Weeds are among the significant factors that could harm crop yield by invading crops and smother pastures, and significantly decrease the quality of the harvested crops. Herbicides are widely used in agriculture to control weeds; however, excessive use of herbicides in agriculture can lead to environmental pollution as well as yield reduction. Accurate mapping of crops/weeds is essential to determine weeds’ location and locally treat those areas. Increasing demand for flexible, accurate and lower cost precision agriculture technology has resulted in advancements in UAS-based remote sensing data collection and methods. Deep learning methods have been successfully employed for UAS data processing and mapping tasks in different domains. This research investigate, compares and evaluates the performance of deep learning methods for crop/weed discrimination on two open-source and published benchmark datasets captured by different UASs (field robot and UAV) and labeled by experts. We specifically investigate the following architectures: 1) U-Net Model 2) SegNet 3) FCN (FCN-32s, FCN-16s, FCN-8s) 4) DepLabV3+. The deep learning models were fine-tuned to classify the UAS datasets into three classes (background, crops, and weeds). The classification accuracy achieved by U-Net is 77.9% higher than 62.6% of SegNet, 68.4% of FCN-32s, 77.2% of FCN-16s, and slightly lower than 81.1% of FCN-8s, and 84.3% of DepLab v3+. Experimental results showed that the ResNet-18 based segmentation model such as DepLab v3+ could precisely extract weeds compared to other classifiers.

The introduction of unmanned-aerial-vehicle remote sensing for collecting high-spatial- and temporal-resolution imagery to derive crop-growth indicators and analyze and present timely results could potentially improve the management of agricultural businesses and enable farmers to apply appropriate solution, leading to a better food-security framework. This study aimed to analyze crop-growth indicators such as the normalized difference vegetation index (NDVI), crop height, and vegetated surface roughness to determine the growth of corn crops from planting to harvest. Digital elevation models and orthophotos generated from the data captured using multispectral, red/green/blue, and near-infrared sensors mounted on an unmanned aerial vehicle were processed and analyzed to calculate the various crop-growth indicators. The results suggest that remote sensing-based growth indicators can effectively determine crop growth over time, and that there are similarities and correlations between the indicators.

Understanding sustainable livestock production requires consideration of both qualitative and quantitative factors in a temporal and/or spatial frame. This study adapted Qualitative Comparative Analysis (QCA) to relate conditions of social, economic, and governance factors to changes in livestock inventory across several counties and over time. This paper presents an approach that (1) identified factors with the potential to relate to a change in livestock inventory and (2) analyzed commonalities within these factors related to changes spatially and temporally. This paper illustrates the approach and results when applied to five counties in eastern South Dakota. The specific response variables were periods of increasing, no change, or decreasing beef cattle, dairy cattle, and swine inventories in the specific counties for five-year census periods between 1992 and 2017. In the spatial analysis of counties, stable beef inventories and decreasing dairy inventories related to counties with increasing gross domestic products. The presence of specific social communities related to increases in county swine inventories. In the temporal analysis of census periods, local governance and economic factors, particularly market price influences, were more prevalent. Swine inventory showed a stronger link to cash crop markets than to livestock markets, whereas cattle market price increases associated with stable inventories for all animal types. Local governance tools had mixed effects for the different animal types across space and time. The factors and analysis results are context-specific. However, the process considers the various socio-economic processes in livestock production and community development applicable to agricultural sustainability questions in the Midwest and beyond.

Wicked problems are inherent in food–energy–water systems (FEWS) due to the complexity and interconnectedness of these systems, and addressing these challenges necessitates the involvement of the diverse stakeholders in FEWS. However, successful stakeholder engagement requires a strong understanding of the relationships between stakeholders and the specific wicked problem. To better account for these relationships, we adapted a means, motive, and opportunity (MMO) framework to develop a method of stakeholder analysis that evaluates the agency of stakeholders related to a wicked problem in FEWS. This method involves two key components: (1) identification of a challenge at the FEWS nexus and (2) evaluation of stakeholder agency related to the challenge using the dimensions of MMO. This approach provides a method for understanding the characteristics of stakeholders in FEWS and provides information that could be used to inform stakeholder engagement in efforts to address wicked problems at the FEWS nexus. In this article, we present the stakeholder analysis method and describe an example application of the MMO method by examining stakeholder agency related to the adoption of improved swine waste management technology in North Carolina, USA.

No abstract