@article{fdi:010097004,
  title = {{A} time series approach to monitoring agro-ecosystem dynamics and transition signals using vegetation indices in {S}{\'e}dhiou, {S}enegal},
  author = {{T}oure, {L}. and {M}biafeu, {A}. {C}. {N}. and {H}auhouot, {A}. {C}. and {B}arnieh, {B}. {A}. and {G}luski, {P}auline},
  editor = {},
  language = {{ENG}},
  abstract = {{T}his study proposes an integrated high-resolution optical remote-sensing workflow for monitoring agro-ecosystem dynamics and transition signals in {S}enegal's {S}{\'e}dhiou region from 2020 to 2025. {S}entinel-2 imagery was preprocessed in {G}oogle {E}arth {E}ngine (cloud masking, harmonization, and compositing) and used to derive three spectral indices ({NDVI}, {SAVI}, and {NDWI}). {F}ield data collected in {M}arch 2025 were used to train and validate the 2025 land-cover map, while the 2020-2025 component focused on vegetation-index dynamics and transition signals rather than year-by-year validated land-cover conversions. {A} {R}andom {F}orest classifier mapped five land-cover classes in 2025, and achieved 94% overall accuracy and kappa 0.98, with class-specific classification errors of 0.0%, 1.0%, 4.2%, 7.0%, and 10.2% for {W}ater, {B}uilt-up, {F}orest, {C}ropland, and {S}hrubland, respectively. {M}onthly time-series analysis revealed marked intra- and interannual variability across land-cover classes and identified transition-signal hotspots (persistent departures in index trajectories) using rolling variability metrics and breakpoint screening. {F}orests were comparatively stable (mean {NDVI} = 0.53), while shrublands showed intermediate dynamics (mean {NDVI} = 0.49). {C}ropland areas exhibited the highest variability, consistent with crop-fallow cycles and rainfall sensitivity in rainfed systems; this variability alone does not constitute evidence of land-cover transition. {T}he most pronounced break episodes were observed in 2022 and 2024, especially in the {C}ropland class, and are interpreted as transition signals that may reflect rainfall-driven variability and or land-use dynamics, thus requiring cautious attribution. {O}verall, the workflow provides an operational framework, including image preprocessing, feature extraction, classification, index time-series extraction, and breakpoint screening, for identifying variability hotspots and prioritizing areas for targeted field verification and sustainable agro-ecosystem management in {S}{\'e}dhiou.},
  keywords = {{R}emote sensing ; {C}loud computing ; {T}ime series ; {A}gro-ecosystem dynamics ; {S}{\'e}dhiou ; {S}enegal ; {SENEGAL}},
  booktitle = {},
  journal = {{E}arth {S}ystems and {E}nvironment},
  volume = {[{E}arly access]},
  numero = {},
  pages = {[24 p.]},
  ISSN = {2509-9426},
  year = {2026},
  DOI = {10.1007/s41748-026-01166-8},
  URL = {https://www.documentation.ird.fr/hor/fdi:010097004},
}