This paper is a first attempt to compute the total water needs of an agricultural plain with remote sensing and ground data in Iran. The cropping areas were mapped with Sentinels-2 images, based on NDVI profiles classification. This model was validated and 85% of the areas were correctly classified. Second, the crop water needs were computed using PYSEBAL and Landsat-8 images. Crop evapotranspiration (ET_season) and Irrigation Requirements (IR_season) were calculated for each crop and then validated by comparing IR collected in the field from farmers with computed IR_PYSEBAL on 5 plots. IR_PYSEBAL underestimated the reality with an average of 10% while the overestimation average was 17%. The second validation was the comparison of Daily ET from FAO-56 method and Daily ET PYSEBAL showed a RMSE of 0.67 mm/day and MAE of 0.52 mm/day, which assesses the accuracy of PYSEBAL. ET_season varies according to weather parameters in the plain and IR_season, according to different irrigation practices. The most water demanding crops were identified: rice (IR: 1427 mm) and corn (669). The total water balance of Marvdasht was negative in 2018 with 0.2859 km³ of extracted groundwater for irrigation for only 0.098 km³ of available water for aquifers recharge.

本文是首次尝试利用伊朗的遥感和地面数据来计算农业平原的总需水量。根据NDVI配置文件分类，使用Sentinels-2图像绘制作物区域。该模型已经过验证，正确划分了85％的区域。其次，使用PYSEBAL和Landsat-8图像计算了作物的需水量。计算每种作物的作物蒸散量（ET_季节）和灌溉需求（IR_季节），然后通过在5个_样地上用计算的IR _PYSEBAL比较从田间从农民那里收集的IR进行验证。红外_PYSEBAL实际低估了平均水平10％，而高估了平均水平17％。第二个验证是对FAO-56方法的每日ET和PYSEBAL的每日ET的比较，RMSE为0.67 mm /天，MAE为0.52 mm /天，这评估了PYSEBAL的准确性。根据不同的灌溉习惯，ET_季节根据平原和IR_季节的天气参数而变化。确定了最需水的作物：水稻（IR：1427 mm）和玉米（669）。Marvdasht的总水量平衡在2018年为负，其中0.2859 km ³的灌溉提取地下水仅用于含水层补给的0.098 km ³可用水。