Porosity prediction of tight reservoir rock using well logging data and machine learning

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 16, 2025

Language: Английский

---

An improved GRU method for slope stress prediction

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 21, 2025

The stability of open-pit mine slopes is a complex nonlinear system. Stress variation significant influencing factor in the occurrence landslide disasters and also key research focus early warning risk assessment. However, traditional methods are confronted with challenges, including low prediction accuracy poor robustness when dealing time series data. In order to address aforementioned issues, present paper proposes an intelligent model based on Variational Mode Decomposition (VMD) Dung Beetle Optimization (DBO), combined improved Gated Recurrent Unit (GRU), which hereby referred as VMD-DBO-GRU-A model. preliminary preprocessing open pit slope stress data using VMD can provide high decomposition effectively extract localized features stress; method introduces (DBO) determine number hidden neuron layers optimal learning rate for GRU. This reduces uncertainty parameters minimizes required parameter tuning; Self-attention mechanism added assign different weights input features, dependence external information more adept at capturing internal relevance or features. verify validity model, experiments conducted self-constructed dataset this paper. experimental results show that root-mean-square error has decreased by 77% 84% compared LSTM SVM models, respectively, coefficient determination 0.9978, fully verifies excellent comprehensive performance accuracy, great value practical application mines' slopes.

Language: Английский

---

Identification of groundwater potential zones of Alappuzha (Kerala) in South India integrating AHP and GIS

Environment Development and Sustainability, Journal Year: 2024, Volume and Issue: unknown

Published: May 7, 2024

Language: Английский

---

Evidential Neural Network Model for Groundwater Salinization Simulation: A First Application in Hydro-Environmental Engineering

Water, Journal Year: 2024, Volume and Issue: 16(20), P. 2873 - 2873

Published: Oct. 10, 2024

Groundwater salinization is a crucial socio-economic and environmental issue that significant for variety of reasons, including water quality availability, agricultural productivity, health implications, socio-political stability sustainability. Salinization degrades the water, rendering it unfit human consumption increasing demand costly desalination treatments. Consequently, there need to find simple, sustainable, green cost-effective methods can be used in understanding minimizing groundwater salinization. Therefore, this work employed implementation neurocomputing approaches modeling Before starting approach, correlation sensitivity analyses independent dependent variables were conducted. Hence, three different schema groups (G1–G3) subsequently developed based on analysis results. The obtained quantitative results illustrate G2 input grouping depicts substantial performance compared G1 G3. Overall, evidential neural network (EVNN), as novel technique, demonstrates highest accuracy, has capability boosting against classical robust linear regression (RLR) up 46% 46.4% calibration validation stages, respectively. Both EVNN-G1 EVNN-G2 present excellent metrics (RMSE ≈ 0, MAPE = PCC 1, R2 1), indicating perfect prediction while EVNN-G3 slightly lower than EVNN-G2, but still highly accurate 10.5351, 0.1129, 0.9999, 0.9999). Lastly, various state-of-the-art visualizations, contour plot embedded with response plot, bump Taylor diagram, illustrating models.

Language: Английский

---

Innovative mapping of groundwater redox status and cation exchange conditions in a GIS environment

Groundwater for Sustainable Development, Journal Year: 2024, Volume and Issue: 25, P. 101188 - 101188

Published: April 26, 2024

Understanding the complexities of regional groundwater quality is crucial for managing resources. Groundwater assessment involves investigating specific dissolved components, example, comparing them to established standards. To fully understand all aspects quality, one should assess composite properties, being redox status and another cation exchange condition. The first may, impose a control on degradation organic micropollutants. While numerical indices can be easily interpolated visualised using various GIS applications, consistently mapping conditions as non-numerical remains challenging. Furthermore, no study has yet conducted regional-scale classes in environment extensive samples. deepen our understanding these we employed ArcGIS this map two stages. First, mapped components interest, including Cl, SO4, SO4/Cl, Fe, NO3 base exchanges Na Mg, by most appropriate interpolation method identified geostatistical analysis. Then, variables were combined, conditional functions used ArcMap's Math toolbox determine or classes. Our innovative was developed 3,350 sampling locations coastal lowlands Western Netherlands. successful, with generally 75%–95% similarity between predicted observed situations introduced more straightforward than others other linguistic like Wilcox irrigation water classifications, well.

Language: Английский

---

Machine learning-based monitoring and design of managed aquifer rechargers for sustainable groundwater management: scope and challenges

Environmental Science and Pollution Research, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 25, 2024

Abstract Managed aquifer recharge (MAR) replenishes groundwater by artificially entering water into subsurface aquifers. This technology improves storage, reduces over-extraction, and ensures security in water-scarce or variable environments. MAR systems are complex, encompassing various components such as soil, meteorological factors, management (GWM), receiving bodies. Over the past decade, utilization of machine learning (ML) methodologies for modeling prediction has increased significantly. review evaluates all supervised, semi-supervised, unsupervised, ensemble ML models employed to predict factors parameters, rendering it most comprehensive contemporary on this subject. study presents a concise integrated overview MAR’s effective approaches, focusing design, suitability quality (WQ) applications, GWM. The paper examines performance measures, input specifications, variety functions GWM, highlights prospects. It also offers suggestions utilizing MAR, addressing issues related physical aspects, technical advancements, case studies. Additionally, previous research ML-based data-driven soft sensing techniques is critically evaluated. concludes that integrating holds significant promise optimizing WQ enhancing efficiency replenishment strategies.

Language: Английский

---

Application of Machine Learning in Healthcare and Medicine: A Review

Journal of Robotics and Control (JRC), Journal Year: 2023, Volume and Issue: 4(5), P. 621 - 631

Published: Sept. 13, 2023

This extensive literature review investigates the integration of Machine Learning (ML) into healthcare sector, uncovering its potential, challenges, and strategic resolutions. The main objective is to comprehensively explore how ML incorporated medical practices, demonstrate impact, provide relevant solutions. research motivation stems from necessity comprehend convergence services, given intricate implications. Through meticulous analysis existing research, this method elucidates broad spectrum applications in disease prediction personalized treatment. research's precision lies dissecting methodologies, scrutinizing studies, extrapolating critical insights. article establishes that has succeeded various aspects care. In certain algorithms, especially Convolutional Neural Networks (CNNs), have achieved high accuracy diagnosing diseases such as lung cancer, colorectal brain tumors, breast tumors. Apart CNNs, other algorithms like SVM, RF, k-NN, DT also proven effective. Evaluations based on F1-score indicate satisfactory results, with some studies exceeding 90% accuracy. principal finding underscores impressive diverse conditions. outcome signifies transformative potential reshaping conventional diagnostic techniques. Discussions revolve around challenges data quality, security risks, misinterpretations, obstacles integrating clinical realms. To mitigate these, multifaceted solutions are proposed, encompassing standardized formats, robust encryption, model interpretation, clinician training, stakeholder collaboration.

Language: Английский

---

Addressing Nitrate Contamination in Groundwater: The Importance of Spatial and Temporal Understandings and Interpolation Methods

Water, Journal Year: 2023, Volume and Issue: 15(24), P. 4220 - 4220

Published: Dec. 7, 2023

Iranian water security is threatened by groundwater (GW) degradation. The excessive use of GW for agriculture in Iran degrading these resources. Livestock waste disposal and sewage irrigation are also major contributors. Nitrate (NO3) contamination a growing global concern, posing serious health environmental risks. Soil can easily leach NO3 into GW, causing long-term contamination. Understanding the temporal spatial patterns pollution vital protecting human establishing safe drinking limits. Choosing an appropriate interpolation method crucial creating reliable variability map, which essential research decision-making. This study used 85 samples collected over four periods to create interpolated maps examine levels. Spatial methods were performed using geostatistical tool within ArcGIS Software. results showed that Empirical Bayesian Kriging (EBK) was most effective five evaluated methods, although performance each varied depending on period sampled. Therefore, choice should be tailored study’s specific needs characteristics data being interpolated. EBK produced illustrated distribution concentrations, both exceeding recommended guidelines. Interpolation assist identifying sources, developing targeted management strategies. These demonstrate potential impact activities observed patterns. A thorough understanding Iran’s current quality very important valuable policymakers.

Language: Английский

---

Groundwater contamination modelling in Ayad River Basin, Udaipur

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: July 18, 2024

Groundwater, a vital freshwater resource catering to agricultural, domestic, and industrial needs, faces pressing challenge of contamination due escalating human activities. This study focuses on the Ayad River Basin in Udaipur district Rajasthan, employing FEFLOW simulation code for first time. A steady-state numerical model groundwater contaminant prediction total dissolved solids (TDS), nitrate, fluoride were developed, simulating trends over next five years with an accuracy exceeding 95%. The results reveal eastward increase TDS, concentrations, attributed from two waste disposal sites-Titadi Baleecha. Titadi, operational four decades until closure 2010, retains residual 32 thousand m2. initiation new dumping ground at Baleecha by Municipal Corporation post-2010 exacerbates regional contamination. Nitrate is particularly high agricultural zones excessive chemical fertilizer usage. Of 27 scenarios tested, 23 support using water irrigation but would require treatment before it drinking. Recommendations include deploying sensor network real-time data input into web enabled model, monitoring alerts, mobile application providing personalized guidance usage health risks case can be beneficial decision-makers, who work policy management strategies.

Language: Английский

---

Hydrochemical assessment of groundwater with special emphasis on fluoride in parts of Punjab and fluoride prediction using GIS and ML

Environmental Earth Sciences, Journal Year: 2024, Volume and Issue: 83(19)

Published: Sept. 27, 2024

Language: Английский

---