Cropping pattern classification using artificial neural networks and evapotranspiration estimation in the Eastern Mediterranean region of Turkey

Determination of cropping pattern is a very important factor in quantifying irrigation water requirements at catchment scale. In this regard, remote sensing robust tool for generating spatial-temporal variation crops. This study focuses on crop classification by using remotely sensed data coupled with ground truth data. Therefore, aimed both classifying each type and calculating evapotranspiration (ETc) based reference (ETo) the Penman-Monteith model coefficient (Kc). ETo was estimated from two meteorological stations located area. To end, conducted Akarsu Irrigation District (≈95 km2), sub-catchment Lower Seyhan Plain (LSP), 2021 hydrological year. Ground were collected growing seasons. The ENVI program used to classify types Sentinel 2A-2B satellite images 10-m spatial resolution. Image analysis results demonstrated that bare soil citrus made up more than half area winter season, while corn preponderant summer. addition, total about 1308 mm 890 mm, respectively ETc values second soybean, first corn, wheat, showed agreement previous studies direct methods Cukurova region. Furthermore, research findings led us conclude determination promising identifying crops grown large agricultural lands. Moreover, can be accurately summer seasons, has expanded application value large-scale schemes.