Deep learning and computer vision in plant disease detection: a comprehensive review of techniques, models, and trends in precision agriculture

Artificial Intelligence Review, Год журнала: 2025, Номер 58(3)

Опубликована: Янв. 17, 2025

Abstract Plant diseases cause significant damage to agriculture, leading substantial yield losses and posing a major threat food security. Detection, identification, quantification, diagnosis of plant are crucial parts precision agriculture crop protection. Modernizing improving production efficiency significantly affected by using computer vision technology for disease diagnosis. This is notable its non-destructive nature, speed, real-time responsiveness, precision. Deep learning (DL), recent breakthrough in vision, has become focal point agricultural protection that can minimize the biases manually selecting spot features. study reviews techniques tools used automatic state-of-the-art DL models, trends DL-based image analysis. The techniques, performance, benefits, drawbacks, underlying frameworks, reference datasets more than 278 research articles were analyzed subsequently highlighted accordance with architecture deep models. Key findings include effectiveness imaging sensors like RGB, multispectral, hyperspectral cameras early detection. Researchers also evaluated various architectures, such as convolutional neural networks, transformers, generative adversarial language foundation Moreover, connects academic practical applications, providing guidance on suitability these models environments. comprehensive review offers valuable insights into current state future directions detection, making it resource researchers, academicians, practitioners agriculture.

Язык: Английский

---

Integrating reinforcement learning and large language models for crop production process management optimization and control through a new knowledge-based deep learning paradigm

Computers and Electronics in Agriculture, Год журнала: 2025, Номер 232, С. 110028 - 110028

Опубликована: Фев. 12, 2025

Язык: Английский

---

Knowledge assimilation: Implementing knowledge-guided agricultural large language model

Knowledge-Based Systems, Год журнала: 2025, Номер unknown, С. 113197 - 113197

Опубликована: Фев. 1, 2025

Язык: Английский

---

MetaFruit meets foundation models: Leveraging a comprehensive multi-fruit dataset for advancing agricultural foundation models

Computers and Electronics in Agriculture, Год журнала: 2025, Номер 231, С. 109908 - 109908

Опубликована: Янв. 22, 2025

Язык: Английский

---

IPM-AgriGPT: A Large Language Model for Pest and Disease Management with a G-EA Framework and Agricultural Contextual Reasoning

Mathematics, Год журнала: 2025, Номер 13(4), С. 566 - 566

Опубликована: Фев. 8, 2025

Traditional pest and disease management methods are inefficient, relying on agricultural experts or static resources, making it difficult to respond quickly large-scale outbreaks meet local needs. Although deep learning technologies have been applied in management, challenges remain, such as the dependence large amounts of manually labeled data limitations dynamic reasoning. To address these challenges, this study proposes IPM-AgriGPT (Integrated Pest Management—Agricultural Generative Pre-Trained Transformer), a Chinese language model specifically designed for knowledge. The proposed Generation-Evaluation Adversarial (G-EA) framework is used generate high-quality question–answer corpora combined with Agricultural Contextual Reasoning Chain-of-Thought Distillation (ACR-CoTD) low-rank adaptation (LoRA) techniques further optimizes base build IPM-AgriGPT. During evaluation phase, specialized benchmark domain, comprehensively assessing performance tasks. Experimental results show that achieved excellent scores multiple tasks, demonstrating its great potential intelligence management.

Язык: Английский

---

Optimizing agricultural classification with masked image modeling

Cogent Food & Agriculture, Год журнала: 2025, Номер 11(1)

Опубликована: Фев. 12, 2025

Image classification poses a significant challenge in agriculture. However, the utilization of popular algorithms such as vision transformers and convolutional neural networks has often fallen short numerous agricultural tasks owing to scarcity extensively labelled data reliance on pretrained models trained generic datasets. To address this, our study details pretraining ViTs using 224,228 images, employing masked image modeling for preprocessing. The model was then fine-tuned three independent datasets performed better than state-of-the-art methods. For example, method achieved highest accuracy rates 76.18%, 98.49%, 88.56% IP102, DeepWeeds, Tsinghua Dogs datasets, respectively. This enhancement can be attributed robust strategy we have developed through extensive experimentation with MIM model. Our encompasses advanced models, leveraging histogram oriented gradient features reconstruction target, selecting an appropriate mask ratio. We hope that this research will prompt application self-supervised learning techniques, represented by model, wide range image-related future.

Язык: Английский

---

Autonomous navigation method for agricultural robots in high-bed cultivation environments

Computers and Electronics in Agriculture, Год журнала: 2025, Номер 231, С. 110001 - 110001

Опубликована: Фев. 13, 2025

Язык: Английский

---

Satellite Data in Agricultural and Environmental Economics: Theory and Practice

Agricultural Economics, Год журнала: 2025, Номер unknown

Опубликована: Март 16, 2025

ABSTRACT Agricultural and environmental economists are in the fortunate position that a lot of what is happening on ground observable from space. Most agricultural production happens open one can see space when where innovations adopted, crop yields change, or forests converted to pastures, name just few examples. However, converting remotely sensed images into measurements particular variable not trivial, as there more pitfalls nuances than “meet eye”. Overall, however, research benefits tremendously advances available satellite data well complementary tools, such cloud‐based platforms, machine learning algorithms, econometric approaches. Our goal here provide with an accessible introduction working data, show‐case applications, discuss solutions, emphasize best practices. This supported by extensive supporting information, we describe how create different variables, common workflows, discussion required resources skills. Last but least, example reproducible codes made online.

Язык: Английский

---

Foundation Models in Agriculture: A Comprehensive Review

Agriculture, Год журнала: 2025, Номер 15(8), С. 847 - 847

Опубликована: Апрель 14, 2025

This paper explores the transformative potential of Foundation Models (FMs) in agriculture, driven by need for efficient and intelligent decision support systems face growing global population climate change. It begins outlining development history FMs, including general FM training processes, application trends challenges, before focusing on Agricultural (AFMs). The examines diversity applications AFMs areas like crop classification, pest detection, image segmentation, delves into specific use cases such as agricultural knowledge question-answering, video analysis, support, robotics. Furthermore, it discusses challenges faced AFMs, data acquisition, efficiency, shift, practical challenges. Finally, future directions emphasizing multimodal applications, integrating across food sectors, decision-making systems, ultimately aiming to promote digitalization transformation agriculture.

Язык: Английский

---

Diagnosis of early nitrogen, phosphorus and potassium deficiency categories in rice based on multimodal integration and knowledge distillation

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 15, 2025

Язык: Английский

---