@article{fdi:010096117,
  title = {{S}easonal flooded rice area extent dataset during dry seasons 2016 to 2019 at the {T}elangana state scale, {S}outh-{I}ndia},
  author = {{F}errant, {S}ylvain and {S}elles, {A}. and {V}incent, {A}. and {T}hierion, {V}. and {H}agolle, {O}. and {S}hakeel, {A}. and {T}iwari, {V}.{M}.},
  editor = {},
  language = {{ENG}},
  abstract = {{I}ndian agriculture largely depends on the timely and spatially variable availability of water resources which are replenished during the monsoon season. {I}n the state of {T}elangana, a significant portion of the available water is utilized for flooded rice cultivation, both in surface water-fed command areas and in groundwater-dependent regions. {T}he spatial extent of seasonal rice cultivation varies annually in response to water availability that is a key indicator of how farmers adapt to regional and global environmental and socio-economic changes. {I}n this study, we present seasonal land use maps for the dry season ({R}abi) from 2016 to 2019, derived using the {I}nfrastructure pour l'{O}ccupation des sols par {T}raitement {A}utomatique ({IOTA}²) processing chain [1]. {IOTA}² is an open-source software that combines temporal interpolation and classification of multispectral {S}entinel-2 time series to map land cover dynamics. {S}entinel-2 {L}evel 2{A} data processed using the {M}ulti-{T}emporal {C}loud {S}creening and {A}tmospheric {C}orrection {S}oftware ({MAJA}) were used to generate 10-day composite reflectance time series for each season over the entire {T}elangana state. {A} {R}andom {F}orest classifier was trained on interpolated spectral time series using ground-truth data collected by the authors during dedicated field campaigns conducted between {J}anuary and {M}arch of each year from 2016 to 2019. {G}round observations were labelled into nine land use classes: rice, vegetables, maize (when applicable), orchards, natural bush, bare ground, urban, water, and unharvested dry-season cotton (when applicable). {F}or each season, the ground-truth dataset was randomly split into training and validation sets eight times to generate eight classification outputs, from which average precision, recall, and {F}-score values were calculated. {T}he dataset associated with this paper includes four seasonal raster maps, each encoding, for every pixel, the number of times (from 0 to 8) it was classified as rice during the eight classification runs. {T}hese rice extent confidence maps serve as an empirical measure of spatial classification uncertainty and inter-annual variability. {T}he ground-truth polygon dataset used for classification and validation is also provided. {T}ogether, these datasets support the monitoring of seasonal rice dynamics and can serve as a reference for agricultural and hydrological studies in {S}outh {A}sia or training data for deep learning approaches for extension in space and time of those maps. {S}uch a compilation can be used to support decisions on crop or cropping pattern changes in response to climate change, as well as to inform government policy-making.},
  keywords = {{INDE} ; {TELANGANA} {ETAT}},
  booktitle = {},
  journal = {{D}ata in {B}rief},
  volume = {62},
  numero = {},
  pages = {111981 [10 ]},
  ISSN = {2352-3409},
  year = {2025},
  DOI = {10.1016/j.dib.2025.111981},
  URL = {https://www.documentation.ird.fr/hor/fdi:010096117},
}