International Journal of Agriculture Innovation, Technology and Globalisation (6 papers in press)

Regular Issues

• A comparative analysis of machine learning algorithms for plant disease detection using leaf images  
  by Rizwan Ali, Ihtisham Ali, Maqbool Khan, Arshad Iqbal 
  Abstract: This research aimed to evaluate how effectively machine learning algorithms identify plant diseases, with the goal of providing an automated solution for agriculture. The study focused on determining the most accurate model for detecting diseases from plant leaf images, as separating healthy and infected leaves is essential for reliable diagnosis. The algorithms examined included support vector classifier, decision tree (DT), K-nearest neighbour (KNN), random forest classifier (RFC), and na
  Keywords: plant disease detection; machine learning; classification; single disease; multiple disease; image processing.
  DOI: 10.1504/IJAITG.2025.10075685
   
  
• Evaluation of waste secondary cellulose acetate in growth medium for eucalyptus clonal nursery production  
  by Roby Mathew, Tarur Konikkaledom Dinesh, Sreejith Valiavalappil, Demlapura S. Gurumurthy, G.V.S. Saiprasad 
  Abstract: Nursery growers employ various techniques to promote the high-quality root system in saplings to ensure successful plantations. Experiments were carried out to determine the effect of using waste secondary cellulose acetate (SCA) in production of rooted plants of Eucalyptus camaldulensis and it was compared with plant produced with commercial growth medium comprising vermiculite. The experiment involved using three different sources of waste SCA to replace 20% of vermiculite in the rooting medium mixture. The bulk density of SCA-based rooting medium ranged between 0.070.1 gcm3 with high water holding capacity. The rooting medium containing SCA did not exhibit any phyto-toxicity on germination of different types of seeds evaluated. The rate of germination was found to be faster in the rooting medium containing SCA and this medium was able to produce 96 % rooting in E. camaldulensis and 100% rooting in Casurina junghuhniana. Plants grown in the rooting medium containing SCA exhibited higher fresh weight (43%), shoot length (22%), root length (4%), and root biomass (10%) compared to those grown in traditional rooting medium.
  Keywords: secondary cellulose acetate; cigarette butts; nursery; eucalyptus clones; rooting medium; growth of plants.
  DOI: 10.1504/IJAITG.2025.10075982
   
  
• Precision agriculture with machine learning: multi-crop identification from remote sensing data  
  by Khushbu Maurya 
  Abstract: Accurate identification and classification of multiple crops are essential for efficient agricultural management, productivity assessment, and sustainable land use planning. Leveraging advanced machine learning (ML) techniques combined with remote sensing data provides a powerful approach for precise, large-scale crop monitoring. This study presents a multi-crop identification framework utilising ensemble ML classifiers and multi-source remote sensing imagery, including multispectral, hyperspectral, and radar data. Key steps include spectral and textural feature extraction, vegetation index calculation, and data fusion for improved classification accuracy. Our approach integrates satellite data with machine learning algorithms to distinguish crop types in complex agricultural landscapes, achieving high-resolution mapping and reliable temporal analysis. Results demonstrate the models capability to discriminate among various crops effectively, highlighting its potential for real-time crop monitoring and land use analysis, ultimately supporting data-driven agricultural decision-making and policy development.
  Keywords: multi-crop identification; machine learning; remote sensing; ensemble classifiers; vegetation indices; temporal analysis; precision agriculture.
  DOI: 10.1504/IJAITG.2026.10077279
   
  
• Sentimental analysis to enhancing agricultural productivity and sustainability  
  by Puspalatha Chittem Setty, Bhadrappa Haralayya 
  Abstract: In the era of mobile social networks, sentiment analysis has become a crucial tool for understanding public opinion across various domains, including agriculture. This study presents an advanced bidirectional encoder representations from transformers (BERT) model designed to analyse sentiment trends within the agricultural market, supported by machine learning (ML), deep learning (DL), and internet of things (IoT) technologies. By evaluating post-purchase reviews and textual data categorised as positive, negative, or neutral, the model captures valuable insights into consumer perceptions and emotional responses. These findings assist farmers, buyers, and producers in improving product quality and market strategies. Additionally, the study assesses agricultural productivity and performance metrics using the BERT framework, demonstrating its superiority over existing ML and DL models in sentiment classification accuracy and reliability.
  Keywords: deep learning; convolutional neural networks; CNN; bidirectional encoder representations from transformers; BERT; recurrent neural networks; RNN; capsule networks; deep belief networks; DBN.
  DOI: 10.1504/IJAITG.2026.10077395
   
  
• Global hunger is on the rise: investigating the pillar of stability in developing countries agribusinesses  
  by Maximilian Haug, Axel Hund, Heiko Gewald 
  Abstract: The 11th Global Food Security Index reported a deterioration in the global food environment for the third year. This development alarms global food security, especially for developing countries, which was highlighted during the COVID-19 pandemic in how fragile food supply chains can be and, therefore, directly threaten human lives. Literature suggests that digitalisation can overcome problems within the food supply chain. We use the case of Mauritius, a developing country, to various challenges related to food security. We focus on and investigate the food security pillar of stability while elaborating on the role of digital technologies within it. Our interviews reveal challenges such as distrust among stakeholders, a corresponding lack of collaboration among all stakeholders, and inadequate governmental interventions.
  Keywords: food security; digital technology; developing countries; stability; Mauritius; information technology; sustainability; agribusiness; availability; access; pillar.
  DOI: 10.1504/IJAITG.2025.10077662
   
  
• Machine learning and IoT in improving productivity of smart farming: a review  
  by Jaishree Srivastava, Manish Madhava Tripathi 
  Abstract: Soil is essential to plant life, however in the machine learning and IoT era, hydroponic and aeroponic methods can create plants without soil. Research in this sector has grown rapidly. IoT and machine learning are utilised in hydroponics and aeroponics to monitor plant growth, estimate planting time, and most importantly, environmental conditions. These two methods make planting easier. Another novel method is aquaponics, an eco-friendly agricultural method that mixes hydroponics and aquaculture. Fish and plants work together in aquaculture, which raises fish in a closed space, and hydroponics, which grows plants without soil. This article examines how data analytics, sensors, and automation can improve hydroponic aeroponics and aquaponics systems and smart farming. These tools assist farmers in maximising plant development and reduce resource loss by monitoring and managing in real-time. These systems can adapt to changing environmental circumstances by integrating IoT devices, ML, and AI. This paper has high resilience to outliers, with 94.26% prediction accuracy and low error rates compared to support vectors, random forests, etc.
  Keywords: hydroponic; aeroponic; aquaponic; machine learning; real-time monitoring; internet of things; IoT; smart farming; SVM.
  DOI: 10.1504/IJAITG.2026.10077940