Proceedings
Authors
| Filter results8 paper(s) found. |
|---|
1. Quantifying Prediction Uncertainty in Field-scale Soil Maps Generated by Machine Learning.Field-scale maps of soil properties are a key component of precision agriculture, as they are routinely used as inputs for variable-rate fertilization, zone delineation, and site-specific management. While machine learning models have substantially improved the accuracy of spatial predictions, uncertainty associated with these predictions is often ignored, limiting the reliability of soil maps as decision-support tools. Quantifying prediction uncertainty is essential not only to assess map quality,... F. García Seleme, P. Paccioretti, M. Balzarini, M. Córdoba |
2. Soil-Sensing-Based Irrigation Decision Modeling for Greenhouse Tomato Crops Using Machine LearningGlobal agriculture faces increasing pressure to optimize water-use efficiency, particularly for high-demand crops like tomato (Solanum lycopersicum). Tomato is among the most widely consumed vegetables worldwide, playing a central role in global food systems. From an agronomic perspective, tomato crops are highly sensitive to water availability and distribution, requiring precise irrigation management to ensure sustainable production and high-quality yields. In controlled environments such as... P. Guerra, A.R. Raucci, S.A. Gutierrez , J.F. Botero, C. Kamienski, F.M. Campos De Oliveira |
3. Comparison of Machine Learning Models for Within-field Cotton Yield Prediction: Assessing the Value of Temporal Data and GeneralizabilityCotton (Gossypium hirsitum L.) yield prediction is challenging due to the complex interactions between static environmental factors, such as soil properties and topography, and dynamic variables, including weather and crop management. These factors generate significant spatial and temporal variability within and across fields. While remote sensing technologies, particularly satellite-derived vegetation indices, provide spatially explicit data to evaluate crop health, translating... L. Bastos, L. Fuhrer, W. Porter, G.J. Scarpin, A. Kaur Dhaliwal, A. Bhattarai, A. Jakhar |
4. An Online Decision Support Tool for Homogeneous Zone Delineation in Precision AgricultureManagement zone delineation is a key component of site-specific management in precision agriculture, enabling the spatial optimization of inputs and an improved understanding of within-field variability. Traditionally, homogeneous zones have been derived from historical yield maps or soil-related variables obtained through proximal sensing. More recently, the increasing availability of multispectral satellite imagery and derived vegetation indices has expanded the range of data sources available... |
5. Temporal Stability of Management Zones Derived from Vegetation Indices and Yield Data in Contrasting Production SystemsThe delineation of management zones is a central component of site-specific crop management in precision agriculture. However, the temporal stability of zones derived from different data sources remains a key challenge, particularly when vegetation indices and yield data are combined across multiple seasons. This study evaluates the temporal stability of management zones delineated using vegetation indices and yield data derived from long-term commercial field datasets. The proposed methodology... |
6. Statistical Mean Comparisons in Unreplicated Yield Trials with Georeferenced DataPrecision agriculture technologies have enabled the collection of large volumes of georeferenced yield data within experimental fields. In practice, many on-farm experiments (OFE) are implemented as large unreplicated strips or field zones containing numerous observations within each zone. The lack of replication prevents the use of classical statistical models for comparing zone means. Although many yield observations are available per zone, spatial autocorrelation violates independence assumptions... M. Córdoba, P. Paccioretti, M. Balzarini |
7. Development and Field Validation of SMART-C: A Geostatistics and PCA-Based Decision Framework for Site-Specific Cocoa Management in the Brazilian AmazonCocoa production plays a major socioeconomic role in Pará State, Brazil’s largest producing region, with annual output exceeding 140 thousand tons. Although Brazil ranks among the world’s leading cocoa producers, most production systems are still managed using field-average approaches that disregard within-field spatial variability of soil attributes and crop performance. This limitation restricts input efficiency and long-term system sustainability in perennial tropical systems.This... |
8. Data Analytics in Precision Agriculture: Statistical Modelling and Machine Learning... M. Córdoba, P. Paccioretti |