Explainable Machine Learning Framework for District-Level Crop Production Forecasting in Bangladesh

This research explores an explainable machine learning framework for forecasting crop production at the district level in Bangladesh. It brings together agricultural forecasting and model interpretability, focusing on predictions that can be examined and understood.

The district-level scope allows the research to address crop production within different parts of Bangladesh. Explainability is central to the framework, connecting forecasting with an understanding of the factors influencing model predictions.

The work explores the application of machine learning to a locally relevant agricultural problem. Its focus combines production forecasting with clearer interpretation of model outputs, contributing to research in explainable artificial intelligence and agricultural analytics.

The paper was submitted to ICEEICT 2027 under Paper ID 1375.