Elwakeel, Abdallah ElshawadfyElden, Abdallah ZeinAhmed, Saad F.Issa, SaliLi, ChangyouAli, Khaled Abdeen MousaHanafy, Waleed M.Ali, GumaAlzahrani, FawazFathy, Atef2025-12-172025-12-172025-12-012. Elwakeel, A. E., Elden, A. Z., Ahmed, S. F., Issa, S., Li, C., Ali, K. A. M., Hanafy, W. M., Ali, G., Alzahrani, F., & Ahmed, A. F. (2025). Development, performance evaluation and prediction of optimal operational conditions for a double-row sugarcane harvester using deep learning. Scientific Reports, 15, 1–24.2045-2322https://dir.muni.ac.ug/handle/20.500.12260/838The study develops and evaluates a deep-learning–enhanced double-row sugarcane harvester that integrates Feedforward and Deep Neural Networks to predict optimal operational conditions (forward speed, row spacing, cutting height, and knife count). Field trials demonstrated 100% cutting efficiency at ground-level cutting, 3 km/h, and 71 cm spacing, with minimal cost (~USD 4.42/ha) and peak field capacity (0.554 ha/h) at 4.5 km/h, 88.75 cm spacing, 4 cm cutting height, and two knives. This innovation fosters mechanization, boosts agricultural productivity, reduces labor demands, and curbs energy use—advancing SDG 2 (zero hunger), SDG 8 (decent work & economic growth), SDG 9 (industry & innovation), and SDG 12 (sustainable consumption), aligning with Uganda’s NDP IV goals for agro-industrial development, technology adoption, and rural livelihoods enhancement.Sugarcane is a vital global crop, serving as a primary source of sugar, biofuel, and renewable energy. Advancements in harvesting are critical to meeting rising demand, enhancing profitability, and supporting eco-friendly agricultural practices in the sugarcane sector. Based on the current challenges of sugarcane harvesting in developed countries, the current study aimed to develop a semiautomatic whole-stalk sugarcane harvester (SWSH) for harvesting two rows of sugarcane stalks at a time and to be front-mounted on a classic four-wheel agricultural tractor. Then performance evaluation and prediction of optimal operational conditions for a double-row sugarcane harvester using Feedforward Neural Network (FNN) and Deep Neural Network (DNN) at different levels of forward speeds (3, 3.5, 4.5, and 5 km/h), row spacing (71, 78.89, and 88.75 cm), cutting heights (0, 2, and 4 cm), and numbers of knives (2 and 4) of the cutting systems. The obtained results showed that the cutting efficiency of the developed SWSH reached 100%. Where the higher cutting efficiency was observed at a cutting height equal to zero (ground level), forward speed of 3 km/hand row spacing of 71 cm using both 2 and 4 knives. The minimum total operating cost of the developed SWSH was about 4.42 USD/ha, and it was detected when using a forward speed of 4.5 km/h, row spacing of 88.75 cm, a cutting height of 4 cm, and two knives only on the cutting disk. Furthermore, at a row spacing of 88.75 cm, the maximum field capacity of the developed SWSH was 0.554 ha/h, observed at a forward speed of 4.5 km/h.enSugarcane harvestingArtificial intelligence (AI)Farm machineryAgricultural engineeringNeural networksArticle