AI in Agriculture

This podcast episode will explore the YOLO_MRC model, a deep learning model that can detect and count pests in real-time using images. The model was developed to address issues with existing pest detection methods, such as:🍈Long inference times: The time it takes for the model to process an image and make a prediction.🍈 Low accuracy: The ability of the model to correctly identify pests.🍈 Large model sizes: The amount of storage space the model requires.How YOLO_MRC WorksThe YOLO_MRC model is based on the YOLOv8n model and includes three key improvements:👉🏼 Multicat Module: This module helps the model focus on the target by incorporating an attention mechanism.👉🏼 Reducing Detection Heads: The number of detection heads in the model is reduced from three to two, decreasing the number of parameters.👉🏼 C2flite Module: This module enhances the model's ability to extract deep features.These modifications enable YOLO_MRC to achieve faster processing times, higher accuracy, and a smaller model size compared to the original YOLOv8n model.Testing and ResultsThe researchers tested YOLO_MRC on a dataset of Bactrocera cucurbitae pests, which affect melon, fruit, and vegetable crops. The dataset consisted of images captured from videos of trap bottles. The model was compared to four other detection models:● YOLOv5s-ECA● Fast-RCNN (Mobilenetv2)● YOLOv5Ghost● YOLOv7TinyYOLO_MRC achieved the best performance in terms of processing time, recall, and model size. It also had the highest accuracy when compared to manual counting results, with an average accuracy of 94%.Benefits for AgricultureReal-time pest detection and counting can benefit agriculture in several ways:↳ Early pest detection: Enables timely intervention and prevents widespread infestations.↳ Optimised pesticide use: Reduces pesticide waste and environmental pollution by providing accurate pest counts.↳ Data for pest management: Provides valuable information for agricultural managers to make informed decisions.Limitations and Future ResearchThe YOLO_MRC model has some limitations:● It is currently only applicable to Bactrocera cucurbitae pests.● It may not be accurate in all outdoor environments.● It can have errors in cases of overlapping occlusions.Researchers plan to address these limitations in future research by:🟡 Improving the model's accuracy for multi-class pest detection.🟡 Optimising the model's adaptability to different environments.🟡 Enhancing the model to handle overlapping occlusions.🟡 Exploring applications on mobile devices for use in the field.ConclusionThe YOLO_MRC model offers a promising solution for real-time pest detection and counting. Its compact size, high accuracy, and fast processing speed make it suitable for practical use in agriculture. Further research and development will enhance its capabilities and expand its applications. Hosted on Acast. See acast.com/privacy for more information.

In this episode, we dive into the cutting-edge world of smart farming and explore how artificial intelligence (AI) is transforming agriculture, specifically focusing on pitaya (dragon fruit) farming in China. Our discussion centers around a recent breakthrough in precision agriculture with the development of GSE-YOLO, a lightweight, high-precision model based on YOLOv8n. This innovative AI technology is designed to detect the ripeness of pitaya in natural environments, significantly improving efficiency and reducing labor costs.We break down the key advancements in the GSE-YOLO model, including the integration of GhostConv, SPPELAN, and EMA attention mechanisms that make the system more robust and faster, while maintaining high accuracy. Learn how this technology addresses challenges in fruit detection, such as varying lighting conditions, overlapping fruits, and the natural complexity of the farm environment. With an 85.2% detection accuracy and an mAP50 of 90.9%, GSE-YOLO is a game changer for the future of farming.Tune in to discover how these technological advancements could lead to more sustainable farming practices, reduce waste, and potentially revolutionize how we harvest crops across the world. Hosted on Acast. See acast.com/privacy for more information.

In this episode, we dive into how advanced weather forecasting models are transforming precision agriculture. From improving water use to boosting crop yields, cutting-edge models like Temporal Convolutional Neural Networks (TCNN) and CatBoost are helping farmers make smarter decisions.🔍 Key takeaways:140,160 agrometeorological data points from Morocco's Sidi Rahal region were used to build forecasting models based on air temperature, solar radiation, and relative humidity.The TCNN model achieved remarkable accuracy, with an RMSE of 0.88°C for 1-day air temperature forecasts, outperforming traditional models.For solar radiation, TCNN achieved an RMSE of 29.26 W/m², allowing farmers to fine-tune irrigation schedules and conserve water.CatBoost excelled in longer forecasts, with an RMSE of 25.20 W/m² for 1-week solar radiation predictions, showing how machine learning can improve farming efficiency.🌦 Why it matters:Farmers can now plan irrigation with 1-day to 3-day precision, saving water and reducing costs in regions with limited resources.Accurate forecasts prevent crop losses and boost yields by responding quickly to changing weather conditions.💡 What you'll learn:How data-driven models like TCNN and CatBoost are shaping the future of agriculture.The critical role of weather forecasting in improving resource management and sustainability on farms.The impact of AI and machine learning on adapting agriculture to climate change and resource scarcity.Join us to explore the future of farming, where weather tech meets AI innovation! 🎙️🌍🔔 Subscribe now to stay updated on how AI is revolutionizing agriculture!Any questions or ideas? Drop us an email to [email protected] Petiole Pro: https://play.google.com/store/apps/details?id=com.petiolepro.farmvision&hl=en_GB&gl=USFind more about Petiole: https://petiolepro.comGet calibrating plate: https://petiole.aiOur Linkedin: https://www.linkedin.com/company/petioleOur Researchgate: https://www.researchgate.net/lab/Petiole-Pro-Lab-Maryna-KuzmenkoOur Instagram: https://www.instagram.com/petiolepro/Our Facebook: https://facebook.com/petiole.coOur Twitter: https://twitter.com/petioleappOur TikTok: https://tiktok.com/@petiolepro#petiolepro #aiinagriculture #weatherforecast Hosted on Acast. See acast.com/privacy for more information.

In this episode of Harvesting Data: The Future of Crop Yield Prediction, we explore groundbreaking research from Purdue University, USA 🇺🇸, that is transforming the way we predict maize crop yields.We will cover:🌾 How advanced AI and deep learning (LSTM networks) are changing crop yield prediction.🛰️ The use of multi-modal remote sensing data, including hyperspectral imagery and LiDAR, for more accurate forecasts.🌱 How attention mechanisms improve the interpretability of predictions by identifying key factors influencing maize growth.📊 Insights into how genetic, environmental, and physiological data are integrated to improve decision-making in plant breeding.🌍 The potential impact of this research on global food security and sustainable agriculture. Hosted on Acast. See acast.com/privacy for more information.

This podcast episode examines research conducted at the Universidade Federal da Grande Dourados in Brazil, focusing on the development of a real-time pest detection system for soybean crops using the You Only Look Once (YOLO) architecture. The research aimed to address the challenges of accurately detecting and classifying 12 classes of soybean pests, including 10 distinct species with two further categorized into their adult and nymph stages.The researchers created a new dataset, called INSECT12C-Dataset, composed of images of these pests captured in real-world field conditions, which presents variations in lighting, object size, occlusion, and background. The dataset, containing 2,758 annotated insects, was used to train and test the YOLO architecture for real-time pest detection.The podcast will explore:The importance of soybean crops to the Brazilian economy and the significant impact of pests on soybean production.The challenges of pest detection, both in research and practical applications, due to environmental variability, pest camouflage, mobility, diversity, and the limitations of detection technologies.The specific difficulties in detecting all 12 soybean pest classes, including the impact of environmental factors, insect occlusion, data imbalance, and variations in pest appearance.Why accurately distinguishing between adult and nymph stages of certain species, like Euschistus heros, posed a particular challenge for the YOLO architecture.The researchers' findings, including the effectiveness of YOLO in real-time pest detection and the potential for future improvements using higher-resolution cameras, dataset balancing techniques, and the development of pesticide application maps.This podcast episode will be of interest to:Farmers and agricultural professionals seeking to understand the latest advancements in pest detection and control technologies for soybean crops.Researchers and students in the fields of computer vision, artificial intelligence, and precision agriculture.Anyone interested in the applications of technology for sustainable agriculture and food security. Hosted on Acast. See acast.com/privacy for more information.

Join us as we explore a game-changing innovation in agriculture: Bud-YOLO, a sophisticated AI algorithm that's poised to revolutionise cotton farming. This episode unpacks the science behind Bud-YOLO, its potential impact on the industry, and the broader implications for the future of AI in agriculture.We'll be speaking about the complexities of Bud-YOLO. We'll cover:The Challenge of Cotton Topping: Why is this seemingly simple task so crucial for cotton production? We'll discuss the drawbacks of traditional methods and the need for automation.The Power of Computer Vision: Learn how Bud-YOLO utilises deep learning and computer vision to accurately identify and locate cotton top buds in real-time, even within the challenging environment of a cotton field.Under the Hood of Bud-YOLO: We'll take a look at the building blocks of this algorithm, including the CSPPC module, the Efficient RepGFPN, and the Inner CIoU loss function. Understand how these components work together to enhance detection accuracy and speed.Beyond the Lab: What are the real-world applications of Bud-YOLO? We'll explore how this technology can be integrated into intelligent cotton topping machinery to improve efficiency, reduce labour costs, and minimise environmental impact.The Future of AI in Agriculture: Bud-YOLO is just one example of how AI is transforming the agricultural landscape. We'll discuss the broader trends, opportunities, and challenges of integrating AI into farming practices.Tune in to gain a deeper understanding of this exciting technological breakthrough and its potential to shape the future of cotton farming and beyond. Hosted on Acast. See acast.com/privacy for more information.

This podcast examines the potential of using consumer-grade cameras and open-source software to conduct plant phenotyping research. The sources describe a research project where a custom-built lightbox and a consumer camera were used to capture images of turfgrass in a greenhouse over an 8-week period. The images were then analysed to measure plant cover, colour, and other traits. These measurements were compared to data gathered using active spectral reflectance and traditional assessment methods, such as NDVI and visual quality assessments. This podcast explores the possibilities, as well as the challenges, of this approach for plant phenotyping. Hosted on Acast. See acast.com/privacy for more information.

Seed quality significantly affects crop yield and production costs in sugar beet farming, yet traditional methods for sorting monogerm and multigerm seeds are inefficient and lead to seed loss—how can AI technology be leveraged to optimize seed classification and improve productivity?In this episode, we dive into research focused on enhancing sugar beet production quality through AI-driven seed classification. Discover how NVIDIA Jetson Nano and TX2 boards, paired with YOLOv4 models, distinguish between single-embryo and multi-embryo seeds in real-time, reducing waste and improving yield. Join us as we explore how machine vision is tackling a crucial challenge in modern agriculture. Hosted on Acast. See acast.com/privacy for more information.

In today's episode we discuss study investigates a new method for assessing the quality of maize seedlings using high-resolution drone imagery.It combines a deep learning object detection algorithm, YOLO v8, with Voronoi spatial analysis to extract three key indicators: the Voronoi Polygon Uniformity Index (VPUI), missing seedling rate, and repeated seedling rate.The authors compare their method to traditional plant spacing analysis and demonstrate its superior accuracy, particularly in detecting missing seedlings.The research highlights the potential of this method for improving agricultural production efficiency and reducing labour costs. Hosted on Acast. See acast.com/privacy for more information.

Discover how cutting-edge technology is transforming the way we ensure fruit quality. In this episode, we explore groundbreaking research that combines hyperspectral imaging and deep learning to detect frozen pomegranates. Learn how this innovative approach achieves over 99% accuracy, outperforming traditional methods. We'll discuss the potential impact on reducing food waste, preventing fraud, and improving storage efficiency in the agricultural industry. Join us as we delve into the fascinating world where artificial intelligence meets fruit inspection, and glimpse the future of food quality control. Hosted on Acast. See acast.com/privacy for more information.