About this Research Topic
Recent technological advances enabled the collection of extensive amounts of low-cost, high-resolution, and easily accessible agro-environmental information, including soil, crop, and weather datasets, and water, nutrients, and agrochemicals use. The problem farmers still face is how to extract practical information from the available resources for decision-making to improve agricultural efficiency under challenging climatic conditions. A vast landscape of complex decision support systems, for a large part, remains in the realm of the published literature and rarely reaches the farmer. Many current commercial solutions consist of expensive digital decision support systems and electronics embedding obscure modeling and AI techniques, being provided as 'black boxes' whose functioning is rarely disclosed to the users. Consumer-grade and transparent tools must be developed to give practical information and improve cropping systems' sustainability and profitability. Recent technological advances enabled the collection of extensive amounts of low-cost, high-resolution, and easily accessible agro-environmental information, including soil, crop, and weather datasets, and water, nutrients and agrochemicals use. The problem farmers still face is how to extract practical information from the available resources for decision-making to improve agricultural efficiency under challenging climatic conditions. A vast landscape of complex decision support systems, for a large part, remains in the realm of the published literature and rarely reaches the farmer. Many current commercial solutions consist of expensive digital decision support systems and electronics embedding obscure modeling and AI techniques, being provided as 'black boxes' whose functioning is rarely disclosed to the users. Consumer-grade and transparent tools must be developed to give practical information and improve cropping systems' sustainability and profitability.
Science-based open digital tools, developed with the end-user in mind, will allow farmers to gain knowledge from self-collected and publicly available data on the target agroecosystems. These digital solutions require transparent process-based modeling and AI technology, on the one hand, to extract knowledge from big data collected by remote, proximal, and field sensors on the other. This Research Topic within Frontiers in Agronomy aims to contribute to this objective by releasing scientific papers presenting process-based models and AI applications to inform farmers' decision-making. In addition, we aim to provide the community with the source code of the proposed work and examples of its application in case studies to set up a free library of reusable tools for decision support and cropping system analysis.
We seek papers from people willing to transfer their digital solutions based on research in agricultural sciences to those who grow crops to produce food, fiber, feed, and biofuel. Papers will propose the application of AI and process-based models, or data acquisition tools, to support:
a) agronomic management in response to medium and short-term (even real-time) weather phenomena;
b) agronomic planning to cope with medium and long-term climate change and variability.
Each article must present one or more use cases showing the functionality of the digital solution, whose source code must be hosted in an open repository, along with sample input datasets. No limitation on the technology/software is set a priori, provided that the digital solution has been made available to the community. Solutions based on free and open-source software are highly encouraged.
Manuscripts dealing with the following topics are considered a good fit for this Research Topic, but not limited to:
1. Using climate data and weather forecasts to improve agronomic management (planting, harvesting, irrigation, fertilization, pest/disease/weed management);
2. Using climate data (past and future) to design adaptation strategies at the farmer level in the context of climate change ;
3. Crop yield prediction using machine learning and process-based modeling;
4. Use of remote sensing data for crop phenology monitoring and their assimilation for yield forecasting;
5. Using actuation networks to automate the management of resources (water, nutrients, agrochemicals);
6. Using weather and crop data from IoT sensors to improve resource use and crop health;
7. Developing data collection devices/tools and methodologies.
Science-based open digital tools, developed with the end-user in mind, will allow farmers to gain knowledge from self-collected and publicly available data on the target agroecosystems. These digital solutions require transparent process-based modeling and AI technology, on the one hand, to extract knowledge from big data collected by remote, proximal, and field sensors on the other. This Research Topic within Frontiers in Agronomy aims to contribute to this objective by releasing scientific papers presenting process-based models and AI applications to inform farmers' decision-making. In addition, we aim to provide the community with the source code of the proposed work and examples of its application in case studies to set up a free library of reusable tools for decision support and cropping system analysis.
We seek papers from people willing to transfer their digital solutions based on research in agricultural sciences to those who grow crops to produce food, fiber, feed, and biofuel. Papers will propose the application of AI and process-based models, or data acquisition tools, to support:
a) agronomic management in response to medium and short-term (even real-time) weather phenomena;
b) agronomic planning to cope with medium and long-term climate change and variability.
Each article must present one or more use cases showing the functionality of the digital solution, whose source code must be hosted in an open repository, along with sample input datasets. No limitation on the technology/software is set a priori, provided that the digital solution has been made available to the community. Solutions based on free and open-source software are highly encouraged.
Manuscripts dealing with the following topics are considered a good fit for this Research Topic, but not limited to:
1. Using climate data and weather forecasts to improve agronomic management (planting, harvesting, irrigation, fertilization, pest/disease/weed management);
2. Using climate data (past and future) to design adaptation strategies at the farmer level in the context of climate change ;
3. Crop yield prediction using machine learning and process-based modeling;
4. Use of remote sensing data for crop phenology monitoring and their assimilation for yield forecasting;
5. Using actuation networks to automate the management of resources (water, nutrients, agrochemicals);
6. Using weather and crop data from IoT sensors to improve resource use and crop health;
7. Developing data collection devices/tools and methodologies.
Keywords: Modeling, Artificial Intelligence, Machine learning, Decision support systems, Precision agronomy, Internet of Things, Free software, Crop monitoring, Soil monitoring, Agronomic management, Climate variability, Climate change, Big dtaa, Databases, Data analytics, Cloud computing, Automation
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
