期刊
FRONTIERS IN PLANT SCIENCE
卷 13, 期 -, 页码 -出版社
FRONTIERS MEDIA SA
DOI: 10.3389/fpls.2022.762446
关键词
model has also demonstrated its robustness under multiple scenarios. mixed-integer linear programming; time series data; 1D-convolutional neural networks; TBATS; storage capacity; planting window
资金
- Plant Sciences Institute Faculty Scholars program at Iowa State University
- National Science Foundation under the LEAP HI program [1830478]
- National Science Foundation under GOALI program [1830478]
This paper proposes a two-stage decision support system to optimize planting decisions in the agricultural sector. The first stage involves creating a prediction model for Growing Degree Units (GDUs), while the second stage incorporates the prediction model into an optimization model for the planting schedule. The proposed model has been proven effective and robust through a case study.
Technology advancement has contributed significantly to productivity improvement in the agricultural sector. However, field operation and farm resource utilization remain a challenge. For major row crops, designing an optimal crop planting strategy is crucial since the planting dates are contingent upon weather conditions and storage capacity. This manuscript proposes a two-stage decision support system to optimize planting decisions, considering weather uncertainties and resource constraints. The first stage involves creating a weather prediction model for Growing Degree Units (GDUs). In the second stage, the GDUs prediction from the first stage is incorporated to formulate an optimization model for the planting schedule. The efficacy of the proposed model is demonstrated through a case study based on Syngenta Crop Challenge (2021). It has been shown that the 1D-CNN model outperforms other prediction models with an RRMSE of 7 to 8% for two different locations. The decision-making model in the second stage provides an optimal planting schedule such that weekly harvested quantities will be evenly allocated utilizing a minimum number of harvesting weeks. We analyzed the model performance for two scenarios: fixed and flexible storage capacity at multiple geographic locations. Results suggest that the proposed model can provide an optimized planting schedule considering planting window and storage capacity. The model has also demonstrated its robustness under multiple scenarios.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据