Proceedings
Topics
| Filter results24 paper(s) found. |
|---|
1. Variability in Yield Response of Maize to N, P and K Fertilization Towards Site-specific Nutrient Recommendations in Two Maize Belts in TogoSavannah and central regions are the major maize production zones in Togo, but with maize grain yields at a threshold of only 1.5 Mg ha-1. We use a participatory approach to assess the importance of the major three macro elements (N, P and K) for maize cropping in the two regions in order to further allow for site-specific and scalable fertilizer recommendations. Thirty farmers’ fields served as pilot sites, allocated within the two regions to account for spatial variability ... J.M. Sogbedji, M. Lare, A.K. Lotsi, K.A. Amouzou, T. Agneroh |
2. Suitability of ML Algorithms to Predict Wild Blueberry Harvesting LossesThe production of wild blueberries (Vaccinium angustifolium.) is contributing 112.2 million dollars to the Canada’s revenue which can be further increased through controlling harvest losses. A precise prediction of blueberry harvesting losses is necessary to mitigate such losses. In this study, the performance of three machine learning (ML) models was evaluated to predict the wild blueberry harvest losses on the ground. The data from four commercial fields in Atlantic Canada we... H. Khan, T. Esau, A. Farooque, F. Abbas |
3. Comparative Analysis of Light-weight Deep Learning Architectures for Soybean Yield Estimation Based on Pod Count from Proximal Sensing Data for Mobile and Embedded Vision ApplicationsCrop yield prediction is an important aspect of farming and food-production. Therefore, estimating yield is important for crop breeders, seed-companies, and farmers to make informed real-time financial decisions. In-field soybean (Glycine max L.(Merr.)) yield estimation can be of great value to plant breeders as they screen thousands of plots to identify better yielding genotypes that ultimately will strengthen national food security. Existing soybean yield estimation too... J.J. Mathew, P.J. Flores, J. Stenger, C. Miranda, Z. Zhang, A.K. Das |
4. Agriculture Machine Guidance Systems: Performance Analysis of Professional GNSS ReceiversGNSS (Global Navigation Satellite Systems) plays nowadays a major role in different civilian activities and is a key technology enabling innovation in different market sectors. For instance, GNSS-enabled solutions are widespread within the Precision Agriculture and, among them, applications in the field of machinery guidance are commonly employed to optimize typical agriculture practices. The scope of this paper is to present the outcomes of the agriculture testing campaign performe... J. Capolicchio, D. Mennuti, I. Milani, M. Fortunato, R. Petix, J. Reyes gonzalez, M. Sunkevic |
5. Enhancing PA Adoption Through Value ConnectionsDespite an increase in breadth of precision agriculture over time, and the attendant elements of digital agriculture that either support PA or integrates the outputs of PA, the pace of adoption of digital agriculture in our farming systems remains slow. In assessing impediments to adoption of digital agriculture, much work to date has focused on the value proposition as considered by individual producers or value chain actors. At this level, adoption remains constrained by perceptions o... D.W. Lamb, M.T. Schaefer |
6. Farmer Charlie - Low Cost Smart Local Data Available to Remote FarmersFarmer Charlie brings connectivity and information to farmers, who receive tailored agronomic data to improve their agricultural practice. Farmer Charlie is based on on-site sensors through which soil data can be detected, gathered, and processed by a dedicated server. Broadband communication allows farmers to receive real-time, localised information on tablet or mobile phone. Farmer Charlie is a low-cost solution, it can be adapted to various crops and to detect soil humidity, pH, temperatur... B. Bonnardel |
7. Smart Food Oases: Development of a Distributed Point-to-point Urban Food Ecosystem in Food Desert AreasUrban agriculture has been getting much attention in the past decade as a solution to overcome food insecurity and accessibility of food for urban residents and to have better green environments in cities. Urban agriculture is expected to provide better nutrients to residents, reduce transportation and environmental costs, and help urban dwellers access food efficiently. The present study is to build a collaborative ecosystem among urban growers/producers and create bridges from these farmers... J. Lee, S. Song, S. Oh, K. Krishnaswamy, C. Sun, Y. Adu-gyamfi |
8. The ISO Strategic Advisory Group for Smart Farming: a Multi-pronged Opportunity for Greater Global InteroperabilityAgriculture is becoming increasingly complex and producers must secure their profitability, sustainability, and freedom to operate under a progressively more challenging set of constraints such as climate change, regulatory pressure, changes in consumer preferences, increasing cost of inputs, and commodity price volatility. We have not, however, yet reached the level of data interoperability required for a truly "smart" farming that can tackle the aforementioned probl... R. Ferreyra, J. Lehmann |
9. A Flexible Software Architecture for General Precision Agriculture Decision Support SystemsAgricultural data management is a complex problem. Both the data and the needs of the users are diverse. Given the complexity of the problem, it's easy to ascertain that a single solution will not be able to meet the needs of all users. This paper presents a software architecture designed to be extensible as well as flexible enough to provide agricultural management tools for a wide variety of users. The solution is based on a microservice architecture, which allows for the creation of ne... W. Neils, D. Mommen |
10. Field-level Zoning at Regional Scale Using Remote Sensing and GIS: Lessons Learned from the Desert Agriculture Region of Southern CaliforniaA decision support tool, SAMZ-Desert, utilizing GIS and remote sensing techniques, was created to delineate management zones (MZs) for a total of 6852 fields in California's Imperial County. Landsat-8 NDVI data from April 27, 2018, was employed for this purpose. Furthermore, 11 cloud-free images captured between 2018 and 2020 were statistically analyzed to assess within-field NDVI variability and the temporal stability of MZs at the regional level. Approximately 37% of the fields in the r... A.K. Verdi, A. Garg, A. Sapkota |
11. Are Pulses Really More Variable Than Cereals? a Country-wide Analysis of Within-field VariabilityIn Australia, pulses are underutilised by growers relative to cereal crops. There is significant global interest in growing pulses to provide more plant protein, and they also provide a string of agronomic and environmental benefits, such as their ability to fix nitrogen, and provide a pest and disease break for cereal crops. Many studies attribute this underutilisation to pulses exhibiting greater within-field yield variability than cereals. However, this has never been comprehensively exami... P. Filippi, T. Bishop, D. Al-shammari, T. Mcpherson |
12. Precision Irrigation Strategies for Climate-resilient Crop Production and Water Resource ManagementDeficit irrigation management practices that best optimize the use of limited water resources without impacting crop yield are necessary to ensure the sustainability of agricultural production. This is particularly crucial in regions characterized by semi-arid climate, like Western Kansas, where the challenge of depleting water resources is worsened by the occurrence of extreme climate conditions. Therefore, a data-driven irrigation management strategy such as one developed based on crop evap... K.E. Igwe, I. Onyekwelu, V. Sharda |
13. Detailed Derivation of Spatial Soil Attributes Using Soil Sensor Data, Terrain Analysis and Soil Maps with Supervised ClassificationDetailed knowledge of the spatial distribution of soils is critical for improved management and modeling in agriculture and forestry. However, information from existing soil maps is often not accurate enough and soil units are too large. In the current study, we used intensively collected information from soil profile analyses at the Scheyern site and used this as training data to map soil relationships on land in Dürnast with long-term fertilization experiments (BonaRes). Both... K. Heil |
14. Decision Support Tools for Developing Aflatoxin Risk Maps in Peanut FieldsAspergillus flavus and Aspergillus parasiticus hereafter referred to jointly as A. flavus, are soil fungi that infect and contaminate preharvest and postharvest peanuts with the carcinogenic secondary metabolite aflatoxin. A. flavus can cause extensive economic losses to peanut growers and shellers by contaminating peanut kernels with aflatoxins. In the southeastern U.S., contamination from aflatoxin continues to be a major threat to the peanut industry and... G. Vellidis, M. Abney, T. Burlai, J. Fountain, R.C. Kemerait, S. Kukal, L. Lacerda, S. Maktabi, A. Peduzzi, C. Pilcon, M. Sysskind |
15. A Decision-support Tool to Optimize Mid-season Corn Nitrogen Fertilizer Management from Red, Green, Blue SUAS ImagesCorn receives more nitrogen (N) fertilizer per unit area than any other row crop and optimized soil fertility management is needed to help maximize farm profitability. In Arkansas, N fertilizer for corn is delivered in two- or three-split applications. Three-split applications may provide a better match to crop needs and contribute to minimizing yield loss from N deficiency. However, the total amounts are selected based on soil texture and yield goal without accounting for early-season losses... A. Poncet, T. Bui, W. France, T. Roberts, L. Purcell, J. Kelley |
16. Coupling Macro-scale Variability in Soil and Micro-scale Variability in Crop Canopy for Delineation of Site-specific Management GridThe efficient application of fertilizers via Site-Specific Management Units (SSMUs) or Management Zones (MZs) can significantly enhance crop productivity and nitrogen use efficiency. Conventional mathematical and data-driven clustering methods for MZ delineation, while prevalent, often lack precision in identifying productivity zones. This research introduces a knowledge-driven productivity zone to mitigate these limitations, offering a more precise and efficacious approach. The hyp... W.A. Admasu, D. Mandal, R. Khosla |
17. Using Remote Sensing to Benchmark Crop Coefficient Curves of Sweet Corn Grown in the Southeastern United StatesIrrigation is responsible for over 75% of global freshwater use, making it the largest consumer of the world’s freshwater resources. With freshwater scarcity increasing worldwide, increased efficient irrigation water use is necessary. Smart irrigation is described as ‘the linking of technology and fundamental knowledge of crop physiology to significantly increase irrigation water use efficiency'. Irrigation scheduling tools such as smartphone applications have become... E. Bedwell, L. Lacerda, T. Mcavoy, B.V. Ortiz, J. Snider, G. Vellidis, Z. Yu |
18. AI Tools in Agri DSS Pipeline - the Case of Irrigated SugarbeetA general pipeline that can be associated to a DSS includes several steps. Data Collectionn includes Acquisition, extraction, and aggregation of data from previously identified and selected sources. Data Cleaning and preparation make data available for exploratory analysis that make them usable. Data Analysis is then applied to extract meaningful information e.g. by statistical and/or simulation models. Data are successively synthesized and visualized to make them clear to the decision-maker ... G.-. Vitali, C. Ferraz |
19. Field Validation of Airblast Spray Advisor Decision Support Web App for Citrus ApplicationsField conditions influencing the effectiveness of pesticide application in orchard and vineyard production systems are complex. As a result, growers and pesticide applicators grapple with how to make the right decisions for setting up the sprayer that will lead to the most efficient and effective outcomes. Airblast Spray Advisor, a decision support web app built on MATLAB was designed to assist with planning and evaluation of such applications when using airblast sprayers. It re... P.A. Larbi |
20. Integrated Data-driven Decision Support SystemsSite-specific and data-driven decision support systems in agriculture are evolving fast with the rapid advancements in cutting-edge technologies such as Agricultural Artificial Intelligence (AgAI) and big data integration. Data driven decision support systems have the potential to revolutionize various aspects of farming, from crop monitoring and precision management decisions to the way growers interact with complex technologies. The AgAI decision support-based systems excel at ana... L.A. Puntel, P. Pellegrini, S. Joalland , J. Rattalino, L. Vitantonio |
21. Simulating Climate Change Impacts on Cotton Yield in the Texas High PlainsCrop yield prediction enables stakeholders to plan farming practices and marketing. Crop models can predict crop yield based on cropping system and practices, soil, and other environmental factors. These models are being used for decision support in agriculture in a variety of ways. Cultivar selection, water and nutrient input optimization, planting date selection, climate change analysis and yield prediction are some of the promising area of applications of the models in field level farm man... B. Ghimire, R. Karn, O. Adedeji, G. Ritchie, W. Guo |
22. Predicting Within-field Cotton Yield Variability Using DSSAT for Decision Support in Precision AgricultureThe quantification of spatial and temporal variability of cotton (Gossypium hirsutum L.) yield provides critical information for optimizing resources, especially water, in the Southern High Plains (SHP), Texas, with a diminishing water supply. The within-field yield variation is mostly influenced by the properties of soil and their interaction with water and nutrients. The objective of this study was to predict within-field cotton yield variability using a crop growth mode... B. Ghimire, R. Karn, O. Adedeji, W. Guo |
23. From Scientific Literature to the End User: Democratizing Access to Data Products Through Interactive ApplicationsIn recent years, the sustained advance in the creation of powerful programming libraries is allowing not only the creation of complex models with predictive capabilities but also revolutionizing visualization processes and the deployment of interactive applications. Some of these tools, such as Streamlit or Shiny frameworks in languages such as Python or R, allow us to create from simple applications with friendly interfaces to complex tools. These interactive digital decision dashboards allo... C. Hernandez, A. Correndo, J. Lacasa, P. Magalhaes cisdeli, G.N. Nocera santiago, I. Ciampitti |
24. Predicting the Spatial Distribution of Aflatoxin Hotspots in Peanut Fields Using DSSAT CSM-CROPGRO-PEANUT-AFLATOXINAflatoxin contamination in peanuts (Arachis hypogaea L.) is a persistent concern due to its detrimental effects on both profitability and public health. Several plant stress-inducing factors, including high soil temperatures and low soil moisture, have been associated with aflatoxin contamination levels. Understanding the correlation between stress-inducing factors and contamination levels is essential for implementing effective management strategies. This study uses the DSSAT CSM-CR... S. Maktabi, G. Vellidis, G. Hoogenboom, K. Boote, C. Pilcon, J. Fountain, M. Sysskind, S. Kukal |