Название: Artificial Intelligence and Sustainable Agriculture for Solanaceae Crops
Автор: Mithilesh Kumar Dubey, Kajal Verma, Khalil Ahmed, Sudha Dubey
Издательство: CRC Press
Год: 2026
Страниц: 243
Язык: английский
Формат: pdf (true), epub
Размер: 31.4 MB

The book Artificial Intelligence and Sustainable Agriculture for Solanaceae Crops provides a comprehensive exploration of artificial intelligence techniques and their transformative role in promoting sustainable agriculture, particularly for Solanaceae crops such as tomato, potato, and eggplant. Focusing on disease detection and prediction, the book highlights advanced AI applications, including dimensionality reduction, feature extraction, and the analysis of complex genomics and phenotypic data. It systematically presents the design, implementation, and evaluation of predictive models using widely adopted tools such as MATLAB and Python, while also addressing both software- and hardware-based solutions for enhancing genomics research and crop disease management. Through detailed case studies, experimental results, and practical examples, the book demonstrates how AI can optimize precision agriculture practices, improve crop yield, and support early warning systems for disease outbreaks. Serving as both a theoretical reference and a practical guide, it is an invaluable resource for researchers, graduate students, agronomists, and professional engineers aiming to leverage AI, image analysis, and predictive modeling to address real-world challenges in Solanaceae crop production and genomics.

Deep learning algorithms have made it possible to use a leaf image and identify the disease with great precision with drones, smartphones and sensor packed devices. Even minute changes like a subtle shift in the leaf pattern, colours, and structure which are far too granular to be processed by humans are picked up by these models and thus such observation can be reaped from depending on the driving technology like drones or AI systems. Convolutional Neural Networks (CNNs) are some of the best architectures for image-based disease detection. In Artificial Intelligence, convolutional neural networks, or CNNs, are applied in an array of fields from robotics to medical imaging. Notably, they are used for processes observational in nature, like analyzing images and videos. Spatial detection is the primary focus of convolutional layers. They aim to identify edges, spots, and other graphical characteristics within picture data. These features form the foundation for understanding leaf anomalies linked to specific diseases. With image data input, the pooling layer performs subsampling or downsampling, which helps generalize the extracted features while minimizing the computational load. Prior to the model predicting the class of disease, the processed features at hand are transformed to class probabilities which i done in the dense layers. This gives a high probability of disease prediction accuracy.