Evaluating the Impact of Future Seasonal Climate Extremes on Crop Evapotranspiration of Maize in Western Kansas Using a Machine Learning Approach
Evaluating the Impact of Future Seasonal Climate Extremes on Crop Evapotranspiration of Maize in Western Kansas Using a Machine Learning Approach
复制标题
DOI：
10.3390/land12081500
复制
发表时间：
2023-07
期刊：
影响因子：
3.9
通讯作者：
K. Igwe;Vaishali Sharda;T. Hefley
中科院分区：
文献类型：
--
作者：
K. Igwe;Vaishali Sharda;T. Hefley
数据驱动技术用于农业，以优化有限资源的使用。作物蒸散量（ET）估计作物在不同生长阶段所需的实际水量，因此被证明是精确灌溉所需的基本信息。作物ET在美国高平原等地区至关重要，那里的农民依赖地下水灌溉。该区域灌溉农业的可持续性受到地下水水位下降的威胁，气候变化引起的极端事件日益频繁，进一步加剧了这种情况。这些条件会显著影响作物ET率，导致水分胁迫，从而对作物产量产生不利影响。在这项研究中，我们使用机器学习模型分析历史气候数据，以确定哪些气候极端指数对作物ET影响最大。农作物蒸散量的估算是使用从粮农组织Penman-Monteith方程得出的参考蒸散量，再乘以从遥感归一化植被指数（NDVI）估算的农作物系数数据。结果表明，连续干旱日数和周平均最高气温的极端气候指数对作物蒸散量影响最大。结果发现，温度衍生的指数影响作物ET比降水衍生的指数。在未来气候情景下，在低温室气体排放情景和高温室气体排放情景下，作物蒸散量近期将分别增加0.4%和1.7%，中期将分别增加3.1%和5.9%，世纪末将分别增加3.8%和9.6%。季节性作物ET的这些预测变化可以帮助农业生产者做出充分知情的决策，以优化地下水资源。
Data-driven technologies are employed in agriculture to optimize the use of limited resources. Crop evapotranspiration (ET) estimates the actual amount of water that crops require at different growth stages, thereby proving to be the essential information needed for precision irrigation. Crop ET is essential in areas like the US High Plains, where farmers rely on groundwater for irrigation. The sustainability of irrigated agriculture in the region is threatened by diminishing groundwater levels, and the increasing frequency of extreme events caused by climate change further exacerbates the situation. These conditions can significantly affect crop ET rates, leading to water stress, which adversely affects crop yields. In this study, we analyze historical climate data using a machine learning model to determine which of the climate extreme indices most influences crop ET. Crop ET is estimated using reference ET derived from the FAO Penman–Monteith equation, which is multiplied with the crop coefficient data estimated from the remotely sensed normalized difference vegetation index (NDVI). We found that the climate extreme indices of consecutive dry days and the mean weekly maximum temperatures most influenced crop ET. It was found that temperature-derived indices influenced crop ET more than precipitation-derived indices. Under the future climate scenarios, we predict that crop ET will increase by 0.4% and 1.7% in the near term, by 3.1% and 5.9% in the middle term, and by 3.8% and 9.6% at the end of the century under low greenhouse gas emission and high greenhouse gas emission scenarios, respectively. These predicted changes in seasonal crop ET can help agricultural producers to make well-informed decisions to optimize groundwater resources.