Timely and cost-effective crop yield prediction is vital in crop management decision-making. This study evaluates the efficacy of Unmanned Aerial Vehicle (UAV)-based Vegetation Indices (VIs) coupled with Machine Learning (ML) models for corn (Zea mays) yield prediction at vegetative (V6) and reproductive (R5) growth stages using a limited number of training samples at the farm scale. Four agronomic treatments, namely Austrian Winter Peas (AWP) (Pisum sativum L.) cover crop, biochar, gypsum, and fallow with sixteen replications were applied during the non-growing corn season to assess their impact on the following corn yield. Thirty different variables (i.e., four spectral bands: green, red, red edge, and near-infrared and twenty-six VIs) were derived from UAV multispectral data collected at the V6 and R5 stages to assess their utility in yield prediction. Five different ML algorithms including Linear Regression (LR), k-Nearest Neighbor (KNN), Random Forest (RF), Support Vector Regression (SVR), and Deep Neural Network (DNN) were evaluated in yield prediction. One-year experimental results of different treatments indicated a negligible impact on overall corn yield. Red edge, canopy chlorophyll content index, red edge chlorophyll index, chlorophyll absorption ratio index, green normalized difference vegetation index, green spectral band, and chlorophyll vegetation index were among the most suitable variables in predicting corn yield. The SVR predicted yield for the fallow with a Coefficient of Determination (R²) and Root Mean Square Error (RMSE) of 0.84 and 0.69 Mg/ha at V6 and 0.83 and 1.05 Mg/ha at the R5 stage, respectively. The KNN achieved a higher prediction accuracy for AWP (R² = 0.69 and RMSE = 1.05 Mg/ha at V6 and 0.64 and 1.13 Mg/ha at R5) and gypsum treatment (R² = 0.61 and RMSE = 1.49 Mg/ha at V6 and 0.80 and 1.35 Mg/ha at R5). The DNN achieved a higher prediction accuracy for biochar treatment (R² = 0.71 and RMSE = 1.08 Mg/ha at V6 and 0.74 and 1.27 Mg/ha at R5). For the combined (AWP, biochar, gypsum, and fallow) treatment, the SVR produced the most accurate yield prediction with an R² and RMSE of 0.36 and 1.48 Mg/ha at V6 and 0.41 and 1.43 Mg/ha at the R5. Overall, the treatment-specific yield prediction was more accurate than the combined treatment. Yield was most accurately predicted for fallow than other treatments regardless of the ML model used. SVR and KNN outperformed other ML models in yield prediction. Yields were predicted with similar accuracy at both growth stages. Thus, this study demonstrated that VIs coupled with ML models can be used in multi-stage corn yield prediction at the farm scale, even with a limited number of training data.

Cover crop biomass is helpful for weed and pest control, soil erosion control, nutrient recycling, and overall soil health and crop productivity improvement. These benefits may vary based on cover crop species and their biomass. There is growing interest in the agricultural sector of using remotely sensed imagery to estimate cover crop biomass. Four small plot study sites located at the United States Department of Agriculture Agricultural Research Service, Crop Production Systems Research Unit farm, Stoneville, MS with different cereals, legumes, and their mixture as fall-seeded cover crops were selected for this analysis. A randomized complete block design with four replications was used at all four study sites. Cover crop biomass and canopy-level hyperspectral data were collected at the end of April, just before cover crop termination. High-resolution (3 m) PlanetScope imagery (Dove satellite constellation with PS2.SD and PSB.SD sensors) was collected throughout the cover crop season from November to April in the 2021 and 2022 study cycles. Results showed that mixed cover crop increased biomass production up to 24% higher compared to single species rye. Reflectance bands (blue, green, red and near infrared) and vegetation indices derived from imagery collected during March were more strongly correlated with biomass (r = 0–0.74) compared to imagery from November (r = 0.01–0.41) and April (r = 0.03–0.57), suggesting that the timing of imagery acquisition is important for biomass estimation. The highest correlation was observed with the near-infrared band (r = 0.74) during March. The R² for biomass prediction with the random forest model improved from 0.25 to 0.61 when cover crop species/mix information was added along with Planet imagery bands and vegetation indices as biomass predictors. More study with multiple timepoint biomass, hyperspectral, and imagery collection is needed to choose appropriate bands and estimate the biomass of mix cover crop species.

Carbon dioxide (CO₂) is the most abundant greenhouse gas (GHG) in the atmosphere and the substrate for the photosynthetic fixation of carbohydrates in plants. Increasing GHGs from anthropogenic emissions is warming the Earth’s atmospheric system at an alarming rate and changing its climate, which can affect photosynthesis and other biochemical reactions in crop plants favorably or unfavorably, depending on plant species. For the substrate role in plant carbon reduction reactions, CO₂ concentration ([CO₂]) in air potentially enhances photosynthesis. However, N uptake and availability for protein synthesis can be a potential limiting factor in enhanced biomass synthesis under enriched [CO₂] conditions across species. Legumes are C₃ plants and symbiotic N fixers and are expected to benefit from enhanced [CO₂] in the air. However, the concurrent increase in air temperatures with enhanced [CO₂] demands more detailed investigations on the effects of [CO₂] enhancement on grain legume growth and yield. In this article, we critically reviewed and presented the online literature on growth, phenology, photosynthetic rate, stomatal conductance, productivity, soil health, and insect behavior under elevated [CO₂] and temperature conditions. The review revealed that specific leaf weight, pod weight, and nodule number and weight increased significantly under elevated [CO₂] of up to 750 ppm. Under elevated [CO₂], two mechanisms that were affected were the photosynthesis rate (increased) and stomatal conductivity (decreased), which helped enhance water use efficiency in the C₃ legume plants to achieve higher yields. Exposure of legumes to elevated levels of [CO₂] when water stressed resulted in an increase of 58% in [CO₂] uptake, 73% in transpiration efficiency, and 41% in rubisco carboxylation and decreased stomatal conductance by 15–30%. The elevated [CO₂] enhanced the yields of soybean by 10–101%, peanut by 28–39%, mung bean by 20–28%, chickpea by 26–31%, and pigeon pea by 31–38% over ambient [CO₂]. However, seed nutritional qualities like protein, Zn, and Ca were significantly decreased. Increased soil temperatures stimulate microbial activity, spiking organic matter decomposition rates and nutrient release into the soil system. Elevated temperatures impact insect behavior through higher plant feeding rates, posing an enhanced risk of invasive pest attacks in legumes. However, further investigations on the potential interaction effects of elevated [CO₂] and temperatures and extreme climate events on growth, seed yields and nutritional qualities, soil health, and insect behavior are required to develop climate-resilient management practices through the development of novel genotypes, irrigation technologies, and fertilizer management for sustainable legume production systems.

No‐till (NT) alleviates adverse effects of agricultural production on environmental quality, improves soil health, and reduces greenhouse gas emissions, yet this has not been demonstrated in humid subtropical Mississippi. Research objectives were to evaluate nutrient and C dynamics and soil quality via Soil Management Assessment Framework (SMAF) following 15 years of continuous management under corn ( Zea mays L.) (2008–2018) and soybean [ Glycine max (L.) Merr.] (2019–2022) on a Dundee silt loam soil. After 15 years, soil organic carbon (SOC) stocks (0‐ to 30‐cm depth) under NT were 25% higher than conventional tillage (CT). Between 2020 and 2022, SOC stocks increased 3 Mg ha ⁻¹ under NT and decreased 2 Mg ha ⁻¹ under CT. Increased SOC retention under NT could represent an opportunity for increasing the systems’ profitability as C markets expand. Greater SOC and aggregation scores improved SMAF soil quality index (SQI) under NT (71%), compared to CT (66%), underscoring the critical role of organic matter in soil functioning in managed agrosystems. Soybean yields were not linked to SMAF SQI ( p > 0.05), suggesting that crop yields are mostly affected by non‐edaphic factors (e.g., climate extremes). SMAF illustrated positive impacts of NT on SOC sequestration and soil health, which may foster its adoption as a conservation practice in the Lower Mississippi River basin. As such, NT stands as a climate‐smart management practice that allows for sustainable intensification in humid subtropical regions.

Informed selection of cover crop species is critical for optimizing their benefits by considering the costs of adoption and potential initial negative impact on yields against the proven benefits for sustainable production. The Lower Mississippi Delta region is lagging in cover crop adoption, partly due to a paucity of this information from the area, despite being one of the major row crop‐producing regions in the United States. Common cover crop species in the region, cereal rye (CR) (Secale cereale), hairy vetch (HV) (Vicia villosa), and crimson clover (CC) (Trifolium incarnatum), and their possible two‐ and three‐combination mixes were evaluated for their impact on biomass production, enzyme activities, nutrient cycling, and corn (Zea mays) yields. HV + CC + CR and HV + CR produced the highest biomass and lowest yields compared to all treatments. HV and CC produced the least biomass but comparable yields to no cover crop. HV + CC + CR, HV + CR, CR, CC, and HV treatments had comparable total nitrogen, phosphorus, and soil organic carbon levels in the surface 0‐ to 5‐cm depth. Generally, CC alone and the HV + CR mix consistently displayed significantly higher phosphatase, N‐acetylglucosaminidase, β‐glucosidase, and cellobiohydrolase activities compared to all other treatments, while CR had the lowest. The single species of CC or HV may be the best option in the short term for initial cover crop implementation, rotating with CR a few years down the line for optimum long‐term benefits under corn production in this region.

The Rolling Plains of Texas are historically semi‐arid with sporadic, high intensity storms followed by periods of long drought. Fallow management is a common practice intended to store soil water, but leaves the bare soil exposed to erosive forces that can diminish the soil productivity. Cover crops in no‐till (NT) agriculture have been proposed to increase soil health under environments with low precipitation as an alternative to fallow management. This study evaluated multiple treatments in a dryland cotton system including: (1) conventional tillage (CT); (2) NT; and NT with the following cover crops: (3) wheat; (4) Austrian winter pea; (5) crimson clover; (6) hairy vetch; and (7) mixed species cover. Soil samples were collected at 0, 3, and 6 weeks after cover crop termination and analyzed for soil organic carbon, total nitrogen, inorganic N, water‐extractable organic carbon, water‐extractable organic nitrogen, carbon mineralization, and phospholipid fatty acid analysis. For all parameters tested, there was no significant difference between CT and NT at any date or depth, so the addition of cover crops to NT cotton systems might be needed in order to enhance NT in regard to soil function. The multi‐species mixed treatment was predicted to perform the best out of the cover crop treatments due to its combined benefits from grasses and legumes. However, the single‐species Austrian winter pea treatment had 24% and 28% higher soil carbon and nitrogen than no‐till without a cover crop, and can be a useful alternative to fallow management under these dryland agriculture conditions.