апрель 1, 2025

Язык: Английский

---

A new criteria for determining the best decomposition level and filter for wavelet-based data-driven forecasting frameworks- validating using three case studies on the CAMELS dataset

Stochastic Environmental Research and Risk Assessment, Год журнала: 2023, Номер 37(12), С. 4827 - 4842

Опубликована: Авг. 27, 2023

Язык: Английский

---

Rare events in complex systems: Understanding and prediction

Chaos An Interdisciplinary Journal of Nonlinear Science, Год журнала: 2020, Номер 30(9)

Опубликована: Сен. 1, 2020

First Page

Язык: Английский

---

Improving deep learning-based streamflow forecasting under trend varying conditions through evaluation of new wavelet preprocessing technique

Stochastic Environmental Research and Risk Assessment, Год журнала: 2024, Номер 38(10), С. 3963 - 3984

Опубликована: Авг. 5, 2024

Язык: Английский

---

Quantifying predictive knowledge: Wavelet energy α-divergence measure for time series uncertainty reduction

Chaos Solitons & Fractals, Год журнала: 2024, Номер 188, С. 115488 - 115488

Опубликована: Сен. 6, 2024

Язык: Английский

---