Machine learning in vadose zone hydrology: A flashback
Abstract Artificial intelligence (AI) and machine learning (ML) have been recently applied extensively in various disciplines of vadose zone hydrology. However, not much attention has been paid to their database‐dependent accuracy and uncertainty, reproducibility, and delivery, which undermines thei...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-07-01
|
| Series: | Vadose Zone Journal |
| Online Access: | https://doi.org/10.1002/vzj2.20212 |
| _version_ | 1818517866496917504 |
|---|---|
| author | Behzad Ghanbarian Yakov Pachepsky |
| author_facet | Behzad Ghanbarian Yakov Pachepsky |
| author_sort | Behzad Ghanbarian |
| collection | DOAJ |
| description | Abstract Artificial intelligence (AI) and machine learning (ML) have been recently applied extensively in various disciplines of vadose zone hydrology. However, not much attention has been paid to their database‐dependent accuracy and uncertainty, reproducibility, and delivery, which undermines their applications to real‐world problems. We discuss lessons from the past and emphasize the need for and lack of fundamental protocols (i.e., detailed clarification on data processing, ML models accessibility, and a clear path for reproducing results). |
| first_indexed | 2024-12-11T01:02:03Z |
| format | Article |
| id | doaj.art-d4449f8f2b5e47878d786a15c92017ac |
| institution | Directory Open Access Journal |
| issn | 1539-1663 |
| language | English |
| last_indexed | 2024-12-11T01:02:03Z |
| publishDate | 2022-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | Vadose Zone Journal |
| spelling | doaj.art-d4449f8f2b5e47878d786a15c92017ac2022-12-22T01:26:18ZengWileyVadose Zone Journal1539-16632022-07-01214n/an/a10.1002/vzj2.20212Machine learning in vadose zone hydrology: A flashbackBehzad Ghanbarian0Yakov Pachepsky1Porous Media Research Laboratory, Dep. of Geology Kansas State Univ. Manhattan KS 66506 USAEnvironmental Microbial and Food Safety Laboratory USDA‐ARS Beltsville MD 20705 USAAbstract Artificial intelligence (AI) and machine learning (ML) have been recently applied extensively in various disciplines of vadose zone hydrology. However, not much attention has been paid to their database‐dependent accuracy and uncertainty, reproducibility, and delivery, which undermines their applications to real‐world problems. We discuss lessons from the past and emphasize the need for and lack of fundamental protocols (i.e., detailed clarification on data processing, ML models accessibility, and a clear path for reproducing results).https://doi.org/10.1002/vzj2.20212 |
| spellingShingle | Behzad Ghanbarian Yakov Pachepsky Machine learning in vadose zone hydrology: A flashback Vadose Zone Journal |
| title | Machine learning in vadose zone hydrology: A flashback |
| title_full | Machine learning in vadose zone hydrology: A flashback |
| title_fullStr | Machine learning in vadose zone hydrology: A flashback |
| title_full_unstemmed | Machine learning in vadose zone hydrology: A flashback |
| title_short | Machine learning in vadose zone hydrology: A flashback |
| title_sort | machine learning in vadose zone hydrology a flashback |
| url | https://doi.org/10.1002/vzj2.20212 |
| work_keys_str_mv | AT behzadghanbarian machinelearninginvadosezonehydrologyaflashback AT yakovpachepsky machinelearninginvadosezonehydrologyaflashback |