@article{fdi:010090294,
  title = {{E}stimation of water quality parameters through a combination of deep learning and remote sensing techniques in a lake in {S}outhern {C}hile},
  author = {{R}odríguez-{L}ópez, {L}. and {U}sta, {D}. {B}. and {D}uran-{L}lacer, {I}. and {A}lvarez, {L}. {B}. and {Y}{\'e}pez, {S}. and {B}ourrel, {L}uc and {F}rappart, {F}. and {U}rrutia, {R}.},
  editor = {},
  language = {{ENG}},
  abstract = {{I}n this study, we combined machine learning and remote sensing techniques to estimate the value of chlorophyll-a concentration in a freshwater ecosystem in the {S}outh {A}merican continent (lake in {S}outhern {C}hile). {I}n a previous study, nine artificial intelligence ({AI}) algorithms were tested to predict water quality data from measurements during monitoring campaigns. {I}n this study, in addition to field data ({C}ase {A}), meteorological variables ({C}ase {B}) and satellite data ({C}ase {C}) were used to predict chlorophyll-a in {L}ake {L}lanquihue. {T}he models used were {SARIMAX}, {LSTM}, and {RNN}, all of which showed generally good statistics for the prediction of the chlorophyll-a variable. {M}odel validation metrics showed that all three models effectively predicted chlorophyll as an indicator of the presence of algae in water bodies. {C}oefficient of determination values ranging from 0.64 to 0.93 were obtained, with the {LSTM} model showing the best statistics in any of the cases tested. {T}he {LSTM} model generally performed well across most stations, with lower values for {MSE} (< 0.260 (mu g/{L})2), {RMSE} (< 0.510 ug/{L}), {M}ax{E}rror (< 0.730 mu g/{L}), and {MAE} (< 0.442 mu g/{L}). {T}his model, which combines machine learning and remote sensing techniques, is applicable to other {C}hilean and world lakes that have similar characteristics. {I}n addition, it is a starting point for decision-makers in the protection and conservation of water resource quality.},
  keywords = {water quality ; chlorophyll ; remote sensing ; deep learning ; {C}hile ; lakes ; {CHILI}},
  booktitle = {},
  journal = {{R}emote {S}ensing},
  volume = {15},
  numero = {17},
  pages = {4157 [22 p.]},
  year = {2023},
  DOI = {10.3390/rs15174157},
  URL = {https://www.documentation.ird.fr/hor/fdi:010090294},
}