Statistical and Machine Learning Methods for Climate Sciences: Advances, Applications and Emerging Challenges

A special issue of Atmosphere (ISSN 2073-4433). This special issue belongs to the section "Climatology".

Deadline for manuscript submissions: 30 June 2026 | Viewed by 309

Special Issue Editors


E-Mail Website
Guest Editor
Department of Statistic, Federal University of Piauí, Teresina 64049-550, Brazil
Interests: statistical analysis; statistical modeling; data analysis; applied probability; climate; hydrology; remote sensing data; data manipulation; climate change; extreme events

E-Mail Website
Guest Editor
Department of Atmospheric and Climate Sciences, Graduate Program in Climate Sciences (PPGCC), Federal University of Rio Grande do Norte, Natal 59078-970, Brazil
Interests: population and climate; statistical information; climate statistics

E-Mail Website
Guest Editor
Department of Atmospheric and Climate Sciences, Graduate Program in Climate Sciences (PPGCC), Federal University of Rio Grande do Norte, Natal 59078-970, Brazil
Interests: tropical climatology; soil-plant-atmosphere interactions; climate modeling; extreme events (weather and climate)

Special Issue Information

Dear Colleagues,

Recent advances in statistical and machine learning (ML) methods have revolutionized how climate and hydrometeorological phenomena are investigated. This Special Issue aims to gather studies presenting innovative approaches, practical applications, and methodological developments focused on understanding, predicting, and mitigating the impacts of climate change. Submissions employing classical and modern statistical techniques, as well as ML and deep learning approaches, are welcome for applications such as extreme event detection and prediction, spatio-temporal modeling, dynamic and statistical downscaling, bias adjustment, uncertainty analysis, and integration of multiple data sources (observations, satellites, reanalyses, and climate models). This Special Issue also encourages research exploring teleconnections, ocean–atmosphere interactions, climate services, and scientific communication strategies on climate risk, emphasizing reproducible and open-data approaches. The goal is to foster integration between data science and climatology, highlighting methodological contributions that enhance the predictive capacity, reliability, and applicability of climate analyses across different spatial and temporal scales.

Dr. Daniele Tôrres Rodrigues
Dr. Lára de Melo Barbosa Andrade
Dr. Cláudio Moisés Santos e Silva
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Atmosphere is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • statistical modeling
  • machine learning
  • climate change
  • extreme events
  • bias correction
  • remote sensing
  • data science
  • downscaling
  • teleconnections
  • uncertainty analysis

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

17 pages, 16565 KB  
Article
A Case Study on the Stability of Neural Network Climate Prediction Models with Different Training Stop Criteria
by Xiangjun Shi, Ping Zhou and Sirui He
Atmosphere 2026, 17(5), 523; https://doi.org/10.3390/atmos17050523 - 20 May 2026
Abstract
Due to randomness factors in the machine learning model construction process, reproducibility is compromised. This study investigates the impact of randomness on model stability and evaluates techniques for reducing this impact using the widely adopted shallow neural network model as a testbed. Randomness [...] Read more.
Due to randomness factors in the machine learning model construction process, reproducibility is compromised. This study investigates the impact of randomness on model stability and evaluates techniques for reducing this impact using the widely adopted shallow neural network model as a testbed. Randomness in this neural network model arises from three events: randomly initializing model parameters, randomly selecting a validation subset, and randomly sampling batches for parameter updates. Among these, batch randomness exerts a much weaker impact than the other two factors. In this study, the model training is stopped when the validation performance fails to improve or when a preset threshold for loss or epoch number is met. The final model stability is considerably better when using threshold criteria than when using validation criterion, as the former avoids the randomness associated with selecting a validation subset. Sensitivity experiments show that scaling the model’s initial parameters (i.e., weights) to 0.1 times their original values can mitigate the impact of initialization randomness, thereby markedly improving model stability while also substantially enhancing predictive skill. Furthermore, weight decay and multi-model ensembles, which are two commonly used techniques, can also markedly enhance model stability. From the perspective of this case study, the compression of model initial parameters yields better improvements in stability compared to weight decay, and unlike multi-model ensemble methods that entail substantial increases in computational cost, it serves as a preferable technique for improving model stability. Full article
Show Figures

Figure 1

Back to TopTop