iMESc - an interactive machine learning app for environmental sciences

Aug 4, 2026

Upload by Levi

As environmental sciences increasingly depend on complex datasets, machine learning becomes essential for uncovering patterns and relationships. However, integrating ML into research workflows is often slowed by technical barriers, extensive coding time, and iterative debugging. iMESc is an interactive R/Shiny application that streamlines ML workflows for environmental data. It supports supervised and unsupervised methods, data preprocessing, visualization, descriptive statistics, and spatial analysis, using Datalist transitions and savepoints to improve reproducibility, demonstrated through multiple analysis workflows in a nematode case study.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Introduction

Motivation and challenges of integrating ML in environmental workflows

Methods and platform design

iMESc architecture and features (R, Shiny, supervised/unsupervised workflows)

Data preprocessing, visualization, statistics, and spatial analysis

Case study and results

Four workflows for predicting nematode community structure

Reproducibility and usability

TYPE Technology and Code PUBLISHED 31 January 2025 DOI 10.3389/fenvs.2025.1533292 OPEN ACCESS EDITED BY Yiannis Kamarianakis, Foundation for Research and Technology Hellas, Greece REVIEWED BY Dimitris Poursanidis, Terrasolutions Marine Environment Research, Greece Carolina Crisci, Universidad de la República, Uruguay iMESc – an interactive machine learning app for environmental sciences Danilo Cândido Vieira 1,2*, Fabiana S. Paula 1, Luciana Erika Yaginuma 2 and Gustavo Fonseca 1 1Instituto do Mar, Campus Baixada Santista, Universidade Federal de São Paulo, Santos, Brazil, 2Instituto Oceanográﬁco, Universidade de São Paulo, São Paulo, Brazil *CORRESPONDENCE Danilo Cândido Vieira, [vieiradc@yahoo.com.br](vieiradc@yahoo.com.br) RECEIVED 23 November 2024 ACCEPTED 13 January 2025 PUBLISHED 31 January 2025 CITATION Vieira DC, Paula FS, Yaginuma LE and Fonseca G (2025) iMESc – an interactive machine learning app for environmental sciences. Front. Environ. Sci. 13:1533292 . doi: 10.3389/fenvs.2025.1533292 COPYRIGHT © 2025 Vieira, Paula, Yaginuma and Fonseca. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. As environmental sciences increasingly rely on complex datasets, machine learning (ML) has become crucial for identifying patterns and relationships. However, the integration of ML into workﬂows can pose challenges due to technical barriers or the time-intensive nature of coding. To address these issues, we developed iMESc, an interactive ML app designed to streamline and simplify ML workﬂows for environmental data. Developed in R and built on the Shiny platform, iMESc enables the integration of supervised and unsupervised ML methods, along with tools for data preprocessing, visualization, descriptive statistics, and spatial analysis. The Datalist system ensures seamless transitions between analytical workﬂows, while the “savepoints” feature enhances reproducibility by preserving the analysis state. We demonstrate iMESc’s ﬂexibility with four workﬂows applied to a case study predicting nematode community structure based on environmental data. The classical statistical approaches, the Redundancy Analysis (RDA) and Piecewise RDA (pwRDA), explained 30 .7% and 53%, respectively. The SuperSOM model achieved an R2 of 0.60 for training and 0.291 for testing, identifying spatial patterns across depth zones. Finally, a hybrid model combining an unsupervised SOM and followed by the supervised Random Forest model returned an accuracy of 83.47% for the training and 80.77% for the test, with Bathymetry, Chlorophyll, and Coarse Sand as key predictive variables. IMESc permits the customization of plots and saving the workﬂows into “savepoints” guarantying reproducibility. iMESc bridges the gap between the complexity of machine learning algorithms and the need for userfriendly interfaces in environmental research. By reducing the technical burden of coding, iMESc allows researchers to focus on scientiﬁc inquiry, improving both the efﬁciency and depth of their analyses. KEYWORDS shiny, machine-learning, supervised, unsupervised, environmental sciences, analytical workﬂow 1 Introduction With the fast-paced advances in technologies for data acquisition, environmental researchers are now working with increasingly large datasets from diverse sources. These data volumes present new opportunities for innovative analytical approaches, beyond the traditional hypothesis-driven methods, including the applications of machine learning (ML) algorithms (Tahmasebi et al., 2020; Heil et al., 2021) . ML has become

FAQs

What problem does iMESc address in environmental machine learning workflows?

iMESc addresses the time-intensive coding, troubleshooting, and technical barriers that slow ML adoption in environmental research, especially when working with complex multidimensional datasets.

Which machine learning capabilities does iMESc provide?

iMESc integrates supervised and unsupervised ML methods and includes tools for data preprocessing, visualization, descriptive statistics, and spatial analysis.

How does iMESc support reproducibility during analysis?

The app uses a “savepoints” feature that preserves the analysis state, improving reproducibility when users return to or iterate on workflows.

Aug 4, 2026

Upload by Levi