As players in the sector grapple with threats of pests, diseases and climate change, AI-powered solutions present unparalleled opportunities to enhance productivity and sustainability.
According to the Food and Agriculture Organization (FAO), crop losses from pests and diseases are now responsible for up to 40 percent of global agricultural production.
The CCMT Technology
However, the development of the Cassava, Cashew, Maize, and Tomato (CCMT) dataset offers a significant breakthrough in the sector.
The CCMT is a technology created by AI and machine learning to address agricultural challenges relating to pests and diseases.
It is a key component of the Responsible AI for Agriculture and Food Systems (AI4AFS) project, being undertaken by Dr Samuel Boateng, and a team of researchers at the University of Energy and Natural Resources in Sunyani, Ghana.
Dr Boateng is an Assistant Professor at the School of Information Technology, University of Cincinnati, United States.
The dataset comprises 24,881 raw images including 6,549 Cashew, 7,508 Cassava, 5,389 Maize, and 5,435 Tomato and besides the augmented images, the dataset is divided into train and test sets.
The test sets also include 102,976 images, consisting of 25,811 Cashew, 26,330 Cassava, 23,657 Maize, and 27,178 Tomato, categorized into 22 classes.
It serves as a valuable resource of annotated images and data points specifically curated to train AI models for the accurate detection of crop pests and diseases.
The dataset highlights the importance of collecting, organizing, and sharing original datasets to advance research and the practical application of artificial intelligence in agriculture.
By supporting machine learning algorithms capable of early identification of pest infestations and disease outbreaks, the CCMT dataset empowers farmers to implement timely interventions and mitigate potential losses.
AI with CCMT Datasets
According to Dr Boateng the AI tools trained on datasets like CCMT could analyze crop health on a large scale, saying the approach reduced the manual inspection and improved precisions.
That leads to healthier crops and better yields
AI systems utilizing datasets like CCMT have the potential to minimise crop losses, ensuring food security and economic stability.
Additionally, the CCMT dataset promotes sustainable farming practices by enabling targeted pesticide application, reducing chemical usage, minimising environmental impact and encouraging eco-friendly farming techniques.
“The dataset has been used to develop a mobile application currently being utilised by over 5,000 smallholder cassava, cashew, maize, and tomato farmers in the Bono, Bono East and Northern regions of Ghana”, Dr Boateng indicated.
Aligning with SDGs
According to Dr Boateng, the advancement was in line with the United Nations Sustainable Development Goal (SDGs Two) that enjoins countries around the globe to eradicate hunger, enhance food security and nutrition, and promote sustainable agriculture by 2030.
The AI-powered agricultural technologies are not only beneficial for large-scale farms but are also adaptable and scalable for smallholder farmers.
Through cloud-based platforms and mobile applications, farmers can remotely access AI-powered insights, bridging the digital gap and making technology more accessible.
Interestingly, the CCMT dataset showcases the effectiveness of data-driven approaches in tackling global agricultural issues, laying the foundation for a more resilient and productive food system.
Admittedly, the incorporation of AI and datasets like CCMT remains a pivotal moment in contemporary agriculture.
That is basically because AI continues to contribute significantly in advancing agriculture, with the CCMT dataset playing a crucial role in driving innovation.
Leveraging AI technologies will enable agricultural industry to become a more reliable and sustainable and thereby meet the growing demand of the burgeoning population.
