CEU Credits: 0.5
Predictive Mapping of Agricultural Soil Carbon with Machine Learning Algorithms
This session offers an exploration of the pivotal role played by digital soil mapping and machine learning algorithms in predicting agricultural soil carbon. Attendees will acquire a comprehensive understanding of the fundamental principles of digital soil mapping and its significance in soil carbon prediction. The session will emphasize the effective utilization of machine learning algorithms for soil carbon prediction in agricultural settings, even when faced with challenges such as data scarcity and sparsity. Furthermore, the practical benefits that industry partners and farmers can derive from this technique in predicting soil carbon at the field-level will be highlighted.
Tahmid Huq Easher, Faculty Member, Olds College of Agriculture & Technology
Tahmid Huq Easher is a faculty member at Olds College, bringing over 11 years of diverse experience in agriculture-focused soil and water management research across academia, government institutions, and NGOs in Bangladesh and Canada. He has played a pivotal role in collecting, curating, analyzing, and interpreting vast datasets using advanced statistical software, spatial analytical tools, and visual mediums to support and promote sustainable farming practices.
Tahmid’s primary research focus lies in leveraging machine learning for data analysis to predict soil property information, enhancing our understanding of soil dynamics. His PhD project at the University of Guelph involved pioneering work in predicting soil series and organic carbon of agricultural soils using digital soil mapping techniques. Additionally, Tahmid actively contributes to the development of the Canadian Digital Soil Data Portal as a dedicated member of a working group. This collaborative effort aims to advance digital agriculture and precision farming.
Tahmid aims to build a collaborative platform that brings together modelers, researchers, practitioners, policymakers, private sectors, and communities. This platform will serve as a catalyst for developing precision farming practices in the Canadian prairies, incorporating ideas, practices, and strategies while integrating community practices and indigenous knowledge into data-driven agricultural modeling approaches.