Literature review seaweeds

This dataset compiles information extracted from 106 peer-reviewed journal articles published between 2013 and 2024 that apply remote sensing and machine-learning techniques to macroalgae monitoring in coastal and marine environments. The dataset was assembled through a systematic literature search using Google Scholar and related academic databases, followed by manual screening to ensure relevance to broad-class macroalgae detection and mapping.

For each study, the dataset records reported classification performance metrics (overall accuracy and Kappa coefficient, where available), sensor platforms (e.g., satellite, UAV, aerial, and underwater systems), spatial resolution, geographic region, preprocessing workflows, feature extraction methods, and classification algorithms. Machine-learning methods are categorized into Random Forest (RF), Support Vector Machine (SVM), and Deep Learning families. Sensor platforms are grouped into high-resolution satellites, medium- to low-resolution satellites, and drone/AUV systems based on nominal spatial resolution and acquisition mode.

The dataset also includes derived categorical fields used in the analysis, enabling reproducible aggregation of accuracy distributions across algorithm and sensor groups. No new observational or experimental data were generated; all entries are derived from published studies and are provided for synthesis, comparison, and methodological review purposes.

This dataset supports transparency and reproducibility of the associated review study and can be used by other researchers to explore methodological trends, performance variability, and research gaps in remote sensing-based macroalgae monitoring.