https://sciencescholar.us/journal/index.php/ijpse <p style="text-align: justify;"><strong>IJPSE</strong> is published in English and it is open to authors around the world regardless of the nationality. It is currently published three times a year, i.e. in <em>April</em>, <em>August</em>, and <em>December</em>.<br />p-ISSN: 2550-6951</p> Universidad Tecnica de Manabi en-US International journal of physical sciences and engineering 2550-6951 <p>Articles published in the <em>International Journal of Physical Sciences and Engineering&nbsp;</em>(<strong>IJPSE</strong>)&nbsp;are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (<a href="https://creativecommons.org/licenses/by-nc-nd/4.0/" target="_blank" rel="noopener">CC BY-NC-ND 4.0</a>). Authors retain copyright in their work and grant <strong>IJPSE&nbsp;</strong>right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.</p> <p>Articles published in <strong>IJPSE&nbsp;</strong>can be copied, communicated and shared in their published form for non-commercial purposes provided full attribution is given to the author and the journal. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (<em>e.g., post it to an institutional repository or publish it in a book</em>), with an acknowledgment of its initial publication in this journal.</p> <p>This copyright notice applies to articles published in <strong>IJPSE&nbsp;</strong>volumes 4 onwards. Please read about the copyright notices for previous volumes under&nbsp;<a href="https://www.sciencescholar.us/journal/index.php/ijpse/history">Journal History</a>.</p> https://sciencescholar.us/journal/index.php/ijpse/article/view/15981 <p>In Nigeria&nbsp;buried steel infrastructure suffers premature failure due to soil-induced corrosion, yet&nbsp;existing degradation models rely on idealized laboratory simulations that ignore real-world soil heterogeneity and welding parameter interactions. This study addresses this critical gap by investigating mechanical property decay &nbsp;behavior of mild steel weldments through longitudinal field exposure in Ekpoma &nbsp;soil environment &nbsp;&nbsp;with the aim of developing robust, field-validated predictive models to enhance infrastructure durability.</p> <p>Field exposure tests were conducted over twelve months on 20 weldment specimens per site, with tensile strength, impact energy, and hardness evaluated post-exposure Random Forest (RF) were trained on welding parameters (current, voltage, gas flow) using 16 samples, with rigorous validation on 4 unseen field runs.</p> <p>Random Forest demonstrated exceptional predictive capability across all sites and responses, achieving test-set R² values of &nbsp;( tensile), 0.821 (impact), and 0.882 ( hardness).&nbsp;&nbsp;These results establish RF as a&nbsp;viable tool for field-based corrosion forecasting, proving that integration of real-world exposure data with ensemble learning is essential for accurate durability prediction and proactive infrastructure management in heterogeneous soil environments.</p> Larry Ebhota Copyright (c) 2026 International journal of physical sciences and engineering http://creativecommons.org/licenses/by-nc-nd/4.0 2026-08-01 2026-08-01 10 3