Machine Learning Approaches for Assessing Groundwater Quality and Its Implications for Water Conservation in the Sub-tropical Capital Region of India

Water Conservation Science and Engineering, Journal Year: 2025, Volume and Issue: 10(1)

Published: March 10, 2025

Language: Английский

---

Analysing Temporal Variations in Radon Concentrations: Identifying Trends and Changes

Terra Nova, Journal Year: 2025, Volume and Issue: unknown

Published: April 7, 2025

ABSTRACT Radon is a well‐known precursor for geodynamic events such as earthquakes and volcanic tremors. concentration variations in soil gas have been monitored worldwide, extreme radon values identified anomalies associated with events. A time series contains many noise signals, primarily based on meteorological effects. Therefore, detecting pre‐seismic may not always yield good results. Interpreting long‐term trend changes the offers an alternative to examining specific individual earthquakes. This study examines locally estimated scatterplot smoothing (LOESS) identify of series. In this dataset, two distinct trends anomaly mechanisms were identified. first group, activity concentrations increase before decrease after earthquake, whereas second they exhibit opposite behaviour.

Language: Английский

---

Research on Ultra-Short-Term Load Forecasting Based on Real-Time Electricity Price and Window-Based XGBoost Model

Energies, Journal Year: 2022, Volume and Issue: 15(19), P. 7367 - 7367

Published: Oct. 7, 2022

With the continuous development of new power systems, load demand on user side is becoming more and diverse random, which also brings difficulties in accurate prediction load. Although introduction deep learning algorithms has improved accuracy to a certain extent, it faces problems such as large data requirements low computing efficiency. An ultra-short-term forecasting method based windowed XGBoost model proposed, not only reduces complexity model, but helps capture autocorrelation effect forecast object. At same time, real-time electricity price introduced into improve its accuracy. By simulating Singapore’s market, proved that proposed fewer errors than other algorithms, model. Furthermore, broad applicability verified by sensitivity analysis with different sample sizes.

Language: Английский

---

Impact of long-term mining activity on groundwater dynamics in a mining district in Xinjiang coal Mine Base, Northwest China: insight from geochemical fingerprint and machine learning

Environmental Science and Pollution Research, Journal Year: 2024, Volume and Issue: 31(22), P. 32136 - 32151

Published: April 22, 2024

Language: Английский

---

Importance of Machine Learning and Deep Learning Algorithms in Earthquake Prediction: A Review

Published: May 11, 2023

Earthquakes are the leading natural disasters that have caused loss of life and property since formation world. Machine learning deep frequently used in studies for earthquake prediction. This article consists a compilation using machine algorithms. In article, on topics such as magnitude estimation, signal discrimination, electron density estimations ionosphere, examination radon gas anomalies algorithms included. The this paper show Deep Learning more forecasting. It is expected will provide successful results future due to its ability work with larger data sets compared improve itself from errors.

Language: Английский

---

Prediction of groundwater level under the influence of groundwater exploitation using a data-driven method with the combination of time series analysis and long short-term memory: a case study of a coastal aquifer in Rizhao City, Northern China

Frontiers in Environmental Science, Journal Year: 2023, Volume and Issue: 11

Published: Nov. 8, 2023

The excessive exploitation of groundwater not only destroys the dynamic balance between coastal aquifer and seawater but also causes a series geological environmental problems. Groundwater level prediction provides an efficient way to solve these intractable ecological Although several hydrological numerical models have been employed conduct prediction, no study has accurately predicted change under consideration exploitation, especially in aquifers. This is due characteristics spatially temporally complex processes. proposes novel data-driven method based on combination time analysis machine learning for predicting variation influence exploitation. partial autocorrelation function continuous wavelet coherence were used analyze monitoring data at three wells, which indicated that historical monitored dataset precipitation could be considered as input variables construct model. Then, different inputs constructed, namely, LSTM, PACF-LSTM, PACF-WC-LSTM models. performances compared by calculation four error metrics. results showed performance PACF-LSTM was better than LSTM model achieved best performance. Accurately basis managing resources preserving environment.

Language: Английский

---

Hydrogeochemical changes with emphasis on trace elements in an artesian well before and after the September 8, 2018 Ms 5.9 Mojiang Earthquake in Yunnan, southwest China

Applied Geochemistry, Journal Year: 2024, Volume and Issue: 167, P. 106013 - 106013

Published: April 21, 2024

Language: Английский

---

Application of the Data-Driven Method and Hydrochemistry Analysis to Predict Groundwater Level Change Induced by the Mining Activities: A Case Study of Yili Coalfield in Xinjiang, Norwest China

Water, Journal Year: 2024, Volume and Issue: 16(11), P. 1611 - 1611

Published: June 5, 2024

As the medium of geological information, groundwater provides an indirect method to solve secondary disasters mining activities. Identifying regime overburden aquifers induced by disturbance is significant in safety and environment protection. This study proposes novel data-driven algorithm based on combination machine learning methods hydrochemical analyses predict anomalous changes levels within mine its neighboring areas after activities accurately. The hydrochemistry analysis reveals that dissolution carbonate evaporite cation exchange function are main process for controlling environment. change characteristic different hydraulic connection between enhanced continuous wavelet coherence used reveal nonlinear relationship level external influencing factors. Based above analysis, level, precipitation, water inflow, unit goal area could be considered as input variables hydrological model. Two algorithms, Decision Tree Long Short-Term Memory (LSTM) neural network, introduced construct prediction Four error metrics (MAPE, RMSE, NSE R2) applied evaluating performance For value, predictive accuracy model constructed using LSTM 8% higher than algorithm. Accurately predicting caused ensure coal prevent disaster

Language: Английский

---

Decifrando o mecanismo das mudanças de temperatura das águas subterrâneas associadas à mineração longwall em uma jazida de carvão, China, usando o método de aumento de gradiente extremo

Hydrogeology Journal, Journal Year: 2024, Volume and Issue: 32(5), P. 1419 - 1432

Published: June 27, 2024

Language: Английский

---

Transient analysis of functionally graded plates using extreme gradient boosting

Tạp chí Khoa học Công nghệ Xây dựng (KHCNXD) - ĐHXDHN, Journal Year: 2023, Volume and Issue: 17(4), P. 26 - 36

Published: Dec. 25, 2023

This paper is aimed at quickly predicting the dynamic behavior of functionally graded plates using nontraditional computational approaches consisting artificial neural networks (ANN) and extreme gradient boosting (XGBoost). Through use ANN XGBoost, plate can be directly predicted based on optimal mapping, which found by learning relationship between input output data from a set during training process. A including 1000 pairs (input output) generated combination isogeometric analysis (IGA) third-order shear deformation theory through iterations. In this model, power index that controls plate’s material distribution regarded as input, consists 200 values deflection versus time. order to demonstrate effectiveness XGBoost in terms accuracy time, results obtained model are compared those IGA.

Language: Английский

---