Category: AJAAR

ajaar/2025/A Neuromorphic Edge-Based Irrigation Control System for Precision Agriculture

Post author By editoracademians@gmail.com
Post date October 1, 2025
No Comments on ajaar/2025/A Neuromorphic Edge-Based Irrigation Control System for Precision Agriculture

International Journal of Advanced Agriculture and Research

An Open Access Peer Reviewed International Journal.
Publication Frequency: Bimonthly
ISSN Online: XXXX-XXXX
Country of Origin: Nigeria
Language: English
Publisher Name: Academians Publishers

A Neuromorphic Edge-Based Irrigation Control System for Precision Agriculture

Keywords:

Precision irrigation; neuromorphic computing; spiking neural networks; edge computing; soil matric potential; energy-efficient control.

Abstract

Efficient water utilization is paramount for sustainable agriculture under increasing environmental pressures, especially as global populations rise and climate change intensifies water scarcity. Traditional precision irrigation systems rely on centralized architectures and periodic remote data processing, resulting in high energy costs and dependency on reliable connectivity, which can be particularly problematic in remote or undeveloped regions where robust infrastructure is lacking. This study presents a novel, fully autonomous irrigation controller leveraging a mixed-signal neuromorphic processor (DYNAP-SE1) to perform local, event-driven decision-making based on soil matric potential (SMP) measurements, thus reducing reliance on external networks and enhancing system resilience. In our approach, soil moisture data from apple and kiwi orchards were encoded into spike trains and processed by a spiking neural state machine with excitatory–inhibitory (EI) balanced dynamics to maintain long-term memory of sparse sensor inputs, allowing for more efficient and timely irrigation decisions. A direction-sensitive readout module generated “open” and “close” actuator commands, replicating conventional threshold-based irrigation rules and ensuring that water is delivered precisely when and where it is needed, minimizing waste. Validation on real-world datasets demonstrated close alignment with standard methods across -20 cm and -40 cm depths, with temporal discrepancies under 2 minutes, indicating the high reliability and accuracy of the neuromorphic controller in practical scenarios. Energy consumption per irrigation decision was estimated at 5.97 µWh, exceeding the efficiency of comparable IoT solutions and offering significant energy savings that are critical for sustainable agriculture. This neuromorphic pipeline offers a scalable, ultra-low-power platform for edge-based irrigation control, eliminating the need for cloud infrastructure and enabling resilient water management in resource-constrained environments, ultimately contributing to long-term agricultural sustainability.

Editorial Team
Join as Editor

AJAAR

ajaar/2025/Leveraging Generative Adversarial Networks for Synthetic Data Augmentation in Maize Seedling Detection: A Novel Approach to Mitigate Class Imbalance in the MSDD Benchmark

International Journal of Advanced Agriculture and Research

Leveraging Generative Adversarial Networks for Synthetic Data Augmentation in Maize Seedling Detection: A Novel Approach to Mitigate Class Imbalance in the MSDD Benchmark

Keywords:

Synthetic Data Augmentation, Generative Adversarial Networks (GANs), Class Imbalance, Precision Agriculture, Maize Seedling Detection, YOLO, Deep Learning, UAV.

Abstract

The automation of plant stand counting via Unmanned Aerial Vehicles (UAVs) and deep learning represents a paradigm shift in precision agriculture. However, the performance of object detection models is severely hampered by a fundamental challenge: extreme class imbalance in real-world agricultural datasets. Models excel at detecting prevalent “single plant” instances but fail on rare yet agronomically critical “double” and “triple” plant clusters. This study proposes a novel methodology to mitigate this imbalance by leveraging Generative Adversarial Networks (GANs) for synthetic data augmentation. Building upon the publicly available Maize Seedling Detection Dataset (MSDD), we developed a conditional StyleGAN2-ADA architecture to generate high-fidelity, synthetic images of double and triple maize seedlings across varied growth stages (V4-V8) and environmental conditions. We augmented the original MSDD training set with this synthetic data and benchmarked the performance of YOLOv9 and YOLO11 models. Results demonstrate that models trained on the augmented dataset showed a marked improvement in detecting rare classes. The mAP@0.5 for double plants increased by 18.7% for YOLOv9 and 22.3% for YOLO11, while recall for triple plants improved by 15.1% and 19.8%, respectively, without compromising performance on the single plant class. This research establishes a robust, scalable framework for synthetic data generation in agricultural computer vision, effectively addressing data scarcity for rare classes and paving the way for more reliable automated stand counting systems in precision agriculture.

Editorial Team
Join as Editor

AJAAR

ajaar/2025/Economic Performance Assessment of Greenhouse Vegetable Production in the Arabian Peninsula: A Comparative Analysis Using Stochastic Production Functions

International Journal of Advanced Agriculture and Research

Economic Performance Assessment of Greenhouse Vegetable Production in the Arabian Peninsula: A Comparative Analysis Using Stochastic Production Functions

Keywords:

Greenhouse agriculture, technical efficiency, production frontier, Arabian Peninsula, protected agriculture, policy recommendations.

Abstract

This study examines the economic performance and production efficiency of greenhouse vegetable cultivation in the Arabian Peninsula, with particular emphasis on the role of protected agriculture systems in addressing the challenges of arid climates. Using data from 150 farms across four Gulf countries—United Arab Emirates (UAE), Saudi Arabia, Kuwait, and Oman—we employ stochastic production frontier analysis to assess technical efficiency variations in greenhouse vegetable operations. Primary data were collected through structured surveys covering farm characteristics, input utilization, output metrics, and management practices during the period 2020–2022. Our results indicate a mean technical efficiency of 78.5%, with significant variations across countries and farm types. Notably, the analysis reveals that farmer education, technology adoption, and farm size are key determinants of efficiency, underscoring the importance of capacity building and investment in modern technologies. Furthermore, the findings suggest there is potential for a 21.5% output increase through improved management practices and targeted technology transfer programs. These insights provide valuable guidance for policymakers and stakeholders seeking to enhance the sustainability and competitiveness of greenhouse vegetable production in the region.

Editorial Team
Join as Editor

AJAAR

Co-Design of Morphology and Oscillation in Bio-Inspired Tails for Enhanced Robotic Locomotion on Deformable Granular Substrates

International Journal of Advanced Agriculture and Research

Co-Design of Morphology and Oscillation in Bio-Inspired Tails for Enhanced Robotic Locomotion on Deformable Granular Substrates

Keywords:

bio-inspired robotics, granular media, terradynamics, robot locomotion, tail morphology, substrate fluidization, mudskipper, co-design

Abstract

Locomotion on deformable granular substrates like sand and mud remains a significant challenge for terrestrial robots, primarily due to complex terradynamic interactions leading to sinkage and slippage. Drawing inspiration from the mudskipper (Periophthalmus barbarus), an amphibious fish that modulates its tail morphology and kinematics to traverse such terrains, this study investigates the synergistic role of tail design and control in a flipper-driven robot. Through systematic robophysical experiments, we evaluated the performance of a mudskipper-inspired robot equipped with interchangeable tails of varying support areas (2 cm² to 24 cm²) under both idle and actively oscillating (5 Hz, 60° amplitude) conditions. Our results demonstrate that tail oscillation significantly enhances locomotion performance, but only when coupled with an appropriate morphological design. Specifically, for tails with a support area ≥ 8 cm², active oscillation increased forward speed by up to 20% and reduced body drag by 46% by locally fluidizing the substrate and reducing shear resistance. Conversely, oscillation with smaller tails increased sinkage and was detrimental to performance. A mechanistic model, validated by penetration and shear force measurements, reveals that the benefits of oscillation-induced fluidization are contingent upon the tail’s ability to limit sinkage. This establishes a critical co-design principle: effective mobility on flowable ground requires the simultaneous optimization of tail morphology (large support area) and motion (oscillation). These findings provide a framework for the design of next-generation robots capable of traversing complex natural terrains for applications in planetary exploration, search and rescue, and agricultural robotics.

Editorial Team
Join as Editor