Optimized convolutional neural network - kernel ridge regression-error correction method: an advanced model for predicting soil saturated hydraulic conductivity

Parisa Kahkhamoghadam, Mohammad Mahdi Chari, Mohammad ehteram · 2026

Read Optimized convolutional neural network - kernel ridge regression-error correction method: an advanced model for predicting soil saturated hydraulic conductivity by Parisa Kahkhamoghadam, Mohammad Mahdi Chari, Mohammad ehteram (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13538496.txt.

Description

Parisa Kahkhamoghadam and co-authors build a stacked learning model to predict how fast water moves through saturated soil in a 2026 study. The property guides irrigation and drainage design, yet direct measurement is slow. Four soil traits feed a tuned pipeline where a convolutional network compresses data, a ridge method predicts, and an error step mops up leftover gaps. A mutated grasshopper search tunes settings, with uncertainty bands added.

All four traits carried useful signal for prediction. The full stack beat simpler and hybrid rivals on accuracy, error size, and sturdiness by wide margins, slashing percentage error dramatically in comparisons. The authors offer the framework as a reliable stand-in for field measurement across varied conditions, easing water system design where lab access is thin.

Catalog record

CREATORParisa Kahkhamoghadam, Mohammad Mahdi Chari, Mohammad ehteram
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE120648
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13538496

Browse the full library · About the Tower of Babel