Muhammad Adnan Islam

Peanut also called groundnut (Arachis hypogaea L.) is an important oilseed and cash crop that is grown in tropical and subtropical regions of the world. Nowadays, tractor mounted peanut threshers without grading systems are commonly used to thresh the harvested groundnut plants, which results in the mixing of standard quality groundnut pods with immature/dead pods, mud/clods, and other impurities. To address this challenge, the conventional thresher was incorporated with a grader. The modified thresher was evaluated during the threshing season of 2023-24 in district Rawalpindi, Pothwar region of Punjab, Pakistan. The performance of the newly developed groundnut thresher (TH₁) was compared with conventional thresher (TH₂) based on threshing productivity (capacity) (kg h-1), pod breakage percentage (%), cleaning efficiency (%), and threshing efficiency (%) at three different ranges of moisture contents viz. M₁ = 19-23%, M₂ = 14-17%, M₃ = 8-12%. Experimental data were collected and statistically analyzed at a 5% level of probability. The experimental results revealed that maximum cleaning efficiency in the improved (TH₁) and conventional (TH₂) threshers were 97.88% and 84.92% respectively at the minimum moisture content (8-12%) while the minimum pod damage percentage was observed 2.24% and 4.44% at higher moisture content (19-23%). The overall performance of improved groundnut thresher was more satisfactory than the conventional thresher based on cleaning efficiency and pod damage percentage while it performed equally for threshing productivity and threshing efficiency. From the experimental results, it reveals that the modified groundnut thresher performed better to clean and grade the groundnut pods in one operation.

Precision planting is critical for improving crop establishment and productivity in smallholder farming systems in Pakistan, where manual seeding remains labour-intensive, imprecise, and inefficient. The limited availability of suitable small planters and the impracticality of larger precision seeders for fragmented holdings further constrain mechanization. This study addressed these limitations by redesigning and enhancing a vertical-plate, single-row precision planter through the integration of a straight seed delivery path and shutter mechanism and evaluating it alongside three other manually operated precision planters. Laboratory experiments quantified the seed physical properties, metering accuracy, calibration performance, and seed damage, while field trials assessed the spacing precision, plant population, labour demand, field efficiency, and operating costs across 1000 m² test plots. The punch-wheel planter exhibited the best performance, achieving a spacing precision coefficient of 6.79%, a field efficiency of 88.2%, and the lowest operating cost (PKR 799 acre⁻¹), while the remaining planters also met acceptable operational standards. In comparison with manual sowing (20–25 man-hours acre⁻¹), precision planters reduced labour to 6–8 man-hours acre⁻¹, saving PKR 7000–9000 acre⁻¹. Enhanced spacing uniformity improved the stand establishment and yield potential. These low-cost precision planters reduce drudgery, particularly for women farmers, minimize soil disturbance, and contribute to the Sustainable Development Goals of the United Nations by promoting sustainable smallholder mechanization.

To speed up the olive harvesting process, a tractor-driven olive harvesting machine was designed and manufactured at the Institute of Agricultural Engineering (AEI), Islamabad. This newly developed equipment was tested on the Bari Zaitoon-I cultivar for its performance evaluation. This innovative technology has proven valuable in efficiently replacing expensive manual harvesting operations with timely and economic alternative. It was experimentally evaluated at different PTO speeds, stroke lengths (SL), and vertical clamp positions (CP) on the tree to find the harvested and leftover fruit (%) and field capacity (trees/h) of the machine. Data collected was statistically analyzed by using “Statistix 8.1” software at a 5 % le vel of probability. The best results were recorded as 92.4 % harvested fruit, 7.6 % leftover fruit and 23.6 trees/h field capacity at the PTO speed of 300 rpm along with the stroke length of 10 cm and clamp position of 1 m on the tree trunk from the ground. The use of the developed equipment will make it possible to harvest olives in a shorter time than with manual harves ting without reducing the quality and weight of the obtained products.

The accurate and rapid detection of apple leaf diseases is a critical component of precision management in apple orchards. The existing deep-learning-based detection algorithms for apple leaf diseases typically demand high computational resources, which limits their practical applicability in orchard environments. Furthermore, the detection of apple leaf diseases in natural settings faces significant challenges due to the diversity of disease types, the varied morphology of affected areas, and the influence of factors such as lighting variations, leaf occlusions, and differences in disease severity. To address the above challenges, we constructed an apple leaf disease detection (ALD) dataset, which was collected from real-world scenarios, and we applied data augmentation techniques, resulting in a total of 9808 images. Based on the ALD dataset, we proposed a lightweight YOLO11n-based detection network, named CEFW-YOLO, designed to tackle the current issues in apple leaf disease identification. First, we designed a novel channel-wise squeeze convolution (CWSConv), which employs channel compression and standard convolution to reduce computational resource consumption, enhance the detection of small objects, and improve the model’s adaptability to the morphological diversity of apple leaf diseases and complex backgrounds. Second, we developed an enhanced cross-channel attention (ECCAttention) module and integrated it into the C2PSA_ECCAttention module. By extracting global information, combining horizontal and vertical convolutions, and strengthening cross-channel interactions, this module enables the model to more accurately capture disease features on apple leaves, thereby enhancing detection accuracy and robustness. Additionally, we introduced a new fine-grained multi-level linear attention (FMLAttention) module, which utilizes multi-level asymmetric convolutions and linear attention mechanisms to improve the model’s ability to capture fine-grained features and local details critical for disease detection. Finally, we incorporated the Wise-IoU (WIoU) loss function, which enhances the model’s ability to differentiate overlapping targets across multiple scales. A comprehensive evaluation of CEFW-YOLO was conducted, comparing its performance against state-of-the-art (SOTA) models. CEFW-YOLO achieved a 20.6% reduction in computational complexity. Compared to the original YOLO11n, it improved detection precision by 3.7%, with the mAP@0.5 and mAP@0.5:0.95 increasing by 7.6% and 5.2%, respectively. Notably, CEFW-YOLO outperformed advanced SOTA algorithms in apple leaf disease detection, underscoring its practical application potential in real-world orchard scenarios.