Cotton is the most widely cultivated natural fiber crop worldwide, yet it is highly susceptible to various diseases and pests that significantly compromise both yield and quality. To enable rapid and accurate diagnosis of cotton diseases and pests—thus supporting the development of effective control strategies and facilitating genetic breeding research—we propose a lightweight model, the Resource-efficient Cotton Network (RF-Cott-Net), alongside an open-source image dataset, CCDPHD-11, encompassing 11 disease categories. Built upon the MobileViTv2 backbone, RF-Cott-Net integrates an early exit mechanism and quantization-aware training (QAT) to enhance deployment efficiency without sacrificing accuracy. Experimental results on CCDPHD-11 demonstrate that RF-Cott-Net achieves an accuracy of 98.4%, an F1-score of 98.4%, a precision of 98.5%, and a recall of 98.3%. With only 4.9 M parameters, 310 M FLOPs, an inference time of 3.8 ms, and a storage footprint of just 4.8 MB, RF-Cott-Net delivers outstanding accuracy and real-time performance, making it highly suitable for deployment on agricultural edge devices and providing robust support for in-field automated detection of cotton diseases and pests.

Cotton leafroll dwarf disease (CLRDD) caused by cotton leafroll dwarf virus (CLRDV) is an emerging threat to cotton production in the United States. The disease was first reported in Alabama in 2017 and subsequently has been reported in 10 other cotton producing states in the United States, including Georgia. A field study was conducted at field sites near Tifton, Georgia in 2019 and 2020 to evaluate leaf gas exchange, chlorophyll fluorescence, and leaf temperature responses for a symptomatic cultivar (diseased plants observed at regular frequency) at multiple stages of disease progression and for asymptomatic cultivars (0% disease incidence observed). Disease-induced reductions in net photosynthetic rate (A_n, decreased by 63–101%), stomatal conductance (g_s, decreased by 65–99%), and efficiency of the thylakoid reactions (32–92% decline in primary photochemistry) were observed, whereas leaf temperature significantly increased by 0.5–3.8°C at advanced stages of the disease. Net photosynthesis was substantially more sensitive to disease-induced declines in g_s than the thylakoid reactions. Symptomatic plants with more advanced disease stages remained stunted throughout the growing season, and yield was reduced by 99% by CLRDD due to reductions in boll number per plant and declines in boll mass resulting from fewer seeds per boll. Asymptomatic cultivars exhibited more conservative gas exchange responses than apparently healthy plants of the symptomatic cultivar but were less productive. Overall, it is concluded that CLRDV limits stomatal conductance and photosynthetic activity of individual leaves, causing substantial declines in productivity for individual plants. Future studies should evaluate the physiological contributors to genotypic variation in disease tolerance under controlled conditions.