Suitability of Satellite Imagery for Surveillance of Maize Ear Damage by Cotton Bollworm (Helicoverpa armigera) Larvae

Cotton aphids (Aphis gossypii Glover) pose a significant threat to cotton growth, exerting detrimental effects on both yield and quality. Conventional methods for pest and disease surveillance in agricultural settings suffer from a lack of real-time capability. The use of edge computing devices for real-time processing of cotton aphid-damaged leaves captured by field cameras holds significant practical research value for large-scale disease and pest control measures. The mainstream detection models are generally large in size, making it challenging to achieve real-time detection on edge computing devices with limited resources. In response to these challenges, we propose GVC-YOLO, a real-time detection method for cotton aphid-damaged leaves based on edge computing. Building upon YOLOv8n, lightweight GSConv and VoVGSCSP modules are employed to reconstruct the neck and backbone networks, thereby reducing model complexity while enhancing multiscale feature fusion. In the backbone network, we integrate the coordinate attention (CA) mechanism and the SimSPPF network to increase the model’s ability to extract features of cotton aphid-damaged leaves, balancing the accuracy loss of the model after becoming lightweight. The experimental results demonstrate that the size of the GVC-YOLO model is only 5.4 MB, a decrease of 14.3% compared with the baseline network, with a reduction of 16.7% in the number of parameters and 17.1% in floating-point operations (FLOPs). The mAP@0.5 and mAP@0.5:0.95 reach 97.9% and 90.3%, respectively. The GVC-YOLO model is optimized and accelerated by TensorRT and then deployed onto the embedded edge computing device Jetson Xavier NX for detecting cotton aphid damage video captured from the camera. Under FP16 quantization, the detection speed reaches 48 frames per second (FPS). In summary, the proposed GVC-YOLO model demonstrates good detection accuracy and speed, and its performance in detecting cotton aphid damage in edge computing scenarios meets practical application needs. This research provides a convenient and effective intelligent method for the large-scale detection and precise control of pests in cotton fields.

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

Zhang,

Yang,

et al. 2024

Monitoring Helicoverpa armigera Damage with PRISMA Hyperspectral Imagery: First Experience in Maize and Comparison with Sentinel-2 Imagery

Sári-Barnácz,

Zalai,

Milics

et al. 2024

The cotton bollworm (CBW) poses a significant risk to maize crops worldwide. This study investigated whether hyperspectral satellites offer an accurate evaluation method for monitoring maize ear damage caused by CBW larvae. The study analyzed the records of maize ear damage for four maize fields in Southeast Hungary, Csongrád-Csanád County, in 2021. The performance of Sentinel-2 bands, PRISMA bands, and synthesized Sentinel-2 bands was compared using linear regression, partial least squares regression (PLSR), and two-band vegetation index (TBVI) methods. The best newly developed indices derived from the TBVI method were compared with existing vegetation indices. In mid-early grain maize fields, narrow bands of PRISMA generally performed better than wide bands, unlike in sweet maize fields, where the Sentinel-2 bands performed better. In grain maize fields, the best index was the normalized difference of λA = 571 and λB = 2276 (R2 = 0.33–0.54, RMSE 0.06–0.05), while in sweet maize fields, the best-performing index was the normalized difference of green (B03) and blue (B02) Sentinel-2 bands (R2 = 0.54–0.72, RMSE 0.02). The findings demonstrate the advantages and constraints of remote sensing for plant protection and pest monitoring.

Large-Scale Maize Condition Mapping to Support Agricultural Risk Management

Birinyi,

Kristóf,

Hollós

et al. 2024

Crop condition mapping and yield loss detection are highly relevant scientific fields due to their economic importance. Here, we report a new, robust six-category crop condition mapping methodology based on five vegetation indices (VIs) using Sentinel-2 imagery at a 10 m spatial resolution. We focused on maize, the most drought-affected crop in the Carpathian Basin, using three selected years of data (2017, 2022, and 2023). Our methodology was validated at two different spatial scales against independent reference data. At the parcel level, we used harvester-derived precision yield data from six maize parcels. The agreement between the yield category maps and those predicted from the crop condition time series by our Random Forest model was 84.56%, while the F1 score was 0.74 with a two-category yield map. Using a six-category yield map, the accuracy decreased to 48.57%, while the F1 score was 0.42. The parcel-level analysis corroborates the applicability of the method on large scales. Country-level validation was conducted for the six-category crop condition map against official county-scale census data. The proportion of areas with the best and worst crop condition categories in July explained 64% and 77% of the crop yield variability at the county level, respectively. We found that the inclusion of the year 2022 (associated with a severe drought event) was important, as it represented a strong baseline for the scaling. The study’s novelty is also supported by the inclusion of damage claims from the Hungarian Agricultural Risk Management System (ARMS). The crop condition map was compared with these claims, with further quantitative analysis confirming the method’s applicability. This method offers a cost-effective solution for assessing damage claims and can provide early yield loss estimates using only remote sensing data.