MLAir (v1.0) – a tool to enable fast and flexible machine learning on air data time series

Abstract

Abstract. With MLAir (Machine Learning on Air data) we created a software environment that simplifies and accelerates the exploration of new machine learning (ML) models for the analysis and forecasting of meteorological and air quality time series. Thereby MLAir is not developed as an abstract workflow, but hand in hand with actual scientific questions. It thus addresses scientists with either a meteorological or a ML background. Due to their relative ease of use and spectacular results in other application areas, neural networks and other ML methods are gaining enormous momentum also in the weather and air quality research communities. Even though there are already many books and tutorials describing how to conduct a ML experiment, there are many stumbling blocks for a newcomer. In contrast, people familiar with ML concepts and technology often have difficulties understanding the nature of atmospheric data. With MLAir we have addressed a number of these pitfalls so that it becomes easier for scientists of both domains to rapidly start off their ML application. MLAir has been developed in such a way that it is easy to use and is designed from the very beginning as a standalone, fully functional experiment. Due to its flexible, modular code base, code modifications are easy and personal experiment schedules can be quickly derived. The package also includes a set of simple validation tools to facilitate the evaluation of ML results using standard meteorological statistics. MLAir can easily be ported onto different computing environments from desktop workstations to high-end supercomputers with or without graphics processing units (GPU).

Exploring decomposition of temporal patterns to facilitate learning of neural networks for ground-level daily maximum 8-hour average ozone prediction

“…For data preprocessing and model training and evaluation, we employ the software MLAir (version 2.0.0; Leufen et al, 2022). MLAir is a tool written in Python that was developed especially for the application of ML to meteorological time series.…”

“…Note that the uncertainty estimation reported here is independent of the results shown in Table C1, and therefore numbers may vary for statistical reasons. Cite this article: Leufen LH, Kleinert F. and Schultz MG (2022). Exploring decomposition of temporal patterns to facilitate learning of neural networks for ground-level daily maximum 8-hour average ozone prediction.…”

“…The program executes a complete life cycle of an ML training, from preprocessing to training and evaluation. A detailed description of MLAir can be found in Leufen et al (2021).…”

“…The program executes a complete life cycle of an ML training, from preprocessing to training and evaluation. A detailed description of MLAir can be found in Leufen et al (2021). about the future (solid light gray), the filtering of the time series composed of observation and a priori information x ĩ j ð Þ t 0 ð Þ (solid black), and the response of a noncausal filter with access to future values (dashed black) as a reference for a perfect filtering.…”

AI4Water v1.0: an open-source python package for modeling hydrological time series using data-driven methods

“…For the advancement of machine learning in the field of hydrology, experimentation with readily available and fully documented benchmark datasets is required (Leufen et al, 2021). The collection of hydrological data is usually expensive and time-consuming.…”