With the rapid advancement of artificial intelligence technology, the widespread application of deep learning in computer vision is driving the transformation of agricultural pest detection and control toward greater intelligence and precision. This paper systematically reviews the evolution of agricultural pest detection and control technologies, with a special focus on the effectiveness of deep-learning-based image recognition methods for pest identification, as well as their integrated applications in drone-based remote sensing, spectral imaging, and Internet of Things sensor systems. Through multimodal data fusion and dynamic prediction, artificial intelligence has significantly improved the response times and accuracy of pest monitoring. On the control side, the development of intelligent prediction and early-warning systems, precision pesticide-application technologies, and smart equipment has advanced the goals of eco-friendly pest management and ecological regulation. However, challenges such as high data-annotation costs, limited model generalization, and constrained computing power on edge devices remain. Moving forward, further exploration of cutting-edge approaches such as self-supervised learning, federated learning, and digital twins will be essential to build more efficient and reliable intelligent control systems, providing robust technical support for sustainable agricultural development.

Multi-class detection of cherry tomatoes using improved Yolov4-tiny model

The soluble solid content (SSC) is one of the important parameters depicting the quality, maturity and taste of fruits. This study explored hyperspectral imaging (HSI) and fluorescence spectral imaging (FSI) techniques, as well as suitable chemometric techniques to predict the SSC in kiwifruit. 90 kiwifruit samples were divided into 70 calibration sets and 20 prediction sets. The hyperspectral images of samples in the spectral range of 387 nm~1034 nm and the fluorescence spectral images in the spectral range of 400 nm~1000 nm were collected, and their regions of interest were extracted. Six spectral pre-processing techniques were used to pre-process the two spectral data, and the best pre-processing method was selected after comparing it with the predicted results. Then, five primary and three secondary feature extraction algorithms were used to extract feature variables from the pre-processed spectral data. Subsequently, three regression prediction models, i.e., the extreme learning machines (ELM), the partial least squares regression (PLSR) and the particle swarm optimization - least square support vector machine (PSO-LSSVM), were established. The prediction results were analyzed and compared further. MASS-Boss-ELM, based on fluorescence spectral imaging technique, exhibited the best prediction performance for the kiwifruit SSC, with the Rp2, Rc2 and RPD of 0.8894, 0.9429 and 2.88, respectively. MASS-Boss-PLSR based on the hyperspectral imaging technique showed a slightly lower prediction performance, with the Rp2, Rc2, and RPD of 0.8717, 0.8747, and 2.89, respectively. The outcome presents that the two spectral imaging techniques are suitable for the non-destructive prediction of fruit quality. Among them, the FSI technology illustrates better prediction, providing technical support for the non-destructive detection of intrinsic fruit quality.

Airborne crop diseases cause great losses to agricultural production and can affect people’s physical health. Timely monitoring of the situation of airborne disease spores and effective prevention and control measures are particularly important. In this study, a two-stage separation and enrichment microfluidic chip with arcuate pretreatment channel was designed for the separation and enrichment of crop disease spores, which was combined with micro Raman for Raman fingerprinting of disease conidia and quasi identification. The chip was mainly composed of arc preprocessing and two separated enriched structures, and the designed chip was numerically simulated using COMSOL multiphysics5.5, with the best enrichment effect at W2/W1 = 1.6 and W4/W3 = 1.1. The spectra were preprocessed with standard normal variables (SNVs) to improve the signal-to-noise ratio, which was baseline corrected using an iterative polynomial fitting method to further improve spectral features. Raman spectra were dimensionally reduced using principal component analysis (PCA) and stability competitive adaptive weighting (SCARS), support vector machine (SVM) and back-propagation artificial neural network (BPANN) were employed to identify fungal spore species, and the best discrimination effect was achieved using the SCARS-SVM model with 94.31% discrimination accuracy. Thus, the microfluidic-chip- and micro-Raman-based methods for spore capture and identification of crop diseases have the potential to be precise, convenient, and low-cost methods for fungal spore detection.