Marko Oskar, Brdar Sanja, Panić Marko, Šašić Isidora, Despotović Danica, Knežević Milivoje, Crnojević Vladimir
BioSense Institute, University of Novi Sad, Novi Sad, Serbia.
Faculty of Technical Sciences, University of Novi Sad, Novi Sad, Serbia.
PLoS One. 2017 Sep 1;12(9):e0184198. doi: 10.1371/journal.pone.0184198. eCollection 2017.
The aim of this work was to develop a method for selection of optimal soybean varieties for the American Midwest using data analytics. We extracted the knowledge about 174 varieties from the dataset, which contained information about weather, soil, yield and regional statistical parameters. Next, we predicted the yield of each variety in each of 6,490 observed subregions of the Midwest. Furthermore, yield was predicted for all the possible weather scenarios approximated by 15 historical weather instances contained in the dataset. Using predicted yields and covariance between varieties through different weather scenarios, we performed portfolio optimisation. In this way, for each subregion, we obtained a selection of varieties, that proved superior to others in terms of the amount and stability of yield. According to the rules of Syngenta Crop Challenge, for which this research was conducted, we aggregated the results across all subregions and selected up to five soybean varieties that should be distributed across the network of seed retailers. The work presented in this paper was the winning solution for Syngenta Crop Challenge 2017.
这项工作的目的是利用数据分析开发一种为美国中西部地区选择最优大豆品种的方法。我们从数据集中提取了174个品种的相关知识，该数据集包含天气、土壤、产量和区域统计参数等信息。接下来，我们预测了中西部地区6490个观测子区域中每个品种的产量。此外，我们还根据数据集中包含的15个历史天气实例估算出所有可能的天气情况，预测了这些情况下的产量。利用预测产量以及不同天气情况下品种之间的协方差，我们进行了投资组合优化。通过这种方式，对于每个子区域，我们都选出了一些品种，这些品种在产量数量和稳定性方面都优于其他品种。根据先正达作物挑战大赛（开展本研究就是为了参加该大赛）的规则，我们汇总了所有子区域的结果，并选出了最多五个应在种子零售商网络中推广的大豆品种。本文所展示的工作是2017年先正达作物挑战大赛的获胜方案。
