@incollection{fdi:010084185,
  title = {{M}ulti-scale time series analysis of evapotranspiration for high-throughput phenotyping frequency optimization},
  author = {{K}ar, {S}. and {T}anaka, {R}. and {I}wata, {H}. and {K}holova, {J}. and {D}urbha, {S}.{S}. and {A}dinarayana, {J}. and {V}adez, {V}incent},
  editor = {},
  language = {{ENG}},
  abstract = {{T}his work is undertaken considering the significance of functional phenotyping (primarily measured from continuous profiles of plant-water relations) for crop selection purposes. {H}igh-{T}hroughput {P}lant {P}henotyping ({HTPP}) platforms which largely employ state-of-the-art sensor technologies for acquisition of vast amount of field data, often fail to efficiently translate sensor information into knowledge due to the major challenges of data handling and processing. {H}ence, it is imperative to concurrently find a way for dissociating noise from useful data. {A}dditionally, another important aspect is understanding how frequent should be the data collection, so that information is maximized. {T}his paper presents a novel approach for identifying the optimal frequency for phenotyping evapotranspiration ({ET}) by assimilating results from both time series forecast as well as classification models. {T}hus, at the optimal frequency, plant-water relations can not only be desirably predicted but genotypes can also be classified based on the characteristics of their {ET} profiles. {C}onsequently, this will aid better crop selection, besides minimizing noise, redundancy, cost and effort in {HTPP} data collection. {H}igh frequency (15 min) {ET} time series data of 48 chickpea varieties (with considerable genotypic diversity) collected at the {L}easy{S}can {HTPP} platform, {ICRISAT} is used for this study. {T}ime series forecast and classification is performed by varying frequency up to 180 min. {M}ultiple performance measures of time series forecast and classification are combined, followed by implementation of entropy theory for sampling frequency optimization. {T}he results demonstrate that {ET} time series with a frequency of 60 min per day potentially yield the optimum information.},
  keywords = {},
  booktitle = {2020 {IEEE} {L}atin {A}merican {GRSS} and {ISPRS} {R}emote {S}ensing {C}onference ({LAGIRS}) : proceedings},
  numero = {},
  pages = {98--103},
  address = {{P}iscataway},
  publisher = {{IEEE}},
  series = {},
  year = {2020},
  DOI = {10.1109/{LAGIRS}48042.2020.9165630},
  ISBN = {978-1-7281-4350-7},
  URL = {https://www.documentation.ird.fr/hor/fdi:010084185},
}