Water is considered one of the vital natural resources and factors for performing short- and long-term agricultural practices on Earth. Meanwhile, globally, most of the available freshwater resources are utilized for irrigation purposes in agriculture. Currently, many world regions are facing extreme water shortage problems, which can worsen if not managed properly. In the literature, numerous methods and remedies are used to cope with the increasing global water crises. The use of precision irrigation water-saving systems (PISs) for efficient water management under climate change is one of them and is a highly recommended approach by researchers. It can mitigate the adverse effects of changing climate and help enhance water use efficiency, crop yield, and environmental footprints. Thus, the present study aimed to comprehensively examine and review PISs, focusing on their development, implementation, and positive impacts on sustainable water management. In addition, we searched the literature using different online search engines and reviewed and summarized the main results of the previously published papers on PISs. We discussed the traditional irrigation method and its modernization for enhancing water use efficiency, PIS monitoring and controlling, architecture, data sharing communication technologies, the role of artificial intelligence for irrigation water-saving, and the future prospects of the PIS. Based on the brief literature review, the present study concluded that the future of PISs seems bright, driven by the need for efficient irrigation water management systems, technological advancements, and increasing environmental awareness. As the water scarcity problem intensifies due to climate change and population growth, the PIS is poised to play a critical role in optimizing and modernizing water usage, increasing water use efficiency, and reducing environmental footprints, thus ensuring sustainable agriculture development.

Plastic products in plant production and protection help farmers increase crop production, enhance food quality, and reduce global water use and their environmental footprint. Simultaneously, plastic has emerged as a critical ecological issue in recent years, and its pollution has significantly impacted soil, water, and plants. Thus, this review examines the multifaceted problems of plastic pollution in agriculture as a risk to food security, the ecosystem, and the environment. The study’s objective was to review and present the most recent information on using different plastic products in agriculture, the sources of plastic pollution, the advantages and drawbacks of using plastic products, and the strategies for mitigating plastic pollution in agriculture. Furthermore, after examining current plastic applications, benefits, adverse effects, and risks to soil, plants, and the environment, we addressed the requirements for technological advancements, regulations, and social processes that could contribute to mitigating plastic pollution in our ecosystems. We identified different pathways toward more sustainable use of plastics in agriculture and discussed future research directions.

Rapid urbanization, climate variability, and land degradation are increasingly challenging traditional open-field farming systems. Soilless farming (SLF) has emerged as a complementary approach to enhance horticultural resilience in space-constrained and climate-stressed environments. This review critically evaluates the role of SLF within the broader framework of climate-smart agriculture (C-SA), with a particular focus on its applications in urban and peri-urban settings. Drawing on a systematic review of the existing literature, the study explores how SLF technologies contribute to efficient resource use, localized food production, and environmental sustainability. By decoupling crop cultivation from soil, SLF enables precise control over nutrient delivery and water use in enclosed environments, such as vertical farms, greenhouses, and container-based units. These systems offer notable advantages regarding water conservation, increased yield per unit area, and adaptability to non-arable or degraded land, making them particularly relevant for high-density cities, arid zones, and climate-sensitive regions. SLF systems are categorized into substrate-based (e.g., coco peat and rock wool) and water-based systems (e.g., hydroponics, aquaponics, and aeroponics), each with distinct design requirements, nutrient management strategies, and crop compatibility. Emerging technologies—including artificial intelligence, the Internet of Things, and automation—further enhance SLF system efficiency through real-time data monitoring and precision control. Despite these advancements, challenges remain. High setup costs, energy demands, and the need for technical expertise continue to limit large-scale adoption. While SLF is not a replacement for traditional agriculture, it offers a strategic supplement to bolster localized food systems and address climate-related risks in horticultural production. Urban horticulture is no longer a peripheral activity; it is becoming an integral element of sustainable urban development. SLF should be embedded within broader resilience strategies, tailored to specific socioeconomic and environmental contexts.

Overview of the aeroponic agriculture – An emerging technology for global food security

Autonomous navigation in agricultural environments requires precise obstacle classification to ensure collision-free movement. This study proposes a convolutional neural network (CNN)-based model designed to enhance obstacle classification for agricultural robots, particularly in orchards. Building upon a previously developed YOLOv8n-based real-time detection system, the model incorporates Ghost Modules and Squeeze-and-Excitation (SE) blocks to enhance feature extraction while maintaining computational efficiency. Obstacles are categorized as “Real”—those that physically impact navigation, such as tree trunks and persons—and “Fake”—those that do not, such as tall weeds and tree branches—allowing for precise navigation decisions. The model was trained on separate orchard and campus datasets and fine-tuned using Hyperband optimization and evaluated on an external test set to assess generalization to unseen obstacles. The model’s robustness was tested under varied lighting conditions, including low-light scenarios, to ensure real-world applicability. Computational efficiency was analyzed based on inference speed, memory consumption, and hardware requirements. Comparative analysis against state-of-the-art classification models (VGG16, ResNet50, MobileNetV3, DenseNet121, EfficientNetB0, and InceptionV3) confirmed the proposed model’s superior precision (p), recall (r), and F1-score, particularly in complex orchard scenarios. The model maintained strong generalization across diverse environmental conditions, including varying illumination and previously unseen obstacles. Furthermore, computational analysis revealed that the orchard-combined model achieved the highest inference speed at 2.31 FPS while maintaining a strong balance between accuracy and efficiency. When deployed in real-time, the model achieved 95.0% classification accuracy in orchards and 92.0% in campus environments. The real-time system demonstrated a false positive rate of 8.0% in the campus environment and 2.0% in the orchard, with a consistent false negative rate of 8.0% across both environments. These results validate the model’s effectiveness for real-time obstacle differentiation in agricultural settings. Its strong generalization, robustness to unseen obstacles, and computational efficiency make it well-suited for deployment in precision agriculture. Future work will focus on enhancing inference speed, improving performance under occlusion, and expanding dataset diversity to further strengthen real-world applicability.