Mohsen Shahhosseini

Mohsen Shahhosseini, Guiping Hu, Saeed Khaki et al.

We investigate the predictive performance of two novel CNN-DNN machine learning ensemble models in predicting county-level corn yields across the US Corn Belt (12 states). The developed data set is a combination of management, environment, and historical corn yields from 1980-2019. Two scenarios for ensemble creation are considered: homogenous and heterogeneous ensembles. In homogenous ensembles, the base CNN-DNN models are all the same, but they are generated with a bagging procedure to ensure they exhibit a certain level of diversity. Heterogenous ensembles are created from different base CNN-DNN models which share the same architecture but have different levels of depth. Three types of ensemble creation methods were used to create several ensembles for either of the scenarios: Basic Ensemble Method (BEM), Generalized Ensemble Method (GEM), and stacked generalized ensembles. Results indicated that both designed ensemble types (heterogenous and homogenous) outperform the ensembles created from five individual ML models (linear regression, LASSO, random forest, XGBoost, and LightGBM). Furthermore, by introducing improvements over the heterogeneous ensembles, the homogenous ensembles provide the most accurate yield predictions across US Corn Belt states. This model could make 2019 yield predictions with a root mean square error of 866 kg/ha, equivalent to 8.5% relative root mean square, and could successfully explain about 77% of the spatio-temporal variation in the corn grain yields. The significant predictive power of this model can be leveraged for designing a reliable tool for corn yield prediction which will, in turn, assist agronomic decision-makers.

Mohsen Shahhosseini, Guiping Hu

Several studies have shown that combining machine learning models in an appropriate way will introduce improvements in the individual predictions made by the base models. The key to make well-performing ensemble model is in the diversity of the base models. Of the most common solutions for introducing diversity into the decision trees are bagging and random forest. Bagging enhances the diversity by sampling with replacement and generating many training data sets, while random forest adds selecting a random number of features as well. This has made the random forest a winning candidate for many machine learning applications. However, assuming equal weights for all base decision trees does not seem reasonable as the randomization of sampling and input feature selection may lead to different levels of decision-making abilities across base decision trees. Therefore, we propose several algorithms that intend to modify the weighting strategy of regular random forest and consequently make better predictions. The designed weighting frameworks include optimal weighted random forest based on ac-curacy, optimal weighted random forest based on the area under the curve (AUC), performance-based weighted random forest, and several stacking-based weighted random forest models. The numerical results show that the proposed models are able to introduce significant improvements compared to regular random forest.

Mohsen Shahhosseini, Rafael A. Martinez-Feria, Guiping Hu et al.

Pre-season prediction of crop production outcomes such as grain yields and N losses can provide insights to stakeholders when making decisions. Simulation models can assist in scenario planning, but their use is limited because of data requirements and long run times. Thus, there is a need for more computationally expedient approaches to scale up predictions. We evaluated the potential of five machine learning (ML) algorithms as meta-models for a cropping systems simulator (APSIM) to inform future decision-support tool development. We asked: 1) How well do ML meta-models predict maize yield and N losses using pre-season information? 2) How many data are needed to train ML algorithms to achieve acceptable predictions?; 3) Which input data variables are most important for accurate prediction?; and 4) Do ensembles of ML meta-models improve prediction? The simulated dataset included more than 3 million genotype, environment and management scenarios. Random forests most accurately predicted maize yield and N loss at planting time, with a RRMSE of 14% and 55%, respectively. ML meta-models reasonably reproduced simulated maize yields but not N loss. They also differed in their sensitivities to the size of the training dataset. Across all ML models, yield prediction error decreased by 10-40% as the training dataset increased from 0.5 to 1.8 million data points, whereas N loss prediction error showed no consistent pattern. ML models also differed in their sensitivities to input variables. Averaged across all ML models, weather conditions, soil properties, management information and initial conditions were roughly equally important when predicting yields. Modest prediction improvements resulted from ML ensembles. These results can help accelerate progress in coupling simulation models and ML toward developing dynamic decision support tools for pre-season management.

Mohsen Shahhosseini, Guiping Hu, Hieu Pham

Aggregating multiple learners through an ensemble of models aim to make better predictions by capturing the underlying distribution of the data more accurately. Different ensembling methods, such as bagging, boosting, and stacking/blending, have been studied and adopted extensively in research and practice. While bagging and boosting focus more on reducing variance and bias, respectively, stacking approaches target both by finding the optimal way to combine base learners. In stacking with the weighted average, ensembles are created from weighted averages of multiple base learners. It is known that tuning hyperparameters of each base learner inside the ensemble weight optimization process can produce better performing ensembles. To this end, an optimization-based nested algorithm that considers tuning hyperparameters as well as finding the optimal weights to combine ensembles (Generalized Weighted Ensemble with Internally Tuned Hyperparameters (GEM-ITH)) is designed. Besides, Bayesian search was used to speed-up the optimizing process, and a heuristic was implemented to generate diverse and well-performing base learners. The algorithm is shown to be generalizable to real data sets through analyses with ten publicly available data sets.