22 pages, The objective of this study was to provide a comprehensive overview of the recent advancements in the use of deep learning (DL) in the agricultural sector. The author conducted a review of studies published between 2016 and 2022 to highlight the various applications of DL in agriculture, which include counting fruits, managing water, crop management, soil management, weed detection, seed classification, yield prediction, disease detection, and harvesting. The author found that DL’s ability to learn from large datasets has great promise for the transformation of the agriculture industry, but there are challenges, such as the difficulty of compiling datasets, the cost of computational power, and the shortage of DL experts. The author aimed to address these challenges by presenting his survey as a resource for future research and development regarding the use of DL in agriculture.
Hundal, Gaganpreet Singh (author), Laux, Chad Matthew (author), Buckmaster, Dennis (author), Sutton, Mathias J (author), and Langemeier, Michael (author)
Format:
Journal article
Publication Date:
2023-01-09
Published:
Switzerland: MDPI
Location:
Agricultural Communications Documentation Center, Funk Library, University of Illinois Box: 206 Document Number: D12835
16 pages, The production of row crops in the Midwestern (Indiana) region of the US has been facing environmental and economic sustainability issues. There has been an increase in trend for the application of fertilizers (nitrogen & phosphorus), farm machinery fuel costs and decreasing labor productivity leading to non-optimized usage of farm inputs. Literature describes how sustainable practices such as profitability (return on investments), operational cost reduction, hazardous waste reduction, delivery performance and overall productivity might be adopted in the context of precision agriculture technologies (variable rate irrigation, variable rate fertilization, cloud-based analytics, and telematics for farm machinery navigation). The literature review describes low adoption of Internet of Things (IoT)-based precision agriculture technologies, such as variable rate fertilizer (39%), variable rate pesticide (8%), variable rate irrigation (4%), cloud-based data analytics (21%) and telematics (10%) amongst Midwestern row crop producers. Barriers to the adoption of IoT-based precision agriculture technologies cited in the literature include cost effectiveness, power requirements, wireless communication range, data latency, data scalability, data storage, data processing and data interoperability. Therefore, this study focused on exploring and understanding decision-making variables related to barriers through three focus group interview sessions conducted with eighteen (n = 18) subject matter experts (SME) in IoT- based precision agriculture practices. Dependency relationships described between cost, data latency, data scalability, power consumption, communication range, type of wireless communication and precision agriculture application is one of the main findings. The results might inform precision agriculture practitioners, producers and other stakeholders about variables related to technical and operational barriers for the adoption of IoT-based precision agriculture practices.
22pgs, To explore the structures and processes within agricultural advisory organisations that may enhance absorptive capacity (AC) and determine how organisations develop their AC.
22 pages, This paper presents direct evidence on the impact of a specific extension program that is aimed at promoting the adoption of varieties resistant to the soybean cyst nematode (SCN), specifically the Iowa State University SCN-Resistant Soybean Variety Trials. We use two data sources: experimental data from these variety trials and a rich proprietary dataset on farmers’ seed purchases. Combining these data, we estimate the value of soybean cyst nematode-resistant variety availability, and the associated variety trials that provide information on their performance to farmers and seed companies. Given the scope and diffusion of this extension program, the focus of the analysis is on Iowa and northern Illinois over the period 2011–2016. Farmers’ seed choices are modeled in a discrete choice framework, specifically a one-level nested logit model. Using the estimated demand model, we find farmers’ marginal willingness to pay for soybean cyst nematode-resistant varieties, and for related extension information provided by the Iowa State University SCN-Resistant Soybean Variety Trials program, to be large. These results are confirmed by counterfactual analyses showing that, over the six-year period and region of the study, the total ex post welfare change associated with the existence of, and information about, SCN-resistant seeds is about $478 million. About one-third of this surplus is captured by seed suppliers, and two-thirds accrues to farmers.
19 pages, This special issue presents recent European Commission-funded research into on-farm demonstration, undertaken through the Horizon 2020 PLAID (Peer-to-peer learning: Accessing innovation through demonstration), AgriDemo-F2F (building an interactive agridemo-hub community: enhancing peer-to-peer learning), and NEFERTITI (Networking European Farms to Enhance Cross Fertilisation and Innovation Uptake through Demonstration) projects, jointly branded ‘FarmDemo’.
