University of Maryland Eastern Shore

• Multi-year ML framework improves yield prediction under high climatic variability. • Integrating agronomic and environmental data outperforms single-factor models. • Random Forest and XGBoost capture nonlinear yield responses across bean cultivars. • Heat stress and reproductive traits emerge as key yield-driving predictors. • Framework supports climate-smart, cultivar-specific decision making for growers. Accurate yield prediction remains a major challenge for legume production in environmentally variable regions such as the USA Delmarva Peninsula, where sandy soils and fluctuating climatic conditions intensify crop sensitivity to heat and moisture stresses. To address this challenge, this study developed a multi-year machine learning framework to predict grain yield for four bean species, mung bean, pigeon pea, kidney bean, and cowpea, represented by a total of 11 cultivars evaluated across eight growing seasons. The framework integrated four categories of predictors: Genotype (G) (cultivars), agronomic (A) traits (plant height, pods and seeds metrics, plant biomass, and yield), management (M) practices (trial structure and replications), and environmental (E) factors (temperature, heat stress index: HSI, growing degree days: GDD, and precipitation). Two nonlinear algorithms, Random Forest (RF) and eXtreme Gradient Boosting (XGBoost), were evaluated under single-input, two-input, three-input, and full multi-component configurations to assess the relative predictive contributions of G, A, M, and E. Mean annual grain yield varied substantially across seasons, ranging from 93.5 kg/ha in 2014 to 6,279.9 kg/ha in 2023, reflecting pronounced interannual climatic variability and environmental heterogeneity in the Delmarva region. Both models achieved their highest predictive accuracy in years with more consistent E patterns and narrower yield distributions (coefficient of determination: R² = 0.98–0.87 in 2017–2019), whereas predictive performance declined in seasons characterized by greater climatic variability and more dispersed yield values. Among single-input models, A traits showed the strongest predictive ability ( R² ≈ 0.53), followed by E variables ( R² ≤ 0.49), while G-only and M-only inputs contributed minimally. Across multi-input configurations, the E+A combination delivered the highest overall two-input performance (RF R² = 0.69; XGBoost R² = 0.71), and the three-input models that combined A and E with G or M also showed strong predictive ability ( R² ≈ 0.70–0.73), while the full G+E+A+M model achieved the strongest combined-year accuracy (RF R² = 0.73; XGBoost R² = 0.76). These results demonstrate that integrating agronomic structure with environmental variability substantially improves multi-year yield prediction, and support cultivar-specific recommendations and climate-informed management strategies for Delmarva and other coastal agroecosystems.

Abstract Crop diversification through the integration of push‒pull technology (PPT) and other agronomic practices, such as intercropping, provides ecological functions, including insect pest management. This study evaluated the effects of integrating maize‒potato intercropping and PPT (an integrated approach) on the management of fall armyworm ( Spodoptera frugiperda ), stem borer ( Chilo partellus ) and potato tuber moth ( Phthorimaea operculella ) larvae. The study was conducted in Hatset district, Hawzien, northern Ethiopia. A significantly lower number of S. frugiperda and C. partellus larvae and a lower level of plant damage were recorded in the maize plots treated with PPT and the integrated approach than in the maize monocropped plots and the maize‒potato intercropped plots. A significantly lower number of P. operculella larvae and a lower level of plant damage were recorded in the intercropped maize‒potato plots than in the monocropped potato plots. Thus, combining maize‒potato intercropping with PPT significantly reduced S. frugiperda and C. partellus larval infestation in maize and P. operculella larval infestation in potato. This study revealed that integrating maize‒potato intercropping and PPT can be an effective management approach to control S. frugiperda , C. partellus and P. operculella larval infestations, providing a comparative advantage for controlling multiple insect pests in an ecologically diversified cropping system.

Global climate change poses increasing challenges to agricultural production and global food security by intensifying temperature and precipitation variability and increasing the frequency of extreme weather events. While several studies have examined farmers’ perceptions of climate change in the United States, limited empirical evidence exists for the Delaware, Maryland, and Virginia (Delmarva) Peninsula. This study assessed farmers’ perceptions of climate change in the Delmarva region and identified key factors influencing these perceptions, as well as adaptation strategies employed to address climate-related risks. Primary data were collected through a structured survey administered to farmers across the Delmarva Peninsula, while secondary data consisted of historical temperature and precipitation records obtained from meteorological stations in the region. Descriptive statistics were used to summarize farmer perceptions and adaptation practices, and a logit regression model was applied to examine socioeconomic and experiential factors influencing perceptions of climate change. Analysis of climate data revealed notable variability in temperature and rainfall patterns, with the warmest temperatures occurring during June, July, and August and peak rainfall generally observed between May and September. Survey results showed that a large majority of respondents (88.2%) perceived that climate change is occurring. Logit model results indicated that farmers’ age, education level, acceptance of climate change adaptation practices, and observed changes in climate over the past 5–10 years positively influenced perceptions of climate change. Adaptation strategies included selective crop choices, avoiding cultivation in flood-prone areas, adoption of soil conservation practices, and the use of crop insurance.

The optimal choice of antibiotic prophylaxis in elective colorectal surgery remains uncertain, with most reviews emphasizing timing and route of administration rather than direct comparisons of antibiotic classes. To compare the outcomes associated with different antibiotic classes and class combinations administered within 24 hours before elective colorectal surgery. MEDLINE, Embase, Cochrane Central, and Scopus were searched from inception to July 17, 2025. Eligible studies were randomized clinical trials that enrolled adult patients undergoing elective colorectal procedures and were required to report on surgical site infection (SSI) within 30 days of surgery. Data on SSIs, adverse events, all-cause mortality, and length of hospital stay were extracted when available by 2 independent reviewers. A frequentist random-effects model was used for network meta-analysis. Reporting followed the Preferred Reporting Items for Systematic Review and Meta-Analyses, Extension Statement for Reporting of Systematic Reviews Incorporating Network Meta-Analyses of Health Care Interventions. The primary outcome was risk of SSI; secondary outcomes were 30-day mortality, adverse events, and length of hospital stay. Risk ratios (RRs) with 95% CIs were calculated for binary outcomes, and mean differences (MDs) with SDs were calculated for continuous outcomes. The certainty of evidence was assessed using the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) approach. A total of 105 randomized clinical trials involving 18 273 patients were included. The network included 32 distinct antibiotic nodes defined by antimicrobial class or combination. High to moderate certainty of evidence indicated that, compared with placebo or no antibiotic, several regimens were associated with reduced the risk of SSI. Regimens including broad-spectrum penicillin (RR, 0.26; 95% CI, 0.16-0.42), third-generation cephalosporins (RR, 0.27; 95% CI, 0.16-0.45), a combination of metronidazole and second-generation cephalosporins (RR, 0.27; 95% CI, 0.17-0.44), and tetracyclines (RR, 0.32; 95% CI, 0.20-0.53) were all associated with significant reductions. The antibiotics associated with a significant decrease in mortality compared with placebo were broad-spectrum penicillin (RR, 0.21; 95% CI, 0.05-0.90) and a combination of fluoroquinolones and penicillins (RR, 0.14; 95% CI, 0.03-0.79). No significant differences were observed between antibiotic classes regarding hospital length of stay or adverse events. The certainty of evidence ranged from very low to moderate across outcomes. In this systematic review and network meta-analysis, several antibiotic regimens were associated with substantially reduced risk of SSIs after elective colorectal surgery compared with placebo. Broad-spectrum penicillins had the most consistent benefits, with moderate-certainty evidence supporting reductions in risk of both SSI and mortality.

Self-efficacy beliefs and mindset influence student success, impacting how a learner experiences and responds to learning situations and setbacks. Accordingly, mindset interventions, are successful at increasing student performance with particular efficacy with historically underserved students such as those attending HBCUs. This paper studies a classroom-based mindset intervention that was implemented with the goal of increasing learning and achievement through improving the students’ cognitive disposition. The intervention, implemented at a mid-Atlantic minority serving institution of higher education, involved the creation of a custom-designed three-tool self-assessment developed to engender students’ critical reflection. The scales in question measured self-efficacy, growth mindset, and mastery goal orientation. This paper presents the results of reliability testing via Cronbach’s alpha and inter-item covariance. According to the findings, all three tools showed strong (good to excellent) reliability with acceptable positive covariance indicating that they are capable of serving as appropriate instruments for further adoption, usage, and analysis. It is the goal that this paper contributes to the body of literature on mindset interventions encouraging more individuals working with traditionally underserved learners to consider exploring efforts to increase students’ positive mindsets.

Oyster aquaculture is essential for ensuring a sustainable food source. Despite stringent controls, cases of oyster-related illnesses linked to pathogenic Vibrio parahaemolyticus (Vp) and Vibrio vulnificus (Vv) persist. This study investigated the impact of aquaculture practices on the oyster microbiome and pathogen levels, focusing on two common systems: on-bottom and floating cages. From June to November 2019, monthly samples were collected from the Chesapeake Bay, including oysters and water from each aquaculture system. Oyster samples included both fresh and temperature-abused oysters. The study utilized the most probable number and real-time PCR (MPN-qPCR) method to quantify total and pathogenic Vp and Vv in water and oyster samples. DNA was extracted from oyster homogenates and filtered water samples for shotgun metagenomic sequencing. The results revealed significant impacts of aquaculture practices on the diversity of the oyster microbiome, particularly affecting the distribution of phages, antibiotic resistance, and virulence factor genes. Shotgun metagenomic sequencing consistently showed higher genetic representation of Vibrio in floating cages for both fresh and temperature-abused oyster samples. MPN-qPCR results differed between practices, showing higher Vibrio levels in bottom cages for fresh oysters and higher levels in floating cages under temperature abuse. These discrepancies are likely explained by the stable conditions in bottom cages, the effects of temperature abuse, and the growth bias inherent to the MPN method. These results underscore the need for a holistic, time-sensitive approach, taking into account microbial states and the dynamic aspects of the oyster environment to understand the complex relationship between aquaculture practices and the oyster microbiome.IMPORTANCEThis study holds great importance for food safety, antibiotic resistance surveillance, aquaculture management, and environmental health. Unraveling the population dynamics of microbial communities in oysters and their responses to different aquaculture practices enhances our ability to ensure safer seafood, monitor antibiotic resistance, optimize aquaculture methods, and mitigate potential public health challenges. Moreover, it demonstrates the applicability of advanced metagenomic tools for future research. Furthermore, this research addresses critical aspects of food safety, food security, public health, and sustainable aquaculture practices, making it highly relevant in today's context.