Soilcast, a multitask encoder-decoder AI model
for precision agriculture 

9 April 2025 | Sala Stringa - Online | 10:00 | Paolo Grazieschi (FBK-OpenIoT) 

Abstract

We introduce "Soilcast", a multitask encoder-decoder predictive model designed to accurately forecast soil moisture in agricultural fields. By leveraging data from multiple sources and locations, Soilcast enhances resilience against overfitting, a common issue with traditional Long Short-Term Memory (LSTM) models. Tested on agricultural fields within the region of Trentino, Soilcast demonstrated good performance compared to pure "single-task" LSTM models.

The model's flexible architecture allows for both generalization across diverse datasets and specialization for specific fields, ensuring accurate daily soil moisture predictions, which are crucial for effectively optimizing irrigation. Additionally, Soilcast achieved a classification accuracy exceeding 92% in predicting soil moisture stress, outperforming singletask models in both robustness and generalization. These results position Soilcast as a valuable tool for improving water efficiency in response to climate challenges, fostering sustainable precision agriculture practices.  

Bio
Paolo Grazieschi is a PostDoc at the OpenIoT unit of FBK, under the Digital Industry Center. He has a background in pure mathematics, holding a PhD in Stochastic Analysis from the University of Bath, UK. Currently, he is working on AI models for the Agritech sector.