As urban populations increase, there is growing interest in developing innovative technologies, sustainable urban farming practices, policy measures, and other strategies to address key barriers in urban agriculture that impede improved food security and sustained urban livelihoods. We surveyed forty urban farmers and gardeners (growers) in Louisville, Kentucky, for base-level information to assess their agricultural practices and the various factors or key barriers that could influence such practices. Secondary objectives were identifying areas where practices could be improved, and identifying opportunities for research, outreach, and incentives for urban growers to transition to more sustainable and higher-yielding practices. The majority of these urban growers were white females, were more diverse than Kentucky farmers, and attained a higher degree of education than Kentucky residents as a whole. Most were engaged in urban agriculture for non-commercial reasons, and 11% were full-time urban growers operating farms for profit. Smaller farms were less likely to be operated for profit or have farm certifications than medium-sized or larger farms (Chi-squared = 14.459, p = 0.042). We found no significant differences among farm sizes in terms of whether growers rented or owned the land they were on (Chi-squared = 9.094, p = 0.168). The most common sustainable practices recorded were composting (60%), crop rotation (54%), polyculture (54%), organic farming (49%), and low or no-till (46%). The least common practices were alley cropping (5%), plasticulture (3%), and hydroponics (3%). Small farms were less likely to use crop rotation than medium-sized or large farms (Chi-squared = 13.548, p = 0.003), and farms responding to the survey in the latter part of the data collection were less likely to use compost than expected based on responses from the early part of data collection (Chi-shared = 5.972, p = 0.014). Challenges faced by these growers included limited space, accessibility to farm certification, presence of pests and diseases, and lack of record keeping and soil testing for fertility and contamination. Our study documents the need for more farm certification, education, outreach, training, research, investment, innovative ideas and solutions, collaboration among stakeholders, and better access to land through favorable urban policies and local support.

Management that degrades soil can be one of the main causes of low agricultural productivity and environmental problems in many agricultural regions. There is renewed interest in soil conservation practices to promote sustainable agriculture by improving soil quality and productivity. In this study, the short-term on-farm benefits of cover crops and manure on crop yield and biomass were examined during two consecutive growing seasons. The experiment was conducted at a small-producer farm in Logan County, Kentucky, USA. Soybean (Glycine max L.) and maize (Zea mays L.) were used as summer annual rotation crops in no-tilled soils. A cover crop mix of cereal rye (Secale cereale L.), Austrian winter pea (Pisum sativum L.), and crimson clover (Trifolium incarnatum L.) was planted after the main crop was harvested each year. Aboveground biomass of the soybean and maize were assessed, and yield was estimated from hand-harvested plants. In the first year of the study (2016), there were apparent but not significant beneficial effects of animal manure and cover crops on soybean yield, but not on biomass. The biomass and maize grain yield in the second year (2017) were detectable, significant, and increased as a result of the cover crops and manure application (p < 0.05). While beneficial effects of combining cover crops and manure may not be obvious in the first year of a rotation, they can be apparent in subsequent years. However, longer-term observation and measurement are necessary to better quantify the relationship between sustainable conservation practices and productivity.

Farmers’ training through experiential learning plays a crucial role in the success of their farming businesses. Aspiring farmers seek crucial skill sets, including financial management, marketing strategies, pricing, budgeting, whole-farm planning, and long-term decision-making. The objective of this study was to assess African American farmers’ attitudes and perceptions towards an urban agriculture certificate program launched to equip them with farming skills to help them become more successful in an urban setting. A mixed-method (qualitative and quantitative) research approach was used to evaluate the impact of this certificate program. Pre- and post-survey questionnaires and interviews were administered to assess farmers’ prior urban farming knowledge and skills and if there were any changes after the certificate program was launched. Eighteen participants (n = 18) who participated and completed the program were surveyed to measure knowledge and skills gained. Results showed that African American farmers participating in the Gary Urban Agriculture Certificate Program significantly (p < 0.03) increased their skill sets and knowledge about farming in comparison to their mean scores from pre- and post-certificate program. When participants were asked to summarize the impact of the course, several mentioned that it helped them develop a comprehensive approach to planning, planting, maintaining, and harvesting the produce of their farms. Narratives from interview discussions also support the survey results in which the majority expressed a positive impact of the certificate in helping them learn about the useful farming resources around them and gain skills in running a farm. Key findings support the concept that the urban agriculture certificate program administered by Purdue University impacted participant knowledge and provided a positive attitude towards farming. This study helped us understand the impact of the certificate program. Results provided greater awareness of creating programs to support the development of Gary urban farmers’ ability to become more knowledgeable and successful in their farming endeavors.

We propose an end-to-end differentiable framework for hedonic agricultural land pricing that integrates deep learning-based land cover classification with spatial econometric modeling into a single neural architecture. Traditional hedonic pricing approaches typically separate land cover extraction from price regression, leading to suboptimal feature representations that fail to capture the spatial spillover effects inherent to agricultural markets. In our system, a Swin Transformer-based semantic segmentation network extracts pixel-level land cover features from high-resolution multispectral imagery, which are then aggregated within parcel boundaries to produce composition vectors. These features are combined with static parcel attributes and fed into a graph isomorphism network that models spatial dependencies among neighboring parcels through message passing. The central methodological innovation is a differentiable Moran’s I operator that computes spatial autocorrelation from predicted parcel prices and incorporates this statistic into the training objective as a regularizing loss term. This constraint explicitly penalizes deviations from empirically observed target levels of positive spatial autocorrelation in agricultural land markets, thereby ensuring that the learned land cover features are optimized to explain spatial price clustering rather than generic class categories. The complete pipeline, including the segmentation backbone, graph neural network, and spatial autocorrelation computation, is fully differentiable, allowing gradients from the spatial loss to flow backwards and update pixel-level features. This design transforms land cover classification from a mere preprocessing step into an economically informed feature-learning process. The unified framework thereby produces parcel valuations that are both pixel-accurate and spatially coherent, capturing complex nonlinear dependencies such as irrigation network effects or soil-type continuity that conventional spatial econometric models cannot represent. By jointly optimizing segmentation features and their spatial spillover effects on market prices, our approach represents a significant departure from the two-stage hedonic pricing methodology.