Jadwal Sholat

Memuat jadwal sholat…

Pertanian & Lingkungan editorial

Open AccessOA2025

iMESc – an interactive machine learning app for environmental sciences

iMESc is an interactive R Shiny app that integrates supervised and unsupervised machine learning with data preprocessing, visualization, and spatial analysis for environmental sciences. It features a Datalist system and savepoints for reproducibility, demonstrated through a nematode community case study achieving up to 83.47% accuracy.
D. Vieira; Fabiana S. Paula; L. Yaginuma; Gustavo Fonseca· Frontiers in Environmental Science· 2025· DOI 10.3389/fenvs.2025.1533292

The core problem

Environmental sciences increasingly rely on complex datasets, making machine learning (ML) crucial for identifying patterns and relationships. However, integrating ML into workflows poses challenges due to technical barriers and the time-intensive nature of coding. To address these issues, the authors developed iMESc, an interactive ML app designed to streamline and simplify ML workflows for environmental data. The app aims to bridge the gap between the complexity of ML algorithms and the need for user-friendly interfaces in environmental research, allowing researchers to focus on scientific inquiry by reducing the technical burden of coding.

Innovation

iMESc is developed in R and built on the Shiny platform. It enables the integration of supervised and unsupervised ML methods, along with tools for data preprocessing, visualization, descriptive statistics, and spatial analysis. Key features include:

- **Datalist system**: ensures seamless transitions between analytical workflows.
- **Savepoints**: enhances reproducibility by preserving the analysis state.

The app supports various ML models, including Self-Organizing Maps (SOM), Supervised SOM (SuperSOM), and Random Forest, as well as classical statistical approaches like Redundancy Analysis (RDA) and Piecewise RDA (pwRDA). The authors demonstrate iMESc’s flexibility with four workflows applied to a case study predicting nematode community structure based on environmental data.

Introduction
Environmental sciences increasingly rely on complex datasets, making machine learning (ML) crucial for identifying patterns and relationships. However, integrating ML into workflows poses challenges due to technical barriers and the time-intensive nature of coding. To address these issues, the authors developed iMESc, an interactive ML app designed to streamline and simplify ML workflows for environmental data. The app aims to bridge the gap between the complexity of ML algorithms and the need for user-friendly interfaces in environmental research, allowing researchers to focus on scientific inquiry by reducing the technical burden of coding.

Why it matters

iMESc permits the customization of plots and saving workflows into “savepoints,” guaranteeing reproducibility. By bridging the gap between the complexity of ML algorithms and the need for user-friendly interfaces, iMESc reduces the technical burden of coding, allowing researchers to focus on scientific inquiry. This improves both the efficiency and depth of analyses in environmental research. The app’s integration of multiple ML methods and classical statistics within a single interactive platform makes it a versatile tool for environmental scientists dealing with complex datasets.

Who should read this

Pembaca Research Digest dan praktisi rumpun ini.

Opening member content…