Hydrochemistry and modeling nitrate concentration in farmland groundwater under different hydrological seasons by integrating hybrid quantum-classical ML, virtual sample generation and AlphaEarth Foundation
J. Xu; X. Wei; Y. Yu; L. Yang; Y. Zhai; C. Lv; X. Song · DOAJ Open Access Articles
Abstrak / Ringkasan
<p>Precise seasonal prediction of groundwater nitrate concentrations in intensive agricultural areas faces challenges such as data sparsity, strong spatiotemporal heterogeneity, and complex hydro-biogeochemical processes. To address these issues, this study proposes an integrated prediction framework combining hybrid quantum-classical machine learning, advanced virtual sample generation (t-SNE-GMM-KNN), and remote sensing foundation model semantic embedding (AEF). Modeling was conducted across the 2022–2023 normal, dry, and wet seasons in Xiong'an New Area. Hydrochemical types were dominated by Ca-Mg-HCO<span class="inline-formula"><math xmlns="http://www.w3.org/1998/Math/MathML" id="M1" display="inline" overflow="scroll" dspmath="mathml"><mrow><msubsup><mi/><mn mathvariant="normal">3</mn><mo>-</mo></msubsup></mrow></math><span><svg:svg xmlns:svg="http://www.w3.org/2000/svg" width="9pt" height="16pt" class="svg-formula" dspmath="mathimg" md5hash="5c4cefaf8b78d41c1ce2f2ef151f712f"><svg:image xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="hess-30-5647-2026-ie00001.svg" width="9pt" height="16pt" src="hess-30-5647-2026-ie00001.png"/></svg:svg></span></span>, controlled by mineral dissolution and evaporation. Nitrate concentrations were highest in the dry season (mean 42.93?mg?L<span class="inline-formula"><sup>?1</sup></span>), driven by evaporative concentration. Spatially, high-value zones shifted: southeast (normal), central (dry), and northwest (wet). MixSIAR modeling based on isotopes indicated domestic sewage and livestock manure (74.1?%) as dominant sources. The t-SNE-GMM-KNN strategy mitigated small-sample bias while preserving nonlinear structure. When virtual samples were augmented to 10-fold, the Random Forest <span class="inline-formula"><i>R</i><sup>2</sup></span> in the dry season increased from 0.284 to <span class="inline-formula"><i>></i></span>?0.85. Furthermore, a hybrid quantum-classical Random Forest exhibited superior robustness for data sparsity, achieving peak performance in the normal season (<span class="inline-formula"><i>R</i><sup>2</sup>=</span>?0.962, RMSE?<span class="inline-formula">=</span>?5.73?mg?L<span class="inline-formula"><sup>?1</sup></span>). Additionally, using only AEF embeddings achieved screening-level accuracy (<span class="inline-formula"><i>R</i><sup>2</sup></span> up to 0.860), providing a feasible rapid survey scheme for extensive unmonitored regions, where field sampling is impractical, whereas the field-parameter-based model serves primarily to elucidate hydrochemical driving mechanisms and enables rapid on-site nitrate estimation using portable water quality meters. Correlation analysis identified TDS and EC as persistent top predictors (<span class="inline-formula"><i>r</i><i>></i></span>?0.8). This comprehensive framework offers a robust solution for seasonal nitrate prediction by distinguishing between mechanistic analysis, field-operational estimation, and large-scale screening and sustainable water management.</p>
Topik Terkait
Referensi Serupa
Enhanced hybrid residual learning framework for robust wind turbine power prediction using machine learning
Mohammad Y. Mhawiash; Bashar S. Khassawneh; Kamal Alieyan; Issa Alsmadi; Mohammad Bani Younes; Mohamed S. Sawah
Virtual literacy instruction: An investigation of how elementary educators exhibited TPACK during COVID-19 school closures
Michelle Gonzalez; Gihan A. Mohamad
A systematic review and mapping of the literature of virtual reality studies in earth science engineering education
Özcan Özyurt; Nergiz Ercil Cagiltay; Hacer Özyurt; Aykut Akgun
Effects of violating the assumptions of equal variance and independent and identically distributed random variables: A case using {B}ayesian statistical modeling
Sawada, Tadamasa
Enhancing aridity index assessment in Pakistan's dryland ecosystems: A machine learning approach integrating remote sensing and seasonal lag effects
Mazhar, N.; Ghalub, A.K.; Malki, I.; Noreena; Arshad, S.
Prediction model of preeclampsia using single nucleotide polymorphism and machine learning methods: A population-based cohort study in Jordan
Shatha Awawdeh; Hasan Rawashdeh; Hanaa Fathi; Arar Al Tawil; Fatima Al-Shannaq; Esraa Henawi; Omar F. Khabour
Omnichannel, ZMOT, and Virtual try-on: Perceived behavioral control in purchase decision
Desak Made Febri Purnama Sari; Ida Ayu Oka Martini; Made Ermawan Yoga Antara; Ni Wayan Kerni Sinthya Dewi
A hybrid machine learning framework for optimized MSME classification and knowledge discovery in smart village systems
Eneng Tita Tosida; Ajiz Abdul Majid; Irma Anggraeni; Jumadil Saputra; Muhamad Deni Johansyah
A hybrid structural–machine learning framework: Conventional SVAR and random forest regression
Augusto Aliaga-Miranda; Luis Ricardo Flores-Vilcapoma; Jorge Miguel Chávez-Díaz; Luis Antonio Visurraga-Camargo; Jacqueline Denisse Llacza-Molina; Wilmar Salvador Chavarry-Becerra
Virtually Viral Hangouts: Reflections on the role of community during crisis
Lauren G. McClanahan
Using Virtual Exchange to Advance Media Literacy Competencies through Analysis of Contemporary Propaganda
Renee Hobbs; Christian Seyferth-Zapf; Silke Grafe
Critical Media Literacies in the Twenty-First Century: Writing Autoethnographies, Making Connections, and Creating Virtual Identities
Ah-Young Song
Literatur Lain dari DOAJ Open Access Articles
Enhanced hybrid residual learning framework for robust wind turbine power prediction using machine learning
Mohammad Y. Mhawiash; Bashar S. Khassawneh; Kamal Alieyan; Issa Alsmadi; Mohammad Bani Younes; Mohamed S. Sawah · 2026
Virtual literacy instruction: An investigation of how elementary educators exhibited TPACK during COVID-19 school closures
Michelle Gonzalez; Gihan A. Mohamad · 2022
A systematic review and mapping of the literature of virtual reality studies in earth science engineering education
Özcan Özyurt; Nergiz Ercil Cagiltay; Hacer Özyurt; Aykut Akgun · 2021
Effects of violating the assumptions of equal variance and independent and identically distributed random variables: A case using {B}ayesian statistical modeling
Sawada, Tadamasa · 2023
Prediction model of preeclampsia using single nucleotide polymorphism and machine learning methods: A population-based cohort study in Jordan
Shatha Awawdeh; Hasan Rawashdeh; Hanaa Fathi; Arar Al Tawil; Fatima Al-Shannaq; Esraa Henawi; Omar F. Khabour · 2026
Omnichannel, ZMOT, and Virtual try-on: Perceived behavioral control in purchase decision
Desak Made Febri Purnama Sari; Ida Ayu Oka Martini; Made Ermawan Yoga Antara; Ni Wayan Kerni Sinthya Dewi · 2026
A hybrid machine learning framework for optimized MSME classification and knowledge discovery in smart village systems
Eneng Tita Tosida; Ajiz Abdul Majid; Irma Anggraeni; Jumadil Saputra; Muhamad Deni Johansyah · 2026
A hybrid structural–machine learning framework: Conventional SVAR and random forest regression
Augusto Aliaga-Miranda; Luis Ricardo Flores-Vilcapoma; Jorge Miguel Chávez-Díaz; Luis Antonio Visurraga-Camargo; Jacqueline Denisse Llacza-Molina; Wilmar Salvador Chavarry-Becerra · 2026
Literatur Terbaru yang Relevan
Enhanced hybrid residual learning framework for robust wind turbine power prediction using machine learning
Mohammad Y. Mhawiash; Bashar S. Khassawneh; Kamal Alieyan; Issa Alsmadi; Mohammad Bani Younes; Mohamed S. Sawah · 2026
Virtual literacy instruction: An investigation of how elementary educators exhibited TPACK during COVID-19 school closures
Michelle Gonzalez; Gihan A. Mohamad · 2022
A systematic review and mapping of the literature of virtual reality studies in earth science engineering education
Özcan Özyurt; Nergiz Ercil Cagiltay; Hacer Özyurt; Aykut Akgun · 2021
Effects of violating the assumptions of equal variance and independent and identically distributed random variables: A case using {B}ayesian statistical modeling
Sawada, Tadamasa · 2023
Enhancing aridity index assessment in Pakistan's dryland ecosystems: A machine learning approach integrating remote sensing and seasonal lag effects
Mazhar, N.; Ghalub, A.K.; Malki, I.; Noreena; Arshad, S. · 2025
Prediction model of preeclampsia using single nucleotide polymorphism and machine learning methods: A population-based cohort study in Jordan
Shatha Awawdeh; Hasan Rawashdeh; Hanaa Fathi; Arar Al Tawil; Fatima Al-Shannaq; Esraa Henawi; Omar F. Khabour · 2026
Omnichannel, ZMOT, and Virtual try-on: Perceived behavioral control in purchase decision
Desak Made Febri Purnama Sari; Ida Ayu Oka Martini; Made Ermawan Yoga Antara; Ni Wayan Kerni Sinthya Dewi · 2026
A hybrid machine learning framework for optimized MSME classification and knowledge discovery in smart village systems
Eneng Tita Tosida; Ajiz Abdul Majid; Irma Anggraeni; Jumadil Saputra; Muhamad Deni Johansyah · 2026