Data scientists used the opportunity to learn advanced trends in artificial intelligence, machine learning and deep learning methods in genomic prediction models. Photo: ICRISAT

Aug

CGIAR data scientists join hands to better machine learning in agriculture

Data scientists used the opportunity to learn advanced trends in artificial intelligence, machine learning and deep learning methods in genomic prediction models. Photo: ICRISAT

A deeper understanding of advanced trends in artificial intelligence (AI), machine learning (ML) and deep learning methods in genomic prediction models is critical to the success of smallholder agriculture. AI and ML algorithms are now being used to reduce risks in agriculture while also making it possible to forecast pest and disease outbreaks and alert farmers in advance.

The annual collaborative workshop for Bioinformatics & Biometrics Community of Practices (CoP) under Excellence in Breeding (EiB) Platform Module 5, held in July in Montpellier, France, discussed the untapped potential of deep learning methods to make a significant impact on farming.

With the theme: “Artificial Intelligence & Machine Learning with Genomic Selection Use Cases”, the workshop served as a platform for data scientists across CGIAR institutions to explore using advanced agricultural research ML algorithms for genomics including prediction of plant phenotype, image identification, disease identification, and annotation of DNA sequences.

“During the EiB Platform Module 5 meetings, a need to properly implement AI/ML algorithms in breeding programs was seen as a major opportunity to boost genetic gains in crops. It was further decided to have an EiB-supported CGIAR-wide collaborative workshop to share experiences, learn new methodologies and plan for the future,” said Dr Abhishek Rathore, EiB Platform Module 5 – Bioinformatics & Biometrics CoP Coordinator & Theme Leader, Statistics, Bioinformatics and Data Management, ICRISAT.

Dr Osval Antonio Montesinos López, Associate Professor from University of Colima, Mexico who served as the instructor for the workshop, detailed methodologies under the umbrella of machine learning. Participants were trained in algorithms of general elements of prediction and logistic regression, artificial neural networks and deep learning for different types of outcomes, support vector regression and support vector machines, linear mixed models for genomic prediction and functional regression.

Four women data scientists were among the group of 11 participants from CGIAR centers including AfricaRice, Bioversity International, International Center for Tropical Agriculture (CIAT), International Maize and Wheat Improvement Center (CIMMYT), International Potato Center (CIP), International Center for Agricultural Research in the Dry Areas (ICARDA), International Institute of Tropical Agriculture (IITA), International Livestock Research Institute (ILRI), International Rice Research Institute (IRRI) and ICRISAT.

EiB Platform Module 5 Leader, Dr Kelly Robbins supported and mentored the workshop planning and activities. The workshop was supported by the EiB Platform Module 5.