Welcome to the latest issue of the Journal of Agricultural Technology Futures Research (JATFR). This issue features cutting-edge research and developments in agricultural technologies, focusing on innovative solutions, emerging trends, and futuristic methodologies that address the evolving challenges in agriculture.
Featured Articles in the Latest Issue
- Volume 2 (Issue 2) JULY– DECEMBER 2025
Research Articles
Machine Learning and Predictive Analytics of Early Crop Yield Forecasting in Maize based On Vegetation Indices Derived by Satellites
Vol.2(2); Pages:1-8. Published on November-2025
Abstract
In food security, logistics and markets planning, good crop yield prediction is the important factor in making the right decisions. In this work a system of machine learning aimed at forecasting the early yield of maize with the help of the vegetation indices in a satellite image received with Sentinel-2 was developed. These two models; Random Forest and XGBoost were trained using four years of yield data and satellite data and the results were correspondingly validated using field data performed in the year 2025 before harvest. XGBoost model was the best with R 2 = 0.86 and the RMSE of 0.42 t/ha, representing a strong predictive role. The most accurate forecasting was made at stage of silking of the maize plants and R 2 = 0.91 which could be made 45 days before harvest. Such results support the possibility of the implementation of AI-integrated satellite monitoring to realtime, high-resolution estimate yield in commercial maize systems, which can be a highly powerful instrument to optimize farm management, market prediction, and resource distribution. This will be a positive way forward in the future of precision agriculture, which will lead to the production of more efficient and sustainable food.
View Full PDF
Please LOGIN to View Full PDF or Read more.
An Autonomous Field Robot to do Site-Specific Weed Detection and Targeted Herbicide Application in Row Crops
Vol.2(2); Pages:9-16. Published on November-2025
Abstract
The trend in reducing the application of herbicides in farming has put much attention to precision weed control. The paper is the result of the development and the field testing of an autonomous robot to detect weeds on the site and locally apply a herbicide in row crops. The robot employs convolutional neural networks (CNNs) technology in real-time detection of weeds and variable-rate actuator in accurate herbicide treatment. Areas covered in the field tests in the Netherlands in the maize and sugar beet fields indicated that herbicide use was reduced by 71.5 per cent with an efficacy of 94.2 per cent of weed control. The robot reached an operating coverage of 1.6 hectares per hour, and very little disruption to crops. The findings indicate that AI-enabled robotics has great promise in sustainable crop protection and it can provide a solution to overcome herbicide reliance and efficiency improvement in precision farming.
View Full PDF
Please LOGIN to View Full PDF or Read more.
Blockchain and IoT in real time monitoring and transparent traceability of perishable horticultural supply chains
Vol.2(2); Pages:17-24. Published on November-2025
Abstract
Perishable crops like tomatoes are very susceptible to quality loss in case of post-harvest handling, mainly because of the absence of real time visibility in the supply chain. This paper introduces the deployment and the evaluation of an integrated system of IoT-based environmental monitoring and blockchain in order to enhance the supply chains of tomatoes in Brazil and Italy, addressing both traceability and quality assurance. The system also recorded real-time temperature and humidity during transport and irreversibly documented the events of critical supplies using Ethereum based smart contracts. The overall field implementation in 14 farms and 3 distribution centers resulted in the decrease of the spoilage by 34 percent, the improvement of the quality tracking and verification speed, and the enhancement of consumer confidence provided by QR-related history of products. The study shows that it is possible to use the combination of blockchain and IoT and create new generation agri-supply chains that would take transparency, efficiency and sustainability in the realm of food safety and quality assurance and consumer trust in perishable product management to new levels.
View Full PDF
Please LOGIN to View Full PDF or Read more.
AR-Enhanced Knowledge Transfer in Precision Agriculture: A Pilot Study on Knowledge Transfer in Protected Smallholders
Vol.2(2); Pages:25-32. Published on December-2025
Abstract
The use of Precision agriculture technology is usually inhibited by the use of complicated machinery and unavailability of training on the location. This pilot study considered the efficiency of augmented reality ( AR )-based training modules to impart precision farming among smallholders of vegetable growers in Telangana, India. AR simulations included the soil testing by GPS, variable-rate application, and scouting by the drones and presented through the glasses mounted on the head. Knowledge retentions and levels of confidence were checked in pre- and post-training evaluation. The use of AR modules in training farmers resulted in a 61 percent change in the understanding of the concepts involved, and the farmers experienced a greater level of post-education precision in the use of tools (p < 0.01) than was the case among farmers trained in traditional classrooms. The AR-trained group also estimated a higher level of confidence to utilize precision farming tools. Based on the findings, it is proposed that the gaps towards effective training can be closed through immersive AR technology that can improve the level of knowledge and skills of the smallholder farmers and boost the adoption of smart farming much quicker in low-resource scenarios. AR training would thus be an expandable option in encouraging the use of precision agriculture.
View Full PDF
Please LOGIN to View Full PDF or Read more.
Edge Computing and Integration of the Climate Forecast through Smart Greenhouse Automation to Produce High-Value Crop Production
Vol.2(2); Pages:33-41. Published on December-2025
Abstract
The paper examines how edge computing suits greenhouse grown capsicum production by combining it with climate forecast information. The designed system allows using real-time feedback of the sensors in combination with local short-term climate forecasts considering machine learning models, implemented on local microcontrollers to make autonomous decisions about irrigation, ventilation, and shading. Within a 3- month production period, the system recorded 17-percent decrease in energy consumption and a 11.4-percent boost in yield owing to conventional automated system. The projections of climate-wise interventions, based on the predictions of the change of temperatures, contributed to the mitigation of acute changes in temperature that improved the physiological stability of plants. The findings show that edge-AI systems could enhance resource use as well as yield in controlled environment agriculture. The research shows how automation can respond to climate and promote more accurate, sustainable, and energy-efficient greenhouse farming practices to open a window into the future of next-generation smart agriculture.
View Full PDF
Please LOGIN to View Full PDF or Read more.
Accessing the Articles
You can access the full text of these articles by clicking on the titles or visiting our journal’s online archives.
Stay Updated
To stay informed about the latest research and updates in the journal, consider subscribing to our newsletter or following us on social media.
