SmartPDE: forecasting plant disease for smart agriculture

November 01, 2023

Plant diseases cut yields and threaten food security, and in many places farmers spot them only once the damage is visible across a field. SmartPDE set out to use deep learning not only to recognize plant diseases but to model how they spread and to forecast outbreaks, so that farmers can act earlier.

At a glance

Project: SmartPDE: Deep Learning Based Plant Disease Epidemiology and Forecasting for Smart Agriculture
Status: Completed (November 2023 – October 2024)
Funding: University Grants Commission (UGC), Bangladesh
Principal investigator: Dr. Md Mehedi Hasan
Area: Precision agriculture

What came out of it

SmartPDE was also the subject of Muhaiminul Islam’s MSc thesis (2024). Closely related work from the same period produced PlantCareNet, published in Plant Methods in 2025. PlantCareNet is an end-to-end diagnostic system: a CNN classifies diseases from leaf images, and the system then gives two kinds of advice, automated suggestions based on the detected symptoms and expert-guided recommendations for prevention and treatment.

Overview of the PlantCareNet workflow, from data preparation and model training to the recommendation system and app. Islam et al., Plant Methods , 2025 CC BY-NC-ND 4.0 . — Overview of the PlantCareNet workflow, from data preparation and model training to the recommendation system and app. Islam et al., *Plant Methods*, 2025 (CC BY-NC-ND 4.0).

The lab’s plant-health work has continued since, with SugarcaneShuffleNet for on-device diagnosis of sugarcane leaf diseases and the current PlantPhenoBot project.