@inproceedings{fdi:010095094,
  title = {{C}ombining remote sensing and low-cost sensors for {LULC} and irrigation characterization in the {S}outh of {F}rance [r{\'e}sum{\'e}]},
  author = {{O}rieschnig, {C}hristina and {V}and{\^o}me, {P}.},
  editor = {},
  language = {{ENG}},
  abstract = {{I}n the face of climate change, {M}editerranean regions, such as the {S}outh of {F}rance, are increasingly struggling with drought, water scarcity, and low groundwater levels. {F}or agricultural regions relying on irrigation systems to guarantee summertime crop productivity, this is a central issue. {C}onsequently, optimizing agricultural water uses and understanding the impact of irrigation systems on local and regional hydrological processes is indispensable. {A}t larger scales, another challenge is to identify crop types as well as cropping and irrigation patterns for irrigation water management, reservoir operation, and real-time resource allocation. {I}n this context, remote sensing provides a promising approach.  {T}his study focuses on combining land use - land cover ({LULC}) analyses based on {S}entinel-1 and -2 data and in-situ measurements realized using innovative low-cost sensors, to characterize irrigation water use in two {S}outhern {F}rench case study areas. {T}he first of these, the {C}rau area in {P}rovence, is specialized in using gravity irrigation to make the production of high-quality hay possible even during the arid summer months. {T}he second area is a viticultural one, centred around the {C}anal de {G}ignac approximately 100 km further {W}est, in which the majority of vines are sustained using drip irrigation, provided consistent water access is possible. {I}n both cases, the study aimed first to identify irrigated plots, and then to further characterize the irrigation practices with regard to agricultural water use efficiency. {T}he {LULC} analysis was carried out in {G}oogle {E}arth {E}ngine, using a {G}radient {T}ree {B}oosting ({GTB}) algorithm on combined {S}entinel-1 and -2 imagery from which several spectral indices as well as {H}aralick texture features were calculated. {T}he detection of irrigated grassland plots further relied on a temporal characterization of phenological stages. {S}ubsequently, a comparative implementation of different irrigation monitoring approaches was carried out, using soil moisture estimates derived from {S}entinel-1 and different optical spectral indices. {D}ata from low-cost sensors and local water user associations was used for calibration and validation. {P}reliminary results indicate that combining these diverse approaches make an operational detection and monitoring of irrigation practices possible. {F}or the detection of irrigated vineyard and grassland plots during the 2023 growing season, overall accuracies of 92% and 95% respectively were achieved. {T}he comparison of different irrigation monitoring approaches showed that the {N}ormalized {D}ifference {M}oisture {I}ndex ({NDMI}, p=0.002), the {S}hortwave {I}nfrared {W}ater {S}tress {I}ndex ({SIWSI}, p=0.001) and the {S}pecific {L}eaf {A}rea {V}egetation {I}ndex ({SLAVI}, p=0.001) showed the highest potential for accurate irrigation detection.},
  keywords = {{FRANCE} ; {MEDITERRANEE}},
  numero = {},
  pages = {{EGU}24--9299 [1 ]},
  booktitle = {},
  year = {2025},
  DOI = {10.5194/egusphere-egu24-9299},
  URL = {https://www.documentation.ird.fr/hor/fdi:010095094},
}