A novel deep learning prediction method for PM2.5 integrating improved MSTL decomposition and FATA optimization algorithm

Xiaoliang Zhao, Pinyuan Qiao, Bandna Bharti, Hanliang Li, Shitong Yang, Qi Shi, Qiuhong Qin, Jundian Chen · 2026

Read A novel deep learning prediction method for PM2.5 integrating improved MSTL decomposition and FATA optimization algorithm by Xiaoliang Zhao, Pinyuan Qiao, Bandna Bharti, Hanliang Li, Shitong Yang, Qi Shi, Qiuhong Qin, Jundian Chen (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/pmc-13577383.txt.

Description

Xiaoliang Zhao and co-authors build, in a 2026 study, a deep learning model to forecast fine dust in city air, known as PM2.5. Sharp forecasts of this dust aid health warns and smog control. Their model stacks three stages. First, a search picks the best input traits, matched with a check on how traits move as one. Next, a split method breaks the dust time line into trend and season parts, tuned by a spectrum scan and a grid search. Last, a mixed neural net reads the rebuilt data and makes the forecast.

A new search method, named for the Fata Morgana mirage, tunes the net's dials. Tests ran in two cities, Guangzhou and Xianyang, split by heating and non-heating seasons to weigh weather and land. The model beat rivals on accuracy and stability, the team reports.

Catalog record

CREATORXiaoliang Zhao, Pinyuan Qiao, Bandna Bharti, Hanliang Li, Shitong Yang, Qi Shi, Qiuhong Qin, Jundian Chen
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE74 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13577383

Browse the full library · About the Tower of Babel