Integration of Machine Learning Methods into Lagrangian Particle Models of Atmospheric Transport

Туркменова, Р.Т.

Рақамли технологияларнинг назарий ва амалий масалалари · 2025-yil

Annotatsiya

This review systematizes how machine learning (ML) can be integrated into Lagrangian particle dispersion models (LPDM: FLEXPART, HYSPLIT, STILT, NAME) as a physics-consistent augmentation rather than a replacement of the core dynamics. We highlight four strands: (1) physics-informed surrogates for parameterizations (notably PBL/vertical diffusion and wet removal), (2) variance-reduction and Monte-Carlo acceleration (importance sampling, control variates), (3) bias correction and probabilistic calibration of ensembles (EMOS/quantile mapping) using proper scoring rules (CRPS, reliability), and (4) mass-conserving super-resolution of concentration fields without re-integrating trajectories. Inversions based on footprint matrices (Bayesian, variational, and ensemble approaches) and observation-network requirements are discussed separately. The methodology includes a formalized literature search (2000–2025; WoS/Scopus/Scholar) and reproducibility practices (fixed meteorological drivers, reporting protocols). We argue that robust ML gains depend on two disciplines: preserving physical invariants (mass balance, well-mixed, non-negativity) and methodological rigor (RMSE/correlation/CSI-POFD/CRPS, reliability diagnostics). A “minimal viable” operational pipeline is proposed: fix ERA5/WRF or GDAS/GFS forcings and LPDM configs; add mass-conserving bias correctors and probabilistic calibration; apply a sum-preserving SR module; optionally use PI surrogates for nocturnal PBL regimes, with mandatory validation on real episodes.

Maqola ma’lumotlari
MualliflarТуркменова, Р.Т.
JurnalРақамли технологияларнинг назарий ва амалий масалалари
Nashr sanasi2025-09-30
Jild8
Son3
Betlar130-141
TilRus
DOI10.62132/ijdt.v8i3.296

DOI: 10.62132/ijdt.v8i3.296 · Maqolaning asl sahifasi

Kalit so‘zlar

лагранжево-частичные модели, FLEXPART, HYSPLIT, STILT, NAME, машинное обучение, супер-разрешение, вероятностная калибровка, CRPS, инверсии источников, воспроизводимость, Lagrangian particle dispersion, FLEXPART, HYSPLIT, STILT, NAME, machine learning, physics-informed, super-resolution, probabilistic calibration, CRPS, source inversions, reproducibility

Ilmiy soha

Texnika

Рақамли технологияларнинг назарий ва амалий масалалари jurnalidan boshqa maqolalar

Рақамли технологияларнинг назарий ва амалий масалалари — barcha maqolalar