Key Intelligent Pesticide Prescription Spraying Technologies for the Control of Pests, Diseases, and Weeds: A Review

Agriculture, Journal Year: 2025, Volume and Issue: 15(1), P. 81 - 81

Published: Jan. 1, 2025

In modern agriculture, plant protection is the key to ensuring crop health and improving yields. Intelligent pesticide prescription spraying (IPPS) technologies monitor, diagnose, make scientific decisions about pests, diseases, weeds; formulate personalized precision control plans; prevent pests through use of intelligent equipment. This study discusses IPSS from four perspectives: target information acquisition, processing, spraying, implementation control. acquisition section, identification based on images, remote sensing, acoustic waves, electronic nose are introduced. processing methods such as pre-processing, feature extraction, pest disease identification, bioinformatics analysis, time series data addressed. impact selection, dose calculation, time, method resulting effect formulation in a certain area explored. implement vehicle automatic technology, droplet characteristic technology their applications studied. addition, this future development prospectives IPPS technologies, including multifunctional systems, decision-support systems generative AI, sprayers. The advancement these will enhance agricultural productivity more efficient, environmentally sustainable manner.

Language: Английский

---

GVC-YOLO: A Lightweight Real-Time Detection Method for Cotton Aphid-Damaged Leaves Based on Edge Computing

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(16), P. 3046 - 3046

Published: Aug. 19, 2024

Cotton aphids (Aphis gossypii Glover) pose a significant threat to cotton growth, exerting detrimental effects on both yield and quality. Conventional methods for pest disease surveillance in agricultural settings suffer from lack of real-time capability. The use edge computing devices processing aphid-damaged leaves captured by field cameras holds practical research value large-scale control measures. mainstream detection models are generally large size, making it challenging achieve with limited resources. In response these challenges, we propose GVC-YOLO, method based computing. Building upon YOLOv8n, lightweight GSConv VoVGSCSP modules employed reconstruct the neck backbone networks, thereby reducing model complexity while enhancing multiscale feature fusion. network, integrate coordinate attention (CA) mechanism SimSPPF network increase model’s ability extract features leaves, balancing accuracy loss after becoming lightweight. experimental results demonstrate that size GVC-YOLO is only 5.4 MB, decrease 14.3% compared baseline reduction 16.7% number parameters 17.1% floating-point operations (FLOPs). [email protected] [email protected]:0.95 reach 97.9% 90.3%, respectively. optimized accelerated TensorRT then deployed onto embedded device Jetson Xavier NX detecting aphid damage video camera. Under FP16 quantization, speed reaches 48 frames per second (FPS). summary, proposed demonstrates good speed, its performance scenarios meets application needs. This provides convenient effective intelligent precise pests fields.

Language: Английский

---

An Innovative Method of Monitoring Cotton Aphid Infestation Based on Data Fusion and Multi-Source Remote Sensing Using Unmanned Aerial Vehicles

Drones, Journal Year: 2025, Volume and Issue: 9(4), P. 229 - 229

Published: March 21, 2025

Cotton aphids are the primary pests that adversely affect cotton growth, and they also transmit a variety of viral diseases, seriously threatening yield quality. Although traditional remote sensing method with single data source improves monitoring efficiency to certain extent, it has limitations regard reflecting complex distribution characteristics aphid accurate identification. Accordingly, there is pressing need for efficient high-precision UAV technology effective identification localization. To address above problems, this study began by presenting fusion two kinds images, namely panchromatic multispectral using Gram–Schmidt image technique extract multiple vegetation indices analyze their correlation damage indices. After fusing between infestation degree was significantly improved, which could more accurately reflect spatial infestation. Subsequently, these machine learning techniques were applied modeling evaluation performance fused data. The results validation revealed GBDT (Gradient-Boosting Decision Tree) model GLI, RVI, DVI, SAVI based on performed best, an estimation accuracy R2 0.88 RMSE 0.0918, obviously better than other five models, combining imagery noticeably higher those imaging. images combined outperformed in terms precision efficiency. In conclusion, demonstrated effectiveness pest monitoring.

Language: Английский

---

Agricultural Drone-Based Variable-Rate N Application for Regulating Wheat Protein Content

Drones, Journal Year: 2025, Volume and Issue: 9(4), P. 310 - 310

Published: April 16, 2025

Implementing a variable-rate application (VRA) of fertilization based on real-time crop growth status reduces costs and enhances work efficiency. However, the technical challenges associated with obtaining accurate growth-distribution maps applying VRA, particularly agricultural drones, remain underexplored. In this study, we specifically focused drone-based VRA for regulating wheat protein content. First, normalized difference vegetation index (NDVI) distribution were obtained using multispectral images captured small unmanned aerial vehicle. Subsequently, prescription map NDVI values was generated to facilitate implementation fertilization. Continuous monitoring changes in related indices conducted from post-topdressing harvest. Experimental results indicated that selecting targeted experimental survey areas different conditions can result predictions final yield. it is sill ineffective predicting content or Additionally, less fertilizer high-NDVI more low-NDVI showed no significant yield compared conventional uniform These findings provide reference data advancing precision agriculture by addressing field-scale variability high-quality production while presenting further research challenges.

Language: Английский

---

Severity Assessment of Cotton Canopy Verticillium Wilt by Machine Learning Based on Feature Selection and Optimization Algorithm Using UAV Hyperspectral Data

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(24), P. 4637 - 4637

Published: Dec. 11, 2024

Verticillium wilt (VW) represents the most formidable challenge in cotton cultivation, critically impairing both fiber yield and quality. Conventional resistance assessment techniques, which are largely reliant on subjective manual evaluation, fail to meet demands for precision scalability required advanced genetic research. This study introduces a robust evaluation framework utilizing feature selection optimization algorithms enhance accuracy efficiency of severity VW. We conducted comprehensive time-series UAV hyperspectral imaging (400 995 nm) canopy field environment different days after sowing (DAS). After preprocessing data extract wavelet coefficients vegetation indices, various methods were implemented select sensitive spectral features By leveraging these selected features, we developed machine learning models assess VW at scale. Model validation revealed that performance responded dynamically as progressed achieved highest R2 0.5807 DAS 80, with an RMSE 6.0887. Optimization made marked improvement SVM using all observation data, increasing from 0.6986 0.9007. demonstrates potential based enhancing management, promising advancements high-throughput automated disease assessment, supporting sustainable agricultural practices.

Language: Английский

---

Enhanced YOLOv8 algorithm for leaf disease detection with lightweight GOCR-ELAN module and loss function: WSIoU

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 186, P. 109630 - 109630

Published: Dec. 29, 2024

Language: Английский

---