Plant lodging is one of the most essential phenotypes for soybean breeding programs. Soybean lodging is conventionally evaluated visually by breeders, which is time-consuming and subject to human errors. This study aimed to investigate the potential of unmanned aerial vehicle (UAV)-based imagery and machine learning in assessing the lodging conditions of soybean breeding lines. A UAV imaging system equipped with an RGB (red-green-blue) camera was used to collect the imagery data of 1266 four-row plots in a soybean breeding field at the reproductive stage. Soybean lodging scores were visually assessed by experienced breeders, and the scores were grouped into four classes, i.e., non-lodging, moderate lodging, high lodging, and severe lodging. UAV images were stitched to build orthomosaics, and soybean plots were segmented using a grid method. Twelve image features were extracted from the collected images to assess the lodging scores of each breeding line. Four models, i.e., extreme gradient boosting (XGBoost), random forest (RF), K-nearest neighbor (KNN) and artificial neural network (ANN), were evaluated to classify soybean lodging classes. Five data preprocessing methods were used to treat the imbalanced dataset to improve classification accuracy. Results indicate that the preprocessing method SMOTE-ENN consistently performs well for all four (XGBoost, RF, KNN, and ANN) classifiers, achieving the highest overall accuracy (OA), lowest misclassification, higher F1-score, and higher Kappa coefficient. This suggests that Synthetic Minority Oversampling-Edited Nearest Neighbor (SMOTE-ENN) may be a good preprocessing method for using unbalanced datasets and the classification task. Furthermore, an overall accuracy of 96% was obtained using the SMOTE-ENN dataset and ANN classifier. The study indicated that an imagery-based classification model could be implemented in a breeding program to differentiate soybean lodging phenotype and classify lodging scores effectively.

We develop the first spatially integrated economic-hydrologic model of the western Lake Erie basin explicitly linking economic models of farmers’ field-level best management practice (BMP) adoption choices with the Soil and Water Assessment Tool to evaluate nutrient management policy cost-effectiveness. We quantify trade-offs among phosphorus reduction policies and find that a hybrid policy coupling a fertilizer tax with cost-share payments for subsurface placement is the most cost-effective and can achieve the policy goal of 40% reduction in nutrient loadings. We also find economic adoption models alone can overstate the potential for BMPs to reduce nutrient loadings by ignoring biophysical complexities. (JEL Q18, Q53)

The summer of 2022 was very dry across Missouri and the surrounding regions including much of the Great Lakes, Midwest, and southern plains of the USA. A comparison of this summer to the dry summer of 2012 and the relatively wet summers of 2018 and 2021 was carried out using the National Centers for Environmental Prediction/National Centers for Atmospheric Research reanalysis, the Climate Prediction Center teleconnection indexes, and the blocking archive at the University of Missouri. The summer of 2022 was like that of 2012 which was characterized by a strong 500 hPa height anomaly centered over the western US and plains as well as very little blocking in the East Pacific. The summers of 2018 and 2021 were characterized by more zonal flow over the USA and more blocking in the East Pacific, similarly to the results of an earlier study. The teleconnection indexes for the prior spring and summer were largely similar for the two drier years and opposite for the wetter years. The surface conditions for the drier years were more similar while these were opposite for the wetter years. The integrated enstrophy (IE) used in earlier studies identified a change in the large-scale flow regime in early June 2022, which coincided with a decrease in the precipitation over the study region. However, one key difference was that the spring of 2022 was characterized by blocking more consistent with a wetter summer. This would have made the predictability of the drought of summer 2022 less certain.

In this study, we propose an enhanced methodology for assessing drought conditions through the systematic categorization of Condition Monitoring Observer Reports (CMORs) from Missouri between 2018 and 2024. Our approach introduces a novel classification framework to categorize drought impacts—meteorological, agricultural, hydrological, and socioeconomic—and aligns the analysis with established United States Drought Monitor (USDM) severity classifications. To complement this framework, we incorporate the New Drought Index (NDI), a recently developed quantitative metric that integrates atmospheric anomalies. Brief consideration is also given to atmospheric blocking patterns, which influence drought development. Advanced text processing techniques are employed to bridge qualitative and quantitative insights. The findings underscore the importance of integrating observer insights, atmospheric processes, and advanced indices to refine drought monitoring, inform climate adaptation strategies, and support proactive resource management.