Experimental corn hybrids are created in plant breeding programs by crossing two parents, so-called inbred and tester, together. Identification of best parent combinations for crossing is challenging since the total number of possible cross combinations of parents is large and it is impractical to test all possible cross combinations due to limited resources of time and budget. In the 2020 Syngenta Crop Challenge, Syngenta released several large datasets that recorded the historical yield performances of around 4% of total cross combinations of 593 inbreds with 496 testers which were planted in 280 locations between 2016 and 2018 and asked participants to predict the yield performance of cross combinations of inbreds and testers that have not been planted based on the historical yield data collected from crossing other inbreds and testers. In this paper, we present a collaborative filtering method which is an ensemble of matrix factorization method and a neural network to solve this problem. Our computational results suggested that the proposed model significantly outperformed other models such as deep factorization machines (DeepFM), generalized matrix factorization (GMF), LASSO, random forest (RF), and neural networks. Presented method and results were produced within the 2020 Syngenta Crop Challenge.

Environmental stresses such as drought and heat can cause substantial yield loss in agriculture. As such, hybrid crops that are tolerant to drought and heat stress would produce more consistent yields compared to the hybrids that are not tolerant to these stresses. In the 2019 Syngenta Crop Challenge, Syngenta released several large datasets that recorded the yield performances of 2,452 corn hybrids planted in 1,560 locations between 2008 and 2017 and asked participants to classify the corn hybrids as either tolerant or susceptible to drought stress, heat stress, and combined drought and heat stress. However, no data was provided that classified any set of hybrids as tolerant or susceptible to any type of stress. In this paper, we present an unsupervised approach to solving this problem, which was recognized as one of the winners in the 2019 Syngenta Crop Challenge. Our results labeled 121 hybrids as drought tolerant, 193 as heat tolerant, and 29 as tolerant to both stresses.

The landscape of farming and plant breeding is rapidly transforming due to the complex requirements of our world. The explosion of collectible data has started a revolution in agriculture to the point where innovation must occur. To a commercial organization, the accurate and efficient collection of information is necessary to ensure that optimal decisions are made at key points of the breeding cycle. In particular, recent technology has enabled organizations to capture in-field images of crops to record color, shape, chemical properties, and disease susceptibility. However, this new challenge necessitates the need for advanced algorithms to accurately identify phenotypic traits. This work, advanced the current literature by developing an innovative deep learning algorithm, named DeepStand, for image-based counting of corn stands at early phenological stages. The proposed method adopts a truncated VGG-16 network to act as a feature extractor backbone. We then combine multiple feature maps with different dimensions to ensure the network is robust against size variation. Our extensive computational experiments demonstrate that our DeepStand framework accurately identifies corn stands and out-performs other cutting-edge methods.

Corn planting and harvest scheduling is an important problem due to having a significant impact on corn yield, balancing the capacities for harvest, transport, and storage operations. Different corn hybrids also have different planting window and poor planting and harvest schedules may cause erratic weekly harvest quantities and logistical and productivity issues. In the 2021 Syngenta Crop Challenge, Syngenta released several large datasets that recorded the historical daily growing degree units (GDU) of two sites and provided planting window, required GDUs, and harvest quantity of corn hybrids planted in these two sites. Then, participants of this challenge were asked to schedule planting and harvesting dates of corn hybrids under two storage capacity scenarios so that facilities are not over capacity in harvesting weeks and have consistent weekly harvest quantities. The two storage capacity scenarios include: (1) planting and harvest scheduling given the maximum storage capacity, and (2) planting and harvest scheduling without maximum storage capacity to determine the lowest possible capacity for each site. In this paper, we propose two mixed integer linear programming (MILP) models for solving this problem considering both the storage capacity and the uncertainty in GDUs. Our results indicate that our proposed models can provide optimal planting and harvest scheduling under different GDU possibilities which ensures consistent weekly harvest quantities that are below the maximum capacity.

Planting and harvest scheduling is a crucial part of crop production due to its significant impact on other factors such as balancing the capacities for harvest, yield potential, sales price, storage, and transportation. Corn planting and harvest scheduling is challenging because corn hybrids have different planting windows, and, subsequently, inaccurate planting and harvest scheduling can result in inconsistent and unpredictable weekly harvest quantities and logistical and productivity issues. In the 2021 Syngenta Crop Challenge, participants were given several large datasets including recorded historical daily growing degree units (GDU) of two sites and provided with planting windows, required GDUs, and harvest quantities of corn hybrids planted in these two sites, and were asked to schedule planting and harvesting dates of corn hybrids under two storage capacity cases so that facilities are not over capacity in harvesting weeks and have consistent weekly harvest quantities. The research problem includes determining the planting and harvest scheduling of corn hybrids under two storage capacity cases: (1) given the maximum storage capacity, and (2) without maximum storage capacity to determine the lowest storage capacity for each site. To help improve corn planting and harvest scheduling, we propose two mixed-integer linear programming (MILP) models and a heuristic algorithm to solve this problem for both storage capacity cases. Daily GDUs are required for planting and harvest scheduling, but they are unknown at the beginning of the growing season. As such, we use recurrent neural networks to predict the weekly GDUs of 70 weeks and consider this as the predicted GDU scenario to solve this problem. In addition, we solve this problem considering all given 10 historical GDU scenarios from 2010 to 2019 together for both storage capacity cases to include historical GDUs directly to our model rather than using predicted GDUs. Our extensive computational experiments and results demonstrate the effectiveness of our proposed methods, which can provide optimal planting and harvest scheduling considering deterministic GDU scenario and uncertainties in historical GDU scenarios for both storage capacity cases to provide consistent weekly harvest quantities that are below the maximum capacity.