<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Portal</title><link>https://personlin.github.io/portal/</link><description>Recent content on Portal</description><generator>Hugo -- 0.146.0</generator><language>zh-tw</language><lastBuildDate>Mon, 30 Mar 2026 12:00:00 +0800</lastBuildDate><atom:link href="https://personlin.github.io/portal/index.xml" rel="self" type="application/rss+xml"/><item><title>GeoSci 精選 2026-03-30</title><link>https://personlin.github.io/portal/notes/geosci-picks-2026-03-30/</link><pubDate>Mon, 30 Mar 2026 12:00:00 +0800</pubDate><guid>https://personlin.github.io/portal/notes/geosci-picks-2026-03-30/</guid><description>&lt;p>本日選文（共 3 篇）。&lt;/p>
&lt;h2 id="1024-spider用於雙差地震重定位的可擴展機率推論">[1024] SPIDER：用於雙差地震重定位的可擴展機率推論&lt;/h2>
&lt;p>&lt;strong>SPIDER: Scalable Probabilistic Inference for Differential Earthquake Relocation&lt;/strong>&lt;/p>
&lt;ul>
&lt;li>期刊：Earth and Space Science (AGU/Wiley) — eTOC&lt;/li>
&lt;li>Published：Wed, 25 Mar 2026 05:58:33 -0700&lt;/li>
&lt;li>DOI：10.1029/2025JB032769&lt;/li>
&lt;li>原文連結：&lt;a href="https://onlinelibrary.wiley.com/doi/10.1029/2025JB032769?af=R" target="_blank" rel="noopener noreferrer">連結&lt;/a>
&lt;/li>
&lt;/ul>
&lt;p>&lt;strong>Summary (EN)&lt;/strong>
Seismicity catalogs have grown hugely, but Bayesian double‐difference earthquake relocation struggles to scale to the millions of parameters involved. The authors introduce SPIDER, a scalable Bayesian framework for double‐difference hypocenter relocation that pairs a physics‑informed neural network Eikonal solver with Stochastic Gradient Langevin Dynamics to generate posterior samples jointly for entire catalogs. SPIDER explicitly whitens residual correlations that traditional formulations neglect, is designed for multi‑GPU parallelization, and is demonstrated on a synthetic catalog and three real catalogs from California and Japan, with proposed tools to analyze high‑dimensional posteriors.&lt;/p></description></item><item><title>GeoSci 精選 2026-03-26</title><link>https://personlin.github.io/portal/notes/geosci-picks-2026-03-26/</link><pubDate>Thu, 26 Mar 2026 12:00:00 +0800</pubDate><guid>https://personlin.github.io/portal/notes/geosci-picks-2026-03-26/</guid><description>&lt;p>本日選文（共 4 篇）。&lt;/p>
&lt;h2 id="1004-利用kik-net二十年資料估算日本岩手縣地下速度與共振頻率變化">[1004] 利用KiK-net二十年資料估算日本岩手縣地下速度與共振頻率變化&lt;/h2>
&lt;p>&lt;strong>Estimating subsurface velocity and resonance frequency changes using two decades of KiK-net data in the Iwate Prefecture, Japan&lt;/strong>&lt;/p>
&lt;ul>
&lt;li>期刊：GJI (OUP) — RSS&lt;/li>
&lt;li>Published：Fri, 13 Mar 2026 00:00:00 GMT&lt;/li>
&lt;li>DOI：10.1093/gji/ggag088&lt;/li>
&lt;li>原文連結：&lt;a href="https://academic.oup.com/gji/article/doi/10.1093/gji/ggag088/8519287?rss=1" target="_blank" rel="noopener noreferrer">連結&lt;/a>
&lt;/li>
&lt;/ul>
&lt;p>&lt;strong>Summary (EN)&lt;/strong>
Using over two decades of KiK-net borehole–surface recordings at 28 stations in Iwate Prefecture, the authors show consistent frequency-domain (stacked Stockwell PSD) and time-domain (multitaper deconvolution and phase cross-correlation) evidence that resonance frequencies and seismic velocities systematically decrease with increasing peak ground acceleration (PGA). Frequency shifts mainly reflect the very shallow layers, while borehole-referenced velocity changes represent a path-averaged perturbation that depends on borehole depth. Across stations, relative velocity reductions average ~12% for the 200–400 cm/s^2 PGA range (implying a shear modulus reduction of ~23%), with stronger nonlinear effects at sites with thicker sedimentary deposits and no clear correlation with VS30.&lt;/p></description></item><item><title>GeoSci 精選 2026-03-25</title><link>https://personlin.github.io/portal/notes/geosci-picks-2026-03-25/</link><pubDate>Wed, 25 Mar 2026 12:00:00 +0800</pubDate><guid>https://personlin.github.io/portal/notes/geosci-picks-2026-03-25/</guid><description>&lt;p>本日選文（共 4 篇）。&lt;/p>
&lt;h2 id="907-利用新建立的-n-net-海底地震儀網於南海溝日向灘檢測淺部構造性顫動">[907] 利用新建立的 N-net 海底地震儀網於南海溝日向灘檢測淺部構造性顫動&lt;/h2>
&lt;p>&lt;strong>Detection of Shallow Tectonic Tremors in Hyuga‐nada, Nankai Trough, Using the Newly Established N‐Net OBS Network&lt;/strong>&lt;/p>
&lt;ul>
&lt;li>期刊：JGR: Solid Earth (AGU/Wiley) — eTOC&lt;/li>
&lt;li>Published：Tue, 17 Mar 2026 02:06:18 -0700&lt;/li>
&lt;li>DOI：10.1029/2025GL121198&lt;/li>
&lt;li>原文連結：&lt;a href="https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2025GL121198?af=R" target="_blank" rel="noopener noreferrer">連結&lt;/a>
&lt;/li>
&lt;/ul>
&lt;p>&lt;strong>Summary (EN)&lt;/strong>
Using machine-learning on newly deployed offshore N‑net OBS data, the authors detected shallow tectonic tremors in Hyuga‑nada between July 2024 and September 2025. Two major tremor episodes occurred: one immediately after the August 2024 M7.0 earthquake and another three days before the January 2025 M6.7 event, with several tremors migrating alongside seismicity—suggesting slow‑slip transients promoted stress transfer along the plate boundary. Tremors clustered in fluid‑rich plate‑boundary zones and were absent in drained areas, indicating structural heterogeneity controls shallow slow‑earthquake dynamics and providing new insights into slow‑earthquake mechanics.&lt;/p></description></item><item><title>GeoSci 精選 2026-03-19</title><link>https://personlin.github.io/portal/notes/geosci-picks-2026-03-19/</link><pubDate>Thu, 19 Mar 2026 12:00:00 +0800</pubDate><guid>https://personlin.github.io/portal/notes/geosci-picks-2026-03-19/</guid><description>&lt;p>本日選文（共 2 篇）。&lt;/p>
&lt;h2 id="907-利用新建立的-n-net-海底地震儀網於南海溝日向灘檢測淺部構造性顫動">[907] 利用新建立的 N-net 海底地震儀網於南海溝日向灘檢測淺部構造性顫動&lt;/h2>
&lt;p>&lt;strong>Detection of Shallow Tectonic Tremors in Hyuga‐nada, Nankai Trough, Using the Newly Established N‐Net OBS Network&lt;/strong>&lt;/p>
&lt;ul>
&lt;li>期刊：JGR: Solid Earth (AGU/Wiley) — eTOC&lt;/li>
&lt;li>Published：Tue, 17 Mar 2026 02:06:18 -0700&lt;/li>
&lt;li>DOI：10.1029/2025GL121198&lt;/li>
&lt;li>原文連結：&lt;a href="https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2025GL121198?af=R" target="_blank" rel="noopener noreferrer">連結&lt;/a>
&lt;/li>
&lt;/ul>
&lt;p>&lt;strong>Summary (EN)&lt;/strong>
Using machine-learning on newly deployed offshore N‑net OBS data, the authors detected shallow tectonic tremors in Hyuga‑nada between July 2024 and September 2025. Two major tremor episodes occurred: one immediately after the August 2024 M7.0 earthquake and another three days before the January 2025 M6.7 event, with several tremors migrating alongside seismicity—suggesting slow‑slip transients promoted stress transfer along the plate boundary. Tremors clustered in fluid‑rich plate‑boundary zones and were absent in drained areas, indicating structural heterogeneity controls shallow slow‑earthquake dynamics and providing new insights into slow‑earthquake mechanics.&lt;/p></description></item><item><title>GeoSci 精選 2026-03-13</title><link>https://personlin.github.io/portal/notes/geosci-picks-2026-03-13/</link><pubDate>Fri, 13 Mar 2026 12:00:00 +0800</pubDate><guid>https://personlin.github.io/portal/notes/geosci-picks-2026-03-13/</guid><description>&lt;p>本日選文（共 6 篇）。&lt;/p>
&lt;h2 id="809-deepsubdas基於海底分布式聲學感測das資料的地震相位挑選器">[809] DeepSubDAS：基於海底分布式聲學感測（DAS）資料的地震相位挑選器&lt;/h2>
&lt;p>&lt;strong>DeepSubDAS: an earthquake phase picker from submarine distributed acoustic sensing data&lt;/strong>&lt;/p>
&lt;ul>
&lt;li>期刊：GJI (OUP) — RSS&lt;/li>
&lt;li>Published：Mon, 09 Feb 2026 00:00:00 GMT&lt;/li>
&lt;li>DOI：10.1093/gji/ggag061&lt;/li>
&lt;li>原文連結：&lt;a href="https://academic.oup.com/gji/article/doi/10.1093/gji/ggag061/8468857?rss=1" target="_blank" rel="noopener noreferrer">連結&lt;/a>
&lt;/li>
&lt;/ul>
&lt;p>&lt;strong>Summary (EN)&lt;/strong>
Submarine Distributed Acoustic Sensing (DAS) can address the scarcity of seismometers in oceanic regions, but land-trained models perform poorly on submarine data. This study develops a DeepLab v3–based machine learning model specifically for submarine DAS to detect seismic events and pick P- and S-waves, trained and validated on nearly 57 million manually and semi-automatically labelled records from multiple global submarine sites. The model is designed to handle different cable lengths, configurations and channel spacings, providing an adaptable tool for automated earthquake analysis and with potential to support real-time monitoring and tsunami early warning.&lt;/p></description></item><item><title>GeoSci 精選 2026-03-09</title><link>https://personlin.github.io/portal/notes/geosci-picks-2026-03-09/</link><pubDate>Mon, 09 Mar 2026 12:00:00 +0800</pubDate><guid>https://personlin.github.io/portal/notes/geosci-picks-2026-03-09/</guid><description>&lt;p>本日選文（共 1 篇）。&lt;/p>
&lt;h2 id="742-尺度相依的地震成核對地震活動構造與實驗室實驗的啟示">[742] 尺度相依的地震成核：對地震活動、構造與實驗室實驗的啟示&lt;/h2>
&lt;p>&lt;strong>Scale-dependent earthquake nucleation: Implications for seismicity, tectonics and laboratory experiments&lt;/strong>&lt;/p>
&lt;ul>
&lt;li>期刊：Tectonophysics (ScienceDirect)&lt;/li>
&lt;li>DOI：10.1016/j.tecto.2026.231156&lt;/li>
&lt;li>原文連結：&lt;a href="https://www.sciencedirect.com/science/article/pii/S0040195126000909?dgcid=rss_sd_all" target="_blank" rel="noopener noreferrer">連結&lt;/a>
&lt;/li>
&lt;/ul>
&lt;p>&lt;strong>Summary (EN)&lt;/strong>
The paper unifies strength-based and fracture-energy views of earthquake nucleation into a single scale-dependent framework in which nucleation stress depends on asperity size relative to a fault characteristic dimension (typically the down-dip width W). Three regimes are identified: small/ thin brittle zones where rupture requires exceeding rock strength, intermediate-sized asperities governed by both strength and energy criteria, and very large seismogenic structures that can fail under very low differential stress. By linking nucleation physics to statistical seismology and tectonics, the framework explains systematic variations in frequency–magnitude distributions (b-values) across settings and provides testable predictions for seismic catalogs and physics-based hazard models.&lt;/p></description></item><item><title>GeoSci 精選 2026-03-02</title><link>https://personlin.github.io/portal/notes/geosci-picks-2026-03-02/</link><pubDate>Mon, 02 Mar 2026 12:00:00 +0800</pubDate><guid>https://personlin.github.io/portal/notes/geosci-picks-2026-03-02/</guid><description>&lt;p>本日選文（共 1 篇）。&lt;/p>
&lt;h2 id="646-在地形條件嚴峻的瑞士-lavey-地熱儲層周圍之大型-n-陣列與分布式聲學感測das">[646] 在地形條件嚴峻的瑞士 Lavey 地熱儲層周圍之大型 N 陣列與分布式聲學感測（DAS）&lt;/h2>
&lt;p>&lt;strong>Large N-array and DAS around the Lavey geothermal reservoir in Switzerland in challenging topographic settings&lt;/strong>&lt;/p>
&lt;ul>
&lt;li>期刊：GJI (OUP) — RSS&lt;/li>
&lt;li>Published：Wed, 11 Feb 2026 00:00:00 GMT&lt;/li>
&lt;li>DOI：10.1093/gji/ggag063&lt;/li>
&lt;li>原文連結：&lt;a href="https://academic.oup.com/gji/article/doi/10.1093/gji/ggag063/8472862?rss=1" target="_blank" rel="noopener noreferrer">連結&lt;/a>
&lt;/li>
&lt;/ul>
&lt;p>&lt;strong>Summary (EN)&lt;/strong>
From April to June 2025, a dense seismic network of 271 three‑component stations was deployed within an 8 km radius around Lavey‑les‑Bains, Switzerland, and complemented by distributed acoustic sensing (DAS) along a buried telecommunication cable to investigate the country’s hottest known natural geothermal system. The site—home to the 3 km‑deep Lavey‑1 well drilled in 2022, which showed unexpectedly low flow despite temperatures above 120°C—lies in the narrow Rhône Valley with steep topography, strong lateral heterogeneity and elevated anthropogenic noise that complicate seismic imaging. The paper describes the network geometry, instrumentation and deployment logistics, assesses data completeness and noise characteristics, and presents initial ambient‑noise and earthquake recordings, reporting high data quality and spatial coverage and establishing a benchmark dataset for developing passive imaging techniques in complex Alpine environments.&lt;/p></description></item><item><title>GeoSci 精選 2026-02-26</title><link>https://personlin.github.io/portal/notes/geosci-picks-2026-02-26/</link><pubDate>Thu, 26 Feb 2026 12:00:00 +0800</pubDate><guid>https://personlin.github.io/portal/notes/geosci-picks-2026-02-26/</guid><description>&lt;p>本日選文（共 5 篇）。&lt;/p>
&lt;h2 id="562-2016-年熊本序列的前震後瞬態滑動第四種前震模式">[562] 2016 年熊本序列的前震後瞬態滑動：第四種前震模式&lt;/h2>
&lt;p>&lt;strong>Post-Foreshock Transient Slip in the 2016 Kumamoto Sequence: A Fourth Foreshock Mode&lt;/strong>&lt;/p>
&lt;ul>
&lt;li>期刊：Earth and Planetary Science Letters (ScienceDirect)&lt;/li>
&lt;li>DOI：10.1016/j.epsl.2026.119905&lt;/li>
&lt;li>原文連結：&lt;a href="https://www.sciencedirect.com/science/article/pii/S0012821X26000889?dgcid=rss_sd_all" target="_blank" rel="noopener noreferrer">連結&lt;/a>
&lt;/li>
&lt;/ul>
&lt;p>&lt;strong>Summary (EN)&lt;/strong>
Using high-rate GPS and tilt-meter time series, the authors invert the 2016 Kumamoto foreshock sequence and resolve an Mw ∼6.1 afterslip and an Mw ∼5.5 transient slow slip occurring between major foreshocks and the mainshock. The transient slow slip began about 9 hours after the M6.0 foreshock near the mainshock hypocenter and was accompanied by accelerated nearby seismicity, which appears to promote mainshock nucleation through quasi-static stress loading. The paper proposes a classification of foreshock-to-mainshock triggering based on the temporal evolution of seismic versus aseismic slip and identifies a distinct fourth foreshock evolution mode beyond the previously recognized “pre-slip,” “cascade,” and “rate-dependent cascade-up” modes.&lt;/p></description></item><item><title>GeoSci 精選 2026-02-25</title><link>https://personlin.github.io/portal/notes/geosci-picks-2026-02-25/</link><pubDate>Wed, 25 Feb 2026 12:00:00 +0800</pubDate><guid>https://personlin.github.io/portal/notes/geosci-picks-2026-02-25/</guid><description>&lt;p>本日選文（共 1 篇）。&lt;/p>
&lt;h2 id="551-月球採礦試驗場址de-gerlacheshackleton-與-sverdruphenson-區域資源開採機會與挑戰之綜述">[551] 月球採礦試驗場址：de Gerlache、Shackleton 與 Sverdrup–Henson 區域資源開採機會與挑戰之綜述&lt;/h2>
&lt;p>&lt;strong>Test mining sites at the moon: A review of resource extraction opportunities and challenges at de Gerlache, Shackleton, and Sverdrup-Henson Regions&lt;/strong>&lt;/p>
&lt;ul>
&lt;li>期刊：Earth-Science Reviews (ScienceDirect)&lt;/li>
&lt;li>DOI：10.1016/j.enggeo.2026.108628&lt;/li>
&lt;li>原文連結：&lt;a href="https://www.sciencedirect.com/science/article/pii/S0013795226000876?dgcid=rss_sd_all" target="_blank" rel="noopener noreferrer">連結&lt;/a>
&lt;/li>
&lt;/ul>
&lt;p>&lt;strong>Summary (EN)&lt;/strong>
This paper evaluates the feasibility of nine candidate sites in the de Gerlache–Shackleton region of the lunar south pole for future mining and extraction activities by comparing geological characteristics, surface slopes, illumination, permanently shadowed regions, thermal environments, and communication constraints. The authors introduce a preliminary optimization-based scoring framework to rank sites by resource potential, engineering constraints, and geologic hazards. Results highlight trade-offs between resource accessibility and operational risk, identify locations that could serve as early testbeds for lunar mining demonstrations, and promote an engineering-geology approach to environmentally informed, transferable site-assessment planning.&lt;/p></description></item><item><title>每日精選 2026-02-09</title><link>https://personlin.github.io/portal/notes/daily-picks-2026-02-09/</link><pubDate>Mon, 09 Feb 2026 08:00:00 +0800</pubDate><guid>https://personlin.github.io/portal/notes/daily-picks-2026-02-09/</guid><description>&lt;p>今天挑兩篇：&lt;/p>
&lt;hr>
&lt;h2 id="1-seismicxr在混合實境中模擬與視覺化地震地面運動">1) Seismic‐XR：在混合實境中模擬與視覺化地震地面運動&lt;/h2>
&lt;p>&lt;strong>Seismic‐XR: Simulating and Visualizing Seismic Ground Motions in Mixed Reality&lt;/strong>&lt;/p>
&lt;ul>
&lt;li>期刊：Seismological Research Letters Advance Access&lt;/li>
&lt;li>原文連結：&lt;a href="https://pubs.geoscienceworld.org/ssa/srl/article/doi/10.1785/0220250169/725511/Seismic-XR-Simulating-and-Visualizing-Seismic" target="_blank" rel="noopener noreferrer">連結&lt;/a>
&lt;/li>
&lt;/ul>
&lt;h3 id="摘要中文">摘要（中文）&lt;/h3>
&lt;p>Seismic-XR 是一個混合實境的教育工具，旨在可視化地震地面運動，讓使用者探索地震波如何與不同地形互動。針對烏塔拉坎地區一次地震的案例研究展示了計算建模、地理空間數據和 XR 技術的結合如何創造引人入勝的視覺體驗。儘管這提高了使用者的參與感，但 XR 對於提升概念理解的影響仍然不確定。&lt;/p>
&lt;h3 id="summary-en">Summary (EN)&lt;/h3>
&lt;p>Seismic-XR is a mixed-reality educational tool designed to visualize seismic ground motions, allowing users to explore how seismic waves interact with various landscapes. A case study from Uttarakhand illustrates how computational modeling, geospatial data, and XR visualization can be combined into an engaging visual experience. While the approach appears to improve engagement, the abstract notes that the effect of XR on deeper conceptual understanding remains uncertain.&lt;/p></description></item><item><title>每日精選 2026-02-08（II）</title><link>https://personlin.github.io/portal/notes/daily-picks-2026-02-08-2/</link><pubDate>Sun, 08 Feb 2026 12:00:00 +0800</pubDate><guid>https://personlin.github.io/portal/notes/daily-picks-2026-02-08-2/</guid><description>&lt;p>今天我挑了三篇：&lt;/p>
&lt;hr>
&lt;h2 id="1-seismicxr在混合實境中模擬與視覺化地震地面運動">1) Seismic‐XR：在混合實境中模擬與視覺化地震地面運動&lt;/h2>
&lt;p>&lt;strong>Seismic‐XR: Simulating and Visualizing Seismic Ground Motions in Mixed Reality&lt;/strong>&lt;/p>
&lt;ul>
&lt;li>期刊：Seismological Research Letters Advance Access&lt;/li>
&lt;li>原文連結：&lt;a href="https://pubs.geoscienceworld.org/ssa/srl/article/doi/10.1785/0220250169/725511/Seismic-XR-Simulating-and-Visualizing-Seismic" target="_blank" rel="noopener noreferrer">連結&lt;/a>
&lt;/li>
&lt;/ul>
&lt;h3 id="摘要中文">摘要（中文）&lt;/h3>
&lt;p>Seismic-XR 是一個混合實境的教育工具，旨在可視化地震地面運動，讓使用者探索地震波如何與不同地形互動。針對烏塔拉坎地區一次地震的案例研究展示了計算建模、地理空間數據和 XR 技術的結合如何創造引人入勝的視覺體驗。儘管這提高了使用者的參與感，但 XR 對於提升概念理解的影響仍然不確定。&lt;/p>
&lt;h3 id="summary-en">Summary (EN)&lt;/h3>
&lt;p>Seismic-XR is a mixed-reality educational tool that visualizes ground motion so users can explore how seismic waves interact with terrain. The paper demonstrates the workflow with a case study from Uttarakhand, combining computational modeling, geospatial data, and XR visualization to create an engaging learning experience. While the approach appears promising for engagement, the abstract notes that the impact of XR on conceptual understanding still needs clearer evaluation.&lt;/p></description></item><item><title>每日精選 2026-02-08</title><link>https://personlin.github.io/portal/notes/daily-picks-2026-02-08/</link><pubDate>Sun, 08 Feb 2026 00:00:00 +0800</pubDate><guid>https://personlin.github.io/portal/notes/daily-picks-2026-02-08/</guid><description>&lt;p>今天我選的一篇：&lt;/p>
&lt;h2 id="基於深度學習並結合疊層學岩性約束的混合模型用於提升遺失測井曲線的預測準確度">基於深度學習並結合疊層學岩性約束的混合模型，用於提升遺失測井曲線的預測準確度&lt;/h2>
&lt;p>&lt;strong>Deep-learning-based hybrid model with iterative lithology constraints for the enhanced prediction of missing well-logs&lt;/strong>&lt;/p>
&lt;ul>
&lt;li>期刊：ScienceDirect Publication: Computers &amp;amp; Geosciences&lt;/li>
&lt;li>原文連結：&lt;a href="https://www.sciencedirect.com/science/article/pii/S0098300426000038?dgcid=rss_sd_all" target="_blank" rel="noopener noreferrer">連結&lt;/a>
&lt;/li>
&lt;/ul>
&lt;h3 id="摘要中文">摘要（中文）&lt;/h3>
&lt;p>本研究提出了一種名為ILCH-Net的深度學習模型，透過將岩性資訊作為限制條件，提升缺失井資料的預測準確度。該模型結合條件變分自編碼器與基於長短期記憶網絡的岩性預測器，在挪威北海六口油井資料上進行測試，結果優於傳統方法，且重建結果在不同井間更具一致性。此方法對石灰岩和黏土岩的預測效果尤其顯著，為儲層特徵描述及相關應用提供可行的建模途徑。&lt;/p>
&lt;h3 id="summary-en">Summary (EN)&lt;/h3>
&lt;p>The authors propose ILCH-Net, a deep-learning model for imputing missing well logs by iteratively enforcing lithology constraints so predictions remain geologically consistent rather than purely data-driven. The approach combines a conditional variational autoencoder with an LSTM-based lithology predictor and trains in a way that can leverage both the log waveforms and lithology information to guide reconstruction. Tests on six wells from the Norwegian North Sea show improved accuracy over baseline methods and better cross-well consistency, with particularly strong gains for limestone and claystone intervals.&lt;/p></description></item><item><title>First post</title><link>https://personlin.github.io/portal/notes/first-post/</link><pubDate>Sat, 07 Feb 2026 00:00:00 +0000</pubDate><guid>https://personlin.github.io/portal/notes/first-post/</guid><description>&lt;p>This is a sample note.&lt;/p></description></item></channel></rss>